tests: add tests for per-role timeouts

The test cases verify that setting timeout parameters per-role works and is validated.
docs: add a paragaph about per-role parameters
2020-11-27 12:43:53 +01:00 · 2020-11-27 12:43:53 +01:00 · 2020-11-27 12:37:27 +01:00 · 2020-11-27 12:37:27 +01:00 · 2020-11-27 12:37:17 +01:00 · 2020-11-26 17:56:55 +01:00
2520 changed files with 85484 additions and 154938 deletions
--- a/.github/CODEOWNERS
+++ b/.github/CODEOWNERS
@@ -4,7 +4,7 @@ auth/* @elcallio @vladzcloudius
 # CACHE
 row_cache* @tgrabiec @haaawk
 *mutation* @tgrabiec @haaawk
-test/boost/mvcc* @tgrabiec @haaawk
+tests/mvcc* @tgrabiec @haaawk

 # CDC
 cdc/* @haaawk @kbr- @elcallio @piodul @jul-stas
@@ -19,13 +19,13 @@ db/batch* @elcallio
 service/storage_proxy* @gleb-cloudius

 # COMPACTION
-compaction/* @raphaelsc @nyh
+sstables/compaction* @raphaelsc @nyh

 # CQL TRANSPORT LAYER
-transport/*
+transport/* @penberg

 # CQL QUERY LANGUAGE
-cql3/* @tgrabiec @psarna @cvybhu
+cql3/* @tgrabiec @penberg @psarna

 # COUNTERS
 counters* @haaawk @jul-stas
@@ -35,7 +35,7 @@ tests/counter_test* @haaawk @jul-stas
 gms/* @tgrabiec @asias

 # DOCKER
-dist/docker/*
+dist/docker/* @penberg

 # LSA
 utils/logalloc* @tgrabiec
@@ -58,9 +58,9 @@ service/migration* @tgrabiec @nyh
 schema* @tgrabiec @nyh

 # SECONDARY INDEXES
-db/index/* @nyh @psarna
-cql3/statements/*index* @nyh @psarna
-test/boost/*index* @nyh @psarna
+db/index/* @nyh @penberg @psarna
+cql3/statements/*index* @nyh @penberg @psarna
+test/boost/*index* @nyh @penberg @psarna

 # SSTABLES
 sstables/* @tgrabiec @raphaelsc @nyh
@@ -78,20 +78,10 @@ db/hints/* @haaawk @piodul @vladzcloudius

 # REDIS
 redis/* @nyh @syuu1228
-test/redis/* @nyh @syuu1228
+redis-test/* @nyh @syuu1228

 # READERS
 reader_* @denesb
 querier* @denesb
 test/boost/mutation_reader_test.cc @denesb
 test/boost/querier_cache_test.cc @denesb
-
-# PYTEST-BASED CQL TESTS
-test/cql-pytest/* @nyh
-
-# RAFT
-raft/* @kbr- @gleb-cloudius @kostja
-test/raft/* @kbr- @gleb-cloudius @kostja
-
-# HEAT-WEIGHTED LOAD BALANCING
-db/heat_load_balance.* @nyh @gleb-cloudius
--- a/.github/workflows/docs-pages@v2.yaml
+++ b/.github/workflows/docs-pages@v2.yaml
@@ -1,29 +0,0 @@
-name: "Docs / Publish"
-
-on:
-  push:
-    branches:
-    - master
-    paths:
-    - "docs/**"
-  workflow_dispatch:
-
-jobs:
-  release:
-    runs-on: ubuntu-latest
-    steps:
-    - name: Checkout
-      uses: actions/checkout@v2
-      with:
-        persist-credentials: false
-        fetch-depth: 0
-    - name: Set up Python
-      uses: actions/setup-python@v1
-      with:
-        python-version: 3.7
-    - name: Build docs
-      run: make -C docs multiversion
-    - name: Deploy
-      run: ./docs/_utils/deploy.sh
-      env:
-        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
--- a/.github/workflows/docs-pr@v1.yaml
+++ b/.github/workflows/docs-pr@v1.yaml
@@ -1,25 +0,0 @@
-name: "Docs / Build PR"
-
-on:
-  pull_request:
-    branches:
-    - master
-    paths:
-    - "docs/**"
-
-jobs:
-  build:
-    name: Build
-    runs-on: ubuntu-latest
-    steps:
-    - name: Checkout
-      uses: actions/checkout@v2
-      with:
-        persist-credentials: false
-        fetch-depth: 0
-    - name: Set up Python
-      uses: actions/setup-python@v1
-      with:
-        python-version: 3.7
-    - name: Build docs
-      run: make -C docs test
--- a/.gitignore
+++ b/.gitignore
@@ -25,7 +25,3 @@ tags
 testlog
 test/*/*.reject
 .vscode
-docs/_build
-docs/poetry.lock
-compile_commands.json
-.ccls-cache/
--- a/.gitmodules
+++ b/.gitmodules
@@ -1,6 +1,6 @@
 [submodule "seastar"]
 	path = seastar
-	url = ../scylla-seastar
+	url = ../seastar
 	ignore = dirty
 [submodule "swagger-ui"]
 	path = swagger-ui
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -32,13 +32,8 @@ if(target_arch)
    set(target_arch_flag "-march=${target_arch}")
 endif()

-set(cxx_coro_flag)
-if (CMAKE_CXX_COMPILER_ID MATCHES GNU)
-    set(cxx_coro_flag -fcoroutines)
-endif()
-
 # Configure Seastar compile options to align with Scylla
-set(Seastar_CXX_FLAGS ${cxx_coro_flag} ${target_arch_flag} CACHE INTERNAL "" FORCE)
+set(Seastar_CXX_FLAGS -fcoroutines ${target_arch_flag} CACHE INTERNAL "" FORCE)
 set(Seastar_CXX_DIALECT gnu++20 CACHE INTERNAL "" FORCE)

 add_subdirectory(seastar)
@@ -101,7 +96,7 @@ endfunction()
 scylla_generate_thrift(
    TARGET scylla_thrift_gen_cassandra
    VAR scylla_thrift_gen_cassandra_files
-    IN_FILE "${CMAKE_SOURCE_DIR}/interface/cassandra.thrift"
+    IN_FILE interface/cassandra.thrift
    OUT_DIR ${scylla_gen_build_dir}
    SERVICE Cassandra)

@@ -158,7 +153,7 @@ foreach(f ${antlr3_grammar_files})
    scylla_generate_antlr3(
        TARGET scylla_antlr3_gen_${grammar_file_name}
        VAR scylla_antlr3_gen_${grammar_file_name}_files
-        IN_FILE "${CMAKE_SOURCE_DIR}/${f}"
+        IN_FILE ${f}
        OUT_DIR ${scylla_gen_build_dir}/${f_dir})
    list(APPEND antlr3_gen_files "${scylla_antlr3_gen_${grammar_file_name}_files}")
 endforeach()
@@ -167,7 +162,7 @@ endforeach()
 seastar_generate_ragel(
    TARGET scylla_ragel_gen_protocol_parser
    VAR scylla_ragel_gen_protocol_parser_file
-    IN_FILE "${CMAKE_SOURCE_DIR}/redis/protocol_parser.rl"
+    IN_FILE redis/protocol_parser.rl
    OUT_FILE ${scylla_gen_build_dir}/redis/protocol_parser.hh)

 # Generate C++ sources from Swagger definitions
@@ -199,7 +194,7 @@ foreach(f ${swagger_files})
    seastar_generate_swagger(
        TARGET scylla_swagger_gen_${fname}
        VAR scylla_swagger_gen_${fname}_files
-        IN_FILE "${CMAKE_SOURCE_DIR}/${f}"
+        IN_FILE "${f}"
        OUT_DIR "${scylla_gen_build_dir}/${dir}")
    list(APPEND swagger_gen_files "${scylla_swagger_gen_${fname}_files}")
 endforeach()
@@ -234,7 +229,6 @@ set(idl_serializers
    idl/frozen_mutation.idl.hh
    idl/frozen_schema.idl.hh
    idl/gossip_digest.idl.hh
-    idl/hinted_handoff.idl.hh
    idl/idl_test.idl.hh
    idl/keys.idl.hh
    idl/messaging_service.idl.hh
@@ -243,7 +237,6 @@ set(idl_serializers
    idl/partition_checksum.idl.hh
    idl/paxos.idl.hh
    idl/query.idl.hh
-    idl/raft.idl.hh
    idl/range.idl.hh
    idl/read_command.idl.hh
    idl/reconcilable_result.idl.hh
@@ -267,7 +260,7 @@ foreach(f ${idl_serializers})
    scylla_generate_idl_serializer(
        TARGET scylla_idl_gen_${idl_target}
        VAR scylla_idl_gen_${idl_target}_files
-        IN_FILE "${CMAKE_SOURCE_DIR}/${f}"
+        IN_FILE ${f}
        OUT_FILE ${scylla_gen_build_dir}/${idl_dir}/${idl_out_hdr_name})
    list(APPEND idl_gen_files "${scylla_idl_gen_${idl_target}_files}")
 endforeach()
@@ -275,8 +268,8 @@ endforeach()
 set(scylla_sources
    absl-flat_hash_map.cc
    alternator/auth.cc
+    alternator/base64.cc
    alternator/conditions.cc
-    alternator/controller.cc
    alternator/executor.cc
    alternator/expressions.cc
    alternator/serialization.cc
@@ -321,7 +314,6 @@ set(scylla_sources
    auth/standard_role_manager.cc
    auth/transitional.cc
    bytes.cc
-    caching_options.cc
    canonical_mutation.cc
    cdc/cdc_partitioner.cc
    cdc/generation.cc
@@ -330,12 +322,6 @@ set(scylla_sources
    cdc/split.cc
    clocks-impl.cc
    collection_mutation.cc
-    compaction/compaction.cc
-    compaction/compaction_manager.cc
-    compaction/compaction_strategy.cc
-    compaction/leveled_compaction_strategy.cc
-    compaction/size_tiered_compaction_strategy.cc
-    compaction/time_window_compaction_strategy.cc
    compress.cc
    connection_notifier.cc
    converting_mutation_partition_applier.cc
@@ -349,7 +335,6 @@ set(scylla_sources
    cql3/constants.cc
    cql3/cql3_type.cc
    cql3/expr/expression.cc
-    cql3/expr/prepare_expr.cc
    cql3/functions/aggregate_fcts.cc
    cql3/functions/castas_fcts.cc
    cql3/functions/error_injection_fcts.cc
@@ -360,7 +345,6 @@ set(scylla_sources
    cql3/lists.cc
    cql3/maps.cc
    cql3/operation.cc
-    cql3/prepare_context.cc
    cql3/query_options.cc
    cql3/query_processor.cc
    cql3/relation.cc
@@ -376,32 +360,25 @@ set(scylla_sources
    cql3/sets.cc
    cql3/single_column_relation.cc
    cql3/statements/alter_keyspace_statement.cc
-    cql3/statements/alter_service_level_statement.cc
    cql3/statements/alter_table_statement.cc
    cql3/statements/alter_type_statement.cc
    cql3/statements/alter_view_statement.cc
-    cql3/statements/attach_service_level_statement.cc
    cql3/statements/authentication_statement.cc
    cql3/statements/authorization_statement.cc
    cql3/statements/batch_statement.cc
    cql3/statements/cas_request.cc
    cql3/statements/cf_prop_defs.cc
    cql3/statements/cf_statement.cc
-    cql3/statements/create_aggregate_statement.cc
    cql3/statements/create_function_statement.cc
    cql3/statements/create_index_statement.cc
    cql3/statements/create_keyspace_statement.cc
-    cql3/statements/create_service_level_statement.cc
    cql3/statements/create_table_statement.cc
    cql3/statements/create_type_statement.cc
    cql3/statements/create_view_statement.cc
    cql3/statements/delete_statement.cc
-    cql3/statements/detach_service_level_statement.cc
-    cql3/statements/drop_aggregate_statement.cc
    cql3/statements/drop_function_statement.cc
    cql3/statements/drop_index_statement.cc
    cql3/statements/drop_keyspace_statement.cc
-    cql3/statements/drop_service_level_statement.cc
    cql3/statements/drop_table_statement.cc
    cql3/statements/drop_type_statement.cc
    cql3/statements/drop_view_statement.cc
@@ -411,8 +388,6 @@ set(scylla_sources
    cql3/statements/index_target.cc
    cql3/statements/ks_prop_defs.cc
    cql3/statements/list_permissions_statement.cc
-    cql3/statements/list_service_level_attachments_statement.cc
-    cql3/statements/list_service_level_statement.cc
    cql3/statements/list_users_statement.cc
    cql3/statements/modification_statement.cc
    cql3/statements/permission_altering_statement.cc
@@ -422,20 +397,21 @@ set(scylla_sources
    cql3/statements/role-management-statements.cc
    cql3/statements/schema_altering_statement.cc
    cql3/statements/select_statement.cc
-    cql3/statements/service_level_statement.cc
-    cql3/statements/sl_prop_defs.cc
    cql3/statements/truncate_statement.cc
    cql3/statements/update_statement.cc
    cql3/statements/use_statement.cc
    cql3/token_relation.cc
+    cql3/tuples.cc
    cql3/type_json.cc
    cql3/untyped_result_set.cc
    cql3/update_parameters.cc
    cql3/user_types.cc
-    cql3/util.cc
    cql3/ut_name.cc
+    cql3/util.cc
    cql3/values.cc
-    data_dictionary/data_dictionary.cc
+    cql3/variable_specifications.cc
+    data/cell.cc
+    database.cc
    db/batchlog_manager.cc
    db/commitlog/commitlog.cc
    db/commitlog/commitlog_entry.cc
@@ -446,10 +422,8 @@ set(scylla_sources
    db/data_listeners.cc
    db/extensions.cc
    db/heat_load_balance.cc
-    db/hints/host_filter.cc
    db/hints/manager.cc
    db/hints/resource_manager.cc
-    db/hints/sync_point.cc
    db/large_data_handler.cc
    db/legacy_schema_migrator.cc
    db/marshal/type_parser.cc
@@ -462,7 +436,6 @@ set(scylla_sources
    db/view/row_locking.cc
    db/view/view.cc
    db/view/view_update_generator.cc
-    db/virtual_table.cc
    dht/boot_strapper.cc
    dht/i_partitioner.cc
    dht/murmur3_partitioner.cc
@@ -474,18 +447,17 @@ set(scylla_sources
    flat_mutation_reader.cc
    frozen_mutation.cc
    frozen_schema.cc
-    generic_server.cc
    gms/application_state.cc
    gms/endpoint_state.cc
    gms/failure_detector.cc
    gms/feature_service.cc
-    gms/gossip_digest_ack2.cc
    gms/gossip_digest_ack.cc
+    gms/gossip_digest_ack2.cc
    gms/gossip_digest_syn.cc
    gms/gossiper.cc
    gms/inet_address.cc
-    gms/versioned_value.cc
    gms/version_generator.cc
+    gms/versioned_value.cc
    hashers.cc
    index/secondary_index.cc
    index/secondary_index_manager.cc
@@ -493,7 +465,6 @@ set(scylla_sources
    keys.cc
    lister.cc
    locator/abstract_replication_strategy.cc
-    locator/azure_snitch.cc
    locator/ec2_multi_region_snitch.cc
    locator/ec2_snitch.cc
    locator/everywhere_replication_strategy.cc
@@ -507,37 +478,33 @@ set(scylla_sources
    locator/simple_strategy.cc
    locator/snitch_base.cc
    locator/token_metadata.cc
-    lang/lua.cc
+    lua.cc
    main.cc
    memtable.cc
    message/messaging_service.cc
    multishard_mutation_query.cc
    mutation.cc
+    raft/fsm.cc
+    raft/log.cc
+    raft/progress.cc
+    raft/raft.cc
+    raft/server.cc
    mutation_fragment.cc
    mutation_partition.cc
    mutation_partition_serializer.cc
    mutation_partition_view.cc
    mutation_query.cc
    mutation_reader.cc
-    mutation_writer/feed_writers.cc
    mutation_writer/multishard_writer.cc
-    mutation_writer/partition_based_splitting_writer.cc
    mutation_writer/shard_based_splitting_writer.cc
    mutation_writer/timestamp_based_splitting_writer.cc
    partition_slice_builder.cc
    partition_version.cc
    querier.cc
-    query.cc
    query-result-set.cc
-    raft/fsm.cc
-    raft/log.cc
-    raft/raft.cc
-    raft/server.cc
-    raft/tracker.cc
+    query.cc
    range_tombstone.cc
    range_tombstone_list.cc
-    tombstone_gc_options.cc
-    tombstone_gc.cc
    reader_concurrency_semaphore.cc
    redis/abstract_command.cc
    redis/command_factory.cc
@@ -551,18 +518,15 @@ set(scylla_sources
    redis/server.cc
    redis/service.cc
    redis/stats.cc
-    release.cc
    repair/repair.cc
    repair/row_level.cc
-    replica/database.cc
-    replica/table.cc
    row_cache.cc
    schema.cc
    schema_mutations.cc
    schema_registry.cc
-    serializer.cc
    service/client_state.cc
    service/migration_manager.cc
+    service/migration_task.cc
    service/misc_services.cc
    service/pager/paging_state.cc
    service/pager/query_pagers.cc
@@ -571,33 +535,29 @@ set(scylla_sources
    service/paxos/prepare_summary.cc
    service/paxos/proposal.cc
    service/priority_manager.cc
-    service/qos/qos_common.cc
-    service/qos/service_level_controller.cc
-    service/qos/standard_service_level_distributed_data_accessor.cc
-    service/raft/raft_gossip_failure_detector.cc
-    service/raft/raft_group_registry.cc
-    service/raft/raft_rpc.cc
-    service/raft/raft_sys_table_storage.cc
-    service/raft/group0_state_machine.cc
    service/storage_proxy.cc
    service/storage_service.cc
+    sstables/compaction.cc
+    sstables/compaction_manager.cc
+    sstables/compaction_strategy.cc
    sstables/compress.cc
    sstables/integrity_checked_file_impl.cc
-    sstables/kl/reader.cc
-    sstables/metadata_collector.cc
+    sstables/kl/writer.cc
+    sstables/leveled_compaction_strategy.cc
    sstables/m_format_read_helpers.cc
-    sstables/mx/reader.cc
+    sstables/metadata_collector.cc
+    sstables/mp_row_consumer.cc
    sstables/mx/writer.cc
+    sstables/partition.cc
    sstables/prepended_input_stream.cc
    sstables/random_access_reader.cc
+    sstables/size_tiered_compaction_strategy.cc
    sstables/sstable_directory.cc
-    sstables/sstable_mutation_reader.cc
-    sstables/sstables.cc
-    sstables/sstable_set.cc
-    sstables/sstables_manager.cc
    sstables/sstable_version.cc
+    sstables/sstables.cc
+    sstables/sstables_manager.cc
+    sstables/time_window_compaction_strategy.cc
    sstables/writer.cc
-    streaming/consumer.cc
    streaming/progress_info.cc
    streaming/session_info.cc
    streaming/stream_coordinator.cc
@@ -612,19 +572,18 @@ set(scylla_sources
    streaming/stream_summary.cc
    streaming/stream_task.cc
    streaming/stream_transfer_task.cc
+    table.cc
    table_helper.cc
    thrift/controller.cc
    thrift/handler.cc
    thrift/server.cc
    thrift/thrift_validation.cc
    timeout_config.cc
-    tools/scylla-sstable-index.cc
-    tools/scylla-types.cc
-    tracing/traced_file.cc
    tracing/trace_keyspace_helper.cc
    tracing/trace_state.cc
-    tracing/tracing_backend_registry.cc
+    tracing/traced_file.cc
    tracing/tracing.cc
+    tracing/tracing_backend_registry.cc
    transport/controller.cc
    transport/cql_protocol_extension.cc
    transport/event.cc
@@ -633,10 +592,10 @@ set(scylla_sources
    transport/server.cc
    types.cc
    unimplemented.cc
+    utils/UUID_gen.cc
    utils/arch/powerpc/crc32-vpmsum/crc32_wrapper.cc
    utils/array-search.cc
    utils/ascii.cc
-    utils/base64.cc
    utils/big_decimal.cc
    utils/bloom_calculations.cc
    utils/bloom_filter.cc
@@ -651,7 +610,6 @@ set(scylla_sources
    utils/file_lock.cc
    utils/generation-number.cc
    utils/gz/crc_combine.cc
-    utils/gz/gen_crc_combine_table.cc
    utils/human_readable.cc
    utils/i_filter.cc
    utils/large_bitset.cc
@@ -667,10 +625,10 @@ set(scylla_sources
    utils/updateable_value.cc
    utils/utf8.cc
    utils/uuid.cc
-    utils/UUID_gen.cc
    validation.cc
    vint-serialization.cc
-    zstd.cc)
+    zstd.cc
+    release.cc)

 set(scylla_gen_sources
    "${scylla_thrift_gen_cassandra_files}"
@@ -731,7 +689,7 @@ target_link_libraries(scylla PRIVATE

 target_compile_options(scylla PRIVATE
    -std=gnu++20
-    ${cxx_coro_flag}
+    -fcoroutines # TODO: Clang does not have this flag, adjust to both variants
    ${target_arch_flag})
 # Hacks needed to expose internal APIs for xxhash dependencies
 target_compile_definitions(scylla PRIVATE XXH_PRIVATE_API HAVE_LZ4_COMPRESS_DEFAULT)
@@ -751,7 +709,7 @@ target_link_libraries(crc_combine_table PRIVATE seastar)
 target_include_directories(crc_combine_table PRIVATE "${CMAKE_CURRENT_SOURCE_DIR}")
 target_compile_options(crc_combine_table PRIVATE
    -std=gnu++20
-    ${cxx_coro_flag}
+    -fcoroutines
    ${target_arch_flag})
 add_dependencies(scylla crc_combine_table)

@@ -764,15 +722,15 @@ target_sources(scylla PRIVATE "${scylla_gen_build_dir}/utils/gz/crc_combine_tabl
 ###
 ### Generate version file and supply appropriate compile definitions for release.cc
 ###
-execute_process(COMMAND ${CMAKE_SOURCE_DIR}/SCYLLA-VERSION-GEN --output-dir "${CMAKE_BINARY_DIR}/gen" RESULT_VARIABLE scylla_version_gen_res)
+execute_process(COMMAND ${CMAKE_SOURCE_DIR}/SCYLLA-VERSION-GEN RESULT_VARIABLE scylla_version_gen_res)
 if(scylla_version_gen_res)
    message(SEND_ERROR "Version file generation failed. Return code: ${scylla_version_gen_res}")
 endif()

-file(READ "${CMAKE_BINARY_DIR}/gen/SCYLLA-VERSION-FILE" scylla_version)
+file(READ build/SCYLLA-VERSION-FILE scylla_version)
 string(STRIP "${scylla_version}" scylla_version)

-file(READ "${CMAKE_BINARY_DIR}/gen/SCYLLA-RELEASE-FILE" scylla_release)
+file(READ build/SCYLLA-RELEASE-FILE scylla_release)
 string(STRIP "${scylla_release}" scylla_release)

 get_property(release_cdefs SOURCE "${CMAKE_SOURCE_DIR}/release.cc" PROPERTY COMPILE_DEFINITIONS)
@@ -784,7 +742,7 @@ set_source_files_properties("${CMAKE_SOURCE_DIR}/release.cc" PROPERTIES COMPILE_
 ###
 set(libdeflate_lib "${scylla_build_dir}/libdeflate/libdeflate.a")
 add_custom_command(OUTPUT "${libdeflate_lib}"
-    COMMAND make -C "${CMAKE_SOURCE_DIR}/libdeflate"
+    COMMAND make -C libdeflate
        BUILD_DIR=../build/${BUILD_TYPE}/libdeflate/
        CC=${CMAKE_C_COMPILER}
        "CFLAGS=${target_arch_flag}"
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -1,20 +1,11 @@
-# Contributing to Scylla
+# Asking questions or requesting help

-## Asking questions or requesting help
+Use the [ScyllaDB user mailing list](https://groups.google.com/forum/#!forum/scylladb-users) or the [Slack workspace](http://slack.scylladb.com) for general questions and help.

-Use the [Scylla Users mailing list](https://groups.google.com/g/scylladb-users) or the [Slack workspace](http://slack.scylladb.com) for general questions and help.
+# Reporting an issue

-Join the [Scylla Developers mailing list](https://groups.google.com/g/scylladb-dev) for deeper technical discussions and to discuss your ideas for contributions.
+Please use the [Issue Tracker](https://github.com/scylladb/scylla/issues/) to report issues.  Fill in as much information as you can in the issue template, especially for performance problems.

-## Reporting an issue
+# Contributing Code to Scylla

-Please use the [issue tracker](https://github.com/scylladb/scylla/issues/) to report issues or to suggest features. Fill in as much information as you can in the issue template, especially for performance problems.
-
-## Contributing code to Scylla
-
-Before you can contribute code to Scylla for the first time, you should sign the [Contributor License Agreement](https://www.scylladb.com/open-source/contributor-agreement/) and send the signed form cla@scylladb.com. You can then submit your changes as patches to the to the [scylladb-dev mailing list](https://groups.google.com/forum/#!forum/scylladb-dev) or as a pull request to the [Scylla project on github](https://github.com/scylladb/scylla).
-If you need help formatting or sending patches, [check out these instructions](https://github.com/scylladb/scylla/wiki/Formatting-and-sending-patches).
-
-The Scylla C++ source code uses the [Seastar coding style](https://github.com/scylladb/seastar/blob/master/coding-style.md) so please adhere to that in your patches. Note that Scylla code is written with `using namespace seastar`, so should not explicitly add the `seastar::` prefix to Seastar symbols. You will usually not need to add `using namespace seastar` to new source files, because most Scylla header files have `#include "seastarx.hh"`, which does this.
-
-Header files in Scylla must be self-contained, i.e., each can be included without having to include specific other headers first. To verify that your change did not break this property, run `ninja dev-headers`. If you added or removed header files, you must `touch configure.py` first - this will cause `configure.py` to be automatically re-run to generate a fresh list of header files.
+To contribute code to Scylla, you need to sign the [Contributor License Agreement](https://www.scylladb.com/open-source/contributor-agreement/) and send your changes as [patches](https://github.com/scylladb/scylla/wiki/Formatting-and-sending-patches) to the [mailing list](https://groups.google.com/forum/#!forum/scylladb-dev). We don't accept pull requests on GitHub.
--- a/HACKING.md
+++ b/HACKING.md
@@ -172,8 +172,12 @@ and you will get output like this:
 ```
 CQL QUERY LANGUAGE
  Tomasz Grabiec <tgrabiec@scylladb.com>   [maintainer]
+  Pekka Enberg <penberg@scylladb.com>      [maintainer]
 MATERIALIZED VIEWS
+  Pekka Enberg <penberg@scylladb.com>      [maintainer]
+  Duarte Nunes <duarte@scylladb.com>       [maintainer]
  Nadav Har'El <nyh@scylladb.com>          [reviewer]
+  Duarte Nunes <duarte@scylladb.com>       [reviewer]
 ```

 ### Running Scylla
@@ -362,27 +366,7 @@ $ git remote update
 $ git checkout -t local/my_local_seastar_branch
 ```

-### Generating code coverage report
-
-Install dependencies:
-
-    $ dnf install llvm # for llvm-profdata and llvm-cov
-    $ dnf install lcov # for genhtml
-
-Instruct `configure.py` to generate build files for `coverage` mode:
-
-    $ ./configure.py --mode=coverage
-
-Build the tests you want to run, then run them via `test.py` (important!):
-
-    $ ./test.py --mode=coverage [...]
-
-Alternatively, you can run individual tests via `./scripts/coverage.py --run`.
-
-Open the link printed at the end. Be horrified. Go and write more tests.
-
-For more details see `./scripts/coverage.py --help`.
-
 ### Core dump debugging

-See [debugging.md](debugging.md).
+Slides:
+2018.11.20: https://www.slideshare.net/tomekgrabiec/scylla-core-dump-debugging-tools
--- a/NOTICE.txt
+++ b/NOTICE.txt
@@ -5,7 +5,3 @@ It includes files from https://github.com/antonblanchard/crc32-vpmsum (author An
 These files are located in utils/arch/powerpc/crc32-vpmsum. Their license may be found in licenses/LICENSE-crc32-vpmsum.TXT.

 It includes modified code from https://gitbox.apache.org/repos/asf?p=cassandra-dtest.git (owned by The Apache Software Foundation)
-
-It includes modified tests from https://github.com/etcd-io/etcd.git (owned by The etcd Authors)
-
-It includes files from https://github.com/bytecodealliance/wasmtime-cpp (owned by Bytecode Alliance), licensed with Apache License 2.0.
--- a/README.md
+++ b/README.md
@@ -42,8 +42,8 @@ For further information, please see:
 * [Docker image build documentation] for information on how to build Docker images.

 [developer documentation]: HACKING.md
-[build documentation]: docs/guides/building.md
-[docker image build documentation]: dist/docker/debian/README.md
+[build documentation]: docs/building.md
+[docker image build documentation]: dist/docker/redhat/README.md

 ## Running Scylla

@@ -65,7 +65,7 @@ $ ./tools/toolchain/dbuild ./build/release/scylla --help

 ## Testing

-See [test.py manual](docs/guides/testing.md).
+See [test.py manual](docs/testing.md).

 ## Scylla APIs and compatibility
 By default, Scylla is compatible with Apache Cassandra and its APIs - CQL and
@@ -78,7 +78,10 @@ and the current compatibility of this feature as well as Scylla-specific extensi

 ## Documentation

-Documentation can be found [here](https://scylla.docs.scylladb.com).
+Documentation can be found in [./docs](./docs) and on the
+[wiki](https://github.com/scylladb/scylla/wiki). There is currently no clear
+definition of what goes where, so when looking for something be sure to check
+both.
 Seastar documentation can be found [here](http://docs.seastar.io/master/index.html).
 User documentation can be found [here](https://docs.scylladb.com/).

--- a/78
+++ b/78
@@ -1,74 +1,15 @@
 #!/bin/sh

-USAGE=$(cat <<-END
-Usage: $(basename "$0") [-h|--help] [-o|--output-dir PATH] -- generate Scylla version and build information files.
-
-Options:
-  -h|--help show this help message.
-  -o|--output-dir PATH specify destination path at which the version files are to be created.
-
-By default, the script will attempt to parse 'version' file
-in the current directory, which should contain a string of
-'\$version-\$release' form.
-
-Otherwise, it will call 'git log' on the source tree (the
-directory, which contains the script) to obtain current
-commit hash and use it for building the version and release
-strings.
-
-The script assumes that it's called from the Scylla source
-tree.
-
-The files created are:
-  SCYLLA-VERSION-FILE
-  SCYLLA-RELEASE-FILE
-  SCYLLA-PRODUCT-FILE
-
-By default, these files are created in the 'build'
-subdirectory under the directory containing the script.
-The destination directory can be overriden by
-using '-o PATH' option.
-END
-)
-
-while [[ $# -gt 0 ]]; do
-	opt="$1"
-	case $opt in
-		-h|--help)
-			echo "$USAGE"
-			exit 0
-			;;
-		-o|--output-dir)
-			OUTPUT_DIR="$2"
-			shift
-			shift
-			;;
-		*)
-			echo "Unexpected argument found: $1"
-			echo
-			echo "$USAGE"
-			exit 1
-			;;
-	esac
-done
-
-SCRIPT_DIR="$(dirname "$0")"
-
-if [ -z "$OUTPUT_DIR" ]; then
-	OUTPUT_DIR="$SCRIPT_DIR/build"
-fi
-
-# Default scylla product/version tags
 PRODUCT=scylla
-VERSION=5.0.13
+VERSION=4.4.dev

 if test -f version
 then
 	SCYLLA_VERSION=$(cat version | awk -F'-' '{print $1}')
 	SCYLLA_RELEASE=$(cat version | awk -F'-' '{print $2}')
 else
-	DATE=$(date --utc +%Y%m%d)
-	GIT_COMMIT=$(git -C "$SCRIPT_DIR" log --pretty=format:'%h' -n 1)
+	DATE=$(date +%Y%m%d)
+	GIT_COMMIT=$(git log --pretty=format:'%h' -n 1)
 	SCYLLA_VERSION=$VERSION
 	# For custom package builds, replace "0" with "counter.your_name",
 	# where counter starts at 1 and increments for successive versions.
@@ -78,15 +19,16 @@ else
 	SCYLLA_RELEASE=$SCYLLA_BUILD.$DATE.$GIT_COMMIT
 fi

-if [ -f "$OUTPUT_DIR/SCYLLA-RELEASE-FILE" ]; then
-	GIT_COMMIT_FILE=$(cat "$OUTPUT_DIR/SCYLLA-RELEASE-FILE" |cut -d . -f 3)
+if [ -f build/SCYLLA-RELEASE-FILE ]; then
+	RELEASE_FILE=$(cat build/SCYLLA-RELEASE-FILE)
+	GIT_COMMIT_FILE=$(cat build/SCYLLA-RELEASE-FILE |cut -d . -f 3)
 	if [ "$GIT_COMMIT" = "$GIT_COMMIT_FILE" ]; then
 		exit 0
 	fi
 fi

 echo "$SCYLLA_VERSION-$SCYLLA_RELEASE"
-mkdir -p "$OUTPUT_DIR"
-echo "$SCYLLA_VERSION" > "$OUTPUT_DIR/SCYLLA-VERSION-FILE"
-echo "$SCYLLA_RELEASE" > "$OUTPUT_DIR/SCYLLA-RELEASE-FILE"
-echo "$PRODUCT" > "$OUTPUT_DIR/SCYLLA-PRODUCT-FILE"
+mkdir -p build
+echo "$SCYLLA_VERSION" > build/SCYLLA-VERSION-FILE
+echo "$SCYLLA_RELEASE" > build/SCYLLA-RELEASE-FILE
+echo "$PRODUCT" > build/SCYLLA-PRODUCT-FILE
--- a/2
+++ b/2
--- a/absl-flat_hash_map.cc
+++ b/absl-flat_hash_map.cc
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2020-present ScyllaDB
+ * Copyright (C) 2020 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #include "absl-flat_hash_map.hh"
--- a/absl-flat_hash_map.hh
+++ b/absl-flat_hash_map.hh
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2020-present ScyllaDB
+ * Copyright (C) 2020 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once
--- a/alternator/auth.cc
+++ b/alternator/auth.cc
@@ -1,9 +1,22 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #include "alternator/error.hh"
@@ -11,6 +24,7 @@
 #include <string>
 #include <string_view>
 #include <gnutls/crypto.h>
+#include <seastar/util/defer.hh>
 #include "hashers.hh"
 #include "bytes.hh"
 #include "alternator/auth.hh"
@@ -18,12 +32,8 @@
 #include "auth/common.hh"
 #include "auth/password_authenticator.hh"
 #include "auth/roles-metadata.hh"
-#include "service/storage_proxy.hh"
-#include "alternator/executor.hh"
-#include "cql3/selection/selection.hh"
-#include "query-result-set.hh"
-#include "cql3/result_set.hh"
-#include <seastar/core/coroutine.hh>
+#include "cql3/query_processor.hh"
+#include "cql3/untyped_result_set.hh"

 namespace alternator {

@@ -52,14 +62,6 @@ static std::string apply_sha256(std::string_view msg) {
    return to_hex(hasher.finalize());
 }

-static std::string apply_sha256(const std::vector<temporary_buffer<char>>& msg) {
-    sha256_hasher hasher;
-    for (const temporary_buffer<char>& buf : msg) {
-        hasher.update(buf.get(), buf.size());
-    }
-    return to_hex(hasher.finalize());
-}
-
 static std::string format_time_point(db_clock::time_point tp) {
    time_t time_point_repr = db_clock::to_time_t(tp);
    std::string time_point_str;
@@ -89,7 +91,7 @@ void check_expiry(std::string_view signature_date) {

 std::string get_signature(std::string_view access_key_id, std::string_view secret_access_key, std::string_view host, std::string_view method,
        std::string_view orig_datestamp, std::string_view signed_headers_str, const std::map<std::string_view, std::string_view>& signed_headers_map,
-        const std::vector<temporary_buffer<char>>& body_content, std::string_view region, std::string_view service, std::string_view query_string) {
+        std::string_view body_content, std::string_view region, std::string_view service, std::string_view query_string) {
    auto amz_date_it = signed_headers_map.find("x-amz-date");
    if (amz_date_it == signed_headers_map.end()) {
        throw api_error::invalid_signature("X-Amz-Date header is mandatory for signature verification");
@@ -122,36 +124,23 @@ std::string get_signature(std::string_view access_key_id, std::string_view secre
    return to_hex(bytes_view(reinterpret_cast<const int8_t*>(signature.data()), signature.size()));
 }

-future<std::string> get_key_from_roles(service::storage_proxy& proxy, std::string username) {
-    schema_ptr schema = proxy.data_dictionary().find_schema("system_auth", "roles");
-    partition_key pk = partition_key::from_single_value(*schema, utf8_type->decompose(username));
-    dht::partition_range_vector partition_ranges{dht::partition_range(dht::decorate_key(*schema, pk))};
-    std::vector<query::clustering_range> bounds{query::clustering_range::make_open_ended_both_sides()};
-    const column_definition* salted_hash_col = schema->get_column_definition(bytes("salted_hash"));
-    if (!salted_hash_col) {
-        co_return coroutine::make_exception(api_error::unrecognized_client(format("Credentials cannot be fetched for: {}", username)));
-    }
-    auto selection = cql3::selection::selection::for_columns(schema, {salted_hash_col});
-    auto partition_slice = query::partition_slice(std::move(bounds), {}, query::column_id_vector{salted_hash_col->id}, selection->get_query_options());
-    auto command = ::make_lw_shared<query::read_command>(schema->id(), schema->version(), partition_slice, proxy.get_max_result_size(partition_slice));
+future<std::string> get_key_from_roles(cql3::query_processor& qp, std::string username) {
+    static const sstring query = format("SELECT salted_hash FROM {} WHERE {} = ?",
+            auth::meta::roles_table::qualified_name, auth::meta::roles_table::role_col_name);
+
    auto cl = auth::password_authenticator::consistency_for_user(username);
-
-    service::client_state client_state{service::client_state::internal_tag()};
-    service::storage_proxy::coordinator_query_result qr = co_await proxy.query(schema, std::move(command), std::move(partition_ranges), cl,
-            service::storage_proxy::coordinator_query_options(executor::default_timeout(), empty_service_permit(), client_state));
-
-    cql3::selection::result_set_builder builder(*selection, gc_clock::now(), cql_serialization_format::latest());
-    query::result_view::consume(*qr.query_result, partition_slice, cql3::selection::result_set_builder::visitor(builder, *schema, *selection));
-
-    auto result_set = builder.build();
-    if (result_set->empty()) {
-        co_return coroutine::make_exception(api_error::unrecognized_client(format("User not found: {}", username)));
-    }
-    const bytes_opt& salted_hash = result_set->rows().front().front(); // We only asked for 1 row and 1 column
-    if (!salted_hash) {
-        co_return coroutine::make_exception(api_error::unrecognized_client(format("No password found for user: {}", username)));
-    }
-    co_return value_cast<sstring>(utf8_type->deserialize(*salted_hash));
+    return qp.execute_internal(query, cl, auth::internal_distributed_query_state(), {sstring(username)}, true).then_wrapped([username = std::move(username)] (future<::shared_ptr<cql3::untyped_result_set>> f) {
+        auto res = f.get0();
+        auto salted_hash = std::optional<sstring>();
+        if (res->empty()) {
+            throw api_error::unrecognized_client(fmt::format("User not found: {}", username));
+        }
+        salted_hash = res->one().get_opt<sstring>("salted_hash");
+        if (!salted_hash) {
+            throw api_error::unrecognized_client(fmt::format("No password found for user: {}", username));
+        }
+        return make_ready_future<std::string>(*salted_hash);
+    });
 }

 }
--- a/alternator/auth.hh
+++ b/alternator/auth.hh
@@ -1,9 +1,22 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once
@@ -14,20 +27,20 @@
 #include "gc_clock.hh"
 #include "utils/loading_cache.hh"

-namespace service {
-class storage_proxy;
+namespace cql3 {
+class query_processor;
 }

 namespace alternator {

 using hmac_sha256_digest = std::array<char, 32>;

-using key_cache = utils::loading_cache<std::string, std::string, 1>;
+using key_cache = utils::loading_cache<std::string, std::string>;

 std::string get_signature(std::string_view access_key_id, std::string_view secret_access_key, std::string_view host, std::string_view method,
        std::string_view orig_datestamp, std::string_view signed_headers_str, const std::map<std::string_view, std::string_view>& signed_headers_map,
-        const std::vector<temporary_buffer<char>>& body_content, std::string_view region, std::string_view service, std::string_view query_string);
+        std::string_view body_content, std::string_view region, std::string_view service, std::string_view query_string);

-future<std::string> get_key_from_roles(service::storage_proxy& proxy, std::string username);
+future<std::string> get_key_from_roles(cql3::query_processor& qp, std::string username);

 }
--- a/alternator/base64.cc
+++ b/alternator/base64.cc
@@ -1,11 +1,28 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

+// The DynamoAPI dictates that "binary" (a.k.a. "bytes" or "blob") values
+// be encoded in the JSON API as base64-encoded strings. This is code to
+// convert byte arrays to base64-encoded strings, and back.
+
 #include "base64.hh"

 #include <ctype.h>
--- a/alternator/base64.hh
+++ b/alternator/base64.hh
@@ -0,0 +1,38 @@
+/*
+ * Copyright 2019 ScyllaDB
+ */
+
+/*
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#pragma once
+
+#include <string_view>
+#include "bytes.hh"
+#include "utils/rjson.hh"
+
+std::string base64_encode(bytes_view);
+
+bytes base64_decode(std::string_view);
+
+inline bytes base64_decode(const rjson::value& v) {
+  return base64_decode(std::string_view(v.GetString(), v.GetStringLength()));
+}
+
+size_t base64_decoded_len(std::string_view str);
+
+bool base64_begins_with(std::string_view base, std::string_view operand);
--- a/alternator/conditions.cc
+++ b/alternator/conditions.cc
@@ -1,9 +1,22 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #include <list>
@@ -15,8 +28,7 @@
 #include <unordered_map>
 #include "utils/rjson.hh"
 #include "serialization.hh"
-#include "utils/base64.hh"
-#include "utils/rjson.hh"
+#include "base64.hh"
 #include <stdexcept>
 #include <boost/algorithm/cxx11/all_of.hpp>
 #include <boost/algorithm/cxx11/any_of.hpp>
@@ -111,7 +123,7 @@ struct rjson_engaged_ptr_comp {
 // as internally they're stored in an array, and the order of elements is
 // not important in set equality. See issue #5021
 static bool check_EQ_for_sets(const rjson::value& set1, const rjson::value& set2) {
-    if (!set1.IsArray() || !set2.IsArray() || set1.Size() != set2.Size()) {
+    if (set1.Size() != set2.Size()) {
        return false;
    }
    std::set<const rjson::value*, rjson_engaged_ptr_comp> set1_raw;
@@ -125,107 +137,45 @@ static bool check_EQ_for_sets(const rjson::value& set1, const rjson::value& set2
    }
    return true;
 }
-// Moreover, the JSON being compared can be a nested document with outer
-// layers of lists and maps and some inner set - and we need to get to that
-// inner set to compare it correctly with check_EQ_for_sets() (issue #8514).
-static bool check_EQ(const rjson::value* v1, const rjson::value& v2);
-static bool check_EQ_for_lists(const rjson::value& list1, const rjson::value& list2) {
-    if (!list1.IsArray() || !list2.IsArray() || list1.Size() != list2.Size()) {
-        return false;
-    }
-    auto it1 = list1.Begin();
-    auto it2 = list2.Begin();
-    while (it1 != list1.End()) {
-        // Note: Alternator limits an item's depth (rjson::parse() limits
-        // it to around 37 levels), so this recursion is safe.
-        if (!check_EQ(&*it1, *it2)) {
-            return false;
-        }
-        ++it1;
-        ++it2;
-    }
-    return true;
-}
-static bool check_EQ_for_maps(const rjson::value& list1, const rjson::value& list2) {
-    if (!list1.IsObject() || !list2.IsObject() || list1.MemberCount() != list2.MemberCount()) {
-        return false;
-    }
-    for (auto it1 = list1.MemberBegin(); it1 != list1.MemberEnd(); ++it1) {
-        auto it2 = list2.FindMember(it1->name);
-        if (it2 == list2.MemberEnd() || !check_EQ(&it1->value, it2->value)) {
-            return false;
-        }
-    }
-    return true;
-}

 // Check if two JSON-encoded values match with the EQ relation
 static bool check_EQ(const rjson::value* v1, const rjson::value& v2) {
-    if (v1 && v1->IsObject() && v1->MemberCount() == 1 && v2.IsObject() && v2.MemberCount() == 1) {
-        auto it1 = v1->MemberBegin();
-        auto it2 = v2.MemberBegin();
-        if (it1->name != it2->name) {
-            return false;
-        }
-        if (it1->name == "SS" || it1->name == "NS" || it1->name == "BS") {
-            return check_EQ_for_sets(it1->value, it2->value);
-        } else if(it1->name == "L") {
-            return check_EQ_for_lists(it1->value, it2->value);
-        } else if(it1->name == "M") {
-            return check_EQ_for_maps(it1->value, it2->value);
-        } else {
-            // Other, non-nested types (number, string, etc.) can be compared
-            // literally, comparing their JSON representation.
-            return it1->value == it2->value;
-        }
-    } else {
-        // If v1 and/or v2 are missing (IsNull()) the result should be false.
-        // In the unlikely case that the object is malformed (issue #8070),
-        // let's also return false.
+    if (!v1) {
        return false;
    }
+    if (v1->IsObject() && v1->MemberCount() == 1 && v2.IsObject() && v2.MemberCount() == 1) {
+        auto it1 = v1->MemberBegin();
+        auto it2 = v2.MemberBegin();
+        if ((it1->name == "SS" && it2->name == "SS") || (it1->name == "NS" && it2->name == "NS") || (it1->name == "BS" && it2->name == "BS")) {
+            return check_EQ_for_sets(it1->value, it2->value);
+        }
+    }
+    return *v1 == v2;
 }

 // Check if two JSON-encoded values match with the NE relation
 static bool check_NE(const rjson::value* v1, const rjson::value& v2) {
-    return !check_EQ(v1, v2);
+    return !v1 || *v1 != v2; // null is unequal to anything.
 }

 // Check if two JSON-encoded values match with the BEGINS_WITH relation
-bool check_BEGINS_WITH(const rjson::value* v1, const rjson::value& v2,
-                       bool v1_from_query, bool v2_from_query) {
-    bool bad = false;
-    if (!v1 || !v1->IsObject() || v1->MemberCount() != 1) {
-        if (v1_from_query) {
-            throw api_error::validation("begins_with() encountered malformed argument");
-        } else {
-            bad = true;
-        }
-    } else if (v1->MemberBegin()->name != "S" && v1->MemberBegin()->name != "B") {
-        if (v1_from_query) {
-            throw api_error::validation(format("begins_with supports only string or binary type, got: {}", *v1));
-        } else {
-            bad = true;
-        }
-    }
+static bool check_BEGINS_WITH(const rjson::value* v1, const rjson::value& v2) {
+    // BEGINS_WITH requires that its single operand (v2) be a string or
+    // binary - otherwise it's a validation error. However, problems with
+    // the stored attribute (v1) will just return false (no match).
    if (!v2.IsObject() || v2.MemberCount() != 1) {
-        if (v2_from_query) {
-            throw api_error::validation("begins_with() encountered malformed argument");
-        } else {
-            bad = true;
-        }
-    } else if (v2.MemberBegin()->name != "S" && v2.MemberBegin()->name != "B") {
-        if (v2_from_query) {
-            throw api_error::validation(format("begins_with() supports only string or binary type, got: {}", v2));
-        } else {
-            bad = true;
-        }
+        throw api_error::validation(format("BEGINS_WITH operator encountered malformed AttributeValue: {}", v2));
    }
-    if (bad) {
+    auto it2 = v2.MemberBegin();
+    if (it2->name != "S" && it2->name != "B") {
+        throw api_error::validation(format("BEGINS_WITH operator requires String or Binary type in AttributeValue, got {}", it2->name));
+    }
+
+
+    if (!v1 || !v1->IsObject() || v1->MemberCount() != 1) {
        return false;
    }
    auto it1 = v1->MemberBegin();
-    auto it2 = v2.MemberBegin();
    if (it1->name != it2->name) {
        return false;
    }
@@ -250,7 +200,7 @@ bool check_CONTAINS(const rjson::value* v1, const rjson::value& v2) {
    if (kv1.name == "S" && kv2.name == "S") {
        return rjson::to_string_view(kv1.value).find(rjson::to_string_view(kv2.value)) != std::string_view::npos;
    } else if (kv1.name == "B" && kv2.name == "B") {
-        return rjson::base64_decode(kv1.value).find(rjson::base64_decode(kv2.value)) != bytes::npos;
+        return base64_decode(kv1.value).find(base64_decode(kv2.value)) != bytes::npos;
    } else if (is_set_of(kv1.name, kv2.name)) {
        for (auto i = kv1.value.Begin(); i != kv1.value.End(); ++i) {
            if (*i == kv2.value) {
@@ -329,40 +279,24 @@ static bool check_NOT_NULL(const rjson::value* val) {
    return val != nullptr;
 }

-// Only types S, N or B (string, number or bytes) may be compared by the
-// various comparion operators - lt, le, gt, ge, and between.
-// Note that in particular, if the value is missing (v->IsNull()), this
-// check returns false.
-static bool check_comparable_type(const rjson::value& v) {
-    if (!v.IsObject() || v.MemberCount() != 1) {
-        return false;
-    }
-    const rjson::value& type = v.MemberBegin()->name;
-    return type == "S" || type == "N" || type == "B";
-}
-
 // Check if two JSON-encoded values match with cmp.
 template <typename Comparator>
-bool check_compare(const rjson::value* v1, const rjson::value& v2, const Comparator& cmp,
-                   bool v1_from_query, bool v2_from_query) {
-    bool bad = false;
-    if (!v1 || !check_comparable_type(*v1)) {
-        if (v1_from_query) {
-            throw api_error::validation(format("{} allow only the types String, Number, or Binary", cmp.diagnostic));
-        }
-        bad = true;
+bool check_compare(const rjson::value* v1, const rjson::value& v2, const Comparator& cmp) {
+    if (!v2.IsObject() || v2.MemberCount() != 1) {
+        throw api_error::validation(
+                        format("{} requires a single AttributeValue of type String, Number, or Binary",
+                               cmp.diagnostic));
    }
-    if (!check_comparable_type(v2)) {
-        if (v2_from_query) {
-            throw api_error::validation(format("{} allow only the types String, Number, or Binary", cmp.diagnostic));
-        }
-        bad = true;
+    const auto& kv2 = *v2.MemberBegin();
+    if (kv2.name != "S" && kv2.name != "N" && kv2.name != "B") {
+        throw api_error::validation(
+                        format("{} requires a single AttributeValue of type String, Number, or Binary",
+                               cmp.diagnostic));
    }
-    if (bad) {
+    if (!v1 || !v1->IsObject() || v1->MemberCount() != 1) {
        return false;
    }
    const auto& kv1 = *v1->MemberBegin();
-    const auto& kv2 = *v2.MemberBegin();
    if (kv1.name != kv2.name) {
        return false;
    }
@@ -374,10 +308,9 @@ bool check_compare(const rjson::value* v1, const rjson::value& v2, const Compara
                   std::string_view(kv2.value.GetString(), kv2.value.GetStringLength()));
    }
    if (kv1.name == "B") {
-        return cmp(rjson::base64_decode(kv1.value), rjson::base64_decode(kv2.value));
+        return cmp(base64_decode(kv1.value), base64_decode(kv2.value));
    }
-    // cannot reach here, as check_comparable_type() verifies the type is one
-    // of the above options.
+    clogger.error("check_compare panic: LHS type equals RHS type, but one is in {N,S,B} while the other isn't");
    return false;
 }

@@ -408,71 +341,56 @@ struct cmp_gt {
    static constexpr const char* diagnostic = "GT operator";
 };

-// True if v is between lb and ub, inclusive.  Throws or returns false
-// (depending on bounds_from_query parameter) if lb > ub.
+// True if v is between lb and ub, inclusive.  Throws if lb > ub.
 template <typename T>
-static bool check_BETWEEN(const T& v, const T& lb, const T& ub, bool bounds_from_query) {
+static bool check_BETWEEN(const T& v, const T& lb, const T& ub) {
    if (cmp_lt()(ub, lb)) {
-        if (bounds_from_query) {
-            throw api_error::validation(
-                format("BETWEEN operator requires lower_bound <= upper_bound, but {} > {}", lb, ub));
-        } else {
-            return false;
-        }
+        throw api_error::validation(
+                        format("BETWEEN operator requires lower_bound <= upper_bound, but {} > {}", lb, ub));
    }
    return cmp_ge()(v, lb) && cmp_le()(v, ub);
 }

-static bool check_BETWEEN(const rjson::value* v, const rjson::value& lb, const rjson::value& ub,
-                          bool v_from_query, bool lb_from_query, bool ub_from_query) {
-    if ((v && v_from_query && !check_comparable_type(*v)) ||
-        (lb_from_query && !check_comparable_type(lb)) ||
-        (ub_from_query && !check_comparable_type(ub))) {
-        throw api_error::validation("between allow only the types String, Number, or Binary");
-
-    }
-    if (!v || !v->IsObject() || v->MemberCount() != 1 ||
-        !lb.IsObject() || lb.MemberCount() != 1 ||
-        !ub.IsObject() || ub.MemberCount() != 1) {
+static bool check_BETWEEN(const rjson::value* v, const rjson::value& lb, const rjson::value& ub) {
+    if (!v) {
        return false;
    }
+    if (!v->IsObject() || v->MemberCount() != 1) {
+        throw api_error::validation(format("BETWEEN operator encountered malformed AttributeValue: {}", *v));
+    }
+    if (!lb.IsObject() || lb.MemberCount() != 1) {
+        throw api_error::validation(format("BETWEEN operator encountered malformed AttributeValue: {}", lb));
+    }
+    if (!ub.IsObject() || ub.MemberCount() != 1) {
+        throw api_error::validation(format("BETWEEN operator encountered malformed AttributeValue: {}", ub));
+    }

    const auto& kv_v = *v->MemberBegin();
    const auto& kv_lb = *lb.MemberBegin();
    const auto& kv_ub = *ub.MemberBegin();
-    bool bounds_from_query = lb_from_query && ub_from_query;
    if (kv_lb.name != kv_ub.name) {
-        if (bounds_from_query) {
-           throw api_error::validation(
+        throw api_error::validation(
                format("BETWEEN operator requires the same type for lower and upper bound; instead got {} and {}",
                       kv_lb.name, kv_ub.name));
-        } else {
-            return false;
-        }
    }
    if (kv_v.name != kv_lb.name) { // Cannot compare different types, so v is NOT between lb and ub.
        return false;
    }
    if (kv_v.name == "N") {
        const char* diag = "BETWEEN operator";
-        return check_BETWEEN(unwrap_number(*v, diag), unwrap_number(lb, diag), unwrap_number(ub, diag), bounds_from_query);
+        return check_BETWEEN(unwrap_number(*v, diag), unwrap_number(lb, diag), unwrap_number(ub, diag));
    }
    if (kv_v.name == "S") {
        return check_BETWEEN(std::string_view(kv_v.value.GetString(), kv_v.value.GetStringLength()),
                             std::string_view(kv_lb.value.GetString(), kv_lb.value.GetStringLength()),
-                             std::string_view(kv_ub.value.GetString(), kv_ub.value.GetStringLength()),
-                             bounds_from_query);
+                             std::string_view(kv_ub.value.GetString(), kv_ub.value.GetStringLength()));
    }
    if (kv_v.name == "B") {
-        return check_BETWEEN(rjson::base64_decode(kv_v.value), rjson::base64_decode(kv_lb.value), rjson::base64_decode(kv_ub.value), bounds_from_query);
+        return check_BETWEEN(base64_decode(kv_v.value), base64_decode(kv_lb.value), base64_decode(kv_ub.value));
    }
-    if (v_from_query) {
-        throw api_error::validation(
-            format("BETWEEN operator requires AttributeValueList elements to be of type String, Number, or Binary; instead got {}",
+    throw api_error::validation(
+        format("BETWEEN operator requires AttributeValueList elements to be of type String, Number, or Binary; instead got {}",
               kv_lb.name));
-    } else {
-        return false;
-    }
 }

 // Verify one Expect condition on one attribute (whose content is "got")
@@ -519,19 +437,19 @@ static bool verify_expected_one(const rjson::value& condition, const rjson::valu
            return check_NE(got, (*attribute_value_list)[0]);
        case comparison_operator_type::LT:
            verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
-            return check_compare(got, (*attribute_value_list)[0], cmp_lt{}, false, true);
+            return check_compare(got, (*attribute_value_list)[0], cmp_lt{});
        case comparison_operator_type::LE:
            verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
-            return check_compare(got, (*attribute_value_list)[0], cmp_le{}, false, true);
+            return check_compare(got, (*attribute_value_list)[0], cmp_le{});
        case comparison_operator_type::GT:
            verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
-            return check_compare(got, (*attribute_value_list)[0], cmp_gt{}, false, true);
+            return check_compare(got, (*attribute_value_list)[0], cmp_gt{});
        case comparison_operator_type::GE:
            verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
-            return check_compare(got, (*attribute_value_list)[0], cmp_ge{}, false, true);
+            return check_compare(got, (*attribute_value_list)[0], cmp_ge{});
        case comparison_operator_type::BEGINS_WITH:
            verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
-            return check_BEGINS_WITH(got, (*attribute_value_list)[0], false, true);
+            return check_BEGINS_WITH(got, (*attribute_value_list)[0]);
        case comparison_operator_type::IN:
            verify_operand_count(attribute_value_list, nonempty(), *comparison_operator);
            return check_IN(got, *attribute_value_list);
@@ -543,8 +461,7 @@ static bool verify_expected_one(const rjson::value& condition, const rjson::valu
            return check_NOT_NULL(got);
        case comparison_operator_type::BETWEEN:
            verify_operand_count(attribute_value_list, exact_size(2), *comparison_operator);
-            return check_BETWEEN(got, (*attribute_value_list)[0], (*attribute_value_list)[1],
-                                 false, true, true);
+            return check_BETWEEN(got, (*attribute_value_list)[0], (*attribute_value_list)[1]);
        case comparison_operator_type::CONTAINS:
            {
                verify_operand_count(attribute_value_list, exact_size(1), *comparison_operator);
@@ -656,8 +573,7 @@ static bool calculate_primitive_condition(const parsed::primitive_condition& con
            // Shouldn't happen unless we have a bug in the parser
            throw std::logic_error(format("Wrong number of values {} in BETWEEN primitive_condition", cond._values.size()));
        }
-        return check_BETWEEN(&calculated_values[0], calculated_values[1], calculated_values[2],
-                             cond._values[0].is_constant(), cond._values[1].is_constant(), cond._values[2].is_constant());
+        return check_BETWEEN(&calculated_values[0], calculated_values[1], calculated_values[2]);
    case parsed::primitive_condition::type::IN:
        return check_IN(calculated_values);
    case parsed::primitive_condition::type::VALUE:
@@ -688,17 +604,13 @@ static bool calculate_primitive_condition(const parsed::primitive_condition& con
    case parsed::primitive_condition::type::NE:
        return check_NE(&calculated_values[0], calculated_values[1]);
    case parsed::primitive_condition::type::GT:
-        return check_compare(&calculated_values[0], calculated_values[1], cmp_gt{},
-            cond._values[0].is_constant(), cond._values[1].is_constant());
+        return check_compare(&calculated_values[0], calculated_values[1], cmp_gt{});
    case parsed::primitive_condition::type::GE:
-        return check_compare(&calculated_values[0], calculated_values[1], cmp_ge{},
-            cond._values[0].is_constant(), cond._values[1].is_constant());
+        return check_compare(&calculated_values[0], calculated_values[1], cmp_ge{});
    case parsed::primitive_condition::type::LT:
-        return check_compare(&calculated_values[0], calculated_values[1], cmp_lt{},
-            cond._values[0].is_constant(), cond._values[1].is_constant());
+        return check_compare(&calculated_values[0], calculated_values[1], cmp_lt{});
    case parsed::primitive_condition::type::LE:
-        return check_compare(&calculated_values[0], calculated_values[1], cmp_le{},
-            cond._values[0].is_constant(), cond._values[1].is_constant());
+        return check_compare(&calculated_values[0], calculated_values[1], cmp_le{});
    default:
        // Shouldn't happen unless we have a bug in the parser
        throw std::logic_error(format("Unknown type {} in primitive_condition object", (int)(cond._op)));
--- a/alternator/conditions.hh
+++ b/alternator/conditions.hh
@@ -1,9 +1,22 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 /*
@@ -39,7 +52,6 @@ bool verify_expected(const rjson::value& req, const rjson::value* previous_item)
 bool verify_condition(const rjson::value& condition, bool require_all, const rjson::value* previous_item);

 bool check_CONTAINS(const rjson::value* v1, const rjson::value& v2);
-bool check_BEGINS_WITH(const rjson::value* v1, const rjson::value& v2, bool v1_from_query, bool v2_from_query);

 bool verify_condition_expression(
        const parsed::condition_expression& condition_expression,
--- a/alternator/controller.cc
+++ b/alternator/controller.cc
@@ -1,153 +0,0 @@
-/*
- * Copyright (C) 2021-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: AGPL-3.0-or-later
- */
-
-#include <seastar/net/dns.hh>
-#include "controller.hh"
-#include "server.hh"
-#include "executor.hh"
-#include "rmw_operation.hh"
-#include "db/config.hh"
-#include "cdc/generation_service.hh"
-#include "service/memory_limiter.hh"
-
-using namespace seastar;
-
-namespace alternator {
-
-static logging::logger logger("alternator_controller");
-
-controller::controller(
-        sharded<gms::gossiper>& gossiper,
-        sharded<service::storage_proxy>& proxy,
-        sharded<service::migration_manager>& mm,
-        sharded<db::system_distributed_keyspace>& sys_dist_ks,
-        sharded<cdc::generation_service>& cdc_gen_svc,
-        sharded<service::memory_limiter>& memory_limiter,
-        const db::config& config)
-    : _gossiper(gossiper)
-    , _proxy(proxy)
-    , _mm(mm)
-    , _sys_dist_ks(sys_dist_ks)
-    , _cdc_gen_svc(cdc_gen_svc)
-    , _memory_limiter(memory_limiter)
-    , _config(config)
-{
-}
-
-sstring controller::name() const {
-    return "alternator";
-}
-
-sstring controller::protocol() const {
-    return "dynamodb";
-}
-
-sstring controller::protocol_version() const {
-    return version;
-}
-
-std::vector<socket_address> controller::listen_addresses() const {
-    return _listen_addresses;
-}
-
-future<> controller::start_server() {
-    return seastar::async([this] {
-        _listen_addresses.clear();
-
-        auto preferred = _config.listen_interface_prefer_ipv6() ? std::make_optional(net::inet_address::family::INET6) : std::nullopt;
-        auto family = _config.enable_ipv6_dns_lookup() || preferred ? std::nullopt : std::make_optional(net::inet_address::family::INET);
-
-        // Create an smp_service_group to be used for limiting the
-        // concurrency when forwarding Alternator request between
-        // shards - if necessary for LWT.
-        smp_service_group_config c;
-        c.max_nonlocal_requests = 5000;
-        _ssg = create_smp_service_group(c).get0();
-
-        rmw_operation::set_default_write_isolation(_config.alternator_write_isolation());
-        executor::set_default_timeout(std::chrono::milliseconds(_config.alternator_timeout_in_ms()));
-
-        net::inet_address addr = utils::resolve(_config.alternator_address, family).get0();
-
-        auto get_cdc_metadata = [] (cdc::generation_service& svc) { return std::ref(svc.get_cdc_metadata()); };
-
-        _executor.start(std::ref(_gossiper), std::ref(_proxy), std::ref(_mm), std::ref(_sys_dist_ks), sharded_parameter(get_cdc_metadata, std::ref(_cdc_gen_svc)), _ssg.value()).get();
-        _server.start(std::ref(_executor), std::ref(_proxy), std::ref(_gossiper)).get();
-        // Note: from this point on, if start_server() throws for any reason,
-        // it must first call stop_server() to stop the executor and server
-        // services we just started - or Scylla will cause an assertion
-        // failure when the controller object is destroyed in the exception
-        // unwinding.
-        std::optional<uint16_t> alternator_port;
-        if (_config.alternator_port()) {
-            alternator_port = _config.alternator_port();
-            _listen_addresses.push_back({addr, *alternator_port});
-        }
-        std::optional<uint16_t> alternator_https_port;
-        std::optional<tls::credentials_builder> creds;
-        if (_config.alternator_https_port()) {
-            alternator_https_port = _config.alternator_https_port();
-            _listen_addresses.push_back({addr, *alternator_https_port});
-            creds.emplace();
-            auto opts = _config.alternator_encryption_options();
-            if (opts.empty()) {
-                // Earlier versions mistakenly configured Alternator's
-                // HTTPS parameters via the "server_encryption_option"
-                // configuration parameter. We *temporarily* continue
-                // to allow this, for backward compatibility.
-                opts = _config.server_encryption_options();
-                if (!opts.empty()) {
-                logger.warn("Setting server_encryption_options to configure "
-                        "Alternator's HTTPS encryption is deprecated. Please "
-                        "switch to setting alternator_encryption_options instead.");
-                }
-            }
-            opts.erase("require_client_auth");
-            opts.erase("truststore");
-            try {
-                utils::configure_tls_creds_builder(creds.value(), std::move(opts)).get();
-            } catch(...) {
-                logger.error("Failed to set up Alternator TLS credentials: {}", std::current_exception());
-                stop_server().get();
-                std::throw_with_nested(std::runtime_error("Failed to set up Alternator TLS credentials"));
-            }
-        }
-        bool alternator_enforce_authorization = _config.alternator_enforce_authorization();
-        _server.invoke_on_all(
-                [this, addr, alternator_port, alternator_https_port, creds = std::move(creds), alternator_enforce_authorization] (server& server) mutable {
-            return server.init(addr, alternator_port, alternator_https_port, creds, alternator_enforce_authorization,
-                    &_memory_limiter.local().get_semaphore(),
-                    _config.max_concurrent_requests_per_shard);
-        }).handle_exception([this, addr, alternator_port, alternator_https_port] (std::exception_ptr ep) {
-            logger.error("Failed to set up Alternator HTTP server on {} port {}, TLS port {}: {}",
-                    addr, alternator_port ? std::to_string(*alternator_port) : "OFF", alternator_https_port ? std::to_string(*alternator_https_port) : "OFF", ep);
-            return stop_server().then([ep = std::move(ep)] { return make_exception_future<>(ep); });
-        }).then([addr, alternator_port, alternator_https_port] {
-            logger.info("Alternator server listening on {}, HTTP port {}, HTTPS port {}",
-                    addr, alternator_port ? std::to_string(*alternator_port) : "OFF", alternator_https_port ? std::to_string(*alternator_https_port) : "OFF");
-        }).get();
-    });
-}
-
-future<> controller::stop_server() {
-    return seastar::async([this] {
-        if (!_ssg) {
-            return;
-        }
-        _server.stop().get();
-        _executor.stop().get();
-        _listen_addresses.clear();
-        destroy_smp_service_group(_ssg.value()).get();
-    });
-}
-
-future<> controller::request_stop_server() {
-    return stop_server();
-}
-
-}
--- a/alternator/controller.hh
+++ b/alternator/controller.hh
@@ -1,82 +0,0 @@
-/*
- * Copyright (C) 2021-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: AGPL-3.0-or-later
- */
-
-#pragma once
-
-#include <seastar/core/sharded.hh>
-#include <seastar/core/smp.hh>
-
-#include "protocol_server.hh"
-
-namespace service {
-class storage_proxy;
-class migration_manager;
-class memory_limiter;
-}
-
-namespace db {
-class system_distributed_keyspace;
-class config;
-}
-
-namespace cdc {
-class generation_service;
-}
-
-namespace gms {
-
-class gossiper;
-
-}
-
-namespace alternator {
-
-// This is the official DynamoDB API version.
-// It represents the last major reorganization of that API, and all the features
-// that were added since did NOT increment this version string.
-constexpr const char* version = "2012-08-10";
-
-using namespace seastar;
-
-class executor;
-class server;
-
-class controller : public protocol_server {
-    sharded<gms::gossiper>& _gossiper;
-    sharded<service::storage_proxy>& _proxy;
-    sharded<service::migration_manager>& _mm;
-    sharded<db::system_distributed_keyspace>& _sys_dist_ks;
-    sharded<cdc::generation_service>& _cdc_gen_svc;
-    sharded<service::memory_limiter>& _memory_limiter;
-    const db::config& _config;
-
-    std::vector<socket_address> _listen_addresses;
-    sharded<executor> _executor;
-    sharded<server> _server;
-    std::optional<smp_service_group> _ssg;
-
-public:
-    controller(
-        sharded<gms::gossiper>& gossiper,
-        sharded<service::storage_proxy>& proxy,
-        sharded<service::migration_manager>& mm,
-        sharded<db::system_distributed_keyspace>& sys_dist_ks,
-        sharded<cdc::generation_service>& cdc_gen_svc,
-        sharded<service::memory_limiter>& memory_limiter,
-        const db::config& config);
-
-    virtual sstring name() const override;
-    virtual sstring protocol() const override;
-    virtual sstring protocol_version() const override;
-    virtual std::vector<socket_address> listen_addresses() const override;
-    virtual future<> start_server() override;
-    virtual future<> stop_server() override;
-    virtual future<> request_stop_server() override;
-};
-
-}
--- a/alternator/error.hh
+++ b/alternator/error.hh
@@ -1,9 +1,22 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once
@@ -21,7 +34,7 @@ namespace alternator {
 // "ResourceNotFoundException", and a human readable message.
 // Eventually alternator::api_handler will convert a returned or thrown
 // api_error into a JSON object, and that is returned to the user.
-class api_error final : public std::exception {
+class api_error final {
 public:
    using status_type = httpd::reply::status_type;
    status_type _http_code;
@@ -46,9 +59,6 @@ public:
    static api_error invalid_signature(std::string msg) {
        return api_error("InvalidSignatureException", std::move(msg));
    }
-    static api_error missing_authentication_token(std::string msg) {
-        return api_error("MissingAuthenticationTokenException", std::move(msg));
-    }
    static api_error unrecognized_client(std::string msg) {
        return api_error("UnrecognizedClientException", std::move(msg));
    }
@@ -67,23 +77,9 @@ public:
    static api_error trimmed_data_access_exception(std::string msg) {
        return api_error("TrimmedDataAccessException", std::move(msg));
    }
-    static api_error request_limit_exceeded(std::string msg) {
-        return api_error("RequestLimitExceeded", std::move(msg));
-    }
-    static api_error serialization(std::string msg) {
-        return api_error("SerializationException", std::move(msg));
-    }
    static api_error internal(std::string msg) {
        return api_error("InternalServerError", std::move(msg), reply::status_type::internal_server_error);
    }
-
-    // Provide the "std::exception" interface, to make it easier to print this
-    // exception in log messages. Note that this function is *not* used to
-    // format the error to send it back to the client - server.cc has
-    // generate_error_reply() to format an api_error as the DynamoDB protocol
-    // requires.
-    virtual const char* what() const noexcept override;
-    mutable std::string _what_string;
 };

 }
--- a/alternator/executor.cc
+++ b/alternator/executor.cc
--- a/alternator/executor.hh
+++ b/alternator/executor.hh
@@ -1,9 +1,22 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once
@@ -14,9 +27,9 @@
 #include <seastar/json/json_elements.hh>
 #include <seastar/core/sharded.hh>

+#include "service/storage_proxy.hh"
 #include "service/migration_manager.hh"
 #include "service/client_state.hh"
-#include "service_permit.hh"
 #include "db/timeout_clock.hh"

 #include "alternator/error.hh"
@@ -37,17 +50,7 @@ namespace cql3::selection {
 }

 namespace service {
-    class storage_proxy;
-}
-
-namespace cdc {
-    class metadata;
-}
-
-namespace gms {
-
-class gossiper;
-
+    class storage_service;
 }

 namespace alternator {
@@ -60,16 +63,6 @@ public:
    explicit make_jsonable(rjson::value&& value);
    std::string to_json() const override;
 };
-
-/**
- * Make return type for serializing the object "streamed",
- * i.e. direct to HTTP output stream. Note: only useful for
- * (very) large objects as there are overhead issues with this
- * as well, but for massive lists of return objects this can
- * help avoid large allocations/many re-allocs
- */ 
-json::json_return_type make_streamed(rjson::value&&);
-
 struct json_string : public json::jsonable {
    std::string _value;
 public:
@@ -77,82 +70,11 @@ public:
    std::string to_json() const override;
 };

-namespace parsed {
-class path;
-};
-
-const std::map<sstring, sstring>& get_tags_of_table(schema_ptr schema);
-std::optional<std::string> find_tag(const schema& s, const sstring& tag);
-future<> update_tags(service::migration_manager& mm, schema_ptr schema, std::map<sstring, sstring>&& tags_map);
-schema_ptr get_table(service::storage_proxy& proxy, const rjson::value& request);
-
-// An attribute_path_map object is used to hold data for various attributes
-// paths (parsed::path) in a hierarchy of attribute paths. Each attribute path
-// has a root attribute, and then modified by member and index operators -
-// for example in "a.b[2].c" we have "a" as the root, then ".b" member, then
-// "[2]" index, and finally ".c" member.
-// Data can be added to an attribute_path_map using the add() function, but
-// requires that attributes with data not be *overlapping* or *conflicting*:
-//
-// 1. Two attribute paths which are identical or an ancestor of one another
-//    are considered *overlapping* and not allowed. If a.b.c has data,
-//    we can't add more data in a.b.c or any of its descendants like a.b.c.d.
-//
-// 2. Two attribute paths which need the same parent to have both a member and
-//    an index are considered *conflicting* and not allowed. E.g., if a.b has
-//    data, you can't add a[1]. The meaning of adding both would be that the
-//    attribute a is both a map and an array, which isn't sensible.
-//
-// These two requirements are common to the two places where Alternator uses
-// this abstraction to describe how a hierarchical item is to be transformed:
-//
-// 1. In ProjectExpression: for filtering from a full top-level attribute
-//    only the parts for which user asked in ProjectionExpression.
-//
-// 2. In UpdateExpression: for taking the previous value of a top-level
-//    attribute, and modifying it based on the instructions in the user
-//    wrote in UpdateExpression.
-
-template<typename T>
-class attribute_path_map_node {
-public:
-    using data_t = T;
-    // We need the extra unique_ptr<> here because libstdc++ unordered_map
-    // doesn't work with incomplete types :-(
-    using members_t =  std::unordered_map<std::string, std::unique_ptr<attribute_path_map_node<T>>>;
-    // The indexes list is sorted because DynamoDB requires handling writes
-    // beyond the end of a list in index order.
-    using indexes_t = std::map<unsigned, std::unique_ptr<attribute_path_map_node<T>>>;
-    // The prohibition on "overlap" and "conflict" explained above means
-    // That only one of data, members or indexes is non-empty.
-    std::optional<std::variant<data_t, members_t, indexes_t>> _content;
-
-    bool is_empty() const { return !_content; }
-    bool has_value() const { return _content && std::holds_alternative<data_t>(*_content); }
-    bool has_members() const { return _content && std::holds_alternative<members_t>(*_content); }
-    bool has_indexes() const { return _content && std::holds_alternative<indexes_t>(*_content); }
-    // get_members() assumes that has_members() is true
-    members_t& get_members() { return std::get<members_t>(*_content); }
-    const members_t& get_members() const { return std::get<members_t>(*_content); }
-    indexes_t& get_indexes() { return std::get<indexes_t>(*_content); }
-    const indexes_t& get_indexes() const { return std::get<indexes_t>(*_content); }
-    T& get_value() { return std::get<T>(*_content); }
-    const T& get_value() const { return std::get<T>(*_content); }
-};
-
-template<typename T>
-using attribute_path_map = std::unordered_map<std::string, attribute_path_map_node<T>>;
-
-using attrs_to_get_node = attribute_path_map_node<std::monostate>;
-using attrs_to_get = attribute_path_map<std::monostate>;
-
-
 class executor : public peering_sharded_service<executor> {
-    gms::gossiper& _gossiper;
    service::storage_proxy& _proxy;
    service::migration_manager& _mm;
    db::system_distributed_keyspace& _sdks;
-    cdc::metadata& _cdc_metadata;
+    service::storage_service& _ss;
    // An smp_service_group to be used for limiting the concurrency when
    // forwarding Alternator request between shards - if necessary for LWT.
    smp_service_group _ssg;
@@ -165,8 +87,8 @@ public:
    static constexpr auto KEYSPACE_NAME_PREFIX = "alternator_";
    static constexpr std::string_view INTERNAL_TABLE_PREFIX = ".scylla.alternator.";

-    executor(gms::gossiper& gossiper, service::storage_proxy& proxy, service::migration_manager& mm, db::system_distributed_keyspace& sdks, cdc::metadata& cdc_metadata, smp_service_group ssg)
-        : _gossiper(gossiper), _proxy(proxy), _mm(mm), _sdks(sdks), _cdc_metadata(cdc_metadata), _ssg(ssg) {}
+    executor(service::storage_proxy& proxy, service::migration_manager& mm, db::system_distributed_keyspace& sdks, service::storage_service& ss, smp_service_group ssg)
+        : _proxy(proxy), _mm(mm), _sdks(sdks), _ss(ss), _ssg(ssg) {}

    future<request_return_type> create_table(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
    future<request_return_type> describe_table(client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value request);
@@ -185,8 +107,6 @@ public:
    future<request_return_type> tag_resource(client_state& client_state, service_permit permit, rjson::value request);
    future<request_return_type> untag_resource(client_state& client_state, service_permit permit, rjson::value request);
    future<request_return_type> list_tags_of_resource(client_state& client_state, service_permit permit, rjson::value request);
-    future<request_return_type> update_time_to_live(client_state& client_state, service_permit permit, rjson::value request);
-    future<request_return_type> describe_time_to_live(client_state& client_state, service_permit permit, rjson::value request);
    future<request_return_type> list_streams(client_state& client_state, service_permit permit, rjson::value request);
    future<request_return_type> describe_stream(client_state& client_state, service_permit permit, rjson::value request);
    future<request_return_type> get_shard_iterator(client_state& client_state, service_permit permit, rjson::value request);
@@ -195,12 +115,12 @@ public:
    future<> start();
    future<> stop() { return make_ready_future<>(); }

+    future<> create_keyspace(std::string_view keyspace_name);
+
+    static tracing::trace_state_ptr maybe_trace_query(client_state& client_state, sstring_view op, sstring_view query);
+
    static sstring table_name(const schema&);
    static db::timeout_clock::time_point default_timeout();
-    static void set_default_timeout(db::timeout_clock::duration timeout);
-private:
-    static db::timeout_clock::duration s_default_timeout;
-public:
    static schema_ptr find_table(service::storage_proxy&, const rjson::value& request);

 private:
@@ -216,17 +136,19 @@ public:
        const query::partition_slice&,
        const cql3::selection::selection&,
        const query::result&,
-        const attrs_to_get&);
+        const std::unordered_set<std::string>&);

    static void describe_single_item(const cql3::selection::selection&,
        const std::vector<bytes_opt>&,
-        const attrs_to_get&,
+        const std::unordered_set<std::string>&,
        rjson::value&,
        bool = false);

-    static void add_stream_options(const rjson::value& stream_spec, schema_builder&, service::storage_proxy& sp);
-    static void supplement_table_info(rjson::value& descr, const schema& schema, service::storage_proxy& sp);
-    static void supplement_table_stream_info(rjson::value& descr, const schema& schema, service::storage_proxy& sp);
+
+
+    void add_stream_options(const rjson::value& stream_spec, schema_builder&) const;
+    void supplement_table_info(rjson::value& descr, const schema& schema) const;
+    void supplement_table_stream_info(rjson::value& descr, const schema& schema) const;
 };

 }
--- a/alternator/expressions.cc
+++ b/alternator/expressions.cc
@@ -1,14 +1,27 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #include "expressions.hh"
 #include "serialization.hh"
-#include "utils/base64.hh"
+#include "base64.hh"
 #include "conditions.hh"
 #include "alternator/expressionsLexer.hpp"
 #include "alternator/expressionsParser.hpp"
@@ -117,27 +130,6 @@ void condition_expression::append(condition_expression&& a, char op) {
    }, _expression);
 }

-void path::check_depth_limit() {
-    if (1 + _operators.size() > depth_limit) {
-        throw expressions_syntax_error(format("Document path exceeded {} nesting levels", depth_limit));
-    }
-}
-
-std::ostream& operator<<(std::ostream& os, const path& p) {
-    os << p.root();
-    for (const auto& op : p.operators()) {
-        std::visit(overloaded_functor {
-            [&] (const std::string& member) {
-                os << '.' << member;
-            },
-            [&] (unsigned index) {
-                os << '[' << index << ']';
-            }
-        }, op);
-    }
-    return os;
-}
-
 } // namespace parsed

 // The following resolve_*() functions resolve references in parsed
@@ -159,9 +151,10 @@ std::ostream& operator<<(std::ostream& os, const path& p) {
 // we need to resolve the expression just once but then use it many times
 // (once for each item to be filtered).

-static std::optional<std::string> resolve_path_component(const std::string& column_name,
+static void resolve_path(parsed::path& p,
        const rjson::value* expression_attribute_names,
        std::unordered_set<std::string>& used_attribute_names) {
+    const std::string& column_name = p.root();
    if (column_name.size() > 0 && column_name.front() == '#') {
        if (!expression_attribute_names) {
            throw api_error::validation(
@@ -173,30 +166,7 @@ static std::optional<std::string> resolve_path_component(const std::string& colu
                    format("ExpressionAttributeNames missing entry '{}' required by expression", column_name));
        }
        used_attribute_names.emplace(column_name);
-        return std::string(rjson::to_string_view(*value));
-    }
-    return std::nullopt;
-}
-
-static void resolve_path(parsed::path& p,
-        const rjson::value* expression_attribute_names,
-        std::unordered_set<std::string>& used_attribute_names) {
-    std::optional<std::string> r = resolve_path_component(p.root(), expression_attribute_names, used_attribute_names);
-    if (r) {
-        p.set_root(std::move(*r));
-    }
-    for (auto& op : p.operators()) {
-        std::visit(overloaded_functor {
-            [&] (std::string& s) {
-                r = resolve_path_component(s, expression_attribute_names, used_attribute_names);
-                if (r) {
-                    s = std::move(*r);
-                }
-            },
-            [&] (unsigned index) {
-                // nothing to resolve
-            }
-        }, op);
+        p.set_root(std::string(rjson::to_string_view(*value)));
    }
 }

@@ -415,6 +385,24 @@ void for_condition_expression_on(const parsed::condition_expression& ce, const n
 // expression. The parsed expression is assumed to have been "resolved", with
 // the matching resolve_* function.

+// Take two JSON-encoded list values (remember that a list value is
+// {"L": [...the actual list]}) and return the concatenation, again as
+// a list value.
+static rjson::value list_concatenate(const rjson::value& v1, const rjson::value& v2) {
+    const rjson::value* list1 = unwrap_list(v1);
+    const rjson::value* list2 = unwrap_list(v2);
+    if (!list1 || !list2) {
+        throw api_error::validation("UpdateExpression: list_append() given a non-list");
+    }
+    rjson::value cat = rjson::copy(*list1);
+    for (const auto& a : list2->GetArray()) {
+        rjson::push_back(cat, rjson::copy(a));
+    }
+    rjson::value ret = rjson::empty_object();
+    rjson::set(ret, "L", std::move(cat));
+    return ret;
+}
+
 // calculate_size() is ConditionExpression's size() function, i.e., it takes
 // a JSON-encoded value and returns its "size" as defined differently for the
 // different types - also as a JSON-encoded number.
@@ -451,11 +439,11 @@ static rjson::value calculate_size(const rjson::value& v) {
        ret = base64_decoded_len(rjson::to_string_view(it->value));
    } else {
        rjson::value json_ret = rjson::empty_object();
-        rjson::add(json_ret, "null", rjson::value(true));
+        rjson::set(json_ret, "null", rjson::value(true));
        return json_ret;
    }
    rjson::value json_ret = rjson::empty_object();
-    rjson::add(json_ret, "N", rjson::from_string(std::to_string(ret)));
+    rjson::set(json_ret, "N", rjson::from_string(std::to_string(ret)));
    return json_ret;
 }

@@ -474,7 +462,7 @@ static const rjson::value& calculate_value(const parsed::constant& c) {

 static rjson::value to_bool_json(bool b) {
    rjson::value json_ret = rjson::empty_object();
-    rjson::add(json_ret, "BOOL", rjson::value(b));
+    rjson::set(json_ret, "BOOL", rjson::value(b));
    return json_ret;
 }

@@ -499,11 +487,7 @@ std::unordered_map<std::string_view, function_handler_type*> function_handlers {
            }
            rjson::value v1 = calculate_value(f._parameters[0], caller, previous_item);
            rjson::value v2 = calculate_value(f._parameters[1], caller, previous_item);
-            rjson::value ret = list_concatenate(v1, v2);
-            if (ret.IsNull()) {
-                throw api_error::validation("UpdateExpression: list_append() given a non-list");
-            }
-            return ret;
+            return list_concatenate(v1, v2);
        }
    },
    {"if_not_exists", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
@@ -619,8 +603,52 @@ std::unordered_map<std::string_view, function_handler_type*> function_handlers {
            }
            rjson::value v1 = calculate_value(f._parameters[0], caller, previous_item);
            rjson::value v2 = calculate_value(f._parameters[1], caller, previous_item);
-            return to_bool_json(check_BEGINS_WITH(v1.IsNull() ? nullptr : &v1,  v2,
-                                    f._parameters[0].is_constant(), f._parameters[1].is_constant()));
+            // TODO: There's duplication here with check_BEGINS_WITH().
+            // But unfortunately, the two functions differ a bit.
+
+            // If one of v1 or v2 is malformed or has an unsupported type
+            // (not B or S), what we do depends on whether it came from
+            // the user's query (is_constant()), or the item. Unsupported
+            // values in the query result in an error, but if they are in
+            // the item, we silently return false (no match).
+            bool bad = false;
+            if (!v1.IsObject() || v1.MemberCount() != 1) {
+                bad = true;
+                if (f._parameters[0].is_constant()) {
+                    throw api_error::validation(format("{}: begins_with() encountered malformed AttributeValue: {}", caller, v1));
+                }
+            } else if (v1.MemberBegin()->name != "S" && v1.MemberBegin()->name != "B") {
+                bad = true;
+                if (f._parameters[0].is_constant()) {
+                    throw api_error::validation(format("{}: begins_with() supports only string or binary in AttributeValue: {}", caller, v1));
+                }
+            }
+            if (!v2.IsObject() || v2.MemberCount() != 1) {
+                bad = true;
+                if (f._parameters[1].is_constant()) {
+                    throw api_error::validation(format("{}: begins_with() encountered malformed AttributeValue: {}", caller, v2));
+                }
+            } else if (v2.MemberBegin()->name != "S" && v2.MemberBegin()->name != "B") {
+                bad = true;
+                if (f._parameters[1].is_constant()) {
+                    throw api_error::validation(format("{}: begins_with() supports only string or binary in AttributeValue: {}", caller, v2));
+                }
+            }
+            bool ret = false;
+            if (!bad) {
+                auto it1 = v1.MemberBegin();
+                auto it2 = v2.MemberBegin();
+                if (it1->name == it2->name) {
+                    if (it2->name == "S") {
+                        std::string_view val1 = rjson::to_string_view(it1->value);
+                        std::string_view val2 = rjson::to_string_view(it2->value);
+                        ret = val1.starts_with(val2);
+                    } else /* it2->name == "B" */ {
+                        ret = base64_begins_with(rjson::to_string_view(it1->value), rjson::to_string_view(it2->value));
+                    }
+                }
+            }
+            return to_bool_json(ret);
        }
    },
    {"contains", [] (calculate_value_caller caller, const rjson::value* previous_item, const parsed::value::function_call& f) {
@@ -639,55 +667,6 @@ std::unordered_map<std::string_view, function_handler_type*> function_handlers {
    },
 };

-// Given a parsed::path and an item read from the table, extract the value
-// of a certain attribute path, such as "a" or "a.b.c[3]". Returns a null
-// value if the item or the requested attribute does not exist.
-// Note that the item is assumed to be encoded in JSON using DynamoDB
-// conventions - each level of a nested document is a map with one key -
-// a type (e.g., "M" for map) - and its value is the representation of
-// that value.
-static rjson::value extract_path(const rjson::value* item,
-        const parsed::path& p, calculate_value_caller caller) {
-    if (!item) {
-        return rjson::null_value();
-    }
-    const rjson::value* v = rjson::find(*item, p.root());
-    if (!v) {
-        return rjson::null_value();
-    }
-    for (const auto& op : p.operators()) {
-        if (!v->IsObject() || v->MemberCount() != 1) {
-            // This shouldn't happen. We shouldn't have stored malformed
-            // objects. But today Alternator does not validate the structure
-            // of nested documents before storing them, so this can happen on
-            // read.
-            throw api_error::validation(format("{}: malformed item read: {}", *item));
-        }
-        const char* type = v->MemberBegin()->name.GetString();
-        v = &(v->MemberBegin()->value);
-        std::visit(overloaded_functor {
-            [&] (const std::string& member) {
-                if (type[0] == 'M' && v->IsObject()) {
-                    v = rjson::find(*v, member);
-                } else {
-                    v = nullptr;
-                }
-            },
-            [&] (unsigned index) {
-                if (type[0] == 'L' && v->IsArray() && index < v->Size()) {
-                    v = &(v->GetArray()[index]);
-                } else {
-                    v = nullptr;
-                }
-            }
-        }, op);
-        if (!v) {
-            return rjson::null_value();
-        }
-    }
-    return rjson::copy(*v);
-}
-
 // Given a parsed::value, which can refer either to a constant value from
 // ExpressionAttributeValues, to the value of some attribute, or to a function
 // of other values, this function calculates the resulting value.
@@ -705,12 +684,21 @@ rjson::value calculate_value(const parsed::value& v,
            auto function_it = function_handlers.find(std::string_view(f._function_name));
            if (function_it == function_handlers.end()) {
                throw api_error::validation(
-                        format("{}: unknown function '{}' called.", caller, f._function_name));
+                        format("UpdateExpression: unknown function '{}' called.", f._function_name));
            }
            return function_it->second(caller, previous_item, f);
        },
        [&] (const parsed::path& p) -> rjson::value {
-            return extract_path(previous_item, p, caller);
+            if (!previous_item) {
+                return rjson::null_value();
+            }
+            std::string update_path = p.root();
+            if (p.has_operators()) {
+                // FIXME: support this
+                throw api_error::validation("Reading attribute paths not yet implemented");
+            }
+            const rjson::value* previous_value = rjson::find(*previous_item, update_path);
+            return previous_value ? rjson::copy(*previous_value) : rjson::null_value();
        }
    }, v._value);
 }
--- a/alternator/expressions.g
+++ b/alternator/expressions.g
@@ -1,9 +1,25 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
+ *
+ * This file is part of Scylla. See the LICENSE.PROPRIETARY file in the
+ * top-level directory for licensing information.
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 /*
--- a/alternator/expressions.hh
+++ b/alternator/expressions.hh
@@ -1,9 +1,22 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once
--- a/alternator/expressions_types.hh
+++ b/alternator/expressions_types.hh
@@ -1,9 +1,22 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once
@@ -36,23 +49,15 @@ class path {
    // dot (e.g., ".xyz").
    std::string _root;
    std::vector<std::variant<std::string, unsigned>> _operators;
-    // It is useful to limit the depth of a user-specified path, because is
-    // allows us to use recursive algorithms without worrying about recursion
-    // depth. DynamoDB officially limits the length of paths to 32 components
-    // (including the root) so let's use the same limit.
-    static constexpr unsigned depth_limit = 32;
-    void check_depth_limit();
 public:
    void set_root(std::string root) {
        _root = std::move(root);
    }
    void add_index(unsigned i) {
        _operators.emplace_back(i);
-        check_depth_limit();
    }
    void add_dot(std::string(name)) {
        _operators.emplace_back(std::move(name));
-        check_depth_limit();
    }
    const std::string& root() const {
        return _root;
@@ -60,13 +65,6 @@ public:
    bool has_operators() const {
        return !_operators.empty();
    }
-    const std::vector<std::variant<std::string, unsigned>>& operators() const {
-        return _operators;
-    }
-    std::vector<std::variant<std::string, unsigned>>& operators() {
-        return _operators;
-    }
-    friend std::ostream& operator<<(std::ostream&, const path&);
 };

 // When an expression is first parsed, all constants are references, like
--- a/alternator/rmw_operation.hh
+++ b/alternator/rmw_operation.hh
@@ -1,15 +1,29 @@
 /*
- * Copyright 2020-present ScyllaDB
+ * Copyright 2020 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once

 #include "seastarx.hh"
-#include "service/paxos/cas_request.hh"
+#include "service/storage_proxy.hh"
+#include "service/storage_proxy.hh"
 #include "utils/rjson.hh"
 #include "executor.hh"

--- a/alternator/serialization.cc
+++ b/alternator/serialization.cc
@@ -1,13 +1,25 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

-#include "utils/base64.hh"
-#include "utils/rjson.hh"
+#include "base64.hh"
 #include "log.hh"
 #include "serialization.hh"
 #include "error.hh"
@@ -56,7 +68,7 @@ struct from_json_visitor {
        bo.write(t.from_string(rjson::to_string_view(v)));
    }
    void operator()(const bytes_type_impl& t) const {
-        bo.write(rjson::base64_decode(v));
+        bo.write(base64_decode(v));
    }
    void operator()(const boolean_type_impl& t) const {
        bo.write(boolean_type->decompose(v.GetBool()));
@@ -102,18 +114,18 @@ struct to_json_visitor {
    void operator()(const decimal_type_impl& t) const {
        auto s = to_json_string(*decimal_type, bytes(bv));
        //FIXME(sarna): unnecessary copy
-        rjson::add_with_string_name(deserialized, type_ident, rjson::from_string(s));
+        rjson::set_with_string_name(deserialized, type_ident, rjson::from_string(s));
    }
    void operator()(const string_type_impl& t) {
-        rjson::add_with_string_name(deserialized, type_ident, rjson::from_string(reinterpret_cast<const char *>(bv.data()), bv.size()));
+        rjson::set_with_string_name(deserialized, type_ident, rjson::from_string(reinterpret_cast<const char *>(bv.data()), bv.size()));
    }
    void operator()(const bytes_type_impl& t) const {
        std::string b64 = base64_encode(bv);
-        rjson::add_with_string_name(deserialized, type_ident, rjson::from_string(b64));
+        rjson::set_with_string_name(deserialized, type_ident, rjson::from_string(b64));
    }
    // default
    void operator()(const abstract_type& t) const {
-        rjson::add_with_string_name(deserialized, type_ident, rjson::parse(to_json_string(t, bytes(bv))));
+        rjson::set_with_string_name(deserialized, type_ident, rjson::parse(to_json_string(t, bytes(bv))));
    }
 };

@@ -184,7 +196,7 @@ bytes get_key_from_typed_value(const rjson::value& key_typed_value, const column
                format("The AttributeValue for a key attribute cannot contain an empty string value. Key: {}", column.name_as_text()));
    }
    if (column.type == bytes_type) {
-        return rjson::base64_decode(it->value);
+        return base64_decode(it->value);
    } else {
        return column.type->from_string(rjson::to_string_view(it->value));
    }
@@ -246,9 +258,11 @@ big_decimal unwrap_number(const rjson::value& v, std::string_view diagnostic) {
        throw api_error::validation(format("{}: expected number, found type '{}'", diagnostic, it->name));
    }
    try {
+        if (it->value.IsNumber()) {
+             // FIXME(sarna): should use big_decimal constructor with numeric values directly:
+            return big_decimal(rjson::print(it->value));
+        }
        if (!it->value.IsString()) {
-            // We shouldn't reach here. Callers normally validate their input
-            // earlier with validate_value().
            throw api_error::validation(format("{}: improperly formatted number constant", diagnostic));
        }
        return big_decimal(rjson::to_string_view(it->value));
@@ -257,21 +271,6 @@ big_decimal unwrap_number(const rjson::value& v, std::string_view diagnostic) {
    }
 }

-std::optional<big_decimal> try_unwrap_number(const rjson::value& v) {
-    if (!v.IsObject() || v.MemberCount() != 1) {
-        return std::nullopt;
-    }
-    auto it = v.MemberBegin();
-    if (it->name != "N" || !it->value.IsString()) {
-        return std::nullopt;
-    }
-    try {
-        return big_decimal(rjson::to_string_view(it->value));
-    } catch (const marshal_exception& e) {
-        return std::nullopt;
-    }
-}
-
 const std::pair<std::string, const rjson::value*> unwrap_set(const rjson::value& v) {
    if (!v.IsObject() || v.MemberCount() != 1) {
        return {"", nullptr};
@@ -279,7 +278,7 @@ const std::pair<std::string, const rjson::value*> unwrap_set(const rjson::value&
    auto it = v.MemberBegin();
    const std::string it_key = it->name.GetString();
    if (it_key != "SS" && it_key != "BS" && it_key != "NS") {
-        return {std::move(it_key), nullptr};
+        return {"", nullptr};
    }
    return std::make_pair(it_key, &(it->value));
 }
@@ -302,7 +301,7 @@ rjson::value number_add(const rjson::value& v1, const rjson::value& v2) {
    auto n2 = unwrap_number(v2, "UpdateExpression");
    rjson::value ret = rjson::empty_object();
    std::string str_ret = std::string((n1 + n2).to_string());
-    rjson::add(ret, "N", rjson::from_string(str_ret));
+    rjson::set(ret, "N", rjson::from_string(str_ret));
    return ret;
 }

@@ -311,7 +310,7 @@ rjson::value number_subtract(const rjson::value& v1, const rjson::value& v2) {
    auto n2 = unwrap_number(v2, "UpdateExpression");
    rjson::value ret = rjson::empty_object();
    std::string str_ret = std::string((n1 - n2).to_string());
-    rjson::add(ret, "N", rjson::from_string(str_ret));
+    rjson::set(ret, "N", rjson::from_string(str_ret));
    return ret;
 }

@@ -337,7 +336,7 @@ rjson::value set_sum(const rjson::value& v1, const rjson::value& v2) {
        }
    }
    rjson::value ret = rjson::empty_object();
-    rjson::add_with_string_name(ret, set1_type, std::move(sum));
+    rjson::set_with_string_name(ret, set1_type, std::move(sum));
    return ret;
 }

@@ -349,7 +348,7 @@ std::optional<rjson::value> set_diff(const rjson::value& v1, const rjson::value&
    auto [set1_type, set1] = unwrap_set(v1);
    auto [set2_type, set2] = unwrap_set(v2);
    if (set1_type != set2_type) {
-        throw api_error::validation(format("Set DELETE type mismatch: {} and {}", set1_type, set2_type));
+        throw api_error::validation(format("Mismatched set types: {} and {}", set1_type, set2_type));
    }
    if (!set1 || !set2) {
        throw api_error::validation("UpdateExpression: DELETE operation can only be performed on a set");
@@ -365,7 +364,7 @@ std::optional<rjson::value> set_diff(const rjson::value& v1, const rjson::value&
        return std::nullopt;
    }
    rjson::value ret = rjson::empty_object();
-    rjson::add_with_string_name(ret, set1_type, rjson::empty_array());
+    rjson::set_with_string_name(ret, set1_type, rjson::empty_array());
    rjson::value& result_set = ret[set1_type];
    for (const auto& a : set1_raw) {
        rjson::push_back(result_set, rjson::copy(a));
@@ -373,23 +372,4 @@ std::optional<rjson::value> set_diff(const rjson::value& v1, const rjson::value&
    return ret;
 }

-// Take two JSON-encoded list values (remember that a list value is
-// {"L": [...the actual list]}) and return the concatenation, again as
-// a list value.
-// Returns a null value if one of the arguments is not actually a list.
-rjson::value list_concatenate(const rjson::value& v1, const rjson::value& v2) {
-    const rjson::value* list1 = unwrap_list(v1);
-    const rjson::value* list2 = unwrap_list(v2);
-    if (!list1 || !list2) {
-        return rjson::null_value();
-    }
-    rjson::value cat = rjson::copy(*list1);
-    for (const auto& a : list2->GetArray()) {
-        rjson::push_back(cat, rjson::copy(a));
-    }
-    rjson::value ret = rjson::empty_object();
-    rjson::add(ret, "L", std::move(cat));
-    return ret;
-}
-
 }
--- a/alternator/serialization.hh
+++ b/alternator/serialization.hh
@@ -1,16 +1,28 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once

 #include <string>
 #include <string_view>
-#include <optional>
 #include "types.hh"
 #include "schema_fwd.hh"
 #include "keys.hh"
@@ -52,10 +64,6 @@ clustering_key ck_from_json(const rjson::value& item, schema_ptr schema);
 // raises ValidationException with diagnostic.
 big_decimal unwrap_number(const rjson::value& v, std::string_view diagnostic);

-// try_unwrap_number is like unwrap_number, but returns an unset optional
-// when the given v does not encode a number.
-std::optional<big_decimal> try_unwrap_number(const rjson::value& v);
-
 // Check if a given JSON object encodes a set (i.e., it is a {"SS": [...]}, or "NS", "BS"
 // and returns set's type and a pointer to that set. If the object does not encode a set,
 // returned value is {"", nullptr}
@@ -77,11 +85,5 @@ rjson::value set_sum(const rjson::value& v1, const rjson::value& v2);
 // DynamoDB does not allow empty sets, so if resulting set is empty, return
 // an unset optional instead.
 std::optional<rjson::value> set_diff(const rjson::value& v1, const rjson::value& v2);
-// Take two JSON-encoded list values (remember that a list value is
-// {"L": [...the actual list]}) and return the concatenation, again as
-// a list value.
-// Returns a null value if one of the arguments is not actually a list.
-rjson::value list_concatenate(const rjson::value& v1, const rjson::value& v2);
-

 }
--- a/alternator/server.cc
+++ b/alternator/server.cc
@@ -1,29 +1,36 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #include "alternator/server.hh"
 #include "log.hh"
 #include <seastar/http/function_handlers.hh>
-#include <seastar/http/short_streams.hh>
-#include <seastar/core/coroutine.hh>
 #include <seastar/json/json_elements.hh>
-#include <seastar/util/defer.hh>
-#include <seastar/util/short_streams.hh>
 #include "seastarx.hh"
 #include "error.hh"
 #include "utils/rjson.hh"
 #include "auth.hh"
 #include <cctype>
-#include "service/storage_proxy.hh"
-#include "locator/snitch_base.hh"
-#include "gms/gossiper.hh"
+#include "cql3/query_processor.hh"
+#include "service/storage_service.hh"
 #include "utils/overloaded_functor.hh"
-#include "utils/fb_utilities.hh"

 static logging::logger slogger("alternator-server");

@@ -52,40 +59,6 @@ inline std::vector<std::string_view> split(std::string_view text, char separator
    return tokens;
 }

-// Handle CORS (Cross-origin resource sharing) in the HTTP request:
-// If the request has the "Origin" header specifying where the script which
-// makes this request comes from, we need to reply with the header
-// "Access-Control-Allow-Origin: *" saying that this (and any) origin is fine.
-// Additionally, if preflight==true (i.e., this is an OPTIONS request),
-// the script can also "request" in headers that the server allows it to use
-// some HTTP methods and headers in the followup request, and the server
-// should respond by "allowing" them in the response headers.
-// We also add the header "Access-Control-Expose-Headers" to let the script
-// access additional headers in the response.
-// This handle_CORS() should be used when handling any HTTP method - both the
-// usual GET and POST, and also the "preflight" OPTIONS method.
-static void handle_CORS(const request& req, reply& rep, bool preflight) {
-    if (!req.get_header("origin").empty()) {
-        rep.add_header("Access-Control-Allow-Origin", "*");
-        // This is the list that DynamoDB returns for expose headers. I am
-        // not sure why not just return "*" here, what's the risk?
-        rep.add_header("Access-Control-Expose-Headers", "x-amzn-RequestId,x-amzn-ErrorType,x-amzn-ErrorMessage,Date");
-        if (preflight) {
-            sstring s = req.get_header("Access-Control-Request-Headers");
-            if (!s.empty()) {
-                rep.add_header("Access-Control-Allow-Headers", std::move(s));
-            }
-            s = req.get_header("Access-Control-Request-Method");
-            if (!s.empty()) {
-                rep.add_header("Access-Control-Allow-Methods", std::move(s));
-            }
-            // Our CORS response never change anyway, let the browser cache it
-            // for two hours (Chrome's maximum):
-            rep.add_header("Access-Control-Max-Age", "7200");
-        }
-    }
-}
-
 // DynamoDB HTTP error responses are structured as follows
 // https://docs.aws.amazon.com/amazondynamodb/latest/developerguide/Programming.Errors.html
 // Our handlers throw an exception to report an error. If the exception
@@ -120,10 +93,6 @@ public:
                 [&] (const json::json_return_type& json_return_value) {
                     slogger.trace("api_handler success case");
                     if (json_return_value._body_writer) {
-                         // Unfortunately, write_body() forces us to choose
-                         // from a fixed and irrelevant list of "mime-types"
-                         // at this point. But we'll override it with the
-                         // one (application/x-amz-json-1.0) below.
                         rep->write_body("json", std::move(json_return_value._body_writer));
                     } else {
                         rep->_content += json_return_value._res;
@@ -136,16 +105,14 @@ public:

             return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
         });
-    }) { }
+    }), _type("json") { }

    api_handler(const api_handler&) = default;
    future<std::unique_ptr<reply>> handle(const sstring& path,
            std::unique_ptr<request> req, std::unique_ptr<reply> rep) override {
-        handle_CORS(*req, *rep, false);
        return _f_handle(std::move(req), std::move(rep)).then(
                [this](std::unique_ptr<reply> rep) {
-                    rep->set_mime_type("application/x-amz-json-1.0");
-                    rep->done();
+                    rep->done(_type);
                    return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
                });
    }
@@ -159,6 +126,7 @@ protected:
    }

    future_handler_function _f_handle;
+    sstring _type;
 };

 class gated_handler : public handler_base {
@@ -178,7 +146,6 @@ public:
    health_handler(seastar::gate& pending_requests) : gated_handler(pending_requests) {}
 protected:
    virtual future<std::unique_ptr<reply>> do_handle(const sstring& path, std::unique_ptr<request> req, std::unique_ptr<reply> rep) override {
-        handle_CORS(*req, *rep, false);
        rep->set_status(reply::status_type::ok);
        rep->write_body("txt", format("healthy: {}", req->get_header("Host")));
        return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
@@ -186,25 +153,21 @@ protected:
 };

 class local_nodelist_handler : public gated_handler {
-    service::storage_proxy& _proxy;
-    gms::gossiper& _gossiper;
 public:
-    local_nodelist_handler(seastar::gate& pending_requests, service::storage_proxy& proxy, gms::gossiper& gossiper)
-        : gated_handler(pending_requests)
-        , _proxy(proxy)
-        , _gossiper(gossiper) {}
+    local_nodelist_handler(seastar::gate& pending_requests) : gated_handler(pending_requests) {}
 protected:
    virtual future<std::unique_ptr<reply>> do_handle(const sstring& path, std::unique_ptr<request> req, std::unique_ptr<reply> rep) override {
        rjson::value results = rjson::empty_array();
        // It's very easy to get a list of all live nodes on the cluster,
-        // using _gossiper().get_live_members(). But getting
+        // using gms::get_local_gossiper().get_live_members(). But getting
        // just the list of live nodes in this DC needs more elaborate code:
        sstring local_dc = locator::i_endpoint_snitch::get_local_snitch_ptr()->get_datacenter(
                utils::fb_utilities::get_broadcast_address());
        std::unordered_set<gms::inet_address> local_dc_nodes =
-                _proxy.get_token_metadata_ptr()->get_topology().get_datacenter_endpoints().at(local_dc);
+                service::get_local_storage_service().get_token_metadata().
+                get_topology().get_datacenter_endpoints().at(local_dc);
        for (auto& ip : local_dc_nodes) {
-            if (_gossiper.is_alive(ip)) {
+            if (gms::get_local_gossiper().is_alive(ip)) {
                rjson::push_back(results, rjson::from_string(ip.to_sstring()));
            }
        }
@@ -215,26 +178,10 @@ protected:
    }
 };

-// The CORS (Cross-origin resource sharing) protocol can send an OPTIONS
-// request before ("pre-flight") the main request. The response to this
-// request can be empty, but needs to have the right headers (which we
-// fill with handle_CORS())
-class options_handler : public gated_handler {
-public:
-    options_handler(seastar::gate& pending_requests) : gated_handler(pending_requests) {}
-protected:
-    virtual future<std::unique_ptr<reply>> do_handle(const sstring& path, std::unique_ptr<request> req, std::unique_ptr<reply> rep) override {
-        handle_CORS(*req, *rep, true);
-        rep->set_status(reply::status_type::ok);
-        rep->write_body("txt", sstring(""));
-        return make_ready_future<std::unique_ptr<reply>>(std::move(rep));
-    }
-};
-
-future<std::string> server::verify_signature(const request& req, const chunked_content& content) {
+future<> server::verify_signature(const request& req) {
    if (!_enforce_authorization) {
        slogger.debug("Skipping authorization");
-        return make_ready_future<std::string>("<unauthenticated request>");
+        return make_ready_future<>();
    }
    auto host_it = req._headers.find("Host");
    if (host_it == req._headers.end()) {
@@ -242,34 +189,27 @@ future<std::string> server::verify_signature(const request& req, const chunked_c
    }
    auto authorization_it = req._headers.find("Authorization");
    if (authorization_it == req._headers.end()) {
-        throw api_error::missing_authentication_token("Authorization header is mandatory for signature verification");
+        throw api_error::invalid_signature("Authorization header is mandatory for signature verification");
    }
    std::string host = host_it->second;
-    std::string_view authorization_header = authorization_it->second;
-    auto pos = authorization_header.find_first_of(' ');
-    if (pos == std::string_view::npos || authorization_header.substr(0, pos) != "AWS4-HMAC-SHA256") {
-        throw api_error::invalid_signature(format("Authorization header must use AWS4-HMAC-SHA256 algorithm: {}", authorization_header));
-    }
-    authorization_header.remove_prefix(pos+1);
+    std::vector<std::string_view> credentials_raw = split(authorization_it->second, ' ');
    std::string credential;
    std::string user_signature;
    std::string signed_headers_str;
    std::vector<std::string_view> signed_headers;
-    do {
-        // Either one of a comma or space can mark the end of an entry
-        pos = authorization_header.find_first_of(" ,");
-        std::string_view entry = authorization_header.substr(0, pos);
-        if (pos != std::string_view::npos) {
-            authorization_header.remove_prefix(pos + 1);
-        }
-        if (entry.empty()) {
-            continue;
-        }
+    for (std::string_view entry : credentials_raw) {
        std::vector<std::string_view> entry_split = split(entry, '=');
        if (entry_split.size() != 2) {
+            if (entry != "AWS4-HMAC-SHA256") {
+                throw api_error::invalid_signature(format("Only AWS4-HMAC-SHA256 algorithm is supported. Found: {}", entry));
+            }
            continue;
        }
        std::string_view auth_value = entry_split[1];
+        // Commas appear as an additional (quite redundant) delimiter
+        if (auth_value.back() == ',') {
+            auth_value.remove_suffix(1);
+        }
        if (entry_split[0] == "Credential") {
            credential = std::string(auth_value);
        } else if (entry_split[0] == "Signature") {
@@ -279,8 +219,7 @@ future<std::string> server::verify_signature(const request& req, const chunked_c
            signed_headers = split(auth_value, ';');
            std::sort(signed_headers.begin(), signed_headers.end());
        }
-    } while (pos != std::string_view::npos);
-
+    }
    std::vector<std::string_view> credential_split = split(credential, '/');
    if (credential_split.size() != 5) {
        throw api_error::validation(format("Incorrect credential information format: {}", credential));
@@ -304,10 +243,10 @@ future<std::string> server::verify_signature(const request& req, const chunked_c
        }
    }

-    auto cache_getter = [&proxy = _proxy] (std::string username) {
-        return get_key_from_roles(proxy, std::move(username));
+    auto cache_getter = [&qp = _qp] (std::string username) {
+        return get_key_from_roles(qp, std::move(username));
    };
-    return _key_cache.get_ptr(user, cache_getter).then([this, &req, &content,
+    return _key_cache.get_ptr(user, cache_getter).then([this, &req,
                                                    user = std::move(user),
                                                    host = std::move(host),
                                                    datestamp = std::move(datestamp),
@@ -317,102 +256,52 @@ future<std::string> server::verify_signature(const request& req, const chunked_c
                                                    service = std::move(service),
                                                    user_signature = std::move(user_signature)] (key_cache::value_ptr key_ptr) {
        std::string signature = get_signature(user, *key_ptr, std::string_view(host), req._method,
-                datestamp, signed_headers_str, signed_headers_map, content, region, service, "");
+                datestamp, signed_headers_str, signed_headers_map, req.content, region, service, "");

        if (signature != std::string_view(user_signature)) {
            _key_cache.remove(user);
            throw api_error::unrecognized_client("The security token included in the request is invalid.");
        }
-        return user;
    });
 }

-static tracing::trace_state_ptr create_tracing_session(tracing::tracing& tracing_instance) {
-    tracing::trace_state_props_set props;
-    props.set<tracing::trace_state_props::full_tracing>();
-    props.set_if<tracing::trace_state_props::log_slow_query>(tracing_instance.slow_query_tracing_enabled());
-    return tracing_instance.create_session(tracing::trace_type::QUERY, props);
-}
-
-// truncated_content_view() prints a potentially long chunked_content for
-// debugging purposes. In the common case when the content is not excessively
-// long, it just returns a view into the given content, without any copying.
-// But when the content is very long, it is truncated after some arbitrary
-// max_len (or one chunk, whichever comes first), with "<truncated>" added at
-// the end. To do this modification to the string, we need to create a new
-// std::string, so the caller must pass us a reference to one, "buf", where
-// we can store the content. The returned view is only alive for as long this
-// buf is kept alive.
-static std::string_view truncated_content_view(const chunked_content& content, std::string& buf) {
-    constexpr size_t max_len = 1024;
-    if (content.empty()) {
-        return std::string_view();
-    } else if (content.size() == 1 && content.begin()->size() <= max_len) {
-        return std::string_view(content.begin()->get(), content.begin()->size());
-    } else {
-        buf = std::string(content.begin()->get(), std::min(content.begin()->size(), max_len)) + "<truncated>";
-        return std::string_view(buf);
-    }
-}
-
-static tracing::trace_state_ptr maybe_trace_query(service::client_state& client_state, std::string_view username, sstring_view op, const chunked_content& query) {
-    tracing::trace_state_ptr trace_state;
-    tracing::tracing& tracing_instance = tracing::tracing::get_local_tracing_instance();
-    if (tracing_instance.trace_next_query() || tracing_instance.slow_query_tracing_enabled()) {
-        trace_state = create_tracing_session(tracing_instance);
-        std::string buf;
-        tracing::add_session_param(trace_state, "alternator_op", op);
-        tracing::add_query(trace_state, truncated_content_view(query, buf));
-        tracing::begin(trace_state, format("Alternator {}", op), client_state.get_client_address());
-        tracing::set_username(trace_state, auth::authenticated_user(username));
-    }
-    return trace_state;
-}
-
-future<executor::request_return_type> server::handle_api_request(std::unique_ptr<request> req) {
+future<executor::request_return_type> server::handle_api_request(std::unique_ptr<request>&& req) {
    _executor._stats.total_operations++;
    sstring target = req->get_header(TARGET);
    std::vector<std::string_view> split_target = split(target, '.');
    //NOTICE(sarna): Target consists of Dynamo API version followed by a dot '.' and operation type (e.g. CreateTable)
    std::string op = split_target.empty() ? std::string() : std::string(split_target.back());
-    // JSON parsing can allocate up to roughly 2x the size of the raw
-    // document, + a couple of bytes for maintenance.
-    // TODO: consider the case where req->content_length is missing. Maybe
-    // we need to take the content_length_limit and return some of the units
-    // when we finish read_content_and_verify_signature?
-    size_t mem_estimate = req->content_length * 2 + 8000;
-    auto units_fut = get_units(*_memory_limiter, mem_estimate);
-    if (_memory_limiter->waiters()) {
-        ++_executor._stats.requests_blocked_memory;
-    }
-    auto units = co_await std::move(units_fut);
-    assert(req->content_stream);
-    chunked_content content = co_await util::read_entire_stream(*req->content_stream);
-    auto username = co_await verify_signature(*req, content);
-
-    if (slogger.is_enabled(log_level::trace)) {
-        std::string buf;
-        slogger.trace("Request: {} {} {}", op, truncated_content_view(content, buf), req->_headers);
-    }
-    auto callback_it = _callbacks.find(op);
-    if (callback_it == _callbacks.end()) {
-        _executor._stats.unsupported_operations++;
-        co_return api_error::unknown_operation(format("Unsupported operation {}", op));
-    }
-    if (_pending_requests.get_count() >= _max_concurrent_requests) {
-        _executor._stats.requests_shed++;
-        co_return api_error::request_limit_exceeded(format("too many in-flight requests (configured via max_concurrent_requests_per_shard): {}", _pending_requests.get_count()));
-    }
-    _pending_requests.enter();
-    auto leave = defer([this] () noexcept { _pending_requests.leave(); });
-    //FIXME: Client state can provide more context, e.g. client's endpoint address
-    // We use unique_ptr because client_state cannot be moved or copied
-    executor::client_state client_state{executor::client_state::internal_tag()};
-    tracing::trace_state_ptr trace_state = maybe_trace_query(client_state, username, op, content);
-    tracing::trace(trace_state, op);
-    rjson::value json_request = co_await _json_parser.parse(std::move(content));
-    co_return co_await callback_it->second(_executor, client_state, trace_state,
-            make_service_permit(std::move(units)), std::move(json_request), std::move(req));
+    slogger.trace("Request: {} {} {}", op, req->content, req->_headers);
+    return verify_signature(*req).then([this, op, req = std::move(req)] () mutable {
+        auto callback_it = _callbacks.find(op);
+        if (callback_it == _callbacks.end()) {
+            _executor._stats.unsupported_operations++;
+            throw api_error::unknown_operation(format("Unsupported operation {}", op));
+        }
+        return with_gate(_pending_requests, [this, callback_it = std::move(callback_it), op = std::move(op), req = std::move(req)] () mutable {
+            //FIXME: Client state can provide more context, e.g. client's endpoint address
+            // We use unique_ptr because client_state cannot be moved or copied
+            return do_with(std::make_unique<executor::client_state>(executor::client_state::internal_tag()),
+                    [this, callback_it = std::move(callback_it), op = std::move(op), req = std::move(req)] (std::unique_ptr<executor::client_state>& client_state) mutable {
+                tracing::trace_state_ptr trace_state = executor::maybe_trace_query(*client_state, op, req->content);
+                tracing::trace(trace_state, op);
+                // JSON parsing can allocate up to roughly 2x the size of the raw document, + a couple of bytes for maintenance.
+                // FIXME: by this time, the whole HTTP request was already read, so some memory is already occupied.
+                // Once HTTP allows working on streams, we should grab the permit *before* reading the HTTP payload.
+                size_t mem_estimate = req->content.size() * 3 + 8000;
+                auto units_fut = get_units(*_memory_limiter, mem_estimate);
+                if (_memory_limiter->waiters()) {
+                    ++_executor._stats.requests_blocked_memory;
+                }
+                return units_fut.then([this, callback_it = std::move(callback_it), &client_state, trace_state, req = std::move(req)] (semaphore_units<> units) mutable {
+                    return _json_parser.parse(req->content).then([this, callback_it = std::move(callback_it), &client_state, trace_state,
+                            units = std::move(units), req = std::move(req)] (rjson::value json_request) mutable {
+                        return callback_it->second(_executor, *client_state, trace_state, make_service_permit(std::move(units)), std::move(json_request), std::move(req)).finally([trace_state] {});
+                    });
+                });
+            });
+        });
+    });
 }

 void server::set_routes(routes& r) {
@@ -433,19 +322,17 @@ void server::set_routes(routes& r) {
    // consider this to be a security risk, because an attacker can already
    // scan an entire subnet for nodes responding to the health request,
    // or even just scan for open ports.
-    r.put(operation_type::GET, "/localnodes", new local_nodelist_handler(_pending_requests, _proxy, _gossiper));
-    r.put(operation_type::OPTIONS, "/", new options_handler(_pending_requests));
+    r.put(operation_type::GET, "/localnodes", new local_nodelist_handler(_pending_requests));
 }

 //FIXME: A way to immediately invalidate the cache should be considered,
 // e.g. when the system table which stores the keys is changed.
 // For now, this propagation may take up to 1 minute.
-server::server(executor& exec, service::storage_proxy& proxy, gms::gossiper& gossiper)
+server::server(executor& exec, cql3::query_processor& qp)
        : _http_server("http-alternator")
        , _https_server("https-alternator")
        , _executor(exec)
-        , _proxy(proxy)
-        , _gossiper(gossiper)
+        , _qp(qp)
        , _key_cache(1024, 1min, slogger)
        , _enforce_authorization(false)
        , _enabled_servers{}
@@ -502,12 +389,6 @@ server::server(executor& exec, service::storage_proxy& proxy, gms::gossiper& gos
        {"ListTagsOfResource", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
            return e.list_tags_of_resource(client_state, std::move(permit), std::move(json_request));
        }},
-        {"UpdateTimeToLive", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.update_time_to_live(client_state, std::move(permit), std::move(json_request));
-        }},
-        {"DescribeTimeToLive", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
-            return e.describe_time_to_live(client_state, std::move(permit), std::move(json_request));
-        }},
        {"ListStreams", [] (executor& e, executor::client_state& client_state, tracing::trace_state_ptr trace_state, service_permit permit, rjson::value json_request, std::unique_ptr<request> req) {
            return e.list_streams(client_state, std::move(permit), std::move(json_request));
        }},
@@ -524,37 +405,42 @@ server::server(executor& exec, service::storage_proxy& proxy, gms::gossiper& gos
 }

 future<> server::init(net::inet_address addr, std::optional<uint16_t> port, std::optional<uint16_t> https_port, std::optional<tls::credentials_builder> creds,
-        bool enforce_authorization, semaphore* memory_limiter, utils::updateable_value<uint32_t> max_concurrent_requests) {
+        bool enforce_authorization, semaphore* memory_limiter) {
    _memory_limiter = memory_limiter;
    _enforce_authorization = enforce_authorization;
-    _max_concurrent_requests = std::move(max_concurrent_requests);
    if (!port && !https_port) {
        return make_exception_future<>(std::runtime_error("Either regular port or TLS port"
                " must be specified in order to init an alternator HTTP server instance"));
    }
    return seastar::async([this, addr, port, https_port, creds] {
-        _executor.start().get();
+        try {
+            _executor.start().get();

-        if (port) {
-            set_routes(_http_server._routes);
-            _http_server.set_content_length_limit(server::content_length_limit);
-            _http_server.set_content_streaming(true);
-            _http_server.listen(socket_address{addr, *port}).get();
-            _enabled_servers.push_back(std::ref(_http_server));
-        }
-        if (https_port) {
-            set_routes(_https_server._routes);
-            _https_server.set_content_length_limit(server::content_length_limit);
-            _https_server.set_content_streaming(true);
-            _https_server.set_tls_credentials(creds->build_reloadable_server_credentials([](const std::unordered_set<sstring>& files, std::exception_ptr ep) {
-                if (ep) {
-                    slogger.warn("Exception loading {}: {}", files, ep);
-                } else {
-                    slogger.info("Reloaded {}", files);
-                }
-            }).get0());
-            _https_server.listen(socket_address{addr, *https_port}).get();
-            _enabled_servers.push_back(std::ref(_https_server));
+            if (port) {
+                set_routes(_http_server._routes);
+                _http_server.set_content_length_limit(server::content_length_limit);
+                _http_server.listen(socket_address{addr, *port}).get();
+                _enabled_servers.push_back(std::ref(_http_server));
+            }
+            if (https_port) {
+                set_routes(_https_server._routes);
+                _https_server.set_content_length_limit(server::content_length_limit);
+                _https_server.set_tls_credentials(creds->build_reloadable_server_credentials([](const std::unordered_set<sstring>& files, std::exception_ptr ep) {
+                    if (ep) {
+                        slogger.warn("Exception loading {}: {}", files, ep);
+                    } else {
+                        slogger.info("Reloaded {}", files);
+                    }
+                }).get0());
+                _https_server.listen(socket_address{addr, *https_port}).get();
+                _enabled_servers.push_back(std::ref(_https_server));
+            }
+        } catch (...) {
+            slogger.error("Failed to set up Alternator HTTP server on {} port {}, TLS port {}: {}",
+                    addr, port ? std::to_string(*port) : "OFF", https_port ? std::to_string(*https_port) : "OFF", std::current_exception());
+            std::throw_with_nested(std::runtime_error(
+                    format("Failed to set up Alternator HTTP server on {} port {}, TLS port {}",
+                            addr, port ? std::to_string(*port) : "OFF", https_port ? std::to_string(*https_port) : "OFF")));
        }
    });
 }
@@ -576,7 +462,7 @@ server::json_parser::json_parser() : _run_parse_json_thread(async([this] {
                return;
            }
            try {
-                _parsed_document = rjson::parse_yieldable(std::move(_raw_document));
+                _parsed_document = rjson::parse_yieldable(_raw_document);
                _current_exception = nullptr;
            } catch (...) {
                _current_exception = std::current_exception();
@@ -586,12 +472,12 @@ server::json_parser::json_parser() : _run_parse_json_thread(async([this] {
    })) {
 }

-future<rjson::value> server::json_parser::parse(chunked_content&& content) {
+future<rjson::value> server::json_parser::parse(std::string_view content) {
    if (content.size() < yieldable_parsing_threshold) {
-        return make_ready_future<rjson::value>(rjson::parse(std::move(content)));
+        return make_ready_future<rjson::value>(rjson::parse(content));
    }
-    return with_semaphore(_parsing_sem, 1, [this, content = std::move(content)] () mutable {
-        _raw_document = std::move(content);
+    return with_semaphore(_parsing_sem, 1, [this, content] {
+        _raw_document = content;
        _document_waiting.signal();
        return _document_parsed.wait().then([this] {
            if (_current_exception) {
@@ -609,12 +495,5 @@ future<> server::json_parser::stop() {
    return std::move(_run_parse_json_thread);
 }

-const char* api_error::what() const noexcept {
-    if (_what_string.empty()) {
-        _what_string = format("{} {}: {}", _http_code, _type, _msg);
-    }
-    return _what_string.c_str();
-}
-
 }

--- a/alternator/server.hh
+++ b/alternator/server.hh
@@ -1,28 +1,37 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once

 #include "alternator/executor.hh"
 #include <seastar/core/future.hh>
-#include <seastar/core/condition-variable.hh>
 #include <seastar/http/httpd.hh>
 #include <seastar/net/tls.hh>
 #include <optional>
 #include "alternator/auth.hh"
 #include "utils/small_vector.hh"
-#include "utils/updateable_value.hh"
 #include <seastar/core/units.hh>

 namespace alternator {

-using chunked_content = rjson::chunked_content;
-
 class server {
    static constexpr size_t content_length_limit = 16*MB;
    using alternator_callback = std::function<future<executor::request_return_type>(executor&, executor::client_state&,
@@ -32,8 +41,7 @@ class server {
    http_server _http_server;
    http_server _https_server;
    executor& _executor;
-    service::storage_proxy& _proxy;
-    gms::gossiper& _gossiper;
+    cql3::query_processor& _qp;

    key_cache _key_cache;
    bool _enforce_authorization;
@@ -42,11 +50,10 @@ class server {
    alternator_callbacks_map _callbacks;

    semaphore* _memory_limiter;
-    utils::updateable_value<uint32_t> _max_concurrent_requests;

    class json_parser {
        static constexpr size_t yieldable_parsing_threshold = 16*KB;
-        chunked_content _raw_document;
+        std::string_view _raw_document;
        rjson::value _parsed_document;
        std::exception_ptr _current_exception;
        semaphore _parsing_sem{1};
@@ -56,25 +63,21 @@ class server {
        future<> _run_parse_json_thread;
    public:
        json_parser();
-        // Moving a chunked_content into parse() allows parse() to free each
-        // chunk as soon as it is parsed, so when chunks are relatively small,
-        // we don't need to store the sum of unparsed and parsed sizes.
-        future<rjson::value> parse(chunked_content&& content);
+        future<rjson::value> parse(std::string_view content);
        future<> stop();
    };
    json_parser _json_parser;

 public:
-    server(executor& executor, service::storage_proxy& proxy, gms::gossiper& gossiper);
+    server(executor& executor, cql3::query_processor& qp);

    future<> init(net::inet_address addr, std::optional<uint16_t> port, std::optional<uint16_t> https_port, std::optional<tls::credentials_builder> creds,
-            bool enforce_authorization, semaphore* memory_limiter, utils::updateable_value<uint32_t> max_concurrent_requests);
+            bool enforce_authorization, semaphore* memory_limiter);
    future<> stop();
 private:
    void set_routes(seastar::httpd::routes& r);
-    // If verification succeeds, returns the authenticated user's username
-    future<std::string> verify_signature(const seastar::httpd::request&, const chunked_content&);
-    future<executor::request_return_type> handle_api_request(std::unique_ptr<request> req);
+    future<> verify_signature(const seastar::httpd::request& r);
+    future<executor::request_return_type> handle_api_request(std::unique_ptr<request>&& req);
 };

 }
--- a/alternator/stats.cc
+++ b/alternator/stats.cc
@@ -1,9 +1,22 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #include "stats.hh"
@@ -25,7 +38,6 @@ stats::stats() : api_operations{} {
 #define OPERATION_LATENCY(name, CamelCaseName) \
                seastar::metrics::make_histogram("op_latency", \
                        seastar::metrics::description("Latency histogram of an operation via Alternator API"), {op(CamelCaseName)}, [this]{return to_metrics_histogram(api_operations.name);}),
-            OPERATION(batch_get_item, "BatchGetItem")
            OPERATION(batch_write_item, "BatchWriteItem")
            OPERATION(create_backup, "CreateBackup")
            OPERATION(create_global_table, "CreateGlobalTable")
@@ -84,8 +96,6 @@ stats::stats() : api_operations{} {
                    seastar::metrics::description("number writes that had to be bounced from this shard because of LWT requirements")),
            seastar::metrics::make_total_operations("requests_blocked_memory", requests_blocked_memory,
                    seastar::metrics::description("Counts a number of requests blocked due to memory pressure.")),
-            seastar::metrics::make_total_operations("requests_shed", requests_shed,
-                    seastar::metrics::description("Counts a number of requests shed due to overload.")),
            seastar::metrics::make_total_operations("filtered_rows_read_total", cql_stats.filtered_rows_read_total,
                    seastar::metrics::description("number of rows read during filtering operations")),
            seastar::metrics::make_total_operations("filtered_rows_matched_total", cql_stats.filtered_rows_matched_total,
--- a/alternator/stats.hh
+++ b/alternator/stats.hh
@@ -1,9 +1,22 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once
@@ -79,7 +92,6 @@ public:
    uint64_t write_using_lwt = 0;
    uint64_t shard_bounce_for_lwt = 0;
    uint64_t requests_blocked_memory = 0;
-    uint64_t requests_shed = 0;
    // CQL-derived stats
    cql3::cql_stats cql_stats;
 private:
--- a/alternator/streams.cc
+++ b/alternator/streams.cc
@@ -1,9 +1,22 @@
 /*
- * Copyright 2020-present ScyllaDB
+ * Copyright 2020 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #include <type_traits>
@@ -13,22 +26,21 @@

 #include <seastar/json/formatter.hh>

-#include "utils/base64.hh"
+#include "base64.hh"
 #include "log.hh"
+#include "database.hh"
 #include "db/config.hh"

 #include "cdc/log.hh"
 #include "cdc/generation.hh"
 #include "cdc/cdc_options.hh"
-#include "cdc/metadata.hh"
 #include "db/system_distributed_keyspace.hh"
 #include "utils/UUID_gen.hh"
 #include "cql3/selection/selection.hh"
 #include "cql3/result_set.hh"
 #include "cql3/type_json.hh"
-#include "cql3/column_identifier.hh"
 #include "schema_builder.hh"
-#include "service/storage_proxy.hh"
+#include "service/storage_service.hh"
 #include "gms/feature.hh"
 #include "gms/feature_service.hh"

@@ -76,7 +88,7 @@ struct rapidjson::internal::TypeHelper<ValueType, utils::UUID>
 {};

 static db_clock::time_point as_timepoint(const utils::UUID& uuid) {
-    return db_clock::time_point{utils::UUID_gen::unix_timestamp(uuid)};
+    return db_clock::time_point{std::chrono::milliseconds(utils::UUID_gen::get_adjusted_timestamp(uuid))};
 }

 /**
@@ -141,29 +153,24 @@ future<alternator::executor::request_return_type> alternator::executor::list_str
    auto limit = rjson::get_opt<int>(request, "Limit").value_or(std::numeric_limits<int>::max());
    auto streams_start = rjson::get_opt<stream_arn>(request, "ExclusiveStartStreamArn");
    auto table = find_table(_proxy, request);
-    auto db = _proxy.data_dictionary();
-    auto cfs = db.get_tables();
+    auto& db = _proxy.get_db().local();
+    auto& cfs = db.get_column_families();
+    auto i = cfs.begin();
+    auto e = cfs.end();

    if (limit < 1) {
        throw api_error::validation("Limit must be 1 or more");
    }

-    // # 12601 (maybe?) - sort the set of tables on ID. This should ensure we never
-    // generate duplicates in a paged listing here. Can obviously miss things if they 
-    // are added between paged calls and end up with a "smaller" UUID/ARN, but that 
-    // is to be expected.
-    std::sort(cfs.begin(), cfs.end(), [](const data_dictionary::table& t1, const data_dictionary::table& t2) {
-        return t1.schema()->id() < t2.schema()->id();
-    });
-
-    auto i = cfs.begin();
-    auto e = cfs.end();
-
+    // TODO: the unordered_map here is not really well suited for partial
+    // querying - we're sorting on local hash order, and creating a table
+    // between queries may or may not miss info. But that should be rare,
+    // and we can probably expect this to be a single call.
    if (streams_start) {
-        i = std::find_if(i, e, [&](const data_dictionary::table& t) {
-            return t.schema()->id() == streams_start 
-                && cdc::get_base_table(db.real_database(), *t.schema())
-                && is_alternator_keyspace(t.schema()->ks_name())
+        i = std::find_if(i, e, [&](const std::pair<utils::UUID, lw_shared_ptr<column_family>>& p) {
+            return p.first == streams_start 
+                && cdc::get_base_table(db, *p.second->schema())
+                && is_alternator_keyspace(p.second->schema()->ks_name())
                ;
        });
        if (i != e) {
@@ -177,7 +184,7 @@ future<alternator::executor::request_return_type> alternator::executor::list_str
    std::optional<stream_arn> last;

    for (;limit > 0 && i != e; ++i) {
-        auto s = i->schema();
+        auto s = i->second->schema();
        auto& ks_name = s->ks_name();
        auto& cf_name = s->cf_name();

@@ -187,27 +194,27 @@ future<alternator::executor::request_return_type> alternator::executor::list_str
        if (table && ks_name != table->ks_name()) {
            continue;
        }
-        if (cdc::is_log_for_some_table(db.real_database(), ks_name, cf_name)) {
-            if (table && table != cdc::get_base_table(db.real_database(), *s)) {
+        if (cdc::is_log_for_some_table(ks_name, cf_name)) {
+            if (table && table != cdc::get_base_table(db, *s)) {
                continue;
            }

            rjson::value new_entry = rjson::empty_object();

-            last = i->schema()->id();
-            rjson::add(new_entry, "StreamArn", *last);
-            rjson::add(new_entry, "StreamLabel", rjson::from_string(stream_label(*s)));
-            rjson::add(new_entry, "TableName", rjson::from_string(cdc::base_name(table_name(*s))));
+            last = i->first;
+            rjson::set(new_entry, "StreamArn", *last);
+            rjson::set(new_entry, "StreamLabel", rjson::from_string(stream_label(*s)));
+            rjson::set(new_entry, "TableName", rjson::from_string(cdc::base_name(table_name(*s))));
            rjson::push_back(streams, std::move(new_entry));

            --limit;
        }
    }

-    rjson::add(ret, "Streams", std::move(streams));
+    rjson::set(ret, "Streams", std::move(streams));

    if (last) {
-        rjson::add(ret, "LastEvaluatedStreamArn", *last);
+        rjson::set(ret, "LastEvaluatedStreamArn", *last);
    }

    return make_ready_future<executor::request_return_type>(make_jsonable(std::move(ret)));
@@ -287,8 +294,7 @@ sequence_number::sequence_number(std::string_view v)
        // view directly.
        uint128_t tmp{std::string(v)};
        // see above
-        return utils::UUID_gen::get_time_UUID_raw(utils::UUID_gen::decimicroseconds{uint64_t(tmp >> 64)},
-            uint64_t(tmp & std::numeric_limits<uint64_t>::max()));
+        return utils::UUID_gen::get_time_UUID_raw(uint64_t(tmp >> 64), uint64_t(tmp & std::numeric_limits<uint64_t>::max()));
    }())
 {}

@@ -415,7 +421,7 @@ using namespace std::string_literals;
 * This will be a partial overlap, but it is the best we can do.
 */

-static std::chrono::seconds confidence_interval(data_dictionary::database db) {
+static std::chrono::seconds confidence_interval(const database& db) {
    return std::chrono::seconds(db.get_config().alternator_streams_time_window_s());
 }

@@ -433,12 +439,12 @@ future<executor::request_return_type> executor::describe_stream(client_state& cl
    auto stream_arn = rjson::get<alternator::stream_arn>(request, "StreamArn");

    schema_ptr schema, bs;
-    auto db = _proxy.data_dictionary();
+    auto& db = _proxy.get_db().local();

    try {
-        auto cf = db.find_column_family(stream_arn);
+        auto& cf = db.find_column_family(stream_arn);
        schema = cf.schema();
-        bs = cdc::get_base_table(db.real_database(), *schema);
+        bs = cdc::get_base_table(_proxy.get_db().local(), *schema);
    } catch (...) {        
    }
 
@@ -464,7 +470,8 @@ future<executor::request_return_type> executor::describe_stream(client_state& cl
    auto status = "DISABLED";

    if (opts.enabled()) {
-        if (!_cdc_metadata.streams_available()) {
+        auto& metadata = _ss.get_cdc_metadata();
+        if (!metadata.streams_available()) {
            status = "ENABLING";
        } else {
            status = "ENABLED";
@@ -473,18 +480,18 @@ future<executor::request_return_type> executor::describe_stream(client_state& cl

    auto ttl = std::chrono::seconds(opts.ttl());
    
-    rjson::add(stream_desc, "StreamStatus", rjson::from_string(status));
+    rjson::set(stream_desc, "StreamStatus", rjson::from_string(status));

    stream_view_type type = cdc_options_to_steam_view_type(opts);

-    rjson::add(stream_desc, "StreamArn", alternator::stream_arn(schema->id()));
-    rjson::add(stream_desc, "StreamViewType", type);
-    rjson::add(stream_desc, "TableName", rjson::from_string(table_name(*bs)));
+    rjson::set(stream_desc, "StreamArn", alternator::stream_arn(schema->id()));
+    rjson::set(stream_desc, "StreamViewType", type);
+    rjson::set(stream_desc, "TableName", rjson::from_string(table_name(*bs)));

    describe_key_schema(stream_desc, *bs);

    if (!opts.enabled()) {
-        rjson::add(ret, "StreamDescription", std::move(stream_desc));
+        rjson::set(ret, "StreamDescription", std::move(stream_desc));
        return make_ready_future<executor::request_return_type>(make_jsonable(std::move(ret)));
    }

@@ -492,11 +499,19 @@ future<executor::request_return_type> executor::describe_stream(client_state& cl
    // TODO: creation time

    auto normal_token_owners = _proxy.get_token_metadata_ptr()->count_normal_token_owners();
+    // cannot really "resume" query, must iterate all data. because we cannot query neither "time" (pk) > something,
+    // or on expired...
+    // TODO: maybe add secondary index to topology table to enable this?
+    return _sdks.cdc_get_versioned_streams({ normal_token_owners }).then([this, &db, schema, shard_start, limit, ret = std::move(ret), stream_desc = std::move(stream_desc), ttl](std::map<db_clock::time_point, cdc::streams_version> topologies) mutable {

-    // filter out cdc generations older than the table or now() - cdc::ttl (typically dynamodb_streams_max_window - 24h)
-    auto low_ts = std::max(as_timepoint(schema->id()), db_clock::now() - ttl);
+        // filter out cdc generations older than the table or now() - cdc::ttl (typically dynamodb_streams_max_window - 24h)
+        auto low_ts = std::max(as_timepoint(schema->id()), db_clock::now() - ttl);

-    return _sdks.cdc_get_versioned_streams(low_ts, { normal_token_owners }).then([this, db, shard_start, limit, ret = std::move(ret), stream_desc = std::move(stream_desc)] (std::map<db_clock::time_point, cdc::streams_version> topologies) mutable {
+        auto i = topologies.lower_bound(low_ts);
+        // need first gen _intersecting_ the timestamp.
+        if (i != topologies.begin()) {
+            i = std::prev(i);
+        }

        auto e = topologies.end();
        auto prev = e;
@@ -504,7 +519,9 @@ future<executor::request_return_type> executor::describe_stream(client_state& cl

        std::optional<shard_id> last;

-        auto i = topologies.begin();
+        // i is now at the youngest generation we include. make a mark of it.
+        auto first = i;
+
        // if we're a paged query, skip to the generation where we left of.
        if (shard_start) {
            i = topologies.find(shard_start->time);
@@ -530,7 +547,7 @@ future<executor::request_return_type> executor::describe_stream(client_state& cl
        };

        // need a prev even if we are skipping stuff
-        if (i != topologies.begin()) {
+        if (i != first) {
            prev = std::prev(i);
        }

@@ -581,19 +598,19 @@ future<executor::request_return_type> executor::describe_stream(client_state& cl
                        pid = std::prev(pid);
                    }
                    if (pid != pids.end()) {
-                        rjson::add(shard, "ParentShardId", shard_id(prev->first, *pid));
+                        rjson::set(shard, "ParentShardId", shard_id(prev->first, *pid));
                    }
                }

                last.emplace(ts, id);
-                rjson::add(shard, "ShardId", *last);
+                rjson::set(shard, "ShardId", *last);
                auto range = rjson::empty_object();
-                rjson::add(range, "StartingSequenceNumber", sequence_number(utils::UUID_gen::min_time_UUID(ts.time_since_epoch())));
+                rjson::set(range, "StartingSequenceNumber", sequence_number(utils::UUID_gen::min_time_UUID(ts.time_since_epoch().count())));
                if (expired) {
-                    rjson::add(range, "EndingSequenceNumber", sequence_number(utils::UUID_gen::min_time_UUID(expired->time_since_epoch())));
+                    rjson::set(range, "EndingSequenceNumber", sequence_number(utils::UUID_gen::min_time_UUID(expired->time_since_epoch().count())));
                }

-                rjson::add(shard, "SequenceNumberRange", std::move(range));
+                rjson::set(shard, "SequenceNumberRange", std::move(range));
                rjson::push_back(shards, std::move(shard));
                
                if (--limit == 0) {
@@ -605,11 +622,11 @@ future<executor::request_return_type> executor::describe_stream(client_state& cl
        }

        if (last) {
-            rjson::add(stream_desc, "LastEvaluatedShardId", *last);
+            rjson::set(stream_desc, "LastEvaluatedShardId", *last);
        }

-        rjson::add(stream_desc, "Shards", std::move(shards));
-        rjson::add(ret, "StreamDescription", std::move(stream_desc));
+        rjson::set(stream_desc, "Shards", std::move(shards));
+        rjson::set(ret, "StreamDescription", std::move(stream_desc));
            
        return make_ready_future<executor::request_return_type>(make_jsonable(std::move(ret)));
    });
@@ -717,18 +734,18 @@ future<executor::request_return_type> executor::get_shard_iterator(client_state&
    }

    auto stream_arn = rjson::get<alternator::stream_arn>(request, "StreamArn");
-    auto db = _proxy.data_dictionary();
+    auto& db = _proxy.get_db().local();
    
    schema_ptr schema = nullptr;
    std::optional<shard_id> sid;

    try {
-        auto cf = db.find_column_family(stream_arn);
+        auto& cf = db.find_column_family(stream_arn);
        schema = cf.schema();
        sid = rjson::get<shard_id>(request, "ShardId");
    } catch (...) {
    }
-    if (!schema || !cdc::get_base_table(db.real_database(), *schema) || !is_alternator_keyspace(schema->ks_name())) {
+    if (!schema || !cdc::get_base_table(db, *schema) || !is_alternator_keyspace(schema->ks_name())) {
        throw api_error::resource_not_found("Invalid StreamArn");
    }
    if (!sid) {
@@ -754,7 +771,7 @@ future<executor::request_return_type> executor::get_shard_iterator(client_state&
            inclusive_of_threshold = true;
            break;
        case shard_iterator_type::LATEST:
-            threshold = utils::UUID_gen::min_time_UUID((db_clock::now() - confidence_interval(db)).time_since_epoch());
+            threshold = utils::UUID_gen::min_time_UUID((db_clock::now() - confidence_interval(db)).time_since_epoch().count());
            inclusive_of_threshold = true;
            break;
    }
@@ -762,7 +779,7 @@ future<executor::request_return_type> executor::get_shard_iterator(client_state&
    shard_iterator iter(stream_arn, *sid, threshold, inclusive_of_threshold);

    auto ret = rjson::empty_object();
-    rjson::add(ret, "ShardIterator", iter);
+    rjson::set(ret, "ShardIterator", iter);

    return make_ready_future<executor::request_return_type>(make_jsonable(std::move(ret)));
 }
@@ -805,12 +822,12 @@ future<executor::request_return_type> executor::get_records(client_state& client
        throw api_error::validation("Limit must be 1 or more");
    }

-    auto db = _proxy.data_dictionary();
+    auto& db = _proxy.get_db().local();
    schema_ptr schema, base;
    try {
-        auto log_table = db.find_column_family(iter.table);
+        auto& log_table = db.find_column_family(iter.table);
        schema = log_table.schema();
-        base = cdc::get_base_table(db.real_database(), *schema);
+        base = cdc::get_base_table(db, *schema);
    } catch (...) {        
    }

@@ -826,7 +843,7 @@ future<executor::request_return_type> executor::get_records(client_state& client
    dht::partition_range_vector partition_ranges{ dht::partition_range::make_singular(dht::decorate_key(*schema, pk)) };

    auto high_ts = db_clock::now() - confidence_interval(db);
-    auto high_uuid = utils::UUID_gen::min_time_UUID(high_ts.time_since_epoch());
+    auto high_uuid = utils::UUID_gen::min_time_UUID(high_ts.time_since_epoch().count());
    auto lo = clustering_key_prefix::from_exploded(*schema, { iter.threshold.serialize() });
    auto hi = clustering_key_prefix::from_exploded(*schema, { high_uuid.serialize() });

@@ -838,18 +855,16 @@ future<executor::request_return_type> executor::get_records(client_state& client
    static const bytes op_column_name = cdc::log_meta_column_name_bytes("operation");
    static const bytes eor_column_name = cdc::log_meta_column_name_bytes("end_of_batch");

-    auto key_names = boost::copy_range<attrs_to_get>(
+    auto key_names = boost::copy_range<std::unordered_set<std::string>>(
        boost::range::join(std::move(base->partition_key_columns()), std::move(base->clustering_key_columns()))
-        | boost::adaptors::transformed([&] (const column_definition& cdef) {
-            return std::make_pair<std::string, attrs_to_get_node>(cdef.name_as_text(), {}); })
+        | boost::adaptors::transformed([&] (const column_definition& cdef) { return cdef.name_as_text(); })
    );
    // Include all base table columns as values (in case pre or post is enabled).
    // This will include attributes not stored in the frozen map column
-    auto attr_names = boost::copy_range<attrs_to_get>(base->regular_columns()
+    auto attr_names = boost::copy_range<std::unordered_set<std::string>>(base->regular_columns()
        // this will include the :attrs column, which we will also force evaluating. 
        // But not having this set empty forces out any cdc columns from actual result 
-        | boost::adaptors::transformed([] (const column_definition& cdef) {
-            return std::make_pair<std::string, attrs_to_get_node>(cdef.name_as_text(), {}); })
+        | boost::adaptors::transformed([] (const column_definition& cdef) { return cdef.name_as_text(); })
    );

    std::vector<const column_definition*> columns;
@@ -918,13 +933,13 @@ future<executor::request_return_type> executor::get_records(client_state& client

        auto maybe_add_record = [&] {
            if (!dynamodb.ObjectEmpty()) {
-                rjson::add(record, "dynamodb", std::move(dynamodb));
+                rjson::set(record, "dynamodb", std::move(dynamodb));
                dynamodb = rjson::empty_object();
            }
            if (!record.ObjectEmpty()) {
                // TODO: awsRegion?
-                rjson::add(record, "eventID", event_id(iter.shard.id, *timestamp));
-                rjson::add(record, "eventSource", "scylladb:alternator");
+                rjson::set(record, "eventID", event_id(iter.shard.id, *timestamp));
+                rjson::set(record, "eventSource", "scylladb:alternator");
                rjson::push_back(records, std::move(record));
                record = rjson::empty_object();
                --limit;
@@ -939,10 +954,10 @@ future<executor::request_return_type> executor::get_records(client_state& client
            if (!dynamodb.HasMember("Keys")) {
                auto keys = rjson::empty_object();
                describe_single_item(*selection, row, key_names, keys);
-                rjson::add(dynamodb, "Keys", std::move(keys));
-                rjson::add(dynamodb, "ApproximateCreationDateTime", utils::UUID_gen::unix_timestamp_in_sec(ts).count());
-                rjson::add(dynamodb, "SequenceNumber", sequence_number(ts));
-                rjson::add(dynamodb, "StreamViewType", type);
+                rjson::set(dynamodb, "Keys", std::move(keys));
+                rjson::set(dynamodb, "ApproximateCreationDateTime", utils::UUID_gen::unix_timestamp_in_sec(ts).count());
+                rjson::set(dynamodb, "SequenceNumber", sequence_number(ts));
+                rjson::set(dynamodb, "StreamViewType", type);
                //TODO: SizeInBytes
            }

@@ -974,17 +989,17 @@ future<executor::request_return_type> executor::get_records(client_state& client
                auto item = rjson::empty_object();
                describe_single_item(*selection, row, attr_names, item, true);
                describe_single_item(*selection, row, key_names, item);
-                rjson::add(dynamodb, op == cdc::operation::pre_image ? "OldImage" : "NewImage", std::move(item));
+                rjson::set(dynamodb, op == cdc::operation::pre_image ? "OldImage" : "NewImage", std::move(item));
                break;
            }
            case cdc::operation::update:
-                rjson::add(record, "eventName", "MODIFY");
+                rjson::set(record, "eventName", "MODIFY");
                break;
            case cdc::operation::insert:
-                rjson::add(record, "eventName", "INSERT");
+                rjson::set(record, "eventName", "INSERT");
                break;
            default:
-                rjson::add(record, "eventName", "REMOVE");
+                rjson::set(record, "eventName", "REMOVE");
                break;
            }
            if (eor) {
@@ -998,7 +1013,7 @@ future<executor::request_return_type> executor::get_records(client_state& client

        auto ret = rjson::empty_object();
        auto nrecords = records.Size();
-        rjson::add(ret, "Records", std::move(records));
+        rjson::set(ret, "Records", std::move(records));

        if (nrecords != 0) {
            // #9642. Set next iterators threshold to > last
@@ -1007,15 +1022,13 @@ future<executor::request_return_type> executor::get_records(client_state& client
            // without checking if maybe we reached the end-of-shard. If the
            // shard did end, then the next read will have nrecords == 0 and
            // will notice end end of shard and not return NextShardIterator.
-            rjson::add(ret, "NextShardIterator", next_iter);
+            rjson::set(ret, "NextShardIterator", next_iter);
            _stats.api_operations.get_records_latency.add(std::chrono::steady_clock::now() - start_time);
            return make_ready_future<executor::request_return_type>(make_jsonable(std::move(ret)));
        }

        // ugh. figure out if we are and end-of-shard
-        auto normal_token_owners = _proxy.get_token_metadata_ptr()->count_normal_token_owners();
-
-        return _sdks.cdc_current_generation_timestamp({ normal_token_owners }).then([this, iter, high_ts, start_time, ret = std::move(ret), nrecords](db_clock::time_point ts) mutable {
+        return cdc::get_local_streams_timestamp().then([this, iter, high_ts, start_time, ret = std::move(ret)](db_clock::time_point ts) mutable {
            auto& shard = iter.shard;            

            if (shard.time < ts && ts < high_ts) {
@@ -1028,27 +1041,23 @@ future<executor::request_return_type> executor::get_records(client_state& client
                // a search from it until high_ts and found nothing, so we
                // can also start the next search from high_ts.
                // TODO: but why? It's simpler just to leave the iterator be.
-                shard_iterator next_iter(iter.table, iter.shard, utils::UUID_gen::min_time_UUID(high_ts.time_since_epoch()), true);
-                rjson::add(ret, "NextShardIterator", iter);
+                shard_iterator next_iter(iter.table, iter.shard, utils::UUID_gen::min_time_UUID(high_ts.time_since_epoch().count()), true);
+                rjson::set(ret, "NextShardIterator", iter);
            }
            _stats.api_operations.get_records_latency.add(std::chrono::steady_clock::now() - start_time);
-            // TODO: determine a better threshold...
-            if (nrecords > 10) {
-                return make_ready_future<executor::request_return_type>(make_streamed(std::move(ret)));
-            }
            return make_ready_future<executor::request_return_type>(make_jsonable(std::move(ret)));
        });
    });
 }

-void executor::add_stream_options(const rjson::value& stream_specification, schema_builder& builder, service::storage_proxy& sp) {
+void executor::add_stream_options(const rjson::value& stream_specification, schema_builder& builder) const {
    auto stream_enabled = rjson::find(stream_specification, "StreamEnabled");
    if (!stream_enabled || !stream_enabled->IsBool()) {
        throw api_error::validation("StreamSpecification needs boolean StreamEnabled");
    }

    if (stream_enabled->GetBool()) {
-        auto db = sp.data_dictionary();
+        auto& db = _proxy.get_db().local();

        if (!db.features().cluster_supports_cdc()) {
            throw api_error::validation("StreamSpecification: streams (CDC) feature not enabled in cluster.");
@@ -1085,17 +1094,17 @@ void executor::add_stream_options(const rjson::value& stream_specification, sche
    }
 }

-void executor::supplement_table_stream_info(rjson::value& descr, const schema& schema, service::storage_proxy& sp) {
+void executor::supplement_table_stream_info(rjson::value& descr, const schema& schema) const {
    auto& opts = schema.cdc_options();
    if (opts.enabled()) {
-        auto db = sp.data_dictionary();
-        auto cf = db.find_table(schema.ks_name(), cdc::log_name(schema.cf_name()));
+        auto& db = _proxy.get_db().local();
+        auto& cf = db.find_column_family(schema.ks_name(), cdc::log_name(schema.cf_name()));
        stream_arn arn(cf.schema()->id());
-        rjson::add(descr, "LatestStreamArn", arn);
-        rjson::add(descr, "LatestStreamLabel", rjson::from_string(stream_label(*cf.schema())));
+        rjson::set(descr, "LatestStreamArn", arn);
+        rjson::set(descr, "LatestStreamLabel", rjson::from_string(stream_label(*cf.schema())));

        auto stream_desc = rjson::empty_object();
-        rjson::add(stream_desc, "StreamEnabled", true);
+        rjson::set(stream_desc, "StreamEnabled", true);

        auto mode = stream_view_type::KEYS_ONLY;
        if (opts.preimage() && opts.postimage()) {
@@ -1105,8 +1114,8 @@ void executor::supplement_table_stream_info(rjson::value& descr, const schema& s
        } else if (opts.postimage()) {
            mode = stream_view_type::NEW_IMAGE;
        }
-        rjson::add(stream_desc, "StreamViewType", mode);
-        rjson::add(descr, "StreamSpecification", std::move(stream_desc));
+        rjson::set(stream_desc, "StreamViewType", mode);
+        rjson::set(descr, "StreamSpecification", std::move(stream_desc));
    }
 }

--- a/alternator/tags_extension.hh
+++ b/alternator/tags_extension.hh
@@ -1,9 +1,22 @@
 /*
- * Copyright 2019-present ScyllaDB
+ * Copyright 2019 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once
--- a/alternator/ttl.cc
+++ b/alternator/ttl.cc
@@ -1,783 +0,0 @@
-/*
- * Copyright 2021-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: AGPL-3.0-or-later
- */
-
-#include <chrono>
-#include <cstdint>
-#include <optional>
-#include <seastar/core/sstring.hh>
-#include <seastar/core/coroutine.hh>
-#include <seastar/core/sleep.hh>
-#include <seastar/core/future.hh>
-#include <seastar/coroutine/maybe_yield.hh>
-#include <boost/multiprecision/cpp_int.hpp>
-
-#include "gms/gossiper.hh"
-#include "gms/inet_address.hh"
-#include "inet_address_vectors.hh"
-#include "locator/abstract_replication_strategy.hh"
-#include "log.hh"
-#include "gc_clock.hh"
-#include "replica/database.hh"
-#include "service_permit.hh"
-#include "timestamp.hh"
-#include "service/storage_proxy.hh"
-#include "service/pager/paging_state.hh"
-#include "service/pager/query_pagers.hh"
-#include "gms/feature_service.hh"
-#include "sstables/types.hh"
-#include "mutation.hh"
-#include "types.hh"
-#include "types/map.hh"
-#include "utils/rjson.hh"
-#include "utils/big_decimal.hh"
-#include "utils/fb_utilities.hh"
-#include "cql3/selection/selection.hh"
-#include "cql3/values.hh"
-#include "cql3/query_options.hh"
-#include "cql3/column_identifier.hh"
-#include "alternator/executor.hh"
-#include "alternator/controller.hh"
-#include "alternator/serialization.hh"
-#include "dht/sharder.hh"
-
-#include "ttl.hh"
-
-static logging::logger tlogger("alternator_ttl");
-
-namespace alternator {
-
-// We write the expiration-time attribute enabled on a table using a
-// tag TTL_TAG_KEY.
-// Currently, the *value* of this tag is simply the name of the attribute,
-// and the expiration scanner interprets it as an Alternator attribute name -
-// It can refer to a real column or if that doesn't exist, to a member of
-// the ":attrs" map column. Although this is designed for Alternator, it may
-// be good enough for CQL as well (there, the ":attrs" column won't exist).
-static const sstring TTL_TAG_KEY("system:ttl_attribute");
-
-future<executor::request_return_type> executor::update_time_to_live(client_state& client_state, service_permit permit, rjson::value request) {
-    _stats.api_operations.update_time_to_live++;
-    if (!_proxy.data_dictionary().features().cluster_supports_alternator_ttl()) {
-        co_return api_error::unknown_operation("UpdateTimeToLive not yet supported. Experimental support is available if the 'alternator-ttl' experimental feature is enabled on all nodes.");
-    }
-
-    schema_ptr schema = get_table(_proxy, request);
-    rjson::value* spec = rjson::find(request, "TimeToLiveSpecification");
-    if (!spec || !spec->IsObject()) {
-        co_return api_error::validation("UpdateTimeToLive missing mandatory TimeToLiveSpecification");
-    }
-    const rjson::value* v = rjson::find(*spec, "Enabled");
-    if (!v || !v->IsBool()) {
-        co_return api_error::validation("UpdateTimeToLive requires boolean Enabled");
-    }
-    bool enabled = v->GetBool();
-    v = rjson::find(*spec, "AttributeName");
-    if (!v || !v->IsString()) {
-        co_return api_error::validation("UpdateTimeToLive requires string AttributeName");
-    }
-    // Although the DynamoDB documentation specifies that attribute names
-    // should be between 1 and 64K bytes, in practice, it only allows
-    // between 1 and 255 bytes. There are no other limitations on which
-    // characters are allowed in the name.
-    if (v->GetStringLength() < 1 || v->GetStringLength() > 255) {
-        co_return api_error::validation("The length of AttributeName must be between 1 and 255");
-    }
-    sstring attribute_name(v->GetString(), v->GetStringLength());
-
-    std::map<sstring, sstring> tags_map = get_tags_of_table(schema);
-    if (enabled) {
-        if (tags_map.contains(TTL_TAG_KEY)) {
-            co_return api_error::validation("TTL is already enabled");
-        }
-        tags_map[TTL_TAG_KEY] = attribute_name;
-    } else {
-        auto i = tags_map.find(TTL_TAG_KEY);
-        if (i == tags_map.end()) {
-            co_return api_error::validation("TTL is already disabled");
-        } else if (i->second != attribute_name) {
-            co_return api_error::validation(format(
-                "Requested to disable TTL on attribute {}, but a different attribute {} is enabled.",
-                attribute_name, i->second));
-        }
-        tags_map.erase(TTL_TAG_KEY);
-    }
-    co_await update_tags(_mm, schema, std::move(tags_map));
-    // Prepare the response, which contains a TimeToLiveSpecification
-    // basically identical to the request's
-    rjson::value response = rjson::empty_object();
-    rjson::add(response, "TimeToLiveSpecification", std::move(*spec));
-    co_return make_jsonable(std::move(response));
-}
-
-future<executor::request_return_type> executor::describe_time_to_live(client_state& client_state, service_permit permit, rjson::value request) {
-    _stats.api_operations.describe_time_to_live++;
-    schema_ptr schema = get_table(_proxy, request);
-    std::map<sstring, sstring> tags_map = get_tags_of_table(schema);
-    rjson::value desc = rjson::empty_object();
-    auto i = tags_map.find(TTL_TAG_KEY);
-    if (i == tags_map.end()) {
-        rjson::add(desc, "TimeToLiveStatus", "DISABLED");
-    } else {
-        rjson::add(desc, "TimeToLiveStatus", "ENABLED");
-        rjson::add(desc, "AttributeName", rjson::from_string(i->second));
-    }
-    rjson::value response = rjson::empty_object();
-    rjson::add(response, "TimeToLiveDescription", std::move(desc));
-    co_return make_jsonable(std::move(response));
-}
-
-// expiration_service is a sharded service responsible for cleaning up expired
-// items in all tables with per-item expiration enabled. Currently, this means
-// Alternator tables with TTL configured via a UpdateTimeToLeave request.
-//
-// Here is a brief overview of how the expiration service works:
-//
-// An expiration thread on each shard periodically scans the items (i.e.,
-// rows) owned by this shard, looking for items whose chosen expiration-time
-// attribute indicates they are expired, and deletes those items.
-// The expiration-time "attribute" can be either an actual Scylla column
-// (must be numeric) or an Alternator "attribute" - i.e., an element in
-// the ATTRS_COLUMN_NAME map<utf8,bytes> column where the numeric expiration
-// time is encoded in DynamoDB's JSON encoding inside the bytes value.
-// To avoid scanning the same items RF times in RF replicas, only one node is
-// responsible for scanning a token range at a time. Normally, this is the
-// node owning this range as a "primary range" (the first node in the ring
-// with this range), but when this node is down, other nodes may take over
-// (FIXME: this is not implemented yet).
-// An expiration thread is reponsible for all tables which need expiration
-// scans. FIXME: explain how this is done with multiple tables - parallel,
-// staggered, or what?
-// The expiration thread scans item using CL=QUORUM to ensures that it reads
-// a consistent expiration-time attribute. This means that the items are read
-// locally and in addition QUORUM-1 additional nodes (one additional node
-// when RF=3) need to read the data and send digests.
-// FIXME: explain if we can read the exact attribute or the entire map.
-// When the expiration thread decides that an item has expired and wants
-// to delete it, it does it using a CL=QUORUM write. This allows this
-// deletion to be visible for consistent (quorum) reads. The deletion,
-// like user deletions, will also appear on the CDC log and therefore
-// Alternator Streams if enabled (FIXME: explain how we mark the
-// deletion different from user deletes. We don't do it yet.).
-expiration_service::expiration_service(data_dictionary::database db, service::storage_proxy& proxy)
-        : _db(db)
-        , _proxy(proxy)
-{
-    //FIXME: add metrics for the service
-    //setup_metrics();
-}
-
-// Convert the big_decimal used to represent expiration time to an integer.
-// Any fractional part is dropped. If the number is negative or invalid,
-// 0 is returned, and if it's too high, the maximum unsigned long is returned.
-static unsigned long bigdecimal_to_ul(const big_decimal& bd) {
-    // The big_decimal format has an integer mantissa of arbitrary length
-    // "unscaled_value" and then a (power of 10) exponent "scale".
-    if (bd.unscaled_value() <= 0) {
-        return 0;
-    }
-    if (bd.scale() == 0) {
-        // The fast path, when the expiration time is an integer, scale==0.
-        return static_cast<unsigned long>(bd.unscaled_value());
-    }
-    // Because the mantissa can be of arbitrary length, we work on it
-    // as a string. TODO: find a less ugly algorithm.
-    auto str = bd.unscaled_value().str();
-    if (bd.scale() > 0) {
-        int len = str.length();
-        if (len < bd.scale()) {
-            return 0;
-        }
-        str = str.substr(0, len-bd.scale());
-    } else {
-        if (bd.scale() < -20) {
-            return std::numeric_limits<unsigned long>::max();
-        }
-        for (int i = 0; i < -bd.scale(); i++) {
-            str.push_back('0');
-        }
-    }
-    // strtoul() returns ULONG_MAX if the number is too large, or 0 if not
-    // a number.
-    return strtoul(str.c_str(), nullptr, 10);
-}
-
-// The following is_expired() functions all check if an item with the given
-// expiration time has expired, according to the DynamoDB API rules.
-// The rules are:
-// 1. If the expiration time attribute's value is not a number type,
-//    the item is not expired.
-// 2. The expiration time is measured in seconds since the UNIX epoch.
-// 3. If the expiration time is more than 5 years in the past, it is assumed
-//    to be malformed and ignored - and the item does not expire.
-static bool is_expired(gc_clock::time_point expiration_time, gc_clock::time_point now) {
-    return expiration_time <= now &&
-           expiration_time > now - std::chrono::years(5);
-}
-
-static bool is_expired(const big_decimal& expiration_time, gc_clock::time_point now) {
-    unsigned long t = bigdecimal_to_ul(expiration_time);
-    // We assume - and the assumption turns out to be correct - that the
-    // epoch of gc_clock::time_point and the one used by the DynamoDB protocol
-    // are the same (the UNIX epoch in UTC). The resolution (seconds) is also
-    // the same.
-    return is_expired(gc_clock::time_point(gc_clock::duration(std::chrono::seconds(t))), now);
-}
-static bool is_expired(const rjson::value& expiration_time, gc_clock::time_point now) {
-    std::optional<big_decimal> n = try_unwrap_number(expiration_time);
-    return n && is_expired(*n, now);
-}
-
-// expire_item() expires an item - i.e., deletes it as appropriate for
-// expiration - with CL=QUORUM and (FIXME!) in a way Alternator Streams
-// understands it is an expiration event - not a user-initiated deletion.
-static future<> expire_item(service::storage_proxy& proxy,
-                            const service::query_state& qs,
-                            const std::vector<bytes_opt>& row,
-                            schema_ptr schema,
-                            api::timestamp_type ts) {
-    // Prepare the row key to delete
-    // NOTICE: the order of columns is guaranteed by the fact that selection::wildcard
-    // is used, which indicates that columns appear in the order defined by
-    // schema::all_columns_in_select_order() - partition key columns goes first,
-    // immediately followed by clustering key columns
-    std::vector<bytes> exploded_pk;
-    const unsigned pk_size = schema->partition_key_size();
-    const unsigned ck_size = schema->clustering_key_size();
-    for (unsigned c = 0; c < pk_size; ++c) {
-        const auto& row_c = row[c];
-        if (!row_c) {
-            // This shouldn't happen - all key columns must have values.
-            // But if it ever happens, let's just *not* expire the item.
-            // FIXME: log or increment a metric if this happens.
-            return make_ready_future<>();
-        }
-        exploded_pk.push_back(*row_c);
-    }
-    auto pk = partition_key::from_exploded(exploded_pk);
-    mutation m(schema, pk);
-    // If there's no clustering key, a tombstone should be created directly
-    // on a partition, not on a clustering row - otherwise it will look like
-    // an open-ended range tombstone, which will crash on KA/LA sstable format.
-    // See issue #6035
-    if (ck_size == 0) {
-        m.partition().apply(tombstone(ts, gc_clock::now()));
-    } else {
-        std::vector<bytes> exploded_ck;
-        for (unsigned c = pk_size; c < pk_size + ck_size; ++c) {
-            const auto& row_c = row[c];
-            if (!row_c) {
-                // This shouldn't happen - all key columns must have values.
-                // But if it ever happens, let's just *not* expire the item.
-                // FIXME: log or increment a metric if this happens.
-                return make_ready_future<>();
-            }
-            exploded_ck.push_back(*row_c);
-        }
-        auto ck = clustering_key::from_exploded(exploded_ck);
-        m.partition().clustered_row(*schema, ck).apply(tombstone(ts, gc_clock::now()));
-    }
-    return proxy.mutate(std::vector<mutation>{std::move(m)},
-        db::consistency_level::LOCAL_QUORUM,
-        executor::default_timeout(), // FIXME - which timeout?
-        qs.get_trace_state(), qs.get_permit());
-}
-
-static size_t random_offset(size_t min, size_t max) {
-    static thread_local std::default_random_engine re{std::random_device{}()};
-    std::uniform_int_distribution<size_t> dist(min, max);
-    return dist(re);
-}
-
-// Get a list of secondary token ranges for the given node, and the primary
-// node responsible for each of these token ranges.
-// A "secondary range" is a range of tokens where for each token, the second
-// node (in ring order) out of the RF replicas that hold this token is the
-// given node.
-// In the expiration scanner, we want to scan a secondary range but only if
-// this range's primary node is down. For this we need to return not just
-// a list of this node's secondary ranges - but also the primary owner of
-// each of those ranges.
-static std::vector<std::pair<dht::token_range, gms::inet_address>> get_secondary_ranges(
-        const locator::effective_replication_map_ptr& erm,
-        gms::inet_address ep) {
-    const auto& tm = *erm->get_token_metadata_ptr();
-    const auto& sorted_tokens = tm.sorted_tokens();
-    std::vector<std::pair<dht::token_range, gms::inet_address>> ret;
-    if (sorted_tokens.empty()) {
-        on_internal_error(tlogger, "Token metadata is empty");
-    }
-    auto prev_tok = sorted_tokens.back();
-    for (const auto& tok : sorted_tokens) {
-        inet_address_vector_replica_set eps = erm->get_natural_endpoints(tok);
-        if (eps.size() <= 1 || eps[1] != ep) {
-            prev_tok = tok;
-            continue;
-        }
-        // Add the range (prev_tok, tok] to ret. However, if the range wraps
-        // around, split it to two non-wrapping ranges.
-        if (prev_tok < tok) {
-            ret.emplace_back(
-                dht::token_range{
-                    dht::token_range::bound(prev_tok, false),
-                    dht::token_range::bound(tok, true)},
-                eps[0]);
-        } else {
-            ret.emplace_back(
-                dht::token_range{
-                    dht::token_range::bound(prev_tok, false),
-                    std::nullopt},
-                eps[0]);
-            ret.emplace_back(
-                dht::token_range{
-                    std::nullopt,
-                    dht::token_range::bound(tok, true)},
-                eps[0]);
-        }
-        prev_tok = tok;
-    }
-    return ret;
-}
-
-
-// A class for iterating over all the token ranges *owned* by this shard.
-// To avoid code duplication, it is a template with two distinct cases -
-// <primary> and <secondary>:
-//
-// In the <primary> case, we consider a token *owned* by this shard if:
-// 1. This node is a replica for this token.
-// 2. Moreover, this node is the *primary* replica of the token (i.e., the
-//    first replica in the ring).
-// 3. In this node, this shard is responsible for this token.
-// We will use this definition of which shard in the cluster owns which tokens
-// to split the expiration scanner's work between all the shards of the
-// system.
-//
-// In the <secondary> case, we consider a token *owned* by this shard if:
-// 1. This node is the *secondary* replica for this token (i.e., the second
-//    replica in the ring).
-// 2. The primary replica for this token is currently marked down.
-// 3. In this node, this shard is responsible for this token.
-// We use the <secondary> case to handle the possibility that some of the
-// nodes in the system are down. A dead node will not be expiring expiring
-// the tokens owned by it, so we want the secondary owner to take over its
-// primary ranges.
-//
-// FIXME: need to decide how to choose primary ranges in multi-DC setup!
-// We could call get_primary_ranges_within_dc() below instead of get_primary_ranges().
-// NOTICE: Iteration currently starts from a random token range in order to improve
-// the chances of covering all ranges during a scan when restarts occur.
-// A more deterministic way would be to regularly persist the scanning state,
-// but that incurs overhead that we want to avoid if not needed.
-enum primary_or_secondary_t {primary, secondary};
-template<primary_or_secondary_t primary_or_secondary>
-class token_ranges_owned_by_this_shard {
-    template<primary_or_secondary_t> class ranges_holder;
-    // ranges_holder<primary> holds just the primary ranges themselves
-    template<> class ranges_holder<primary> {
-        const dht::token_range_vector _token_ranges;
-     public:
-        ranges_holder(const locator::effective_replication_map_ptr& erm, gms::inet_address ep)
-            : _token_ranges(erm->get_primary_ranges(ep)) {}
-        std::size_t size() const { return _token_ranges.size(); }
-        const dht::token_range& operator[](std::size_t i) const {
-            return _token_ranges[i];
-        }
-        bool should_skip(std::size_t i) const {
-            return false;
-        }
-    };
-    // ranges_holder<secondary> holds the secondary token ranges plus each
-    // range's primary owner, needed to implement should_skip().
-    template<> class ranges_holder<secondary> {
-        std::vector<std::pair<dht::token_range, gms::inet_address>> _token_ranges;
-        gms::gossiper& _gossiper;
-     public:
-        ranges_holder(const locator::effective_replication_map_ptr& erm, gms::inet_address ep)
-            : _token_ranges(get_secondary_ranges(erm, ep))
-            , _gossiper(gms::get_local_gossiper()) {}
-        std::size_t size() const { return _token_ranges.size(); }
-        const dht::token_range& operator[](std::size_t i) const {
-            return _token_ranges[i].first;
-        }
-        // range i should be skipped if its primary owner is alive.
-        bool should_skip(std::size_t i) const {
-            return _gossiper.is_alive(_token_ranges[i].second);
-        }
-    };
-
-    schema_ptr _s;
-    // _token_ranges will contain a list of token ranges owned by this node.
-    // We'll further need to split each such range to the pieces owned by
-    // the current shard, using _intersecter.
-    const ranges_holder<primary_or_secondary> _token_ranges;
-    // NOTICE: _range_idx is used modulo _token_ranges size when accessing
-    // the data to ensure that it doesn't go out of bounds
-    size_t _range_idx;
-    size_t _end_idx;
-    std::optional<dht::selective_token_range_sharder> _intersecter;
-public:
-    token_ranges_owned_by_this_shard(replica::database& db, schema_ptr s)
-        :  _s(s)
-        , _token_ranges(db.find_keyspace(s->ks_name()).get_effective_replication_map(),
-                utils::fb_utilities::get_broadcast_address())
-        , _range_idx(random_offset(0, _token_ranges.size() - 1))
-        , _end_idx(_range_idx + _token_ranges.size())
-    {
-        tlogger.debug("Generating token ranges starting from base range {} of {}", _range_idx, _token_ranges.size());
-    }
-
-    // Return the next token_range owned by this shard, or nullopt when the
-    // iteration ends.
-    std::optional<dht::token_range> next() {
-        // We may need three or more iterations in the following loop if a
-        // vnode doesn't intersect with the given shard at all (such a small
-        // vnode is unlikely, but possible). The loop cannot be infinite
-        // because each iteration of the loop advances _range_idx.
-        for (;;) {
-            if (_intersecter) {
-                std::optional<dht::token_range> ret = _intersecter->next();
-                if (ret) {
-                    return ret;
-                }
-                // done with this range, go to next one
-                ++_range_idx;
-                _intersecter = std::nullopt;
-            }
-            if (_range_idx == _end_idx) {
-                return std::nullopt;
-            }
-            // If should_skip(), the range should be skipped. This happens for
-            // a secondary range whose primary owning node is still alive.
-            while (_token_ranges.should_skip(_range_idx % _token_ranges.size())) {
-                ++_range_idx;
-                if (_range_idx == _end_idx) {
-                    return std::nullopt;
-                }
-            }
-            _intersecter.emplace(_s->get_sharder(), _token_ranges[_range_idx % _token_ranges.size()], this_shard_id());
-        }
-    }
-
-    // Same as next(), just return a partition_range instead of token_range
-    std::optional<dht::partition_range> next_partition_range() {
-        std::optional<dht::token_range> ret = next();
-        if (ret) {
-            return dht::to_partition_range(*ret);
-        } else {
-            return std::nullopt;
-        }
-    }
-};
-
-// Precomputed information needed to perform a scan on partition ranges
-struct scan_ranges_context {
-    schema_ptr s;
-    bytes column_name;
-    std::optional<std::string> member;
-
-    ::shared_ptr<cql3::selection::selection> selection;
-    std::unique_ptr<service::query_state> query_state_ptr;
-    std::unique_ptr<cql3::query_options> query_options;
-    ::lw_shared_ptr<query::read_command> command;
-
-    scan_ranges_context(schema_ptr s, service::storage_proxy& proxy, bytes column_name, std::optional<std::string> member)
-        : s(s)
-        , column_name(column_name)
-        , member(member)
-    {
-        // FIXME: don't read the entire items - read only parts of it.
-        // We must read the key columns (to be able to delete) and also
-        // the requested attribute. If the requested attribute is a map's
-        // member we may be forced to read the entire map - but it would
-        // be good if we can read only the single item of the map - it
-        // should be possible (and a must for issue #7751!).
-        lw_shared_ptr<service::pager::paging_state> paging_state = nullptr;
-        auto regular_columns = boost::copy_range<query::column_id_vector>(
-            s->regular_columns() | boost::adaptors::transformed([] (const column_definition& cdef) { return cdef.id; }));
-        selection = cql3::selection::selection::wildcard(s);
-        query::partition_slice::option_set opts = selection->get_query_options();
-        opts.set<query::partition_slice::option::allow_short_read>();
-        std::vector<query::clustering_range> ck_bounds{query::clustering_range::make_open_ended_both_sides()};
-        auto partition_slice = query::partition_slice(std::move(ck_bounds), {}, std::move(regular_columns), opts);
-        command = ::make_lw_shared<query::read_command>(s->id(), s->version(), partition_slice, proxy.get_max_result_size(partition_slice));
-        executor::client_state client_state{executor::client_state::internal_tag()};
-        tracing::trace_state_ptr trace_state;
-        // NOTICE: empty_service_permit is used because the TTL service has fixed parallelism
-        query_state_ptr = std::make_unique<service::query_state>(client_state, trace_state, empty_service_permit());
-        // FIXME: What should we do on multi-DC? Will we run the expiration on the same ranges on all
-        // DCs or only once for each range? If the latter, we need to change the CLs in the
-        // scanner and deleter.
-        db::consistency_level cl = db::consistency_level::LOCAL_QUORUM;
-        query_options = std::make_unique<cql3::query_options>(cl, std::vector<cql3::raw_value>{});
-        query_options = std::make_unique<cql3::query_options>(std::move(query_options), std::move(paging_state));
-    }
-};
-
-// Scan data in a list of token ranges in one table, looking for expired
-// items and deleting them.
-// Because of issue #9167, partition_ranges must have a single partition
-// for this code to work correctly.
-static future<> scan_table_ranges(
-        service::storage_proxy& proxy,
-        const scan_ranges_context& scan_ctx,
-        dht::partition_range_vector&& partition_ranges,
-        abort_source& abort_source,
-        named_semaphore& page_sem)
-{
-    const schema_ptr& s = scan_ctx.s;
-    assert (partition_ranges.size() == 1); // otherwise issue #9167 will cause incorrect results.
-    auto p = service::pager::query_pagers::pager(proxy, s, scan_ctx.selection, *scan_ctx.query_state_ptr,
-            *scan_ctx.query_options, scan_ctx.command, std::move(partition_ranges), nullptr);
-    while (!p->is_exhausted()) {
-        if (abort_source.abort_requested()) {
-            co_return;
-        }
-        auto units = co_await get_units(page_sem, 1);
-        // We don't to limit page size in number of rows because there is a
-        // builtin limit of the page's size in bytes. Setting this limit to 1
-        // is useful for debugging the paging code with moderate-size data.
-        uint32_t limit = std::numeric_limits<uint32_t>::max();
-        // FIXME: which timeout?
-        // FIXME: if read times out, need to retry it.
-        std::unique_ptr<cql3::result_set> rs = co_await p->fetch_page(limit, gc_clock::now(), executor::default_timeout());
-        auto rows = rs->rows();
-        auto meta = rs->get_metadata().get_names();
-        std::optional<unsigned> expiration_column;
-        for (unsigned i = 0; i < meta.size(); i++) {
-            const cql3::column_specification& col = *meta[i];
-            if (col.name->name() == scan_ctx.column_name) {
-                expiration_column = i;
-                break;
-            }
-        }
-        if (!expiration_column) {
-            continue;
-        }
-        for (const auto& row : rows) {
-            const bytes_opt& cell = row[*expiration_column];
-            if (!cell) {
-                continue;
-            }
-            auto v = meta[*expiration_column]->type->deserialize(*cell);
-            bool expired = false;
-            // FIXME: don't recalculate "now" all the time
-            auto now = gc_clock::now();
-            if (scan_ctx.member) {
-                // In this case, the expiration-time attribute we're
-                // looking for is a member in a map, saved serialized
-                // into bytes using Alternator's serialization (basically
-                // a JSON serialized into bytes)
-                // FIXME: is it possible to find a specific member of a map
-                // without iterating through it like we do here and compare
-                // the key?
-                for (const auto& entry : value_cast<map_type_impl::native_type>(v)) {
-                    std::string attr_name = value_cast<sstring>(entry.first);
-                    if (value_cast<sstring>(entry.first) == *scan_ctx.member) {
-                        bytes value = value_cast<bytes>(entry.second);
-                        rjson::value json = deserialize_item(value);
-                        expired = is_expired(json, now);
-                        break;
-                    }
-                }
-            } else {
-                // For a real column to contain an expiration time, it
-                // must be a numeric type.
-                // FIXME: Currently we only support decimal_type (which is
-                // what Alternator uses), but other numeric types can be
-                // supported as well to make this feature more useful in CQL.
-                // Note that kind::decimal is also checked above.
-                big_decimal n = value_cast<big_decimal>(v);
-                expired = is_expired(n, now);
-            }
-            if (expired) {
-                // FIXME: maybe don't recalculate new_timestamp() all the time
-                // FIXME: if expire_item() throws on timeout, we need to retry it.
-                auto ts = api::new_timestamp();
-                co_await expire_item(proxy, *scan_ctx.query_state_ptr, row, s, ts);
-            }
-        }
-        // FIXME: once in a while, persist p->state(), so on reboot
-        // we don't start from scratch.
-    }
-}
-
-// scan_table() scans data in one table "owned" by this shard, looking for
-// expired items and deleting them.
-// We consider each node to "own" its primary token ranges, i.e., the tokens
-// that this node is their first replica in the ring. Inside the node, each
-// shard "owns" subranges of the node's token ranges - according to the node's
-// sharding algorithm.
-// When a node goes down, the token ranges owned by it will not be scanned
-// and items in those token ranges will not expire, so in the future (FIXME)
-// this function should additionally work on token ranges whose primary owner
-// is down and this node is the range's secondary owner.
-// If the TTL (expiration-time scanning) feature is not enabled for this
-// table, scan_table() returns false without doing anything. Remember that the
-// TTL feature may be enabled later so this function will need to be called
-// again when the feature is enabled.
-// Currently this function scans the entire table (or, rather the parts owned
-// by this shard) at full rate, once. In the future (FIXME) we should consider
-// how to pace this scan, how and when to repeat it, how to interleave or
-// parallelize scanning of multiple tables, and how to continue scans after a
-// reboot.
-static future<bool> scan_table(
-    service::storage_proxy& proxy,
-    data_dictionary::database db,
-    schema_ptr s,
-    abort_source& abort_source,
-    named_semaphore& page_sem)
-{
-    // Check if an expiration-time attribute is enabled for this table.
-    // If not, just return false immediately.
-    std::optional<std::string> attribute_name = find_tag(*s, TTL_TAG_KEY);
-    if (!attribute_name) {
-        co_return false;
-    }
-    // attribute_name may be one of the schema's columns (in Alternator, this
-    // means it's a key column), or an element in Alternator's attrs map
-    // encoded in Alternator's JSON encoding.
-    // FIXME: To make this less Alternators-specific, we should encode in the
-    // single key's value three things:
-    // 1. The name of a column
-    // 2. Optionally if column is a map, a member in the map
-    // 3. The deserializer for the value: CQL or Alternator (JSON).
-    // The deserializer can be guessed: If the given column or map item is
-    // numeric, it can be used directly. If it is a "bytes" type, it needs to
-    // be deserialized using Alternator's deserializer.
-    bytes column_name = to_bytes(*attribute_name);
-    const column_definition *cd = s->get_column_definition(column_name);
-    std::optional<std::string> member;
-    if (!cd) {
-        member = std::move(attribute_name);
-        column_name = bytes(executor::ATTRS_COLUMN_NAME);
-        cd = s->get_column_definition(column_name);
-        tlogger.info("table {} TTL enabled with attribute {} in {}", s->cf_name(), *member, executor::ATTRS_COLUMN_NAME);
-    } else {
-        tlogger.info("table {} TTL enabled with attribute {}", s->cf_name(), *attribute_name);
-    }
-    if (!cd) {
-        tlogger.info("table {} TTL column is missing, not scanning", s->cf_name());
-        co_return false;
-    }
-    data_type column_type = cd->type;
-    // Verify that the column has the right type: If "member" exists
-    // the column must be a map, and if it doesn't, the column must
-    // (currently) be a decimal_type. If the column has the wrong type
-    // nothing can get expired in this table, and it's pointless to
-    // scan it.
-    if ((member && column_type->get_kind() != abstract_type::kind::map) ||
-        (!member && column_type->get_kind() != abstract_type::kind::decimal)) {
-        tlogger.info("table {} TTL column has unsupported type, not scanning", s->cf_name());
-        co_return false;
-    }
-    // FIXME: need to pace the scan, not do it all at once.
-    // FIXME: consider if we should ask the scan without caching?
-    // can we use cache but not fill it?
-    scan_ranges_context scan_ctx{s, proxy, std::move(column_name), std::move(member)};
-    token_ranges_owned_by_this_shard<primary> my_ranges(db.real_database(), s);
-    while (std::optional<dht::partition_range> range = my_ranges.next_partition_range()) {
-        // Note that because of issue #9167 we need to run a separate
-        // query on each partition range, and can't pass several of
-        // them into one partition_range_vector.
-        dht::partition_range_vector partition_ranges;
-        partition_ranges.push_back(std::move(*range));
-        // FIXME: if scanning a single range fails, including network errors,
-        // we fail the entire scan (and rescan from the beginning). Need to
-        // reconsider this. Saving the scan position might be a good enough
-        // solution for this problem.
-        co_await scan_table_ranges(proxy, scan_ctx, std::move(partition_ranges), abort_source, page_sem);
-    }
-    // If each node only scans its own primary ranges, then when any node is
-    // down part of the token range will not get scanned. This can be viewed
-    // as acceptable (when the comes back online, it will resume its scan),
-    // but as noted in issue #9787, we can allow more prompt expiration
-    // by tasking another node to take over scanning of the dead node's primary
-    // ranges. What we do here is that this node will also check expiration
-    // on its *secondary* ranges - but only those whose primary owner is down.
-    token_ranges_owned_by_this_shard<secondary> my_secondary_ranges(db.real_database(), s);
-    while (std::optional<dht::partition_range> range = my_secondary_ranges.next_partition_range()) {
-        dht::partition_range_vector partition_ranges;
-        partition_ranges.push_back(std::move(*range));
-        co_await scan_table_ranges(proxy, scan_ctx, std::move(partition_ranges), abort_source, page_sem);
-    }
-    co_return true;
-}
-
-
-future<> expiration_service::run() {
-    // FIXME: don't just tight-loop, think about timing, pace, and
-    // store position in durable storage, etc.
-    // FIXME: think about working on different tables in parallel.
-    // also need to notice when a new table is added, a table is
-    // deleted or when ttl is enabled or disabled for a table!
-    for (;;) {
-        // _db.tables() may change under our feet during a
-        // long-living loop, so we must keep our own copy of the list of
-        // schemas.
-        std::vector<schema_ptr> schemas;
-        for (auto cf : _db.get_tables()) {
-            schemas.push_back(cf.schema());
-        }
-        for (schema_ptr s : schemas) {
-            co_await coroutine::maybe_yield();
-            if (shutting_down()) {
-                co_return;
-            }
-            try {
-                co_await scan_table(_proxy, _db, s, _abort_source, _page_sem);
-            } catch (...) {
-                // The scan of a table may fail in the middle for many
-                // reasons, including network failure and even the table
-                // being removed. We'll continue scanning this table later
-                // (if it still exists). In any case it's important to catch
-                // the exception and not let the scanning service die for
-                // good.
-                // If the table has been deleted, it is expected that the scan
-                // will fail at some point, and even a warning is excessive.
-                if (_db.has_schema(s->ks_name(), s->cf_name())) {
-                    tlogger.warn("table {}.{} expiration scan failed: {}",
-                        s->ks_name(), s->cf_name(), std::current_exception());
-                } else {
-                    tlogger.info("expiration scan failed when table {}.{} was deleted",
-                        s->ks_name(), s->cf_name());
-                }
-            }
-        }
-        // FIXME: replace this silly 1-second sleep by something smarter.
-        try {
-            co_await seastar::sleep_abortable(std::chrono::seconds(1), _abort_source);
-        } catch(seastar::sleep_aborted&) {}
-    }
-}
-
-future<> expiration_service::start() {
-    // Called by main() on each shard to start the expiration-service
-    // thread. Just runs run() in the background and allows stop().
-    if (_db.features().cluster_supports_alternator_ttl()) {
-        if (!shutting_down()) {
-            _end = run().handle_exception([] (std::exception_ptr ep) {
-                tlogger.error("expiration_service failed: {}", ep);
-            });
-        }
-    }
-    return make_ready_future<>();
-}
-
-future<> expiration_service::stop() {
-    if (_abort_source.abort_requested()) {
-        throw std::logic_error("expiration_service::stop() called a second time");
-    }
-    _abort_source.request_abort();
-    if (!_end) {
-        // if _end is was not set, start() was never called
-        return make_ready_future<>();
-    }
-    return std::move(*_end);
-}
-
-} // namespace alternator
--- a/alternator/ttl.hh
+++ b/alternator/ttl.hh
@@ -1,57 +0,0 @@
-/*
- * Copyright 2021-present ScyllaDB
- */
-
-/*
- * SPDX-License-Identifier: AGPL-3.0-or-later
- */
-
-#pragma once
-
-#include "seastarx.hh"
-#include <seastar/core/sharded.hh>
-#include <seastar/core/abort_source.hh>
-#include <seastar/core/semaphore.hh>
-#include "data_dictionary/data_dictionary.hh"
-
-namespace replica {
-class database;
-}
-
-namespace service {
-    class storage_proxy;
-}
-
-namespace alternator {
-
-// expiration_service is a sharded service responsible for cleaning up expired
-// items in all tables with per-item expiration enabled. Currently, this means
-// Alternator tables with TTL configured via a UpdateTimeToLeave request.
-class expiration_service final : public seastar::peering_sharded_service<expiration_service> {
-    data_dictionary::database _db;
-    service::storage_proxy& _proxy;
-    // _end is set by start(), and resolves when the the background service
-    // started by it ends. To ask the background service to end, _abort_source
-    // should be triggered. stop() below uses both _abort_source and _end.
-    std::optional<future<>> _end;
-    abort_source _abort_source;
-    // Ensures that at most 1 page of scan results at a time is processed by the TTL service
-    named_semaphore _page_sem{1, named_semaphore_exception_factory{"alternator_ttl"}};
-    bool shutting_down() { return _abort_source.abort_requested(); }
-public:
-    // sharded_service<expiration_service>::start() creates this object on
-    // all shards, so calls this constructor on each shard. Later, the
-    // additional start() function should be invoked on all shards.
-    expiration_service(data_dictionary::database, service::storage_proxy&);
-    future<> start();
-    future<> run();
-    // sharded_service<expiration_service>::stop() calls the following stop()
-    // method on each shard. This stop() asks the service on this shard to
-    // shut down as quickly as it can. The returned future indicates when the
-    // service is no longer running.
-    // stop() may be called even before start(), but may only be called once -
-    // calling it twice will result in an exception.
-    future<> stop();
-};
-
-} // namespace alternator
--- a/api/api-doc/column_family.json
+++ b/api/api-doc/column_family.json
@@ -89,7 +89,7 @@
                     "description":"true if the output of the major compaction should be split in several sstables",
                     "required":false,
                     "allowMultiple":false,
-                     "type":"boolean",
+                     "type":"bool",
                     "paramType":"query"
                  }
               ]
@@ -2925,10 +2925,6 @@
         "id":"toppartitions_query_results",
         "description":"nodetool toppartitions query results",
         "properties":{
-            "read_cardinality":{
-               "type":"long",
-               "description":"Number of the unique operations in the sample set"
-            },
            "read":{
               "type":"array",
               "items":{
@@ -2936,10 +2932,6 @@
               },
               "description":"Read results"
            },
-            "write_cardinality":{
-               "type":"long",
-               "description":"Number of the unique operations in the sample set"
-            },
            "write":{
               "type":"array",
               "items":{
--- a/api/api-doc/compaction_manager.json
+++ b/api/api-doc/compaction_manager.json
@@ -102,47 +102,7 @@
               "parameters":[
                  {
                     "name":"type",
-                     "description":"The type of compaction to stop. Can be one of: COMPACTION | CLEANUP | SCRUB | UPGRADE | RESHAPE",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  }
-               ]
-            }
-         ]
-      },
-      {
-         "path":"/compaction_manager/stop_keyspace_compaction/{keyspace}",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Stop all running compaction-like tasks in the given keyspace and tables having the provided type.",
-               "type":"void",
-               "nickname":"stop_keyspace_compaction",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"keyspace",
-                     "description":"The keyspace to stop compaction in",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  },
-                  {
-                     "name":"tables",
-                     "description":"Comma-seperated tables to stop compaction in",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  },
-                  {
-                     "name":"type",
-                     "description":"The type of compaction to stop. Can be one of: COMPACTION | CLEANUP | SCRUB | UPGRADE | RESHAPE",
+                     "description":"the type of compaction to stop. Can be one of: - COMPACTION - VALIDATION - CLEANUP - SCRUB - INDEX_BUILD",
                     "required":true,
                     "allowMultiple":false,
                     "type":"string",
--- a/api/api-doc/gossiper.json
+++ b/api/api-doc/gossiper.json
@@ -148,30 +148,6 @@
               ]
            }
         ]
-      },
-      {
-         "path":"/gossiper/force_remove_endpoint/{addr}",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Force remove an endpoint from gossip",
-               "type":"void",
-               "nickname":"force_remove_endpoint",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"addr",
-                     "description":"The endpoint address",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  }
-               ]
-            }
-         ]
      }
   ]
 }
--- a/api/api-doc/hinted_handoff.json
+++ b/api/api-doc/hinted_handoff.json
@@ -7,61 +7,6 @@
      "application/json"
   ],
   "apis":[
-      {
-         "path":"/hinted_handoff/sync_point",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Creates a hints sync point. It can be used to wait until hints between given nodes are replayed. A sync point allows you to wait for hints accumulated at the moment of its creation - it won't wait for hints generated later. A sync point is described entirely by its ID - there is no state kept server-side, so there is no need to delete it.",
-               "type":"string",
-               "nickname":"create_hints_sync_point",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"target_hosts",
-                     "description":"A list of nodes towards which hints should be replayed. Multiple hosts can be listed by separating them with commas. If not provided or empty, the point will resolve when current hints towards all nodes in the cluster are sent.",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  }
-               ]
-            },
-            {
-               "method":"GET",
-               "summary":"Get the status of a hints sync point, possibly waiting for it to be reached.",
-               "type":"string",
-               "enum":[
-                  "DONE",
-                  "IN_PROGRESS"
-               ],
-               "nickname":"get_hints_sync_point",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"id",
-                     "description":"The ID of the hint sync point which should be checked or waited on",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  },
-                  {
-                     "name":"timeout",
-                     "description":"Timeout in seconds after which the query returns even if hints are still being replayed. No value or 0 will cause the query to return immediately. A negative value will cause the query to wait until the sync point is reached",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"long",
-                     "paramType":"query"
-                  }
-               ]
-            }
-         ]
-      },
      {
         "path":"/hinted_handoff/hints",
         "operations":[
--- a/api/api-doc/messaging_service.json
+++ b/api/api-doc/messaging_service.json
@@ -76,7 +76,7 @@
               "items":{
                  "type":"message_counter"
               },
-               "nickname":"get_replied_messages",
+               "nickname":"get_completed_messages",
               "produces":[
                  "application/json"
               ],
@@ -252,7 +252,7 @@
                 "UNUSED__STREAM_MUTATION",
                 "STREAM_MUTATION_DONE",
                 "COMPLETE_MESSAGE",
-                 "UNUSED__REPAIR_CHECKSUM_RANGE",
+                 "REPAIR_CHECKSUM_RANGE",
                 "GET_SCHEMA_VERSION"
               ]
            }
--- a/api/api-doc/storage_service.json
+++ b/api/api-doc/storage_service.json
@@ -104,68 +104,6 @@
            }
         ]
      },
-      {
-         "path":"/storage_service/toppartitions/",
-         "operations":[
-            {
-               "method":"GET",
-               "summary":"Toppartitions query",
-               "type":"toppartitions_query_results",
-               "nickname":"toppartitions_generic",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"table_filters",
-                     "description":"Optional list of table name filters in keyspace:name format",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"array",
-                     "items":{
-                        "type":"string"
-                     },
-                     "paramType":"query"
-                  },
-                  {
-                     "name":"keyspace_filters",
-                     "description":"Optional list of keyspace filters",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"array",
-                     "items":{
-                        "type":"string"
-                     },
-                     "paramType":"query"
-                  },
-                  {
-                     "name":"duration",
-                     "description":"Duration (in milliseconds) of monitoring operation",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type": "long",
-                     "paramType":"query"
-                  },
-                  {
-                    "name":"list_size",
-                    "description":"number of the top partitions to list",
-                    "required":false,
-                    "allowMultiple":false,
-                    "type": "long",
-                    "paramType":"query"
-                 },
-                 {
-                    "name":"capacity",
-                    "description":"capacity of stream summary: determines amount of resources used in query processing",
-                    "required":false,
-                    "allowMultiple":false,
-                    "type": "long",
-                    "paramType":"query"
-                 }
-              ]
-            }
-         ]
-      },
      {
         "path":"/storage_service/nodes/leaving",
         "operations":[
@@ -624,7 +562,7 @@
                  },
                  {
                     "name":"kn",
-                     "description":"Keyspace(s) to snapshot. Multiple keyspaces can be provided using a comma-separated list. If omitted, snapshot all keyspaces.",
+                     "description":"Comma seperated keyspaces name to snapshot",
                     "required":false,
                     "allowMultiple":false,
                     "type":"string",
@@ -632,19 +570,11 @@
                  },
                  {
                     "name":"cf",
-                     "description":"Table(s) to snapshot. Multiple tables (in a single keyspace) can be provided using a comma-separated list. If omitted, snapshot all tables in the given keyspace(s).",
+                     "description":"the column family to snapshot",
                     "required":false,
                     "allowMultiple":false,
                     "type":"string",
                     "paramType":"query"
-                  },
-                  {
-                     "name":"sf",
-                     "description":"Skip flush. When set to \"true\", do not flush memtables before snapshotting (snapshot will not contain unflushed data)",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"boolean",
-                     "paramType":"query"
                  }
               ]
            },
@@ -765,44 +695,12 @@
            }
         ]
      },
-      {
-         "path":"/storage_service/keyspace_offstrategy_compaction/{keyspace}",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Perform offstrategy compaction, if needed, in a single keyspace",
-               "type":"boolean",
-               "nickname":"perform_keyspace_offstrategy_compaction",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-                  {
-                     "name":"keyspace",
-                     "description":"The keyspace to operate on",
-                     "required":true,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"path"
-                  },
-                  {
-                     "name":"cf",
-                     "description":"Comma-seperated table names",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  }
-               ]
-            }
-         ]
-      },
      {
         "path":"/storage_service/keyspace_scrub/{keyspace}",
         "operations":[
            {
               "method":"GET",
-               "summary":"Scrub (deserialize + reserialize at the latest version, resolving corruptions if any) the given keyspace. If columnFamilies array is empty, all CFs are scrubbed. Scrubbed CFs will be snapshotted first, if disableSnapshot is false. Scrub has the following modes: Abort (default) - abort scrub if corruption is detected; Skip (same as `skip_corrupted=true`) skip over corrupt data, omitting them from the output; Segregate - segregate data into multiple sstables if needed, such that each sstable contains data with valid order; Validate - read (no rewrite) and validate data, logging any problems found.",
+               "summary":"Scrub (deserialize + reserialize at the latest version, skipping bad rows if any) the given keyspace. If columnFamilies array is empty, all CFs are scrubbed. Scrubbed CFs will be snapshotted first, if disableSnapshot is false",
               "type": "long",
               "nickname":"scrub",
               "produces":[
@@ -825,33 +723,6 @@
                     "type":"boolean",
                     "paramType":"query"
                  },
-                  {
-                     "name":"scrub_mode",
-                     "description":"How to handle corrupt data (overrides 'skip_corrupted'); ",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "enum":[
-                        "ABORT",
-                        "SKIP",
-                        "SEGREGATE",
-                        "VALIDATE"
-                     ],
-                     "paramType":"query"
-                  },
-                  {
-                     "name":"quarantine_mode",
-                     "description":"Controls whether to scrub quarantined sstables (default INCLUDE)",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "enum":[
-                        "INCLUDE",
-                        "EXCLUDE",
-                        "ONLY"
-                     ],
-                     "paramType":"query"
-                  },
                  {
                     "name":"keyspace",
                     "description":"The keyspace to query about",
@@ -1099,14 +970,6 @@
                     "type":"string",
                     "paramType":"query"
                  },
-                  {
-                     "name":"ignore_nodes",
-                     "description":"Which hosts are to ignore in this repair. Multiple hosts can be listed separated by commas.",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  },
                  {
                     "name":"trace",
                     "description":"If the value is the string 'true' with any capitalization, enable tracing of the repair.",
@@ -1242,14 +1105,6 @@
                     "allowMultiple":false,
                     "type":"string",
                     "paramType":"query"
-                  },
-                  {
-                     "name":"ignore_nodes",
-                     "description":"List of dead nodes to ingore in removenode operation",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
                  }
               ]
            }
@@ -1901,22 +1756,6 @@
                     "allowMultiple":false,
                     "type":"string",
                     "paramType":"query"
-                  },
-                  {
-                     "name":"load_and_stream",
-                     "description":"Load the sstables and stream to all replica nodes that owns the data",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
-                  },
-                  {
-                     "name":"primary_replica_only",
-                     "description":"Load the sstables and stream to primary replica node that owns the data. Repair is needed after the load and stream process",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"string",
-                     "paramType":"query"
                  }
               ]
            }
@@ -2027,14 +1866,6 @@
                     "allowMultiple":false,
                     "type":"long",
                     "paramType":"query"
-                  },
-                  {
-                     "name":"fast",
-                     "description":"Lightweight tracing mode: if true, slow queries tracing records only session headers",
-                     "required":false,
-                     "allowMultiple":false,
-                     "type":"boolean",
-                     "paramType":"query"
                  }
               ]
            },
@@ -2533,10 +2364,6 @@
            "threshold":{
               "type":"long",
               "description":"The slow query logging threshold in microseconds. Queries that takes longer, will be logged"
-            },
-            "fast":{
-               "type":"boolean",
-               "description":"Is lightweight tracing mode enabled. In that mode tracing ignore events and tracks only sessions."
            }
         }
      },
--- a/api/api-doc/system.json
+++ b/api/api-doc/system.json
@@ -52,22 +52,6 @@
            }
         ]
      },
-      {
-         "path":"/system/drop_sstable_caches",
-         "operations":[
-            {
-               "method":"POST",
-               "summary":"Drop in-memory caches for data which is in sstables",
-               "type":"void",
-               "nickname":"drop_sstable_caches",
-               "produces":[
-                  "application/json"
-               ],
-               "parameters":[
-               ]
-            }
-         ]
-      },
      {
         "path":"/system/uptime_ms",
         "operations":[
--- a/api/api.cc
+++ b/api/api.cc
@@ -1,9 +1,22 @@
 /*
- * Copyright 2015-present ScyllaDB
+ * Copyright 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #include "api.hh"
@@ -36,7 +49,7 @@ namespace api {
 static std::unique_ptr<reply> exception_reply(std::exception_ptr eptr) {
    try {
        std::rethrow_exception(eptr);
-    } catch (const replica::no_such_keyspace& ex) {
+    } catch (const no_such_keyspace& ex) {
        throw bad_param_exception(ex.what());
    }
    // We never going to get here
@@ -62,10 +75,10 @@ future<> set_server_init(http_context& ctx) {
    });
 }

-future<> set_server_config(http_context& ctx, const db::config& cfg) {
+future<> set_server_config(http_context& ctx) {
    auto rb02 = std::make_shared < api_registry_builder20 > (ctx.api_doc, "/v2");
-    return ctx.http_server.set_routes([&ctx, &cfg, rb02](routes& r) {
-        set_config(rb02, ctx, r, cfg);
+    return ctx.http_server.set_routes([&ctx, rb02](routes& r) {
+        set_config(rb02, ctx, r);
    });
 }

@@ -96,30 +109,12 @@ future<> unset_rpc_controller(http_context& ctx) {
    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_rpc_controller(ctx, r); });
 }

-future<> set_server_storage_service(http_context& ctx, sharded<service::storage_service>& ss, sharded<gms::gossiper>& g, sharded<cdc::generation_service>& cdc_gs) {
-    return register_api(ctx, "storage_service", "The storage service API", [&ss, &g, &cdc_gs] (http_context& ctx, routes& r) {
-            set_storage_service(ctx, r, ss, g.local(), cdc_gs);
-        });
+future<> set_server_storage_service(http_context& ctx) {
+    return register_api(ctx, "storage_service", "The storage service API", set_storage_service);
 }

-future<> set_server_sstables_loader(http_context& ctx, sharded<sstables_loader>& sst_loader) {
-    return ctx.http_server.set_routes([&ctx, &sst_loader] (routes& r) { set_sstables_loader(ctx, r, sst_loader); });
-}
-
-future<> unset_server_sstables_loader(http_context& ctx) {
-    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_sstables_loader(ctx, r); });
-}
-
-future<> set_server_view_builder(http_context& ctx, sharded<db::view::view_builder>& vb) {
-    return ctx.http_server.set_routes([&ctx, &vb] (routes& r) { set_view_builder(ctx, r, vb); });
-}
-
-future<> unset_server_view_builder(http_context& ctx) {
-    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_view_builder(ctx, r); });
-}
-
-future<> set_server_repair(http_context& ctx, sharded<repair_service>& repair) {
-    return ctx.http_server.set_routes([&ctx, &repair] (routes& r) { set_repair(ctx, r, repair); });
+future<> set_server_repair(http_context& ctx, sharded<netw::messaging_service>& ms) {
+    return ctx.http_server.set_routes([&ctx, &ms] (routes& r) { set_repair(ctx, r, ms); });
 }

 future<> unset_server_repair(http_context& ctx) {
@@ -138,11 +133,9 @@ future<> set_server_snitch(http_context& ctx) {
    return register_api(ctx, "endpoint_snitch_info", "The endpoint snitch info API", set_endpoint_snitch);
 }

-future<> set_server_gossip(http_context& ctx, sharded<gms::gossiper>& g) {
+future<> set_server_gossip(http_context& ctx) {
    return register_api(ctx, "gossiper",
-                "The gossiper API", [&g] (http_context& ctx, routes& r) {
-                    set_gossiper(ctx, r, g.local());
-                });
+                "The gossiper API", set_gossiper);
 }

 future<> set_server_load_sstable(http_context& ctx) {
@@ -160,22 +153,14 @@ future<> unset_server_messaging_service(http_context& ctx) {
    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_messaging_service(ctx, r); });
 }

-future<> set_server_storage_proxy(http_context& ctx, sharded<service::storage_service>& ss) {
+future<> set_server_storage_proxy(http_context& ctx) {
    return register_api(ctx, "storage_proxy",
-                "The storage proxy API", [&ss] (http_context& ctx, routes& r) {
-                    set_storage_proxy(ctx, r, ss);
-                });
+                "The storage proxy API", set_storage_proxy);
 }

-future<> set_server_stream_manager(http_context& ctx, sharded<streaming::stream_manager>& sm) {
+future<> set_server_stream_manager(http_context& ctx) {
    return register_api(ctx, "stream_manager",
-                "The stream manager API", [&sm] (http_context& ctx, routes& r) {
-                    set_stream_manager(ctx, r, sm);
-                });
-}
-
-future<> unset_server_stream_manager(http_context& ctx) {
-    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_stream_manager(ctx, r); });
+                "The stream manager API", set_stream_manager);
 }

 future<> set_server_cache(http_context& ctx) {
@@ -183,34 +168,13 @@ future<> set_server_cache(http_context& ctx) {
            "The cache service API", set_cache_service);
 }

-future<> set_hinted_handoff(http_context& ctx, sharded<gms::gossiper>& g) {
-    return register_api(ctx, "hinted_handoff",
-                "The hinted handoff API", [&g] (http_context& ctx, routes& r) {
-                    set_hinted_handoff(ctx, r, g.local());
-                });
-}
-
-future<> unset_hinted_handoff(http_context& ctx) {
-    return ctx.http_server.set_routes([&ctx] (routes& r) { unset_hinted_handoff(ctx, r); });
-}
-
-future<> set_server_gossip_settle(http_context& ctx, sharded<gms::gossiper>& g) {
-    auto rb = std::make_shared < api_registry_builder > (ctx.api_doc);
-
-    return ctx.http_server.set_routes([rb, &ctx, &g](routes& r) {
-        rb->register_function(r, "failure_detector",
-                "The failure detector API");
-        set_failure_detector(ctx, r, g.local());
-    });
-}
-
-future<> set_server_compaction_manager(http_context& ctx) {
+future<> set_server_gossip_settle(http_context& ctx) {
    auto rb = std::make_shared < api_registry_builder > (ctx.api_doc);

    return ctx.http_server.set_routes([rb, &ctx](routes& r) {
-        rb->register_function(r, "compaction_manager",
-                "The Compaction manager API");
-        set_compaction_manager(ctx, r);
+        rb->register_function(r, "failure_detector",
+                "The failure detector API");
+        set_failure_detector(ctx,r);
    });
 }

@@ -218,12 +182,18 @@ future<> set_server_done(http_context& ctx) {
    auto rb = std::make_shared < api_registry_builder > (ctx.api_doc);

    return ctx.http_server.set_routes([rb, &ctx](routes& r) {
+        rb->register_function(r, "compaction_manager",
+                "The Compaction manager API");
+        set_compaction_manager(ctx, r);
        rb->register_function(r, "lsa", "Log-structured allocator API");
        set_lsa(ctx, r);

        rb->register_function(r, "commitlog",
                "The commit log API");
        set_commitlog(ctx,r);
+        rb->register_function(r, "hinted_handoff",
+                "The hinted handoff API");
+        set_hinted_handoff(ctx, r);
        rb->register_function(r, "collectd",
                "The collectd API");
        set_collectd(ctx, r);
--- a/api/api.hh
+++ b/api/api.hh
@@ -1,9 +1,22 @@
 /*
- * Copyright 2015-present ScyllaDB
+ * Copyright 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once
@@ -16,7 +29,6 @@
 #include <boost/units/detail/utility.hpp>
 #include "api/api-doc/utils.json.hh"
 #include "utils/histogram.hh"
-#include "utils/estimated_histogram.hh"
 #include <seastar/http/exception.hh>
 #include "api_init.hh"
 #include "seastarx.hh"
@@ -58,7 +70,7 @@ T map_sum(T&& dest, const S& src) {
    for (auto i : src) {
        dest[i.first] += i.second;
    }
-    return std::move(dest);
+    return dest;
 }

 template <typename MAP>
@@ -81,6 +93,13 @@ inline std::vector<sstring> split(const sstring& text, const char* separator) {
    return boost::split(tokens, text, boost::is_any_of(separator));
 }

+/**
+ * Split a column family parameter
+ */
+inline std::vector<sstring> split_cf(const sstring& cf) {
+    return split(cf, ",");
+}
+
 /**
 * A helper function to sum values on an a distributed object that
 * has a get_stats method.
--- a/api/api_init.hh
+++ b/api/api_init.hh
@@ -3,55 +3,32 @@
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */
 #pragma once
-
+#include "database_fwd.hh"
+#include "service/storage_proxy.hh"
 #include <seastar/http/httpd.hh>
-#include <seastar/core/future.hh>
-
-#include "replica/database_fwd.hh"
-#include "seastarx.hh"
-
-namespace service {
-
-class load_meter;
-class storage_proxy;
-class storage_service;
-
-} // namespace service
-
-class sstables_loader;
-
-namespace streaming {
-class stream_manager;
-}
-
-namespace locator {
-
-class token_metadata;
-class shared_token_metadata;
-
-} // namespace locator

+namespace service { class load_meter; }
+namespace locator { class shared_token_metadata; }
 namespace cql_transport { class controller; }
 class thrift_controller;
-namespace db {
-class snapshot_ctl;
-class config;
-namespace view {
-class view_builder;
-}
-}
+namespace db { class snapshot_ctl; }
 namespace netw { class messaging_service; }
-class repair_service;
-namespace cdc { class generation_service; }
-
-namespace gms {
-
-class gossiper;
-
-}

 namespace api {

@@ -59,12 +36,12 @@ struct http_context {
    sstring api_dir;
    sstring api_doc;
    httpd::http_server_control http_server;
-    distributed<replica::database>& db;
+    distributed<database>& db;
    distributed<service::storage_proxy>& sp;
    service::load_meter& lmeter;
    const sharded<locator::shared_token_metadata>& shared_token_metadata;

-    http_context(distributed<replica::database>& _db,
+    http_context(distributed<database>& _db,
            distributed<service::storage_proxy>& _sp,
            service::load_meter& _lm, const sharded<locator::shared_token_metadata>& _stm)
            : db(_db), sp(_sp), lmeter(_lm), shared_token_metadata(_stm) {
@@ -74,14 +51,10 @@ struct http_context {
 };

 future<> set_server_init(http_context& ctx);
-future<> set_server_config(http_context& ctx, const db::config& cfg);
+future<> set_server_config(http_context& ctx);
 future<> set_server_snitch(http_context& ctx);
-future<> set_server_storage_service(http_context& ctx, sharded<service::storage_service>& ss, sharded<gms::gossiper>& g, sharded<cdc::generation_service>& cdc_gs);
-future<> set_server_sstables_loader(http_context& ctx, sharded<sstables_loader>& sst_loader);
-future<> unset_server_sstables_loader(http_context& ctx);
-future<> set_server_view_builder(http_context& ctx, sharded<db::view::view_builder>& vb);
-future<> unset_server_view_builder(http_context& ctx);
-future<> set_server_repair(http_context& ctx, sharded<repair_service>& repair);
+future<> set_server_storage_service(http_context& ctx);
+future<> set_server_repair(http_context& ctx, sharded<netw::messaging_service>& ms);
 future<> unset_server_repair(http_context& ctx);
 future<> set_transport_controller(http_context& ctx, cql_transport::controller& ctl);
 future<> unset_transport_controller(http_context& ctx);
@@ -89,18 +62,14 @@ future<> set_rpc_controller(http_context& ctx, thrift_controller& ctl);
 future<> unset_rpc_controller(http_context& ctx);
 future<> set_server_snapshot(http_context& ctx, sharded<db::snapshot_ctl>& snap_ctl);
 future<> unset_server_snapshot(http_context& ctx);
-future<> set_server_gossip(http_context& ctx, sharded<gms::gossiper>& g);
+future<> set_server_gossip(http_context& ctx);
 future<> set_server_load_sstable(http_context& ctx);
 future<> set_server_messaging_service(http_context& ctx, sharded<netw::messaging_service>& ms);
 future<> unset_server_messaging_service(http_context& ctx);
-future<> set_server_storage_proxy(http_context& ctx, sharded<service::storage_service>& ss);
-future<> set_server_stream_manager(http_context& ctx, sharded<streaming::stream_manager>& sm);
-future<> unset_server_stream_manager(http_context& ctx);
-future<> set_hinted_handoff(http_context& ctx, sharded<gms::gossiper>& g);
-future<> unset_hinted_handoff(http_context& ctx);
-future<> set_server_gossip_settle(http_context& ctx, sharded<gms::gossiper>& g);
+future<> set_server_storage_proxy(http_context& ctx);
+future<> set_server_stream_manager(http_context& ctx);
+future<> set_server_gossip_settle(http_context& ctx);
 future<> set_server_cache(http_context& ctx);
-future<> set_server_compaction_manager(http_context& ctx);
 future<> set_server_done(http_context& ctx);

 }
--- a/api/cache_service.cc
+++ b/api/cache_service.cc
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #include "cache_service.hh"
@@ -195,7 +208,7 @@ void set_cache_service(http_context& ctx, routes& r) {
    });

    cs::get_row_capacity.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return ctx.db.map_reduce0([](replica::database& db) -> uint64_t {
+        return ctx.db.map_reduce0([](database& db) -> uint64_t {
            return db.row_cache_tracker().region().occupancy().used_space();
        }, uint64_t(0), std::plus<uint64_t>()).then([](const int64_t& res) {
            return make_ready_future<json::json_return_type>(res);
@@ -203,26 +216,26 @@ void set_cache_service(http_context& ctx, routes& r) {
    });

    cs::get_row_hits.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, uint64_t(0), [](const replica::column_family& cf) {
+        return map_reduce_cf(ctx, uint64_t(0), [](const column_family& cf) {
            return cf.get_row_cache().stats().hits.count();
        }, std::plus<uint64_t>());
    });

    cs::get_row_requests.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, uint64_t(0), [](const replica::column_family& cf) {
+        return map_reduce_cf(ctx, uint64_t(0), [](const column_family& cf) {
            return cf.get_row_cache().stats().hits.count() + cf.get_row_cache().stats().misses.count();
        }, std::plus<uint64_t>());
    });

    cs::get_row_hit_rate.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, ratio_holder(), [](const replica::column_family& cf) {
+        return map_reduce_cf(ctx, ratio_holder(), [](const column_family& cf) {
            return ratio_holder(cf.get_row_cache().stats().hits.count() + cf.get_row_cache().stats().misses.count(),
                    cf.get_row_cache().stats().hits.count());
        }, std::plus<ratio_holder>());
    });

    cs::get_row_hits_moving_avrage.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf_raw(ctx, utils::rate_moving_average(), [](const replica::column_family& cf) {
+        return map_reduce_cf_raw(ctx, utils::rate_moving_average(), [](const column_family& cf) {
            return cf.get_row_cache().stats().hits.rate();
        }, std::plus<utils::rate_moving_average>()).then([](const utils::rate_moving_average& m) {
            return make_ready_future<json::json_return_type>(meter_to_json(m));
@@ -230,7 +243,7 @@ void set_cache_service(http_context& ctx, routes& r) {
    });

    cs::get_row_requests_moving_avrage.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf_raw(ctx, utils::rate_moving_average(), [](const replica::column_family& cf) {
+        return map_reduce_cf_raw(ctx, utils::rate_moving_average(), [](const column_family& cf) {
            return cf.get_row_cache().stats().hits.rate() + cf.get_row_cache().stats().misses.rate();
        }, std::plus<utils::rate_moving_average>()).then([](const utils::rate_moving_average& m) {
            return make_ready_future<json::json_return_type>(meter_to_json(m));
@@ -240,7 +253,7 @@ void set_cache_service(http_context& ctx, routes& r) {
    cs::get_row_size.set(r, [&ctx] (std::unique_ptr<request> req) {
        // In origin row size is the weighted size.
        // We currently do not support weights, so we use num entries instead
-        return ctx.db.map_reduce0([](replica::database& db) -> uint64_t {
+        return ctx.db.map_reduce0([](database& db) -> uint64_t {
            return db.row_cache_tracker().partitions();
        }, uint64_t(0), std::plus<uint64_t>()).then([](const int64_t& res) {
            return make_ready_future<json::json_return_type>(res);
@@ -248,7 +261,7 @@ void set_cache_service(http_context& ctx, routes& r) {
    });

    cs::get_row_entries.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return ctx.db.map_reduce0([](replica::database& db) -> uint64_t {
+        return ctx.db.map_reduce0([](database& db) -> uint64_t {
            return db.row_cache_tracker().partitions();
        }, uint64_t(0), std::plus<uint64_t>()).then([](const int64_t& res) {
            return make_ready_future<json::json_return_type>(res);
--- a/api/cache_service.hh
+++ b/api/cache_service.hh
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once
--- a/api/collectd.cc
+++ b/api/collectd.cc
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #include "collectd.hh"
--- a/api/collectd.hh
+++ b/api/collectd.hh
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once
--- a/api/column_family.cc
+++ b/api/column_family.cc
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #include "column_family.hh"
@@ -11,13 +24,10 @@
 #include <vector>
 #include <seastar/http/exception.hh>
 #include "sstables/sstables.hh"
-#include "sstables/metadata_collector.hh"
 #include "utils/estimated_histogram.hh"
 #include <algorithm>
 #include "db/system_keyspace_view_types.hh"
 #include "db/data_listeners.hh"
-#include "storage_service.hh"
-#include "unimplemented.hh"

 extern logging::logger apilog;

@@ -43,57 +53,57 @@ std::tuple<sstring, sstring> parse_fully_qualified_cf_name(sstring name) {
    return std::make_tuple(name.substr(0, pos), name.substr(end));
 }

-const utils::UUID& get_uuid(const sstring& ks, const sstring& cf, const replica::database& db) {
+const utils::UUID& get_uuid(const sstring& ks, const sstring& cf, const database& db) {
    try {
        return db.find_uuid(ks, cf);
-    } catch (replica::no_such_column_family& e) {
-        throw bad_param_exception(e.what());
+    } catch (std::out_of_range& e) {
+        throw bad_param_exception(format("Column family '{}:{}' not found", ks, cf));
    }
 }

-const utils::UUID& get_uuid(const sstring& name, const replica::database& db) {
+const utils::UUID& get_uuid(const sstring& name, const database& db) {
    auto [ks, cf] = parse_fully_qualified_cf_name(name);
    return get_uuid(ks, cf, db);
 }

-future<> foreach_column_family(http_context& ctx, const sstring& name, function<void(replica::column_family&)> f) {
+future<> foreach_column_family(http_context& ctx, const sstring& name, function<void(column_family&)> f) {
    auto uuid = get_uuid(name, ctx.db.local());

-    return ctx.db.invoke_on_all([f, uuid](replica::database& db) {
+    return ctx.db.invoke_on_all([f, uuid](database& db) {
        f(db.find_column_family(uuid));
    });
 }

 future<json::json_return_type>  get_cf_stats(http_context& ctx, const sstring& name,
-        int64_t replica::column_family_stats::*f) {
-    return map_reduce_cf(ctx, name, int64_t(0), [f](const replica::column_family& cf) {
+        int64_t column_family_stats::*f) {
+    return map_reduce_cf(ctx, name, int64_t(0), [f](const column_family& cf) {
        return cf.get_stats().*f;
    }, std::plus<int64_t>());
 }

 future<json::json_return_type>  get_cf_stats(http_context& ctx,
-        int64_t replica::column_family_stats::*f) {
-    return map_reduce_cf(ctx, int64_t(0), [f](const replica::column_family& cf) {
+        int64_t column_family_stats::*f) {
+    return map_reduce_cf(ctx, int64_t(0), [f](const column_family& cf) {
        return cf.get_stats().*f;
    }, std::plus<int64_t>());
 }

 static future<json::json_return_type>  get_cf_stats_count(http_context& ctx, const sstring& name,
-        utils::timed_rate_moving_average_and_histogram replica::column_family_stats::*f) {
-    return map_reduce_cf(ctx, name, int64_t(0), [f](const replica::column_family& cf) {
+        utils::timed_rate_moving_average_and_histogram column_family_stats::*f) {
+    return map_reduce_cf(ctx, name, int64_t(0), [f](const column_family& cf) {
        return (cf.get_stats().*f).hist.count;
    }, std::plus<int64_t>());
 }

 static future<json::json_return_type>  get_cf_stats_sum(http_context& ctx, const sstring& name,
-        utils::timed_rate_moving_average_and_histogram replica::column_family_stats::*f) {
+        utils::timed_rate_moving_average_and_histogram column_family_stats::*f) {
    auto uuid = get_uuid(name, ctx.db.local());
-    return ctx.db.map_reduce0([uuid, f](replica::database& db) {
+    return ctx.db.map_reduce0([uuid, f](database& db) {
        // Histograms information is sample of the actual load
        // so to get an estimation of sum, we multiply the mean
        // with count. The information is gather in nano second,
        // but reported in micro
-        replica::column_family& cf = db.find_column_family(uuid);
+        column_family& cf = db.find_column_family(uuid);
        return ((cf.get_stats().*f).hist.count/1000.0) * (cf.get_stats().*f).hist.mean;
    }, 0.0, std::plus<double>()).then([](double res) {
        return make_ready_future<json::json_return_type>((int64_t)res);
@@ -102,16 +112,16 @@ static future<json::json_return_type>  get_cf_stats_sum(http_context& ctx, const


 static future<json::json_return_type>  get_cf_stats_count(http_context& ctx,
-        utils::timed_rate_moving_average_and_histogram replica::column_family_stats::*f) {
-    return map_reduce_cf(ctx, int64_t(0), [f](const replica::column_family& cf) {
+        utils::timed_rate_moving_average_and_histogram column_family_stats::*f) {
+    return map_reduce_cf(ctx, int64_t(0), [f](const column_family& cf) {
        return (cf.get_stats().*f).hist.count;
    }, std::plus<int64_t>());
 }

 static future<json::json_return_type>  get_cf_histogram(http_context& ctx, const sstring& name,
-        utils::timed_rate_moving_average_and_histogram replica::column_family_stats::*f) {
+        utils::timed_rate_moving_average_and_histogram column_family_stats::*f) {
    utils::UUID uuid = get_uuid(name, ctx.db.local());
-    return ctx.db.map_reduce0([f, uuid](const replica::database& p) {
+    return ctx.db.map_reduce0([f, uuid](const database& p) {
        return (p.find_column_family(uuid).get_stats().*f).hist;},
            utils::ihistogram(),
            std::plus<utils::ihistogram>())
@@ -120,8 +130,8 @@ static future<json::json_return_type>  get_cf_histogram(http_context& ctx, const
    });
 }

-static future<json::json_return_type> get_cf_histogram(http_context& ctx, utils::timed_rate_moving_average_and_histogram replica::column_family_stats::*f) {
-    std::function<utils::ihistogram(const replica::database&)> fun = [f] (const replica::database& db)  {
+static future<json::json_return_type> get_cf_histogram(http_context& ctx, utils::timed_rate_moving_average_and_histogram column_family_stats::*f) {
+    std::function<utils::ihistogram(const database&)> fun = [f] (const database& db)  {
        utils::ihistogram res;
        for (auto i : db.get_column_families()) {
            res += (i.second->get_stats().*f).hist;
@@ -136,9 +146,9 @@ static future<json::json_return_type> get_cf_histogram(http_context& ctx, utils:
 }

 static future<json::json_return_type>  get_cf_rate_and_histogram(http_context& ctx, const sstring& name,
-        utils::timed_rate_moving_average_and_histogram replica::column_family_stats::*f) {
+        utils::timed_rate_moving_average_and_histogram column_family_stats::*f) {
    utils::UUID uuid = get_uuid(name, ctx.db.local());
-    return ctx.db.map_reduce0([f, uuid](const replica::database& p) {
+    return ctx.db.map_reduce0([f, uuid](const database& p) {
        return (p.find_column_family(uuid).get_stats().*f).rate();},
            utils::rate_moving_average_and_histogram(),
            std::plus<utils::rate_moving_average_and_histogram>())
@@ -147,8 +157,8 @@ static future<json::json_return_type>  get_cf_rate_and_histogram(http_context& c
    });
 }

-static future<json::json_return_type> get_cf_rate_and_histogram(http_context& ctx, utils::timed_rate_moving_average_and_histogram replica::column_family_stats::*f) {
-    std::function<utils::rate_moving_average_and_histogram(const replica::database&)> fun = [f] (const replica::database& db)  {
+static future<json::json_return_type> get_cf_rate_and_histogram(http_context& ctx, utils::timed_rate_moving_average_and_histogram column_family_stats::*f) {
+    std::function<utils::rate_moving_average_and_histogram(const database&)> fun = [f] (const database& db)  {
        utils::rate_moving_average_and_histogram res;
        for (auto i : db.get_column_families()) {
            res += (i.second->get_stats().*f).rate();
@@ -163,30 +173,30 @@ static future<json::json_return_type> get_cf_rate_and_histogram(http_context& ct
 }

 static future<json::json_return_type> get_cf_unleveled_sstables(http_context& ctx, const sstring& name) {
-    return map_reduce_cf(ctx, name, int64_t(0), [](const replica::column_family& cf) {
+    return map_reduce_cf(ctx, name, int64_t(0), [](const column_family& cf) {
        return cf.get_unleveled_sstables();
    }, std::plus<int64_t>());
 }

-static int64_t min_partition_size(replica::column_family& cf) {
+static int64_t min_partition_size(column_family& cf) {
    int64_t res = INT64_MAX;
-    for (auto sstables = cf.get_sstables(); auto& i : *sstables) {
+    for (auto i: *cf.get_sstables() ) {
        res = std::min(res, i->get_stats_metadata().estimated_partition_size.min());
    }
    return (res == INT64_MAX) ? 0 : res;
 }

-static int64_t max_partition_size(replica::column_family& cf) {
+static int64_t max_partition_size(column_family& cf) {
    int64_t res = 0;
-    for (auto sstables = cf.get_sstables(); auto& i : *sstables) {
+    for (auto i: *cf.get_sstables() ) {
        res = std::max(i->get_stats_metadata().estimated_partition_size.max(), res);
    }
    return res;
 }

-static integral_ratio_holder mean_partition_size(replica::column_family& cf) {
+static integral_ratio_holder mean_partition_size(column_family& cf) {
    integral_ratio_holder res;
-    for (auto sstables = cf.get_sstables(); auto& i : *sstables) {
+    for (auto i: *cf.get_sstables() ) {
        auto c = i->get_stats_metadata().estimated_partition_size.count();
        res.sub += i->get_stats_metadata().estimated_partition_size.mean() * c;
        res.total += c;
@@ -210,7 +220,7 @@ static json::json_return_type sum_map(const std::unordered_map<sstring, uint64_t

 static future<json::json_return_type>  sum_sstable(http_context& ctx, const sstring name, bool total) {
    auto uuid = get_uuid(name, ctx.db.local());
-    return ctx.db.map_reduce0([uuid, total](replica::database& db) {
+    return ctx.db.map_reduce0([uuid, total](database& db) {
        std::unordered_map<sstring, uint64_t> m;
        auto sstables = (total) ? db.find_column_family(uuid).get_sstables_including_compacted_undeleted() :
                db.find_column_family(uuid).get_sstables();
@@ -226,7 +236,7 @@ static future<json::json_return_type>  sum_sstable(http_context& ctx, const sstr


 static future<json::json_return_type> sum_sstable(http_context& ctx, bool total) {
-    return map_reduce_cf_raw(ctx, std::unordered_map<sstring, uint64_t>(), [total](replica::column_family& cf) {
+    return map_reduce_cf_raw(ctx, std::unordered_map<sstring, uint64_t>(), [total](column_family& cf) {
        std::unordered_map<sstring, uint64_t> m;
        auto sstables = (total) ? cf.get_sstables_including_compacted_undeleted() :
                cf.get_sstables();
@@ -239,7 +249,7 @@ static future<json::json_return_type> sum_sstable(http_context& ctx, bool total)
    });
 }

-future<json::json_return_type> map_reduce_cf_time_histogram(http_context& ctx, const sstring& name, std::function<utils::time_estimated_histogram(const replica::column_family&)> f) {
+future<json::json_return_type> map_reduce_cf_time_histogram(http_context& ctx, const sstring& name, std::function<utils::time_estimated_histogram(const column_family&)> f) {
    return map_reduce_cf_raw(ctx, name, utils::time_estimated_histogram(), f, utils::time_estimated_histogram_merge).then([](const utils::time_estimated_histogram& res) {
        return make_ready_future<json::json_return_type>(time_to_json_histogram(res));
    });
@@ -262,9 +272,9 @@ public:
    }
 };

-static double get_compression_ratio(replica::column_family& cf) {
+static double get_compression_ratio(column_family& cf) {
    sum_ratio<double> result;
-    for (auto sstables = cf.get_sstables(); auto& i : *sstables) {
+    for (auto i : *cf.get_sstables()) {
        auto compression_ratio = i->get_compression_ratio();
        if (compression_ratio != sstables::metadata_collector::NO_COMPRESSION_RATIO) {
            result(compression_ratio);
@@ -300,8 +310,8 @@ void set_column_family(http_context& ctx, routes& r) {
        return res;
    });

-    cf::get_column_family.set(r, [&ctx] (std::unique_ptr<request> req){
-            std::list<cf::column_family_info> res;
+    cf::get_column_family.set(r, [&ctx] (const_req req){
+            vector<cf::column_family_info> res;
            for (auto i: ctx.db.local().get_column_families_mapping()) {
                cf::column_family_info info;
                info.ks = i.first.first;
@@ -309,7 +319,7 @@ void set_column_family(http_context& ctx, routes& r) {
                info.type = "ColumnFamilies";
                res.push_back(info);
            }
-            return make_ready_future<json::json_return_type>(json::stream_range_as_array(std::move(res), std::identity()));
+            return res;
        });

    cf::get_column_family_name_keyspace.set(r, [&ctx] (const_req req){
@@ -321,15 +331,15 @@ void set_column_family(http_context& ctx, routes& r) {
    });

    cf::get_memtable_columns_count.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], uint64_t{0}, [](replica::column_family& cf) {
+        return map_reduce_cf(ctx, req->param["name"], 0, [](column_family& cf) {
            return cf.active_memtable().partition_count();
-        }, std::plus<>());
+        }, std::plus<int>());
    });

    cf::get_all_memtable_columns_count.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, uint64_t{0}, [](replica::column_family& cf) {
+        return map_reduce_cf(ctx, 0, [](column_family& cf) {
            return cf.active_memtable().partition_count();
-        }, std::plus<>());
+        }, std::plus<int>());
    });

    cf::get_memtable_on_heap_size.set(r, [] (const_req req) {
@@ -341,25 +351,25 @@ void set_column_family(http_context& ctx, routes& r) {
    });

    cf::get_memtable_off_heap_size.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], int64_t(0), [](replica::column_family& cf) {
+        return map_reduce_cf(ctx, req->param["name"], int64_t(0), [](column_family& cf) {
            return cf.active_memtable().region().occupancy().total_space();
        }, std::plus<int64_t>());
    });

    cf::get_all_memtable_off_heap_size.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, int64_t(0), [](replica::column_family& cf) {
+        return map_reduce_cf(ctx, int64_t(0), [](column_family& cf) {
            return cf.active_memtable().region().occupancy().total_space();
        }, std::plus<int64_t>());
    });

    cf::get_memtable_live_data_size.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], int64_t(0), [](replica::column_family& cf) {
+        return map_reduce_cf(ctx, req->param["name"], int64_t(0), [](column_family& cf) {
            return cf.active_memtable().region().occupancy().used_space();
        }, std::plus<int64_t>());
    });

    cf::get_all_memtable_live_data_size.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, int64_t(0), [](replica::column_family& cf) {
+        return map_reduce_cf(ctx, int64_t(0), [](column_family& cf) {
            return cf.active_memtable().region().occupancy().used_space();
        }, std::plus<int64_t>());
    });
@@ -374,14 +384,14 @@ void set_column_family(http_context& ctx, routes& r) {

    cf::get_cf_all_memtables_off_heap_size.set(r, [&ctx] (std::unique_ptr<request> req) {
        warn(unimplemented::cause::INDEXES);
-        return map_reduce_cf(ctx, req->param["name"], int64_t(0), [](replica::column_family& cf) {
+        return map_reduce_cf(ctx, req->param["name"], int64_t(0), [](column_family& cf) {
            return cf.occupancy().total_space();
        }, std::plus<int64_t>());
    });

    cf::get_all_cf_all_memtables_off_heap_size.set(r, [&ctx] (std::unique_ptr<request> req) {
        warn(unimplemented::cause::INDEXES);
-        return ctx.db.map_reduce0([](const replica::database& db){
+        return ctx.db.map_reduce0([](const database& db){
            return db.dirty_memory_region_group().memory_used();
        }, int64_t(0), std::plus<int64_t>()).then([](int res) {
            return make_ready_future<json::json_return_type>(res);
@@ -390,31 +400,31 @@ void set_column_family(http_context& ctx, routes& r) {

    cf::get_cf_all_memtables_live_data_size.set(r, [&ctx] (std::unique_ptr<request> req) {
        warn(unimplemented::cause::INDEXES);
-        return map_reduce_cf(ctx, req->param["name"], int64_t(0), [](replica::column_family& cf) {
+        return map_reduce_cf(ctx, req->param["name"], int64_t(0), [](column_family& cf) {
            return cf.occupancy().used_space();
        }, std::plus<int64_t>());
    });

    cf::get_all_cf_all_memtables_live_data_size.set(r, [&ctx] (std::unique_ptr<request> req) {
        warn(unimplemented::cause::INDEXES);
-        return map_reduce_cf(ctx, int64_t(0), [](replica::column_family& cf) {
+        return map_reduce_cf(ctx, int64_t(0), [](column_family& cf) {
            return cf.active_memtable().region().occupancy().used_space();
        }, std::plus<int64_t>());
    });

    cf::get_memtable_switch_count.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats(ctx,req->param["name"] ,&replica::column_family_stats::memtable_switch_count);
+        return get_cf_stats(ctx,req->param["name"] ,&column_family_stats::memtable_switch_count);
    });

    cf::get_all_memtable_switch_count.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats(ctx, &replica::column_family_stats::memtable_switch_count);
+        return get_cf_stats(ctx, &column_family_stats::memtable_switch_count);
    });

    // FIXME: this refers to partitions, not rows.
    cf::get_estimated_row_size_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](replica::column_family& cf) {
+        return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
            utils::estimated_histogram res(0);
-            for (auto sstables = cf.get_sstables(); auto& i : *sstables) {
+            for (auto i: *cf.get_sstables() ) {
                res.merge(i->get_stats_metadata().estimated_partition_size);
            }
            return res;
@@ -424,9 +434,9 @@ void set_column_family(http_context& ctx, routes& r) {

    // FIXME: this refers to partitions, not rows.
    cf::get_estimated_row_count.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], int64_t(0), [](replica::column_family& cf) {
+        return map_reduce_cf(ctx, req->param["name"], int64_t(0), [](column_family& cf) {
            uint64_t res = 0;
-            for (auto sstables = cf.get_sstables(); auto& i : *sstables) {
+            for (auto i: *cf.get_sstables() ) {
                res += i->get_stats_metadata().estimated_partition_size.count();
            }
            return res;
@@ -435,9 +445,9 @@ void set_column_family(http_context& ctx, routes& r) {
    });

    cf::get_estimated_column_count_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](replica::column_family& cf) {
+        return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
            utils::estimated_histogram res(0);
-            for (auto sstables = cf.get_sstables(); auto& i : *sstables) {
+            for (auto i: *cf.get_sstables() ) {
                res.merge(i->get_stats_metadata().estimated_cells_count);
            }
            return res;
@@ -452,87 +462,87 @@ void set_column_family(http_context& ctx, routes& r) {
    });

    cf::get_pending_flushes.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats(ctx,req->param["name"] ,&replica::column_family_stats::pending_flushes);
+        return get_cf_stats(ctx,req->param["name"] ,&column_family_stats::pending_flushes);
    });

    cf::get_all_pending_flushes.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats(ctx, &replica::column_family_stats::pending_flushes);
+        return get_cf_stats(ctx, &column_family_stats::pending_flushes);
    });

    cf::get_read.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats_count(ctx,req->param["name"] ,&replica::column_family_stats::reads);
+        return get_cf_stats_count(ctx,req->param["name"] ,&column_family_stats::reads);
    });

    cf::get_all_read.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats_count(ctx, &replica::column_family_stats::reads);
+        return get_cf_stats_count(ctx, &column_family_stats::reads);
    });

    cf::get_write.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats_count(ctx, req->param["name"] ,&replica::column_family_stats::writes);
+        return get_cf_stats_count(ctx, req->param["name"] ,&column_family_stats::writes);
    });

    cf::get_all_write.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats_count(ctx, &replica::column_family_stats::writes);
+        return get_cf_stats_count(ctx, &column_family_stats::writes);
    });

    cf::get_read_latency_histogram_depricated.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_histogram(ctx, req->param["name"], &replica::column_family_stats::reads);
+        return get_cf_histogram(ctx, req->param["name"], &column_family_stats::reads);
    });

    cf::get_read_latency_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_rate_and_histogram(ctx, req->param["name"], &replica::column_family_stats::reads);
+        return get_cf_rate_and_histogram(ctx, req->param["name"], &column_family_stats::reads);
    });

    cf::get_read_latency.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats_sum(ctx,req->param["name"] ,&replica::column_family_stats::reads);
+        return get_cf_stats_sum(ctx,req->param["name"] ,&column_family_stats::reads);
    });

    cf::get_write_latency.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats_sum(ctx, req->param["name"] ,&replica::column_family_stats::writes);
+        return get_cf_stats_sum(ctx, req->param["name"] ,&column_family_stats::writes);
    });

    cf::get_all_read_latency_histogram_depricated.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_histogram(ctx, &replica::column_family_stats::writes);
+        return get_cf_histogram(ctx, &column_family_stats::writes);
    });

    cf::get_all_read_latency_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_rate_and_histogram(ctx, &replica::column_family_stats::writes);
+        return get_cf_rate_and_histogram(ctx, &column_family_stats::writes);
    });

    cf::get_write_latency_histogram_depricated.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_histogram(ctx, req->param["name"], &replica::column_family_stats::writes);
+        return get_cf_histogram(ctx, req->param["name"], &column_family_stats::writes);
    });

    cf::get_write_latency_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_rate_and_histogram(ctx, req->param["name"], &replica::column_family_stats::writes);
+        return get_cf_rate_and_histogram(ctx, req->param["name"], &column_family_stats::writes);
    });

    cf::get_all_write_latency_histogram_depricated.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_histogram(ctx, &replica::column_family_stats::writes);
+        return get_cf_histogram(ctx, &column_family_stats::writes);
    });

    cf::get_all_write_latency_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_rate_and_histogram(ctx, &replica::column_family_stats::writes);
+        return get_cf_rate_and_histogram(ctx, &column_family_stats::writes);
    });

    cf::get_pending_compactions.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], int64_t(0), [](replica::column_family& cf) {
-            return cf.get_compaction_strategy().estimated_pending_compactions(cf.as_table_state());
+        return map_reduce_cf(ctx, req->param["name"], int64_t(0), [](column_family& cf) {
+            return cf.get_compaction_strategy().estimated_pending_compactions(cf);
        }, std::plus<int64_t>());
    });

    cf::get_all_pending_compactions.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, int64_t(0), [](replica::column_family& cf) {
-            return cf.get_compaction_strategy().estimated_pending_compactions(cf.as_table_state());
+        return map_reduce_cf(ctx, int64_t(0), [](column_family& cf) {
+            return cf.get_compaction_strategy().estimated_pending_compactions(cf);
        }, std::plus<int64_t>());
    });

    cf::get_live_ss_table_count.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats(ctx, req->param["name"], &replica::column_family_stats::live_sstable_count);
+        return get_cf_stats(ctx, req->param["name"], &column_family_stats::live_sstable_count);
    });

    cf::get_all_live_ss_table_count.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_stats(ctx, &replica::column_family_stats::live_sstable_count);
+        return get_cf_stats(ctx, &column_family_stats::live_sstable_count);
    });

    cf::get_unleveled_sstables.set(r, [&ctx] (std::unique_ptr<request> req) {
@@ -588,115 +598,105 @@ void set_column_family(http_context& ctx, routes& r) {
    });

    cf::get_bloom_filter_false_positives.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], uint64_t(0), [] (replica::column_family& cf) {
-            auto sstables = cf.get_sstables();
-            return std::accumulate(sstables->begin(), sstables->end(), uint64_t(0), [](uint64_t s, auto& sst) {
+        return map_reduce_cf(ctx, req->param["name"], uint64_t(0), [] (column_family& cf) {
+            return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
                return s + sst->filter_get_false_positive();
            });
        }, std::plus<uint64_t>());
    });

    cf::get_all_bloom_filter_false_positives.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, uint64_t(0), [] (replica::column_family& cf) {
-            auto sstables = cf.get_sstables();
-            return std::accumulate(sstables->begin(), sstables->end(), uint64_t(0), [](uint64_t s, auto& sst) {
+        return map_reduce_cf(ctx, uint64_t(0), [] (column_family& cf) {
+            return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
                return s + sst->filter_get_false_positive();
            });
        }, std::plus<uint64_t>());
    });

    cf::get_recent_bloom_filter_false_positives.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], uint64_t(0), [] (replica::column_family& cf) {
-            auto sstables = cf.get_sstables();
-            return std::accumulate(sstables->begin(), sstables->end(), uint64_t(0), [](uint64_t s, auto& sst) {
+        return map_reduce_cf(ctx, req->param["name"], uint64_t(0), [] (column_family& cf) {
+            return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
                return s + sst->filter_get_recent_false_positive();
            });
        }, std::plus<uint64_t>());
    });

    cf::get_all_recent_bloom_filter_false_positives.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, uint64_t(0), [] (replica::column_family& cf) {
-            auto sstables = cf.get_sstables();
-            return std::accumulate(sstables->begin(), sstables->end(), uint64_t(0), [](uint64_t s, auto& sst) {
+        return map_reduce_cf(ctx, uint64_t(0), [] (column_family& cf) {
+            return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
                return s + sst->filter_get_recent_false_positive();
            });
        }, std::plus<uint64_t>());
    });

    cf::get_bloom_filter_false_ratio.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], ratio_holder(), [] (replica::column_family& cf) {
+        return map_reduce_cf(ctx, req->param["name"], ratio_holder(), [] (column_family& cf) {
            return boost::accumulate(*cf.get_sstables() | boost::adaptors::transformed(filter_false_positive_as_ratio_holder), ratio_holder());
        }, std::plus<>());
    });

    cf::get_all_bloom_filter_false_ratio.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, ratio_holder(), [] (replica::column_family& cf) {
+        return map_reduce_cf(ctx, ratio_holder(), [] (column_family& cf) {
            return boost::accumulate(*cf.get_sstables() | boost::adaptors::transformed(filter_false_positive_as_ratio_holder), ratio_holder());
        }, std::plus<>());
    });

    cf::get_recent_bloom_filter_false_ratio.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], ratio_holder(), [] (replica::column_family& cf) {
+        return map_reduce_cf(ctx, req->param["name"], ratio_holder(), [] (column_family& cf) {
            return boost::accumulate(*cf.get_sstables() | boost::adaptors::transformed(filter_recent_false_positive_as_ratio_holder), ratio_holder());
        }, std::plus<>());
    });

    cf::get_all_recent_bloom_filter_false_ratio.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, ratio_holder(), [] (replica::column_family& cf) {
+        return map_reduce_cf(ctx, ratio_holder(), [] (column_family& cf) {
            return boost::accumulate(*cf.get_sstables() | boost::adaptors::transformed(filter_recent_false_positive_as_ratio_holder), ratio_holder());
        }, std::plus<>());
    });

    cf::get_bloom_filter_disk_space_used.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], uint64_t(0), [] (replica::column_family& cf) {
-            auto sstables = cf.get_sstables();
-            return std::accumulate(sstables->begin(), sstables->end(), uint64_t(0), [](uint64_t s, auto& sst) {
-                return s + sst->filter_size();
+        return map_reduce_cf(ctx, req->param["name"], uint64_t(0), [] (column_family& cf) {
+            return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
+                return sst->filter_size();
            });
        }, std::plus<uint64_t>());
    });

    cf::get_all_bloom_filter_disk_space_used.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, uint64_t(0), [] (replica::column_family& cf) {
-            auto sstables = cf.get_sstables();
-            return std::accumulate(sstables->begin(), sstables->end(), uint64_t(0), [](uint64_t s, auto& sst) {
-                return s + sst->filter_size();
+        return map_reduce_cf(ctx, uint64_t(0), [] (column_family& cf) {
+            return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
+                return sst->filter_size();
            });
        }, std::plus<uint64_t>());
    });

    cf::get_bloom_filter_off_heap_memory_used.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], uint64_t(0), [] (replica::column_family& cf) {
-            auto sstables = cf.get_sstables();
-            return std::accumulate(sstables->begin(), sstables->end(), uint64_t(0), [](uint64_t s, auto& sst) {
-                return s + sst->filter_memory_size();
+        return map_reduce_cf(ctx, req->param["name"], uint64_t(0), [] (column_family& cf) {
+            return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
+                return sst->filter_memory_size();
            });
        }, std::plus<uint64_t>());
    });

    cf::get_all_bloom_filter_off_heap_memory_used.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, uint64_t(0), [] (replica::column_family& cf) {
-            auto sstables = cf.get_sstables();
-            return std::accumulate(sstables->begin(), sstables->end(), uint64_t(0), [](uint64_t s, auto& sst) {
-                return s + sst->filter_memory_size();
+        return map_reduce_cf(ctx, uint64_t(0), [] (column_family& cf) {
+            return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
+                return sst->filter_memory_size();
            });
        }, std::plus<uint64_t>());
    });

    cf::get_index_summary_off_heap_memory_used.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], uint64_t(0), [] (replica::column_family& cf) {
-            auto sstables = cf.get_sstables();
-            return std::accumulate(sstables->begin(), sstables->end(), uint64_t(0), [](uint64_t s, auto& sst) {
-                return s + sst->get_summary().memory_footprint();
+        return map_reduce_cf(ctx, req->param["name"], uint64_t(0), [] (column_family& cf) {
+            return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
+                return sst->get_summary().memory_footprint();
            });
        }, std::plus<uint64_t>());
    });

    cf::get_all_index_summary_off_heap_memory_used.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, uint64_t(0), [] (replica::column_family& cf) {
-            auto sstables = cf.get_sstables();
-            return std::accumulate(sstables->begin(), sstables->end(), uint64_t(0), [](uint64_t s, auto& sst) {
-                return s + sst->get_summary().memory_footprint();
+        return map_reduce_cf(ctx, uint64_t(0), [] (column_family& cf) {
+            return std::accumulate(cf.get_sstables()->begin(), cf.get_sstables()->end(), uint64_t(0), [](uint64_t s, auto& sst) {
+                return sst->get_summary().memory_footprint();
            });
        }, std::plus<uint64_t>());
    });
@@ -740,7 +740,7 @@ void set_column_family(http_context& ctx, routes& r) {
    cf::get_true_snapshots_size.set(r, [&ctx] (std::unique_ptr<request> req) {
        auto uuid = get_uuid(req->param["name"], ctx.db.local());
        return ctx.db.local().find_column_family(uuid).get_snapshot_details().then([](
-                const std::unordered_map<sstring, replica::column_family::snapshot_details>& sd) {
+                const std::unordered_map<sstring, column_family::snapshot_details>& sd) {
            int64_t res = 0;
            for (auto i : sd) {
                res += i.second.total;
@@ -769,7 +769,7 @@ void set_column_family(http_context& ctx, routes& r) {
    });

    cf::get_row_cache_hit.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf_raw(ctx, req->param["name"], utils::rate_moving_average(), [](const replica::column_family& cf) {
+        return map_reduce_cf_raw(ctx, req->param["name"], utils::rate_moving_average(), [](const column_family& cf) {
            return cf.get_row_cache().stats().hits.rate();
        }, std::plus<utils::rate_moving_average>()).then([](const utils::rate_moving_average& m) {
            return make_ready_future<json::json_return_type>(meter_to_json(m));
@@ -777,7 +777,7 @@ void set_column_family(http_context& ctx, routes& r) {
    });

    cf::get_all_row_cache_hit.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf_raw(ctx, utils::rate_moving_average(), [](const replica::column_family& cf) {
+        return map_reduce_cf_raw(ctx, utils::rate_moving_average(), [](const column_family& cf) {
            return cf.get_row_cache().stats().hits.rate();
        }, std::plus<utils::rate_moving_average>()).then([](const utils::rate_moving_average& m) {
            return make_ready_future<json::json_return_type>(meter_to_json(m));
@@ -785,7 +785,7 @@ void set_column_family(http_context& ctx, routes& r) {
    });

    cf::get_row_cache_miss.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf_raw(ctx, req->param["name"], utils::rate_moving_average(), [](const replica::column_family& cf) {
+        return map_reduce_cf_raw(ctx, req->param["name"], utils::rate_moving_average(), [](const column_family& cf) {
            return cf.get_row_cache().stats().misses.rate();
        }, std::plus<utils::rate_moving_average>()).then([](const utils::rate_moving_average& m) {
            return make_ready_future<json::json_return_type>(meter_to_json(m));
@@ -793,7 +793,7 @@ void set_column_family(http_context& ctx, routes& r) {
    });

    cf::get_all_row_cache_miss.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf_raw(ctx, utils::rate_moving_average(), [](const replica::column_family& cf) {
+        return map_reduce_cf_raw(ctx, utils::rate_moving_average(), [](const column_family& cf) {
            return cf.get_row_cache().stats().misses.rate();
        }, std::plus<utils::rate_moving_average>()).then([](const utils::rate_moving_average& m) {
            return make_ready_future<json::json_return_type>(meter_to_json(m));
@@ -802,36 +802,36 @@ void set_column_family(http_context& ctx, routes& r) {
    });

    cf::get_cas_prepare.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf_time_histogram(ctx, req->param["name"], [](const replica::column_family& cf) {
+        return map_reduce_cf_time_histogram(ctx, req->param["name"], [](const column_family& cf) {
            return cf.get_stats().estimated_cas_prepare;
        });
    });

    cf::get_cas_propose.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf_time_histogram(ctx, req->param["name"], [](const replica::column_family& cf) {
+        return map_reduce_cf_time_histogram(ctx, req->param["name"], [](const column_family& cf) {
            return cf.get_stats().estimated_cas_accept;
        });
    });

    cf::get_cas_commit.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf_time_histogram(ctx, req->param["name"], [](const replica::column_family& cf) {
+        return map_reduce_cf_time_histogram(ctx, req->param["name"], [](const column_family& cf) {
            return cf.get_stats().estimated_cas_learn;
        });
    });

    cf::get_sstables_per_read_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](replica::column_family& cf) {
+        return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
            return cf.get_stats().estimated_sstable_per_read;
        },
        utils::estimated_histogram_merge, utils_json::estimated_histogram());
    });

    cf::get_tombstone_scanned_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_histogram(ctx, req->param["name"], &replica::column_family_stats::tombstone_scanned);
+        return get_cf_histogram(ctx, req->param["name"], &column_family_stats::tombstone_scanned);
    });

    cf::get_live_scanned_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return get_cf_histogram(ctx, req->param["name"], &replica::column_family_stats::live_scanned);
+        return get_cf_histogram(ctx, req->param["name"], &column_family_stats::live_scanned);
    });

    cf::get_col_update_time_delta_histogram.set(r, [] (std::unique_ptr<request> req) {
@@ -844,29 +844,23 @@ void set_column_family(http_context& ctx, routes& r) {

    cf::get_auto_compaction.set(r, [&ctx] (const_req req) {
        const utils::UUID& uuid = get_uuid(req.param["name"], ctx.db.local());
-        replica::column_family& cf = ctx.db.local().find_column_family(uuid);
+        column_family& cf = ctx.db.local().find_column_family(uuid);
        return !cf.is_auto_compaction_disabled_by_user();
    });

    cf::enable_auto_compaction.set(r, [&ctx](std::unique_ptr<request> req) {
-        return ctx.db.invoke_on(0, [&ctx, req = std::move(req)] (replica::database& db) {
-            auto g = replica::database::autocompaction_toggle_guard(db);
-            return foreach_column_family(ctx, req->param["name"], [](replica::column_family &cf) {
-                cf.enable_auto_compaction();
-            }).then([g = std::move(g)] {
-                return make_ready_future<json::json_return_type>(json_void());
-            });
+        return foreach_column_family(ctx, req->param["name"], [](column_family &cf) {
+            cf.enable_auto_compaction();
+        }).then([] {
+            return make_ready_future<json::json_return_type>(json_void());
        });
    });

    cf::disable_auto_compaction.set(r, [&ctx](std::unique_ptr<request> req) {
-        return ctx.db.invoke_on(0, [&ctx, req = std::move(req)] (replica::database& db) {
-            auto g = replica::database::autocompaction_toggle_guard(db);
-            return foreach_column_family(ctx, req->param["name"], [](replica::column_family &cf) {
-                return cf.disable_auto_compaction();
-            }).then([g = std::move(g)] {
-                return make_ready_future<json::json_return_type>(json_void());
-            });
+        return foreach_column_family(ctx, req->param["name"], [](column_family &cf) {
+            cf.disable_auto_compaction();
+        }).then([] {
+            return make_ready_future<json::json_return_type>(json_void());
        });
    });

@@ -874,7 +868,7 @@ void set_column_family(http_context& ctx, routes& r) {
        auto ks_cf = parse_fully_qualified_cf_name(req->param["name"]);
        auto&& ks = std::get<0>(ks_cf);
        auto&& cf_name = std::get<1>(ks_cf);
-        return db::system_keyspace::load_view_build_progress().then([ks, cf_name, &ctx](const std::vector<db::system_keyspace_view_build_progress>& vb) mutable {
+        return db::system_keyspace::load_view_build_progress().then([ks, cf_name, &ctx](const std::vector<db::system_keyspace::view_build_progress>& vb) mutable {
            std::set<sstring> vp;
            for (auto b : vb) {
                if (b.view.first == ks) {
@@ -883,7 +877,7 @@ void set_column_family(http_context& ctx, routes& r) {
            }
            std::vector<sstring> res;
            auto uuid = get_uuid(ks, cf_name, ctx.db.local());
-            replica::column_family& cf = ctx.db.local().find_column_family(uuid);
+            column_family& cf = ctx.db.local().find_column_family(uuid);
            res.reserve(cf.get_index_manager().list_indexes().size());
            for (auto&& i : cf.get_index_manager().list_indexes()) {
                if (!vp.contains(secondary_index::index_table_name(i.metadata().name()))) {
@@ -911,8 +905,8 @@ void set_column_family(http_context& ctx, routes& r) {
    cf::get_compression_ratio.set(r, [&ctx](std::unique_ptr<request> req) {
        auto uuid = get_uuid(req->param["name"], ctx.db.local());

-        return ctx.db.map_reduce(sum_ratio<double>(), [uuid](replica::database& db) {
-            replica::column_family& cf = db.find_column_family(uuid);
+        return ctx.db.map_reduce(sum_ratio<double>(), [uuid](database& db) {
+            column_family& cf = db.find_column_family(uuid);
            return make_ready_future<double>(get_compression_ratio(cf));
        }).then([] (const double& result) {
            return make_ready_future<json::json_return_type>(result);
@@ -920,20 +914,20 @@ void set_column_family(http_context& ctx, routes& r) {
    });

    cf::get_read_latency_estimated_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
-        return map_reduce_cf_time_histogram(ctx, req->param["name"], [](const replica::column_family& cf) {
+        return map_reduce_cf_time_histogram(ctx, req->param["name"], [](const column_family& cf) {
            return cf.get_stats().estimated_read;
        });
    });

    cf::get_write_latency_estimated_histogram.set(r, [&ctx](std::unique_ptr<request> req) {
-        return map_reduce_cf_time_histogram(ctx, req->param["name"], [](const replica::column_family& cf) {
+        return map_reduce_cf_time_histogram(ctx, req->param["name"], [](const column_family& cf) {
            return cf.get_stats().estimated_write;
        });
    });

    cf::set_compaction_strategy_class.set(r, [&ctx](std::unique_ptr<request> req) {
        sstring strategy = req->get_query_param("class_name");
-        return foreach_column_family(ctx, req->param["name"], [strategy](replica::column_family& cf) {
+        return foreach_column_family(ctx, req->param["name"], [strategy](column_family& cf) {
            cf.set_compaction_strategy(sstables::compaction_strategy::type(strategy));
        }).then([] {
                return make_ready_future<json::json_return_type>(json_void());
@@ -957,7 +951,7 @@ void set_column_family(http_context& ctx, routes& r) {
    });

    cf::get_sstable_count_per_level.set(r, [&ctx](std::unique_ptr<request> req) {
-        return map_reduce_cf_raw(ctx, req->param["name"], std::vector<uint64_t>(), [](const replica::column_family& cf) {
+        return map_reduce_cf_raw(ctx, req->param["name"], std::vector<uint64_t>(), [](const column_family& cf) {
            return cf.sstable_count_per_level();
        }, concat_sstable_count_per_level).then([](const std::vector<uint64_t>& res) {
            return make_ready_future<json::json_return_type>(res);
@@ -968,7 +962,7 @@ void set_column_family(http_context& ctx, routes& r) {
        auto key = req->get_query_param("key");
        auto uuid = get_uuid(req->param["name"], ctx.db.local());

-        return ctx.db.map_reduce0([key, uuid] (replica::database& db) {
+        return ctx.db.map_reduce0([key, uuid] (database& db) {
            return db.find_column_family(uuid).get_sstables_by_partition_key(key);
        }, std::unordered_set<sstring>(),
            [](std::unordered_set<sstring> a, std::unordered_set<sstring>&& b) mutable {
@@ -979,20 +973,42 @@ void set_column_family(http_context& ctx, routes& r) {
        });
    });

-
    cf::toppartitions.set(r, [&ctx] (std::unique_ptr<request> req) {
-        auto name = req->param["name"];
-        auto [ks, cf] = parse_fully_qualified_cf_name(name);
+        auto name_param = req->param["name"];
+        auto [ks, cf] = parse_fully_qualified_cf_name(name_param);

        api::req_param<std::chrono::milliseconds, unsigned> duration{*req, "duration", 1000ms};
        api::req_param<unsigned> capacity(*req, "capacity", 256);
        api::req_param<unsigned> list_size(*req, "list_size", 10);

        apilog.info("toppartitions query: name={} duration={} list_size={} capacity={}",
-            name, duration.param, list_size.param, capacity.param);
+            name_param, duration.param, list_size.param, capacity.param);

-        return seastar::do_with(db::toppartitions_query(ctx.db, {{ks, cf}}, {}, duration.value, list_size, capacity), [&ctx] (db::toppartitions_query& q) {
-            return run_toppartitions_query(q, ctx, true);
+        return seastar::do_with(db::toppartitions_query(ctx.db, ks, cf, duration.value, list_size, capacity), [&ctx](auto& q) {
+            return q.scatter().then([&q] {
+                return sleep(q.duration()).then([&q] {
+                    return q.gather(q.capacity()).then([&q] (auto topk_results) {
+                        apilog.debug("toppartitions query: processing results");
+                        cf::toppartitions_query_results results;
+
+                        for (auto& d: topk_results.read.top(q.list_size())) {
+                            cf::toppartitions_record r;
+                            r.partition = sstring(d.item);
+                            r.count = d.count;
+                            r.error = d.error;
+                            results.read.push(r);
+                        }
+                        for (auto& d: topk_results.write.top(q.list_size())) {
+                            cf::toppartitions_record r;
+                            r.partition = sstring(d.item);
+                            r.count = d.count;
+                            r.error = d.error;
+                            results.write.push(r);
+                        }
+                        return make_ready_future<json::json_return_type>(results);
+                    });
+                });
+            });
        });
    });

@@ -1000,7 +1016,7 @@ void set_column_family(http_context& ctx, routes& r) {
        if (req->get_query_param("split_output") != "") {
            fail(unimplemented::cause::API);
        }
-        return foreach_column_family(ctx, req->param["name"], [](replica::column_family &cf) {
+        return foreach_column_family(ctx, req->param["name"], [](column_family &cf) {
            return cf.compact_all_sstables();
        }).then([] {
            return make_ready_future<json::json_return_type>(json_void());
--- a/api/column_family.hh
+++ b/api/column_family.hh
@@ -1,16 +1,29 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once

 #include "api.hh"
 #include "api/api-doc/column_family.json.hh"
-#include "replica/database.hh"
+#include "database.hh"
 #include <seastar/core/future-util.hh>
 #include <any>

@@ -18,17 +31,17 @@ namespace api {

 void set_column_family(http_context& ctx, routes& r);

-const utils::UUID& get_uuid(const sstring& name, const replica::database& db);
-future<> foreach_column_family(http_context& ctx, const sstring& name, std::function<void(replica::column_family&)> f);
+const utils::UUID& get_uuid(const sstring& name, const database& db);
+future<> foreach_column_family(http_context& ctx, const sstring& name, std::function<void(column_family&)> f);


 template<class Mapper, class I, class Reducer>
 future<I> map_reduce_cf_raw(http_context& ctx, const sstring& name, I init,
        Mapper mapper, Reducer reducer) {
    auto uuid = get_uuid(name, ctx.db.local());
-    using mapper_type = std::function<std::unique_ptr<std::any>(replica::database&)>;
+    using mapper_type = std::function<std::unique_ptr<std::any>(database&)>;
    using reducer_type = std::function<std::unique_ptr<std::any>(std::unique_ptr<std::any>, std::unique_ptr<std::any>)>;
-    return ctx.db.map_reduce0(mapper_type([mapper, uuid](replica::database& db) {
+    return ctx.db.map_reduce0(mapper_type([mapper, uuid](database& db) {
        return std::make_unique<std::any>(I(mapper(db.find_column_family(uuid))));
    }), std::make_unique<std::any>(std::move(init)), reducer_type([reducer = std::move(reducer)] (std::unique_ptr<std::any> a, std::unique_ptr<std::any> b) mutable {
        return std::make_unique<std::any>(I(reducer(std::any_cast<I>(std::move(*a)), std::any_cast<I>(std::move(*b)))));
@@ -55,16 +68,16 @@ future<json::json_return_type> map_reduce_cf(http_context& ctx, const sstring& n
    });
 }

-future<json::json_return_type> map_reduce_cf_time_histogram(http_context& ctx, const sstring& name, std::function<utils::time_estimated_histogram(const replica::column_family&)> f);
+future<json::json_return_type> map_reduce_cf_time_histogram(http_context& ctx, const sstring& name, std::function<utils::time_estimated_histogram(const column_family&)> f);

 struct map_reduce_column_families_locally {
    std::any init;
-    std::function<std::unique_ptr<std::any>(replica::column_family&)> mapper;
+    std::function<std::unique_ptr<std::any>(column_family&)> mapper;
    std::function<std::unique_ptr<std::any>(std::unique_ptr<std::any>, std::unique_ptr<std::any>)> reducer;
-    future<std::unique_ptr<std::any>> operator()(replica::database& db) const {
+    future<std::unique_ptr<std::any>> operator()(database& db) const {
        auto res = seastar::make_lw_shared<std::unique_ptr<std::any>>(std::make_unique<std::any>(init));
-        return do_for_each(db.get_column_families(), [res, this](const std::pair<utils::UUID, seastar::lw_shared_ptr<replica::table>>& i) {
-            *res = reducer(std::move(*res), mapper(*i.second.get()));
+        return do_for_each(db.get_column_families(), [res, this](const std::pair<utils::UUID, seastar::lw_shared_ptr<table>>& i) {
+            *res = std::move(reducer(std::move(*res), mapper(*i.second.get())));
        }).then([res] {
            return std::move(*res);
        });
@@ -74,9 +87,9 @@ struct map_reduce_column_families_locally {
 template<class Mapper, class I, class Reducer>
 future<I> map_reduce_cf_raw(http_context& ctx, I init,
        Mapper mapper, Reducer reducer) {
-    using mapper_type = std::function<std::unique_ptr<std::any>(replica::column_family&)>;
+    using mapper_type = std::function<std::unique_ptr<std::any>(column_family&)>;
    using reducer_type = std::function<std::unique_ptr<std::any>(std::unique_ptr<std::any>, std::unique_ptr<std::any>)>;
-    auto wrapped_mapper = mapper_type([mapper = std::move(mapper)] (replica::column_family& cf) mutable {
+    auto wrapped_mapper = mapper_type([mapper = std::move(mapper)] (column_family& cf) mutable {
        return std::make_unique<std::any>(I(mapper(cf)));
    });
    auto wrapped_reducer = reducer_type([reducer = std::move(reducer)] (std::unique_ptr<std::any> a, std::unique_ptr<std::any> b) mutable {
@@ -98,12 +111,9 @@ future<json::json_return_type> map_reduce_cf(http_context& ctx, I init,
 }

 future<json::json_return_type>  get_cf_stats(http_context& ctx, const sstring& name,
-        int64_t replica::column_family_stats::*f);
+        int64_t column_family_stats::*f);

 future<json::json_return_type>  get_cf_stats(http_context& ctx,
-        int64_t replica::column_family_stats::*f);
-
-
-std::tuple<sstring, sstring> parse_fully_qualified_cf_name(sstring name);
+        int64_t column_family_stats::*f);

 }
--- a/api/commitlog.cc
+++ b/api/commitlog.cc
@@ -1,15 +1,28 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #include "commitlog.hh"
 #include "db/commitlog/commitlog.hh"
 #include "api/api-doc/commitlog.json.hh"
-#include "replica/database.hh"
+#include "database.hh"
 #include <vector>

 namespace api {
@@ -18,7 +31,7 @@ template<typename T>
 static auto acquire_cl_metric(http_context& ctx, std::function<T (db::commitlog*)> func) {
    typedef T ret_type;

-    return ctx.db.map_reduce0([func = std::move(func)](replica::database& db) {
+    return ctx.db.map_reduce0([func = std::move(func)](database& db) {
        if (db.commitlog() == nullptr) {
            return make_ready_future<ret_type>();
        }
@@ -34,7 +47,7 @@ void set_commitlog(http_context& ctx, routes& r) {
        auto res = make_shared<std::vector<sstring>>();
        return ctx.db.map_reduce([res](std::vector<sstring> names) {
            res->insert(res->end(), names.begin(), names.end());
-        }, [](replica::database& db) {
+        }, [](database& db) {
            if (db.commitlog() == nullptr) {
                return make_ready_future<std::vector<sstring>>(std::vector<sstring>());
            }
--- a/api/commitlog.hh
+++ b/api/commitlog.hh
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once
--- a/api/compaction_manager.cc
+++ b/api/compaction_manager.cc
@@ -1,21 +1,29 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

-#include <seastar/core/coroutine.hh>
-
 #include "compaction_manager.hh"
-#include "compaction/compaction_manager.hh"
+#include "sstables/compaction_manager.hh"
 #include "api/api-doc/compaction_manager.json.hh"
 #include "db/system_keyspace.hh"
 #include "column_family.hh"
-#include "unimplemented.hh"
-#include "storage_service.hh"
-
 #include <utility>

 namespace api {
@@ -25,7 +33,7 @@ using namespace json;

 static future<json::json_return_type> get_cm_stats(http_context& ctx,
        int64_t compaction_manager::stats::*f) {
-    return ctx.db.map_reduce0([f](replica::database& db) {
+    return ctx.db.map_reduce0([f](database& db) {
        return db.get_compaction_manager().get_stats().*f;
    }, int64_t(0), std::plus<int64_t>()).then([](const int64_t& res) {
        return make_ready_future<json::json_return_type>(res);
@@ -44,19 +52,18 @@ static std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_ha

 void set_compaction_manager(http_context& ctx, routes& r) {
    cm::get_compactions.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return ctx.db.map_reduce0([](replica::database& db) {
+        return ctx.db.map_reduce0([](database& db) {
            std::vector<cm::summary> summaries;
            const compaction_manager& cm = db.get_compaction_manager();

            for (const auto& c : cm.get_compactions()) {
                cm::summary s;
-                s.id = c.compaction_uuid.to_sstring();
-                s.ks = c.ks_name;
-                s.cf = c.cf_name;
+                s.ks = c->ks_name;
+                s.cf = c->cf_name;
                s.unit = "keys";
-                s.task_type = sstables::compaction_name(c.type);
-                s.completed = c.total_keys_written;
-                s.total = c.total_partitions;
+                s.task_type = sstables::compaction_name(c->type);
+                s.completed = c->total_keys_written;
+                s.total = c->total_partitions;
                summaries.push_back(std::move(s));
            }
            return summaries;
@@ -66,11 +73,11 @@ void set_compaction_manager(http_context& ctx, routes& r) {
    });

    cm::get_pending_tasks_by_table.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return ctx.db.map_reduce0([&ctx](replica::database& db) {
+        return ctx.db.map_reduce0([&ctx](database& db) {
            return do_with(std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_hash>(), [&ctx, &db](std::unordered_map<std::pair<sstring, sstring>, uint64_t, utils::tuple_hash>& tasks) {
-                return do_for_each(db.get_column_families(), [&tasks](const std::pair<utils::UUID, seastar::lw_shared_ptr<replica::table>>& i) {
-                    replica::table& cf = *i.second.get();
-                    tasks[std::make_pair(cf.schema()->ks_name(), cf.schema()->cf_name())] = cf.get_compaction_strategy().estimated_pending_compactions(cf.as_table_state());
+                return do_for_each(db.get_column_families(), [&tasks](const std::pair<utils::UUID, seastar::lw_shared_ptr<table>>& i) {
+                    table& cf = *i.second.get();
+                    tasks[std::make_pair(cf.schema()->ks_name(), cf.schema()->cf_name())] = cf.get_compaction_strategy().estimated_pending_compactions(cf);
                    return make_ready_future<>();
                }).then([&tasks] {
                    return std::move(tasks);
@@ -100,34 +107,17 @@ void set_compaction_manager(http_context& ctx, routes& r) {

    cm::stop_compaction.set(r, [&ctx] (std::unique_ptr<request> req) {
        auto type = req->get_query_param("type");
-        return ctx.db.invoke_on_all([type] (replica::database& db) {
+        return ctx.db.invoke_on_all([type] (database& db) {
            auto& cm = db.get_compaction_manager();
-            return cm.stop_compaction(type);
+            cm.stop_compaction(type);
        }).then([] {
            return make_ready_future<json::json_return_type>(json_void());
        });
    });

-    cm::stop_keyspace_compaction.set(r, [&ctx] (std::unique_ptr<request> req) -> future<json::json_return_type> {
-        auto ks_name = validate_keyspace(ctx, req->param);
-        auto table_names = parse_tables(ks_name, ctx, req->query_parameters, "tables");
-        if (table_names.empty()) {
-            table_names = map_keys(ctx.db.local().find_keyspace(ks_name).metadata().get()->cf_meta_data());
-        }
-        auto type = req->get_query_param("type");
-        co_await ctx.db.invoke_on_all([&ks_name, &table_names, type] (replica::database& db) {
-            auto& cm = db.get_compaction_manager();
-            return parallel_for_each(table_names, [&db, &cm, &ks_name, type] (sstring& table_name) {
-                auto& t = db.find_column_family(ks_name, table_name);
-                return cm.stop_compaction(type, &t);
-            });
-        });
-        co_return json_void();
-    });
-
    cm::get_pending_tasks.set(r, [&ctx] (std::unique_ptr<request> req) {
-        return map_reduce_cf(ctx, int64_t(0), [](replica::column_family& cf) {
-            return cf.get_compaction_strategy().estimated_pending_compactions(cf.as_table_state());
+        return map_reduce_cf(ctx, int64_t(0), [](column_family& cf) {
+            return cf.get_compaction_strategy().estimated_pending_compactions(cf);
        }, std::plus<int64_t>());
    });

--- a/api/compaction_manager.hh
+++ b/api/compaction_manager.hh
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once
--- a/api/config.cc
+++ b/api/config.cc
@@ -1,14 +1,28 @@
 /*
- * Copyright 2018-present ScyllaDB
+ * Copyright 2018 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #include "api/config.hh"
 #include "api/api-doc/config.json.hh"
 #include "db/config.hh"
+#include "database.hh"
 #include <sstream>
 #include <boost/algorithm/string/replace.hpp>

@@ -75,11 +89,11 @@ future<> get_config_swagger_entry(std::string_view name, const std::string& desc

 namespace cs = httpd::config_json;

-void set_config(std::shared_ptr < api_registry_builder20 > rb, http_context& ctx, routes& r, const db::config& cfg) {
-    rb->register_function(r, [&cfg] (output_stream<char>& os) {
-        return do_with(true, [&os, &cfg] (bool& first) {
+void set_config(std::shared_ptr < api_registry_builder20 > rb, http_context& ctx, routes& r) {
+    rb->register_function(r, [&ctx] (output_stream<char>& os) {
+        return do_with(true, [&os, &ctx] (bool& first) {
            auto f = make_ready_future();
-            for (auto&& cfg_ref : cfg.values()) {
+            for (auto&& cfg_ref : ctx.db.local().get_config().values()) {
                auto&& cfg = cfg_ref.get();
                f = f.then([&os, &first, &cfg] {
                    return get_config_swagger_entry(cfg.name(), std::string(cfg.desc()), cfg.type_name(), first, os);
@@ -89,9 +103,9 @@ void set_config(std::shared_ptr < api_registry_builder20 > rb, http_context& ctx
        });
    });

-    cs::find_config_id.set(r, [&cfg] (const_req r) {
+    cs::find_config_id.set(r, [&ctx] (const_req r) {
        auto id = r.param["id"];
-        for (auto&& cfg_ref : cfg.values()) {
+        for (auto&& cfg_ref : ctx.db.local().get_config().values()) {
            auto&& cfg = cfg_ref.get();
            if (id == cfg.name()) {
                return cfg.value_as_json();
--- a/api/config.hh
+++ b/api/config.hh
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2018-present ScyllaDB
+ * Copyright (C) 2018 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once
@@ -13,5 +26,5 @@

 namespace api {

-void set_config(std::shared_ptr<api_registry_builder20> rb, http_context& ctx, routes& r, const db::config& cfg);
+void set_config(std::shared_ptr<api_registry_builder20> rb, http_context& ctx, routes& r);
 }
--- a/api/endpoint_snitch.cc
+++ b/api/endpoint_snitch.cc
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #include "locator/snitch_base.hh"
--- a/api/endpoint_snitch.hh
+++ b/api/endpoint_snitch.hh
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once
--- a/api/error_injection.cc
+++ b/api/error_injection.cc
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2020-present ScyllaDB
+ * Copyright (C) 2020 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #include "api/api-doc/error_injection.json.hh"
--- a/api/error_injection.hh
+++ b/api/error_injection.hh
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2019-present ScyllaDB
+ * Copyright (C) 2019 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once
--- a/api/failure_detector.cc
+++ b/api/failure_detector.cc
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #include "failure_detector.hh"
@@ -15,10 +28,10 @@ namespace api {

 namespace fd = httpd::failure_detector_json;

-void set_failure_detector(http_context& ctx, routes& r, gms::gossiper& g) {
-    fd::get_all_endpoint_states.set(r, [&g](std::unique_ptr<request> req) {
+void set_failure_detector(http_context& ctx, routes& r) {
+    fd::get_all_endpoint_states.set(r, [](std::unique_ptr<request> req) {
        std::vector<fd::endpoint_state> res;
-        for (auto i : g.endpoint_state_map) {
+        for (auto i : gms::get_local_gossiper().endpoint_state_map) {
            fd::endpoint_state val;
            val.addrs = boost::lexical_cast<std::string>(i.first);
            val.is_alive = i.second.is_alive();
@@ -39,14 +52,14 @@ void set_failure_detector(http_context& ctx, routes& r, gms::gossiper& g) {
        return make_ready_future<json::json_return_type>(res);
    });

-    fd::get_up_endpoint_count.set(r, [&g](std::unique_ptr<request> req) {
-        return gms::get_up_endpoint_count(g).then([](int res) {
+    fd::get_up_endpoint_count.set(r, [](std::unique_ptr<request> req) {
+        return gms::get_up_endpoint_count().then([](int res) {
            return make_ready_future<json::json_return_type>(res);
        });
    });

-    fd::get_down_endpoint_count.set(r, [&g](std::unique_ptr<request> req) {
-        return gms::get_down_endpoint_count(g).then([](int res) {
+    fd::get_down_endpoint_count.set(r, [](std::unique_ptr<request> req) {
+        return gms::get_down_endpoint_count().then([](int res) {
            return make_ready_future<json::json_return_type>(res);
        });
    });
@@ -57,8 +70,8 @@ void set_failure_detector(http_context& ctx, routes& r, gms::gossiper& g) {
        });
    });

-    fd::get_simple_states.set(r, [&g] (std::unique_ptr<request> req) {
-        return gms::get_simple_states(g).then([](const std::map<sstring, sstring>& map) {
+    fd::get_simple_states.set(r, [] (std::unique_ptr<request> req) {
+        return gms::get_simple_states().then([](const std::map<sstring, sstring>& map) {
            return make_ready_future<json::json_return_type>(map_to_key_value<fd::mapper>(map));
        });
    });
@@ -70,8 +83,8 @@ void set_failure_detector(http_context& ctx, routes& r, gms::gossiper& g) {
        });
    });

-    fd::get_endpoint_state.set(r, [&g] (std::unique_ptr<request> req) {
-        return get_endpoint_state(g, req->param["addr"]).then([](const sstring& state) {
+    fd::get_endpoint_state.set(r, [](std::unique_ptr<request> req) {
+        return gms::get_endpoint_state(req->param["addr"]).then([](const sstring& state) {
            return make_ready_future<json::json_return_type>(state);
        });
    });
--- a/api/failure_detector.hh
+++ b/api/failure_detector.hh
@@ -1,23 +1,30 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once

 #include "api.hh"

-namespace gms {
-
-class gossiper;
-
-}
-
 namespace api {

-void set_failure_detector(http_context& ctx, routes& r, gms::gossiper& g);
+void set_failure_detector(http_context& ctx, routes& r);

 }
--- a/api/gossiper.cc
+++ b/api/gossiper.cc
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #include "gossiper.hh"
@@ -13,50 +26,43 @@
 namespace api {
 using namespace json;

-void set_gossiper(http_context& ctx, routes& r, gms::gossiper& g) {
-    httpd::gossiper_json::get_down_endpoint.set(r, [&g] (const_req req) {
-        auto res = g.get_unreachable_members();
+void set_gossiper(http_context& ctx, routes& r) {
+    httpd::gossiper_json::get_down_endpoint.set(r, [] (const_req req) {
+        auto res = gms::get_local_gossiper().get_unreachable_members();
        return container_to_vec(res);
    });

-    httpd::gossiper_json::get_live_endpoint.set(r, [&g] (const_req req) {
-        auto res = g.get_live_members();
+    httpd::gossiper_json::get_live_endpoint.set(r, [] (const_req req) {
+        auto res = gms::get_local_gossiper().get_live_members();
        return container_to_vec(res);
    });

-    httpd::gossiper_json::get_endpoint_downtime.set(r, [&g] (const_req req) {
+    httpd::gossiper_json::get_endpoint_downtime.set(r, [] (const_req req) {
        gms::inet_address ep(req.param["addr"]);
-        return g.get_endpoint_downtime(ep);
+        return gms::get_local_gossiper().get_endpoint_downtime(ep);
    });

-    httpd::gossiper_json::get_current_generation_number.set(r, [&g] (std::unique_ptr<request> req) {
+    httpd::gossiper_json::get_current_generation_number.set(r, [] (std::unique_ptr<request> req) {
        gms::inet_address ep(req->param["addr"]);
-        return g.get_current_generation_number(ep).then([] (int res) {
+        return gms::get_local_gossiper().get_current_generation_number(ep).then([] (int res) {
            return make_ready_future<json::json_return_type>(res);
        });
    });

-    httpd::gossiper_json::get_current_heart_beat_version.set(r, [&g] (std::unique_ptr<request> req) {
+    httpd::gossiper_json::get_current_heart_beat_version.set(r, [] (std::unique_ptr<request> req) {
        gms::inet_address ep(req->param["addr"]);
-        return g.get_current_heart_beat_version(ep).then([] (int res) {
+        return gms::get_local_gossiper().get_current_heart_beat_version(ep).then([] (int res) {
            return make_ready_future<json::json_return_type>(res);
        });
    });

-    httpd::gossiper_json::assassinate_endpoint.set(r, [&g](std::unique_ptr<request> req) {
+    httpd::gossiper_json::assassinate_endpoint.set(r, [](std::unique_ptr<request> req) {
        if (req->get_query_param("unsafe") != "True") {
-            return g.assassinate_endpoint(req->param["addr"]).then([] {
+            return gms::get_local_gossiper().assassinate_endpoint(req->param["addr"]).then([] {
                return make_ready_future<json::json_return_type>(json_void());
            });
        }
-        return g.unsafe_assassinate_endpoint(req->param["addr"]).then([] {
-            return make_ready_future<json::json_return_type>(json_void());
-        });
-    });
-
-    httpd::gossiper_json::force_remove_endpoint.set(r, [&g](std::unique_ptr<request> req) {
-        gms::inet_address ep(req->param["addr"]);
-        return g.force_remove_endpoint(ep).then([] {
+        return gms::get_local_gossiper().unsafe_assassinate_endpoint(req->param["addr"]).then([] {
            return make_ready_future<json::json_return_type>(json_void());
        });
    });
--- a/api/gossiper.hh
+++ b/api/gossiper.hh
@@ -1,23 +1,30 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once

 #include "api.hh"

-namespace gms {
-
-class gossiper;
-
-}
-
 namespace api {

-void set_gossiper(http_context& ctx, routes& r, gms::gossiper& g);
+void set_gossiper(http_context& ctx, routes& r);

 }
--- a/api/hinted_handoff.cc
+++ b/api/hinted_handoff.cc
@@ -1,98 +1,33 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

-#include <algorithm>
-#include <vector>
-
 #include "hinted_handoff.hh"
 #include "api/api-doc/hinted_handoff.json.hh"

-#include "gms/inet_address.hh"
-#include "gms/gossiper.hh"
-#include "service/storage_proxy.hh"
-
 namespace api {

 using namespace json;
 namespace hh = httpd::hinted_handoff_json;

-void set_hinted_handoff(http_context& ctx, routes& r, gms::gossiper& g) {
-    hh::create_hints_sync_point.set(r, [&ctx, &g] (std::unique_ptr<request> req) -> future<json::json_return_type> {
-        auto parse_hosts_list = [&g] (sstring arg) {
-            std::vector<sstring> hosts_str = split(arg, ",");
-            std::vector<gms::inet_address> hosts;
-            hosts.reserve(hosts_str.size());
-
-            if (hosts_str.empty()) {
-                // No target_hosts specified means that we should wait for hints for all nodes to be sent
-                const auto members_set = g.get_live_members();
-                std::copy(members_set.begin(), members_set.end(), std::back_inserter(hosts));
-            } else {
-                for (const auto& host_str : hosts_str) {
-                    try {
-                        gms::inet_address host;
-                        host = gms::inet_address(host_str);
-                        hosts.push_back(host);
-                    } catch (std::exception& e) {
-                        throw httpd::bad_param_exception(format("Failed to parse host address {}: {}", host_str, e.what()));
-                    }
-                }
-            }
-            return hosts;
-        };
-
-        std::vector<gms::inet_address> target_hosts = parse_hosts_list(req->get_query_param("target_hosts"));
-        return ctx.sp.local().create_hint_sync_point(std::move(target_hosts)).then([] (db::hints::sync_point sync_point) {
-            return json::json_return_type(sync_point.encode());
-        });
-    });
-
-    hh::get_hints_sync_point.set(r, [&ctx] (std::unique_ptr<request> req) -> future<json::json_return_type> {
-        db::hints::sync_point sync_point;
-        const sstring encoded = req->get_query_param("id");
-        try {
-            sync_point = db::hints::sync_point::decode(encoded);
-        } catch (std::exception& e) {
-            throw httpd::bad_param_exception(format("Failed to parse the sync point description {}: {}", encoded, e.what()));
-        }
-
-        lowres_clock::time_point deadline;
-        const sstring timeout_str = req->get_query_param("timeout");
-        try {
-            deadline = [&] {
-                if (timeout_str.empty()) {
-                    // Empty string - don't wait at all, just check the status
-                    return lowres_clock::time_point::min();
-                } else {
-                    const auto timeout = std::stoll(timeout_str);
-                    if (timeout >= 0) {
-                        // Wait until the point is reached, or until `timeout` seconds elapse
-                        return lowres_clock::now() + std::chrono::seconds(timeout);
-                    } else {
-                        // Negative value indicates infinite timeout
-                        return lowres_clock::time_point::max();
-                    }
-                }
-            } ();
-        } catch (std::exception& e) {
-            throw httpd::bad_param_exception(format("Failed to parse the timeout parameter {}: {}", timeout_str, e.what()));
-        }
-
-        using return_type = hh::ns_get_hints_sync_point::get_hints_sync_point_return_type;
-        using return_type_wrapper = hh::ns_get_hints_sync_point::return_type_wrapper;
-
-        return ctx.sp.local().wait_for_hint_sync_point(std::move(sync_point), deadline).then([] {
-            return json::json_return_type(return_type_wrapper(return_type::DONE));
-        }).handle_exception_type([] (const timed_out_error&) {
-            return json::json_return_type(return_type_wrapper(return_type::IN_PROGRESS));
-        });
-    });
-
+void set_hinted_handoff(http_context& ctx, routes& r) {
    hh::list_endpoints_pending_hints.set(r, [] (std::unique_ptr<request> req) {
        //TBD
        unimplemented();
@@ -136,16 +71,5 @@ void set_hinted_handoff(http_context& ctx, routes& r, gms::gossiper& g) {
    });
 }

-void unset_hinted_handoff(http_context& ctx, routes& r) {
-    hh::create_hints_sync_point.unset(r);
-    hh::get_hints_sync_point.unset(r);
-
-    hh::list_endpoints_pending_hints.unset(r);
-    hh::truncate_all_hints.unset(r);
-    hh::schedule_hint_delivery.unset(r);
-    hh::pause_hints_delivery.unset(r);
-    hh::get_create_hint_count.unset(r);
-    hh::get_not_stored_hints_count.unset(r);
 }

-}
--- a/api/hinted_handoff.hh
+++ b/api/hinted_handoff.hh
@@ -1,24 +1,30 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once

 #include "api.hh"

-namespace gms {
-
-class gossiper;
-
-}
-
 namespace api {

-void set_hinted_handoff(http_context& ctx, routes& r, gms::gossiper& g);
-void unset_hinted_handoff(http_context& ctx, routes& r);
+void set_hinted_handoff(http_context& ctx, routes& r);

 }
--- a/api/lsa.cc
+++ b/api/lsa.cc
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #include "api/api-doc/lsa.json.hh"
@@ -13,7 +26,6 @@
 #include <seastar/http/exception.hh>
 #include "utils/logalloc.hh"
 #include "log.hh"
-#include "replica/database.hh"

 namespace api {

@@ -22,7 +34,7 @@ static logging::logger alogger("lsa-api");
 void set_lsa(http_context& ctx, routes& r) {
    httpd::lsa_json::lsa_compact.set(r, [&ctx](std::unique_ptr<request> req) {
        alogger.info("Triggering compaction");
-        return ctx.db.invoke_on_all([] (replica::database&) {
+        return ctx.db.invoke_on_all([] (database&) {
            logalloc::shard_tracker().reclaim(std::numeric_limits<size_t>::max());
        }).then([] {
            return json::json_return_type(json::json_void());
--- a/api/lsa.hh
+++ b/api/lsa.hh
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once
--- a/api/messaging_service.cc
+++ b/api/messaging_service.cc
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #include "messaging_service.hh"
@@ -83,10 +96,6 @@ void set_messaging_service(http_context& ctx, routes& r, sharded<netw::messaging
        return c.get_stats().sent_messages;
    }));

-    get_replied_messages.set(r, get_client_getter(ms, [](const shard_info& c) {
-        return c.get_stats().replied;
-    }));
-
    get_dropped_messages.set(r, get_client_getter(ms, [](const shard_info& c) {
        // We don't have the same drop message mechanism
        // as origin has.
@@ -146,7 +155,6 @@ void set_messaging_service(http_context& ctx, routes& r, sharded<netw::messaging
 void unset_messaging_service(http_context& ctx, routes& r) {
    get_timeout_messages.unset(r);
    get_sent_messages.unset(r);
-    get_replied_messages.unset(r);
    get_dropped_messages.unset(r);
    get_exception_messages.unset(r);
    get_pending_messages.unset(r);
--- a/api/messaging_service.hh
+++ b/api/messaging_service.hh
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once
--- a/api/storage_proxy.cc
+++ b/api/storage_proxy.cc
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #include "storage_proxy.hh"
@@ -13,7 +26,7 @@
 #include "service/storage_service.hh"
 #include "db/config.hh"
 #include "utils/histogram.hh"
-#include "replica/database.hh"
+#include "database.hh"
 #include "seastar/core/scheduling_specific.hh"

 namespace api {
@@ -180,7 +193,7 @@ sum_timer_stats_storage_proxy(distributed<proxy>& d,
    });
 }

-void set_storage_proxy(http_context& ctx, routes& r, sharded<service::storage_service>& ss) {
+void set_storage_proxy(http_context& ctx, routes& r) {
    sp::get_total_hints.set(r, [](std::unique_ptr<request> req)  {
        //TBD
        unimplemented();
@@ -350,8 +363,8 @@ void set_storage_proxy(http_context& ctx, routes& r, sharded<service::storage_se
        return sum_stats_storage_proxy(ctx.sp, &service::storage_proxy_stats::stats::read_repair_repaired_background);
    });

-    sp::get_schema_versions.set(r, [&ss](std::unique_ptr<request> req)  {
-        return ss.local().describe_schema_versions().then([] (auto result) {
+    sp::get_schema_versions.set(r, [](std::unique_ptr<request> req)  {
+        return service::get_local_storage_service().describe_schema_versions().then([] (auto result) {
            std::vector<sp::mapper_list> res;
            for (auto e : result) {
                sp::mapper_list entry;
--- a/api/storage_proxy.hh
+++ b/api/storage_proxy.hh
@@ -1,20 +1,30 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once

-#include <seastar/core/sharded.hh>
 #include "api.hh"

-namespace service { class storage_service; }
-
 namespace api {

-void set_storage_proxy(http_context& ctx, routes& r, sharded<service::storage_service>& ss);
+void set_storage_proxy(http_context& ctx, routes& r);

 }
--- a/api/storage_service.cc
+++ b/api/storage_service.cc
--- a/api/storage_service.hh
+++ b/api/storage_service.hh
@@ -1,53 +1,38 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once

 #include <seastar/core/sharded.hh>
 #include "api.hh"
-#include "db/data_listeners.hh"

 namespace cql_transport { class controller; }
 class thrift_controller;
-namespace db {
-class snapshot_ctl;
-namespace view {
-class view_builder;
-}
-}
+namespace db { class snapshot_ctl; }
 namespace netw { class messaging_service; }
-class repair_service;
-namespace cdc { class generation_service; }
-class sstables_loader;
-
-namespace gms {
-
-class gossiper;
-
-}

 namespace api {

-// verify that the keyspace parameter is found, otherwise a bad_param_exception exception is thrown
-// containing the description of the respective keyspace error.
-sstring validate_keyspace(http_context& ctx, const parameters& param);
-
-// splits a request parameter assumed to hold a comma-separated list of table names
-// verify that the tables are found, otherwise a bad_param_exception exception is thrown
-// containing the description of the respective no_such_column_family error.
-std::vector<sstring> parse_tables(const sstring& ks_name, http_context& ctx, const std::unordered_map<sstring, sstring>& query_params, sstring param_name);
-
-void set_storage_service(http_context& ctx, routes& r, sharded<service::storage_service>& ss, gms::gossiper& g, sharded<cdc::generation_service>& cdc_gs);
-void set_sstables_loader(http_context& ctx, routes& r, sharded<sstables_loader>& sst_loader);
-void unset_sstables_loader(http_context& ctx, routes& r);
-void set_view_builder(http_context& ctx, routes& r, sharded<db::view::view_builder>& vb);
-void unset_view_builder(http_context& ctx, routes& r);
-void set_repair(http_context& ctx, routes& r, sharded<repair_service>& repair);
+void set_storage_service(http_context& ctx, routes& r);
+void set_repair(http_context& ctx, routes& r, sharded<netw::messaging_service>& ms);
 void unset_repair(http_context& ctx, routes& r);
 void set_transport_controller(http_context& ctx, routes& r, cql_transport::controller& ctl);
 void unset_transport_controller(http_context& ctx, routes& r);
@@ -55,6 +40,5 @@ void set_rpc_controller(http_context& ctx, routes& r, thrift_controller& ctl);
 void unset_rpc_controller(http_context& ctx, routes& r);
 void set_snapshot(http_context& ctx, routes& r, sharded<db::snapshot_ctl>& snap_ctl);
 void unset_snapshot(http_context& ctx, routes& r);
-seastar::future<json::json_return_type> run_toppartitions_query(db::toppartitions_query& q, http_context &ctx, bool legacy_request = false);

 }
--- a/api/stream_manager.cc
+++ b/api/stream_manager.cc
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #include "stream_manager.hh"
@@ -74,13 +87,13 @@ static hs::stream_state get_state(
    return state;
 }

-void set_stream_manager(http_context& ctx, routes& r, sharded<streaming::stream_manager>& sm) {
+void set_stream_manager(http_context& ctx, routes& r) {
    hs::get_current_streams.set(r,
-            [&sm] (std::unique_ptr<request> req) {
-                return sm.invoke_on_all([] (auto& sm) {
+            [] (std::unique_ptr<request> req) {
+                return streaming::get_stream_manager().invoke_on_all([] (auto& sm) {
                    return sm.update_all_progress_info();
-                }).then([&sm] {
-                    return sm.map_reduce0([](streaming::stream_manager& stream) {
+                }).then([] {
+                    return streaming::get_stream_manager().map_reduce0([](streaming::stream_manager& stream) {
                        std::vector<hs::stream_state> res;
                        for (auto i : stream.get_initiated_streams()) {
                            res.push_back(get_state(*i.second.get()));
@@ -96,17 +109,17 @@ void set_stream_manager(http_context& ctx, routes& r, sharded<streaming::stream_
                });
            });

-    hs::get_all_active_streams_outbound.set(r, [&sm](std::unique_ptr<request> req) {
-        return sm.map_reduce0([](streaming::stream_manager& stream) {
+    hs::get_all_active_streams_outbound.set(r, [](std::unique_ptr<request> req) {
+        return streaming::get_stream_manager().map_reduce0([](streaming::stream_manager& stream) {
            return stream.get_initiated_streams().size();
        }, 0, std::plus<int64_t>()).then([](int64_t res) {
            return make_ready_future<json::json_return_type>(res);
        });
    });

-    hs::get_total_incoming_bytes.set(r, [&sm](std::unique_ptr<request> req) {
+    hs::get_total_incoming_bytes.set(r, [](std::unique_ptr<request> req) {
        gms::inet_address peer(req->param["peer"]);
-        return sm.map_reduce0([peer](streaming::stream_manager& sm) {
+        return streaming::get_stream_manager().map_reduce0([peer](streaming::stream_manager& sm) {
            return sm.get_progress_on_all_shards(peer).then([] (auto sbytes) {
                return sbytes.bytes_received;
            });
@@ -115,8 +128,8 @@ void set_stream_manager(http_context& ctx, routes& r, sharded<streaming::stream_
        });
    });

-    hs::get_all_total_incoming_bytes.set(r, [&sm](std::unique_ptr<request> req) {
-        return sm.map_reduce0([](streaming::stream_manager& sm) {
+    hs::get_all_total_incoming_bytes.set(r, [](std::unique_ptr<request> req) {
+        return streaming::get_stream_manager().map_reduce0([](streaming::stream_manager& sm) {
            return sm.get_progress_on_all_shards().then([] (auto sbytes) {
                return sbytes.bytes_received;
            });
@@ -125,9 +138,9 @@ void set_stream_manager(http_context& ctx, routes& r, sharded<streaming::stream_
        });
    });

-    hs::get_total_outgoing_bytes.set(r, [&sm](std::unique_ptr<request> req) {
+    hs::get_total_outgoing_bytes.set(r, [](std::unique_ptr<request> req) {
        gms::inet_address peer(req->param["peer"]);
-        return sm.map_reduce0([peer] (streaming::stream_manager& sm) {
+        return streaming::get_stream_manager().map_reduce0([peer] (streaming::stream_manager& sm) {
            return sm.get_progress_on_all_shards(peer).then([] (auto sbytes) {
                return sbytes.bytes_sent;
            });
@@ -136,8 +149,8 @@ void set_stream_manager(http_context& ctx, routes& r, sharded<streaming::stream_
        });
    });

-    hs::get_all_total_outgoing_bytes.set(r, [&sm](std::unique_ptr<request> req) {
-        return sm.map_reduce0([](streaming::stream_manager& sm) {
+    hs::get_all_total_outgoing_bytes.set(r, [](std::unique_ptr<request> req) {
+        return streaming::get_stream_manager().map_reduce0([](streaming::stream_manager& sm) {
            return sm.get_progress_on_all_shards().then([] (auto sbytes) {
                return sbytes.bytes_sent;
            });
@@ -147,13 +160,4 @@ void set_stream_manager(http_context& ctx, routes& r, sharded<streaming::stream_
    });
 }

-void unset_stream_manager(http_context& ctx, routes& r) {
-    hs::get_current_streams.unset(r);
-    hs::get_all_active_streams_outbound.unset(r);
-    hs::get_total_incoming_bytes.unset(r);
-    hs::get_all_total_incoming_bytes.unset(r);
-    hs::get_total_outgoing_bytes.unset(r);
-    hs::get_all_total_outgoing_bytes.unset(r);
-}
-
 }
--- a/api/stream_manager.hh
+++ b/api/stream_manager.hh
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once
@@ -12,7 +25,6 @@

 namespace api {

-void set_stream_manager(http_context& ctx, routes& r, sharded<streaming::stream_manager>& sm);
-void unset_stream_manager(http_context& ctx, routes& r);
+void set_stream_manager(http_context& ctx, routes& r);

 }
--- a/api/system.cc
+++ b/api/system.cc
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #include "api/api-doc/system.json.hh"
@@ -12,9 +25,6 @@
 #include <seastar/core/reactor.hh>
 #include <seastar/http/exception.hh>
 #include "log.hh"
-#include "replica/database.hh"
-
-extern logging::logger apilog;

 namespace api {

@@ -60,16 +70,6 @@ void set_system(http_context& ctx, routes& r) {
        }
        return json::json_void();
    });
-
-    hs::drop_sstable_caches.set(r, [&ctx](std::unique_ptr<request> req) {
-        apilog.info("Dropping sstable caches");
-        return ctx.db.invoke_on_all([] (replica::database& db) {
-            return db.drop_caches();
-        }).then([] {
-            apilog.info("Caches dropped");
-            return json::json_return_type(json::json_void());
-        });
-    });
 }

 }
--- a/api/system.hh
+++ b/api/system.hh
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once
--- a/atomic_cell.cc
+++ b/atomic_cell.cc
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2018-present ScyllaDB
+ * Copyright (C) 2018 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #include "atomic_cell.hh"
@@ -11,125 +24,142 @@
 #include "counters.hh"
 #include "types.hh"

+/// LSA mirator for cells with irrelevant type
+///
+///
+const data::type_imr_descriptor& no_type_imr_descriptor() {
+    static thread_local data::type_imr_descriptor state(data::type_info::make_variable_size());
+    return state;
+}
+
 atomic_cell atomic_cell::make_dead(api::timestamp_type timestamp, gc_clock::time_point deletion_time) {
-    return atomic_cell_type::make_dead(timestamp, deletion_time);
+    auto& imr_data = no_type_imr_descriptor();
+    return atomic_cell(
+            imr_data.type_info(),
+            imr_object_type::make(data::cell::make_dead(timestamp, deletion_time), &imr_data.lsa_migrator())
+    );
 }

 atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, bytes_view value, atomic_cell::collection_member cm) {
-    return atomic_cell_type::make_live(timestamp, single_fragment_range(value));
-}
-
-atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, managed_bytes_view value, atomic_cell::collection_member cm) {
-    return atomic_cell_type::make_live(timestamp, fragment_range(value));
+    auto& imr_data = type.imr_state();
+    return atomic_cell(
+        imr_data.type_info(),
+        imr_object_type::make(data::cell::make_live(imr_data.type_info(), timestamp, value, bool(cm)), &imr_data.lsa_migrator())
+    );
 }

 atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, ser::buffer_view<bytes_ostream::fragment_iterator> value, atomic_cell::collection_member cm) {
-    return atomic_cell_type::make_live(timestamp, value);
+    auto& imr_data = type.imr_state();
+    return atomic_cell(
+        imr_data.type_info(),
+        imr_object_type::make(data::cell::make_live(imr_data.type_info(), timestamp, value, bool(cm)), &imr_data.lsa_migrator())
+    );
 }

 atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, const fragmented_temporary_buffer::view& value, collection_member cm)
 {
-    return atomic_cell_type::make_live(timestamp, value);
+    auto& imr_data = type.imr_state();
+    return atomic_cell(
+        imr_data.type_info(),
+        imr_object_type::make(data::cell::make_live(imr_data.type_info(), timestamp, value, bool(cm)), &imr_data.lsa_migrator())
+    );
 }

 atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, bytes_view value,
                             gc_clock::time_point expiry, gc_clock::duration ttl, atomic_cell::collection_member cm) {
-    return atomic_cell_type::make_live(timestamp, single_fragment_range(value), expiry, ttl);
-}
-
-atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, managed_bytes_view value,
-                             gc_clock::time_point expiry, gc_clock::duration ttl, atomic_cell::collection_member cm) {
-    return atomic_cell_type::make_live(timestamp, fragment_range(value), expiry, ttl);
+    auto& imr_data = type.imr_state();
+    return atomic_cell(
+        imr_data.type_info(),
+        imr_object_type::make(data::cell::make_live(imr_data.type_info(), timestamp, value, expiry, ttl, bool(cm)), &imr_data.lsa_migrator())
+    );
 }

 atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, ser::buffer_view<bytes_ostream::fragment_iterator> value,
                             gc_clock::time_point expiry, gc_clock::duration ttl, atomic_cell::collection_member cm) {
-    return atomic_cell_type::make_live(timestamp, value, expiry, ttl);
+    auto& imr_data = type.imr_state();
+    return atomic_cell(
+        imr_data.type_info(),
+        imr_object_type::make(data::cell::make_live(imr_data.type_info(), timestamp, value, expiry, ttl, bool(cm)), &imr_data.lsa_migrator())
+    );
 }

 atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, const fragmented_temporary_buffer::view& value,
                                   gc_clock::time_point expiry, gc_clock::duration ttl, collection_member cm)
 {
-    return atomic_cell_type::make_live(timestamp, value, expiry, ttl);
+    auto& imr_data = type.imr_state();
+    return atomic_cell(
+        imr_data.type_info(),
+        imr_object_type::make(data::cell::make_live(imr_data.type_info(), timestamp, value, expiry, ttl, bool(cm)), &imr_data.lsa_migrator())
+    );
 }

 atomic_cell atomic_cell::make_live_counter_update(api::timestamp_type timestamp, int64_t value) {
-    return atomic_cell_type::make_live_counter_update(timestamp, value);
+    auto& imr_data = no_type_imr_descriptor();
+    return atomic_cell(
+        imr_data.type_info(),
+        imr_object_type::make(data::cell::make_live_counter_update(timestamp, value), &imr_data.lsa_migrator())
+    );
 }

 atomic_cell atomic_cell::make_live_uninitialized(const abstract_type& type, api::timestamp_type timestamp, size_t size) {
-    return atomic_cell_type::make_live_uninitialized(timestamp, size);
+    auto& imr_data = no_type_imr_descriptor();
+    return atomic_cell(
+        imr_data.type_info(),
+        imr_object_type::make(data::cell::make_live_uninitialized(imr_data.type_info(), timestamp, size), &imr_data.lsa_migrator())
+    );
+}
+
+static imr::utils::object<data::cell::structure> copy_cell(const data::type_imr_descriptor& imr_data, const uint8_t* ptr)
+{
+    using imr_object_type = imr::utils::object<data::cell::structure>;
+
+    // If the cell doesn't own any memory it is trivial and can be copied with
+    // memcpy.
+    auto f = data::cell::structure::get_member<data::cell::tags::flags>(ptr);
+    if (!f.template get<data::cell::tags::external_data>()) {
+        data::cell::context ctx(f, imr_data.type_info());
+        // XXX: We may be better off storing the total cell size in memory. Measure!
+        auto size = data::cell::structure::serialized_object_size(ptr, ctx);
+        return imr_object_type::make_raw(size, [&] (uint8_t* dst) noexcept {
+            std::copy_n(ptr, size, dst);
+        }, &imr_data.lsa_migrator());
+    }
+
+    return imr_object_type::make(data::cell::copy_fn(imr_data.type_info(), ptr), &imr_data.lsa_migrator());
 }

 atomic_cell::atomic_cell(const abstract_type& type, atomic_cell_view other)
-    : _data(other._view) {
-    set_view(_data);
-}
-
-// Based on:
-//  - org.apache.cassandra.db.AbstractCell#reconcile()
-//  - org.apache.cassandra.db.BufferExpiringCell#reconcile()
-//  - org.apache.cassandra.db.BufferDeletedCell#reconcile()
-std::strong_ordering
-compare_atomic_cell_for_merge(atomic_cell_view left, atomic_cell_view right) {
-    if (left.timestamp() != right.timestamp()) {
-        return left.timestamp() <=> right.timestamp();
-    }
-    if (left.is_live() != right.is_live()) {
-        return left.is_live() ? std::strong_ordering::less : std::strong_ordering::greater;
-    }
-    if (left.is_live()) {
-        auto c = compare_unsigned(left.value(), right.value()) <=> 0;
-        if (c != 0) {
-            return c;
-        }
-        if (left.is_live_and_has_ttl() != right.is_live_and_has_ttl()) {
-            // prefer expiring cells.
-            return left.is_live_and_has_ttl() ? std::strong_ordering::greater : std::strong_ordering::less;
-        }
-        if (left.is_live_and_has_ttl()) {
-            if (left.expiry() != right.expiry()) {
-                return left.expiry() <=> right.expiry();
-            } else {
-                // prefer the cell that was written later,
-                // so it survives longer after it expires, until purged.
-                return right.ttl() <=> left.ttl();
-            }
-        }
-    } else {
-        // Both are deleted
-
-        // Origin compares big-endian serialized deletion time. That's because it
-        // delegates to AbstractCell.reconcile() which compares values after
-        // comparing timestamps, which in case of deleted cells will hold
-        // serialized expiry.
-        return (uint64_t) left.deletion_time().time_since_epoch().count()
-                <=> (uint64_t) right.deletion_time().time_since_epoch().count();
-    }
-    return std::strong_ordering::equal;
-}
+    : atomic_cell(type.imr_state().type_info(),
+                  copy_cell(type.imr_state(), other._view.raw_pointer()))
+{ }

 atomic_cell_or_collection atomic_cell_or_collection::copy(const abstract_type& type) const {
-    if (_data.empty()) {
+    if (!_data.get()) {
        return atomic_cell_or_collection();
    }
-    return atomic_cell_or_collection(managed_bytes(_data));
+    auto& imr_data = type.imr_state();
+    return atomic_cell_or_collection(
+        copy_cell(imr_data, _data.get())
+    );
 }

 atomic_cell_or_collection::atomic_cell_or_collection(const abstract_type& type, atomic_cell_view acv)
-    : _data(acv._view)
+    : _data(copy_cell(type.imr_state(), acv._view.raw_pointer()))
 {
 }

 bool atomic_cell_or_collection::equals(const abstract_type& type, const atomic_cell_or_collection& other) const
 {
-    if (_data.empty() || other._data.empty()) {
-        return _data.empty() && other._data.empty();
+    auto ptr_a = _data.get();
+    auto ptr_b = other._data.get();
+
+    if (!ptr_a || !ptr_b) {
+        return !ptr_a && !ptr_b;
    }

    if (type.is_atomic()) {
-        auto a = atomic_cell_view::from_bytes(type, _data);
-        auto b = atomic_cell_view::from_bytes(type, other._data);
+        auto a = atomic_cell_view::from_bytes(type.imr_state().type_info(), _data);
+        auto b = atomic_cell_view::from_bytes(type.imr_state().type_info(), other._data);
        if (a.timestamp() != b.timestamp()) {
            return false;
        }
@@ -161,24 +191,44 @@ bool atomic_cell_or_collection::equals(const abstract_type& type, const atomic_c

 size_t atomic_cell_or_collection::external_memory_usage(const abstract_type& t) const
 {
-    return _data.external_memory_usage();
+    if (!_data.get()) {
+        return 0;
+    }
+    auto ctx = data::cell::context(_data.get(), t.imr_state().type_info());
+
+    auto view = data::cell::structure::make_view(_data.get(), ctx);
+    auto flags = view.get<data::cell::tags::flags>();
+
+    size_t external_value_size = 0;
+    if (flags.get<data::cell::tags::external_data>()) {
+        if (flags.get<data::cell::tags::collection>()) {
+            external_value_size = as_collection_mutation().data.size_bytes();
+        } else {
+            auto cell_view = data::cell::atomic_cell_view(t.imr_state().type_info(), view);
+            external_value_size = cell_view.value_size();
+        }
+        // Add overhead of chunk headers. The last one is a special case.
+        external_value_size += (external_value_size - 1) / data::cell::effective_external_chunk_length * data::cell::external_chunk_overhead;
+        external_value_size += data::cell::external_last_chunk_overhead;
+    }
+    return data::cell::structure::serialized_object_size(_data.get(), ctx)
+        + imr_object_type::size_overhead + external_value_size;
 }

 std::ostream&
 operator<<(std::ostream& os, const atomic_cell_view& acv) {
    if (acv.is_live()) {
-        fmt::print(os, "atomic_cell{{{},ts={:d},expiry={:d},ttl={:d}}}",
+        return fmt_print(os, "atomic_cell{{{},ts={:d},expiry={:d},ttl={:d}}}",
            acv.is_counter_update()
                    ? "counter_update_value=" + to_sstring(acv.counter_update_value())
-                    : to_hex(to_bytes(acv.value())),
+                    : to_hex(acv.value().linearize()),
            acv.timestamp(),
            acv.is_live_and_has_ttl() ? acv.expiry().time_since_epoch().count() : -1,
            acv.is_live_and_has_ttl() ? acv.ttl().count() : 0);
    } else {
-        fmt::print(os, "atomic_cell{{DEAD,ts={:d},deletion_time={:d}}}",
+        return fmt_print(os, "atomic_cell{{DEAD,ts={:d},deletion_time={:d}}}",
            acv.timestamp(), acv.deletion_time().time_since_epoch().count());
    }
-    return os;
 }

 std::ostream&
@@ -197,22 +247,22 @@ operator<<(std::ostream& os, const atomic_cell_view::printer& acvp) {
                cell_value_string_builder << "counter_update_value=" << acv.counter_update_value();
            } else {
                cell_value_string_builder << "shards: ";
-                auto ccv = counter_cell_view(acv);
-                cell_value_string_builder << ::join(", ", ccv.shards());
+                counter_cell_view::with_linearized(acv, [&cell_value_string_builder] (counter_cell_view& ccv) {
+                    cell_value_string_builder << ::join(", ", ccv.shards());
+                });
            }
        } else {
-            cell_value_string_builder << type.to_string(to_bytes(acv.value()));
+            cell_value_string_builder << type.to_string(acv.value().linearize());
        }
-        fmt::print(os, "atomic_cell{{{},ts={:d},expiry={:d},ttl={:d}}}",
+        return fmt_print(os, "atomic_cell{{{},ts={:d},expiry={:d},ttl={:d}}}",
            cell_value_string_builder.str(),
            acv.timestamp(),
            acv.is_live_and_has_ttl() ? acv.expiry().time_since_epoch().count() : -1,
            acv.is_live_and_has_ttl() ? acv.ttl().count() : 0);
    } else {
-        fmt::print(os, "atomic_cell{{DEAD,ts={:d},deletion_time={:d}}}",
+        return fmt_print(os, "atomic_cell{{DEAD,ts={:d},deletion_time={:d}}}",
            acv.timestamp(), acv.deletion_time().time_since_epoch().count());
    }
-    return os;
 }

 std::ostream&
@@ -221,11 +271,12 @@ operator<<(std::ostream& os, const atomic_cell::printer& acp) {
 }

 std::ostream& operator<<(std::ostream& os, const atomic_cell_or_collection::printer& p) {
-    if (p._cell._data.empty()) {
+    if (!p._cell._data.get()) {
        return os << "{ null atomic_cell_or_collection }";
    }
+    using dc = data::cell;
    os << "{ ";
-    if (p._cdef.type->is_multi_cell()) {
+    if (dc::structure::get_member<dc::tags::flags>(p._cell._data.get()).get<dc::tags::collection>()) {
        os << "collection ";
        auto cmv = p._cell.as_collection_mutation();
        os << collection_mutation_view::printer(*p._cdef.type, cmv);
--- a/atomic_cell.hh
+++ b/atomic_cell.hh
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once
@@ -14,10 +27,11 @@
 #include "gc_clock.hh"
 #include "utils/managed_bytes.hh"
 #include <seastar/net//byteorder.hh>
-#include <seastar/util/bool_class.hh>
 #include <cstdint>
 #include <iosfwd>
-#include <concepts>
+#include "data/cell.hh"
+#include "data/schema_info.hh"
+#include "imr/utils.hh"
 #include "utils/fragmented_temporary_buffer.hh"

 #include "serializer.hh"
@@ -26,191 +40,41 @@ class abstract_type;
 class collection_type_impl;
 class atomic_cell_or_collection;

-using atomic_cell_value = managed_bytes;
-template <mutable_view is_mutable>
-using atomic_cell_value_basic_view = managed_bytes_basic_view<is_mutable>;
-using atomic_cell_value_view = atomic_cell_value_basic_view<mutable_view::no>;
-using atomic_cell_value_mutable_view = atomic_cell_value_basic_view<mutable_view::yes>;
-
-template <typename T>
-requires std::is_trivial_v<T>
-static void set_field(atomic_cell_value_mutable_view& out, unsigned offset, T val) {
-    auto out_view = managed_bytes_mutable_view(out);
-    out_view.remove_prefix(offset);
-    write<T>(out_view, val);
-}
-
-template <typename T>
-requires std::is_trivial_v<T>
-static void set_field(atomic_cell_value& out, unsigned offset, T val) {
-    auto out_view = atomic_cell_value_mutable_view(out);
-    set_field(out_view, offset, val);
-}
-
-template <FragmentRange Buffer>
-static void set_value(managed_bytes& b, unsigned value_offset, const Buffer& value) {
-    auto v = managed_bytes_mutable_view(b).substr(value_offset, value.size_bytes());
-    for (auto frag : value) {
-        write_fragmented(v, single_fragmented_view(frag));
-    }
-}
-
-template <typename T, FragmentedView Input>
-requires std::is_trivial_v<T>
-static T get_field(Input in, unsigned offset = 0) {
-    in.remove_prefix(offset);
-    return read_simple<T>(in);
-}
-
-/*
- * Represents atomic cell layout. Works on serialized form.
- *
- * Layout:
- *
- *  <live>  := <int8_t:flags><int64_t:timestamp>(<int64_t:expiry><int32_t:ttl>)?<value>
- *  <dead>  := <int8_t:    0><int64_t:timestamp><int64_t:deletion_time>
- */
-class atomic_cell_type final {
-private:
-    static constexpr int8_t LIVE_FLAG = 0x01;
-    static constexpr int8_t EXPIRY_FLAG = 0x02; // When present, expiry field is present. Set only for live cells
-    static constexpr int8_t COUNTER_UPDATE_FLAG = 0x08; // Cell is a counter update.
-    static constexpr unsigned flags_size = 1;
-    static constexpr unsigned timestamp_offset = flags_size;
-    static constexpr unsigned timestamp_size = 8;
-    static constexpr unsigned expiry_offset = timestamp_offset + timestamp_size;
-    static constexpr unsigned expiry_size = 8;
-    static constexpr unsigned deletion_time_offset = timestamp_offset + timestamp_size;
-    static constexpr unsigned deletion_time_size = 8;
-    static constexpr unsigned ttl_offset = expiry_offset + expiry_size;
-    static constexpr unsigned ttl_size = 4;
-    friend class counter_cell_builder;
-private:
-    static bool is_counter_update(atomic_cell_value_view cell) {
-        return cell.front() & COUNTER_UPDATE_FLAG;
-    }
-    static bool is_live(atomic_cell_value_view cell) {
-        return cell.front() & LIVE_FLAG;
-    }
-    static bool is_live_and_has_ttl(atomic_cell_value_view cell) {
-        return cell.front() & EXPIRY_FLAG;
-    }
-    static bool is_dead(atomic_cell_value_view cell) {
-        return !is_live(cell);
-    }
-    // Can be called on live and dead cells
-    static api::timestamp_type timestamp(atomic_cell_value_view cell) {
-        return get_field<api::timestamp_type>(cell, timestamp_offset);
-    }
-    static void set_timestamp(atomic_cell_value_mutable_view& cell, api::timestamp_type ts) {
-        set_field(cell, timestamp_offset, ts);
-    }
-    // Can be called on live cells only
-private:
-    template <mutable_view is_mutable>
-    static managed_bytes_basic_view<is_mutable> do_get_value(managed_bytes_basic_view<is_mutable> cell) {
-        auto expiry_field_size = bool(cell.front() & EXPIRY_FLAG) * (expiry_size + ttl_size);
-        auto value_offset = flags_size + timestamp_size + expiry_field_size;
-        cell.remove_prefix(value_offset);
-        return cell;
-    }
-public:
-    static atomic_cell_value_view value(managed_bytes_view cell) {
-        return do_get_value(cell);
-    }
-    static atomic_cell_value_mutable_view value(managed_bytes_mutable_view cell) {
-        return do_get_value(cell);
-    }
-    // Can be called on live counter update cells only
-    static int64_t counter_update_value(atomic_cell_value_view cell) {
-        return get_field<int64_t>(cell, flags_size + timestamp_size);
-    }
-    // Can be called only when is_dead() is true.
-    static gc_clock::time_point deletion_time(atomic_cell_value_view cell) {
-        assert(is_dead(cell));
-        return gc_clock::time_point(gc_clock::duration(get_field<int64_t>(cell, deletion_time_offset)));
-    }
-    // Can be called only when is_live_and_has_ttl() is true.
-    static gc_clock::time_point expiry(atomic_cell_value_view cell) {
-        assert(is_live_and_has_ttl(cell));
-        auto expiry = get_field<int64_t>(cell, expiry_offset);
-        return gc_clock::time_point(gc_clock::duration(expiry));
-    }
-    // Can be called only when is_live_and_has_ttl() is true.
-    static gc_clock::duration ttl(atomic_cell_value_view cell) {
-        assert(is_live_and_has_ttl(cell));
-        return gc_clock::duration(get_field<int32_t>(cell, ttl_offset));
-    }
-    static managed_bytes make_dead(api::timestamp_type timestamp, gc_clock::time_point deletion_time) {
-        managed_bytes b(managed_bytes::initialized_later(), flags_size + timestamp_size + deletion_time_size);
-        b[0] = 0;
-        set_field(b, timestamp_offset, timestamp);
-        set_field(b, deletion_time_offset, static_cast<int64_t>(deletion_time.time_since_epoch().count()));
-        return b;
-    }
-    template <FragmentRange Buffer>
-    static managed_bytes make_live(api::timestamp_type timestamp, const Buffer& value) {
-        auto value_offset = flags_size + timestamp_size;
-        managed_bytes b(managed_bytes::initialized_later(), value_offset + value.size_bytes());
-        b[0] = LIVE_FLAG;
-        set_field(b, timestamp_offset, timestamp);
-        set_value(b, value_offset, value);
-        return b;
-    }
-    static managed_bytes make_live_counter_update(api::timestamp_type timestamp, int64_t value) {
-        auto value_offset = flags_size + timestamp_size;
-        managed_bytes b(managed_bytes::initialized_later(), value_offset + sizeof(value));
-        b[0] = LIVE_FLAG | COUNTER_UPDATE_FLAG;
-        set_field(b, timestamp_offset, timestamp);
-        set_field(b, value_offset, value);
-        return b;
-    }
-    template <FragmentRange Buffer>
-    static managed_bytes make_live(api::timestamp_type timestamp, const Buffer& value, gc_clock::time_point expiry, gc_clock::duration ttl) {
-        auto value_offset = flags_size + timestamp_size + expiry_size + ttl_size;
-        managed_bytes b(managed_bytes::initialized_later(), value_offset + value.size_bytes());
-        b[0] = EXPIRY_FLAG | LIVE_FLAG;
-        set_field(b, timestamp_offset, timestamp);
-        set_field(b, expiry_offset, static_cast<int64_t>(expiry.time_since_epoch().count()));
-        set_field(b, ttl_offset, static_cast<int32_t>(ttl.count()));
-        set_value(b, value_offset, value);
-        return b;
-    }
-    static managed_bytes make_live_uninitialized(api::timestamp_type timestamp, size_t size) {
-        auto value_offset = flags_size + timestamp_size;
-        managed_bytes b(managed_bytes::initialized_later(), value_offset + size);
-        b[0] = LIVE_FLAG;
-        set_field(b, timestamp_offset, timestamp);
-        return b;
-    }
-    template <mutable_view is_mutable>
-    friend class basic_atomic_cell_view;
-    friend class atomic_cell;
-};
+using atomic_cell_value_view = data::value_view;
+using atomic_cell_value_mutable_view = data::value_mutable_view;

 /// View of an atomic cell
 template<mutable_view is_mutable>
 class basic_atomic_cell_view {
 protected:
-    managed_bytes_basic_view<is_mutable> _view;
-	friend class atomic_cell;
+    data::cell::basic_atomic_cell_view<is_mutable> _view;
+    friend class atomic_cell;
+public:
+    using pointer_type = std::conditional_t<is_mutable == mutable_view::no, const uint8_t*, uint8_t*>;
 protected:
-    void set_view(managed_bytes_basic_view<is_mutable> v) {
-        _view = v;
-    }
-    basic_atomic_cell_view() = default;
-    explicit basic_atomic_cell_view(managed_bytes_basic_view<is_mutable> v) : _view(std::move(v)) { }
+    explicit basic_atomic_cell_view(data::cell::basic_atomic_cell_view<is_mutable> v)
+        : _view(std::move(v)) { }
+
+    basic_atomic_cell_view(const data::type_info& ti, pointer_type ptr)
+        : _view(data::cell::make_atomic_cell_view(ti, ptr))
+    { }
+
    friend class atomic_cell_or_collection;
 public:
    operator basic_atomic_cell_view<mutable_view::no>() const noexcept {
        return basic_atomic_cell_view<mutable_view::no>(_view);
    }

+    void swap(basic_atomic_cell_view& other) noexcept {
+        using std::swap;
+        swap(_view, other._view);
+    }
+
    bool is_counter_update() const {
-        return atomic_cell_type::is_counter_update(_view);
+        return _view.is_counter_update();
    }
    bool is_live() const {
-        return atomic_cell_type::is_live(_view);
+        return _view.is_live();
    }
    bool is_live(tombstone t, bool is_counter) const {
        return is_live() && !is_covered_by(t, is_counter);
@@ -219,69 +83,73 @@ public:
        return is_live() && !is_covered_by(t, is_counter) && !has_expired(now);
    }
    bool is_live_and_has_ttl() const {
-        return atomic_cell_type::is_live_and_has_ttl(_view);
+        return _view.is_expiring();
    }
    bool is_dead(gc_clock::time_point now) const {
-        return atomic_cell_type::is_dead(_view) || has_expired(now);
+        return !is_live() || has_expired(now);
    }
    bool is_covered_by(tombstone t, bool is_counter) const {
        return timestamp() <= t.timestamp || (is_counter && t.timestamp != api::missing_timestamp);
    }
    // Can be called on live and dead cells
    api::timestamp_type timestamp() const {
-        return atomic_cell_type::timestamp(_view);
+        return _view.timestamp();
    }
    void set_timestamp(api::timestamp_type ts) {
-        atomic_cell_type::set_timestamp(_view, ts);
+        _view.set_timestamp(ts);
    }
    // Can be called on live cells only
-    atomic_cell_value_basic_view<is_mutable> value() const {
-        return atomic_cell_type::value(_view);
+    data::basic_value_view<is_mutable> value() const {
+        return _view.value();
    }
    // Can be called on live cells only
    size_t value_size() const {
-        return atomic_cell_type::value(_view).size();
+        return _view.value_size();
+    }
+    bool is_value_fragmented() const {
+        return _view.is_value_fragmented();
    }
    // Can be called on live counter update cells only
    int64_t counter_update_value() const {
-        return atomic_cell_type::counter_update_value(_view);
+        return _view.counter_update_value();
    }
    // Can be called only when is_dead(gc_clock::time_point)
    gc_clock::time_point deletion_time() const {
-        return !is_live() ? atomic_cell_type::deletion_time(_view) : expiry() - ttl();
+        return !is_live() ? _view.deletion_time() : expiry() - ttl();
    }
    // Can be called only when is_live_and_has_ttl()
    gc_clock::time_point expiry() const {
-        return atomic_cell_type::expiry(_view);
+        return _view.expiry();
    }
    // Can be called only when is_live_and_has_ttl()
    gc_clock::duration ttl() const {
-        return atomic_cell_type::ttl(_view);
+        return _view.ttl();
    }
    // Can be called on live and dead cells
    bool has_expired(gc_clock::time_point now) const {
        return is_live_and_has_ttl() && expiry() <= now;
    }

-    managed_bytes_view serialize() const {
-        return _view;
+    bytes_view serialize() const {
+        return _view.serialize();
    }
 };

 class atomic_cell_view final : public basic_atomic_cell_view<mutable_view::no> {
-    atomic_cell_view(managed_bytes_view v)
-        : basic_atomic_cell_view(v) {}
+    atomic_cell_view(const data::type_info& ti, const uint8_t* data)
+        : basic_atomic_cell_view<mutable_view::no>(ti, data) {}

    template<mutable_view is_mutable>
-    atomic_cell_view(basic_atomic_cell_view<is_mutable> view)
-        : basic_atomic_cell_view<mutable_view::no>(view) {}
+    atomic_cell_view(data::cell::basic_atomic_cell_view<is_mutable> view)
+        : basic_atomic_cell_view<mutable_view::no>(view) { }
    friend class atomic_cell;
 public:
-    static atomic_cell_view from_bytes(const abstract_type& t, managed_bytes_view v) {
-        return atomic_cell_view(v);
+    static atomic_cell_view from_bytes(const data::type_info& ti, const imr::utils::object<data::cell::structure>& data) {
+        return atomic_cell_view(ti, data.get());
    }
-    static atomic_cell_view from_bytes(const abstract_type& t, bytes_view v) {
-        return atomic_cell_view(managed_bytes_view(v));
+
+    static atomic_cell_view from_bytes(const data::type_info& ti, bytes_view bv) {
+        return atomic_cell_view(ti, reinterpret_cast<const uint8_t*>(bv.begin()));
    }

    friend std::ostream& operator<<(std::ostream& os, const atomic_cell_view& acv);
@@ -296,11 +164,11 @@ public:
 };

 class atomic_cell_mutable_view final : public basic_atomic_cell_view<mutable_view::yes> {
-    atomic_cell_mutable_view(managed_bytes_mutable_view data)
-        : basic_atomic_cell_view(data) {}
+    atomic_cell_mutable_view(const data::type_info& ti, uint8_t* data)
+        : basic_atomic_cell_view<mutable_view::yes>(ti, data) {}
 public:
-    static atomic_cell_mutable_view from_bytes(const abstract_type& t, managed_bytes_mutable_view v) {
-        return atomic_cell_mutable_view(v);
+    static atomic_cell_mutable_view from_bytes(const data::type_info& ti, imr::utils::object<data::cell::structure>& data) {
+        return atomic_cell_mutable_view(ti, data.get());
    }

    friend class atomic_cell;
@@ -309,31 +177,26 @@ public:
 using atomic_cell_ref = atomic_cell_mutable_view;

 class atomic_cell final : public basic_atomic_cell_view<mutable_view::yes> {
-    managed_bytes _data;
-    atomic_cell(managed_bytes b) : _data(std::move(b))  {
-        set_view(_data);
-    }
-
+    using imr_object_type =  imr::utils::object<data::cell::structure>;
+    imr_object_type _data;
+    atomic_cell(const data::type_info& ti, imr::utils::object<data::cell::structure>&& data)
+        : basic_atomic_cell_view<mutable_view::yes>(ti, data.get()), _data(std::move(data)) {}
 public:
    class collection_member_tag;
    using collection_member = bool_class<collection_member_tag>;

-    atomic_cell(atomic_cell&& o) noexcept : _data(std::move(o._data)) {
-        set_view(_data);
-    }
+    atomic_cell(atomic_cell&&) = default;
    atomic_cell& operator=(const atomic_cell&) = delete;
-    atomic_cell& operator=(atomic_cell&& o) {
-        _data = std::move(o._data);
-        set_view(_data);
-        return *this;
+    atomic_cell& operator=(atomic_cell&&) = default;
+    void swap(atomic_cell& other) noexcept {
+        basic_atomic_cell_view<mutable_view::yes>::swap(other);
+        _data.swap(other._data);
    }
-    operator atomic_cell_view() const { return atomic_cell_view(managed_bytes_view(_data)); }
+    operator atomic_cell_view() const { return atomic_cell_view(_view); }
    atomic_cell(const abstract_type& t, atomic_cell_view other);
    static atomic_cell make_dead(api::timestamp_type timestamp, gc_clock::time_point deletion_time);
    static atomic_cell make_live(const abstract_type& type, api::timestamp_type timestamp, bytes_view value,
                                 collection_member = collection_member::no);
-    static atomic_cell make_live(const abstract_type& type, api::timestamp_type timestamp, managed_bytes_view value,
-                                 collection_member = collection_member::no);
    static atomic_cell make_live(const abstract_type& type, api::timestamp_type timestamp, ser::buffer_view<bytes_ostream::fragment_iterator> value,
                                 collection_member = collection_member::no);
    static atomic_cell make_live(const abstract_type& type, api::timestamp_type timestamp, const fragmented_temporary_buffer::view& value,
@@ -345,8 +208,6 @@ public:
    static atomic_cell make_live_counter_update(api::timestamp_type timestamp, int64_t value);
    static atomic_cell make_live(const abstract_type&, api::timestamp_type timestamp, bytes_view value,
        gc_clock::time_point expiry, gc_clock::duration ttl, collection_member = collection_member::no);
-    static atomic_cell make_live(const abstract_type&, api::timestamp_type timestamp, managed_bytes_view value,
-        gc_clock::time_point expiry, gc_clock::duration ttl, collection_member = collection_member::no);
    static atomic_cell make_live(const abstract_type&, api::timestamp_type timestamp, ser::buffer_view<bytes_ostream::fragment_iterator> value,
        gc_clock::time_point expiry, gc_clock::duration ttl, collection_member = collection_member::no);
    static atomic_cell make_live(const abstract_type&, api::timestamp_type timestamp, const fragmented_temporary_buffer::view& value,
@@ -363,13 +224,6 @@ public:
            return make_live(type, timestamp, value, gc_clock::now() + *ttl, *ttl, cm);
        }
    }
-    static atomic_cell make_live(const abstract_type& type, api::timestamp_type timestamp, const managed_bytes_view& value, ttl_opt ttl, collection_member cm = collection_member::no) {
-        if (!ttl) {
-            return make_live(type, timestamp, value, cm);
-        } else {
-            return make_live(type, timestamp, value, gc_clock::now() + *ttl, *ttl, cm);
-        }
-    }
    static atomic_cell make_live_uninitialized(const abstract_type& type, api::timestamp_type timestamp, size_t size);
    friend class atomic_cell_or_collection;
    friend std::ostream& operator<<(std::ostream& os, const atomic_cell& ac);
@@ -383,7 +237,7 @@ public:

 class column_definition;

-std::strong_ordering compare_atomic_cell_for_merge(atomic_cell_view left, atomic_cell_view right);
+int compare_atomic_cell_for_merge(atomic_cell_view left, atomic_cell_view right);
 void merge_column(const abstract_type& def,
        atomic_cell_or_collection& old,
        const atomic_cell_or_collection& neww);
--- a/atomic_cell_hash.hh
+++ b/atomic_cell_hash.hh
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once
@@ -39,7 +52,9 @@ struct appending_hash<atomic_cell_view> {
        feed_hash(h, cell.timestamp());
        if (cell.is_live()) {
            if (cdef.is_counter()) {
-                ::feed_hash(h, counter_cell_view(cell));
+                counter_cell_view::with_linearized(cell, [&] (counter_cell_view ccv) {
+                    ::feed_hash(h, ccv);
+                });
                return;
            }
            if (cell.is_live_and_has_ttl()) {
--- a/atomic_cell_or_collection.hh
+++ b/atomic_cell_or_collection.hh
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2015-present ScyllaDB
+ * Copyright (C) 2015 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once
@@ -11,15 +24,22 @@
 #include "atomic_cell.hh"
 #include "collection_mutation.hh"
 #include "schema.hh"
+#include "hashing.hh"
+
+#include "imr/utils.hh"

 // A variant type that can hold either an atomic_cell, or a serialized collection.
 // Which type is stored is determined by the schema.
-// Has an "empty" state.
-// Objects moved-from are left in an empty state.
 class atomic_cell_or_collection final {
-    managed_bytes _data;
+    // FIXME: This has made us lose small-buffer optimisation. Unfortunately,
+    // due to the changed cell format it would be less effective now, anyway.
+    // Measure the actual impact because any attempts to fix this will become
+    // irrelevant once rows are converted to the IMR as well, so maybe we can
+    // live with this like that.
+    using imr_object_type = imr::utils::object<data::cell::structure>;
+    imr_object_type _data;
 private:
-    atomic_cell_or_collection(managed_bytes&& data) : _data(std::move(data)) {}
+    atomic_cell_or_collection(imr::utils::object<data::cell::structure>&& data) : _data(std::move(data)) {}
 public:
    atomic_cell_or_collection() = default;
    atomic_cell_or_collection(atomic_cell_or_collection&&) = default;
@@ -29,16 +49,20 @@ public:
    atomic_cell_or_collection(atomic_cell ac) : _data(std::move(ac._data)) {}
    atomic_cell_or_collection(const abstract_type& at, atomic_cell_view acv);
    static atomic_cell_or_collection from_atomic_cell(atomic_cell data) { return { std::move(data._data) }; }
-    atomic_cell_view as_atomic_cell(const column_definition& cdef) const { return atomic_cell_view::from_bytes(*cdef.type, _data); }
-    atomic_cell_mutable_view as_mutable_atomic_cell(const column_definition& cdef) { return atomic_cell_mutable_view::from_bytes(*cdef.type, _data); }
+    atomic_cell_view as_atomic_cell(const column_definition& cdef) const { return atomic_cell_view::from_bytes(cdef.type->imr_state().type_info(), _data); }
+    atomic_cell_ref as_atomic_cell_ref(const column_definition& cdef) { return atomic_cell_mutable_view::from_bytes(cdef.type->imr_state().type_info(), _data); }
+    atomic_cell_mutable_view as_mutable_atomic_cell(const column_definition& cdef) { return atomic_cell_mutable_view::from_bytes(cdef.type->imr_state().type_info(), _data); }
    atomic_cell_or_collection(collection_mutation cm) : _data(std::move(cm._data)) { }
    atomic_cell_or_collection copy(const abstract_type&) const;
    explicit operator bool() const {
-        return !_data.empty();
+        return bool(_data);
    }
    static constexpr bool can_use_mutable_view() {
        return true;
    }
+    void swap(atomic_cell_or_collection& other) noexcept {
+        _data.swap(other._data);
+    }
    static atomic_cell_or_collection from_collection_mutation(collection_mutation data) { return std::move(data._data); }
    collection_mutation_view as_collection_mutation() const;
    bytes_view serialize() const;
@@ -58,3 +82,12 @@ public:
    };
    friend std::ostream& operator<<(std::ostream&, const printer&);
 };
+
+namespace std {
+
+inline void swap(atomic_cell_or_collection& a, atomic_cell_or_collection& b) noexcept
+{
+    a.swap(b);
+}
+
+}
--- a/auth/allow_all_authenticator.cc
+++ b/auth/allow_all_authenticator.cc
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2017-present ScyllaDB
+ * Copyright (C) 2017 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #include "auth/allow_all_authenticator.hh"
--- a/auth/allow_all_authenticator.hh
+++ b/auth/allow_all_authenticator.hh
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2017-present ScyllaDB
+ * Copyright (C) 2017 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once
--- a/auth/allow_all_authorizer.cc
+++ b/auth/allow_all_authorizer.cc
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2017-present ScyllaDB
+ * Copyright (C) 2017 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #include "auth/allow_all_authorizer.hh"
--- a/auth/allow_all_authorizer.hh
+++ b/auth/allow_all_authorizer.hh
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2017-present ScyllaDB
+ * Copyright (C) 2017 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once
--- a/auth/authenticated_user.cc
+++ b/auth/authenticated_user.cc
@@ -1,14 +1,42 @@
 /*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
 */

 /*
- * Copyright (C) 2016-present ScyllaDB
+ * Copyright (C) 2016 ScyllaDB
 *
 * Modified by ScyllaDB
 */

 /*
- * SPDX-License-Identifier: (AGPL-3.0-or-later and Apache-2.0)
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #include "auth/authenticated_user.hh"
--- a/auth/authenticated_user.hh
+++ b/auth/authenticated_user.hh
@@ -1,14 +1,42 @@
 /*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
 */

 /*
- * Copyright (C) 2016-present ScyllaDB
+ * Copyright (C) 2016 ScyllaDB
 *
 * Modified by ScyllaDB
 */

 /*
- * SPDX-License-Identifier: (AGPL-3.0-or-later and Apache-2.0)
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once
--- a/auth/authentication_options.cc
+++ b/auth/authentication_options.cc
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2018-present ScyllaDB
+ * Copyright (C) 2018 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #include "auth/authentication_options.hh"
--- a/auth/authentication_options.hh
+++ b/auth/authentication_options.hh
@@ -1,9 +1,22 @@
 /*
- * Copyright (C) 2018-present ScyllaDB
+ * Copyright (C) 2018 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once
--- a/auth/authenticator.cc
+++ b/auth/authenticator.cc
@@ -1,14 +1,42 @@
 /*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
 */

 /*
- * Copyright (C) 2016-present ScyllaDB
+ * Copyright (C) 2016 ScyllaDB
 *
 * Modified by ScyllaDB
 */

 /*
- * SPDX-License-Identifier: (AGPL-3.0-or-later and Apache-2.0)
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #include "auth/authenticator.hh"
--- a/auth/authenticator.hh
+++ b/auth/authenticator.hh
@@ -1,14 +1,42 @@
 /*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
 */

 /*
- * Copyright (C) 2016-present ScyllaDB
+ * Copyright (C) 2016 ScyllaDB
 *
 * Modified by ScyllaDB
 */

 /*
- * SPDX-License-Identifier: (AGPL-3.0-or-later and Apache-2.0)
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once
@@ -19,6 +47,7 @@
 #include <stdexcept>
 #include <unordered_map>

+#include <boost/any.hpp>
 #include <seastar/core/enum.hh>
 #include <seastar/core/future.hh>
 #include <seastar/core/sstring.hh>
@@ -46,8 +75,6 @@ class authenticated_user;
 ///
 class authenticator {
 public:
-    using ptr_type = std::unique_ptr<authenticator>;
-
    ///
    /// The name of the key to be used for the user-name part of password authentication with \ref authenticate.
    ///
--- a/auth/authorizer.hh
+++ b/auth/authorizer.hh
@@ -1,14 +1,42 @@
 /*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
 */

 /*
- * Copyright (C) 2016-present ScyllaDB
+ * Copyright (C) 2016 ScyllaDB
 *
 * Modified by ScyllaDB
 */

 /*
- * SPDX-License-Identifier: (AGPL-3.0-or-later and Apache-2.0)
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

 #pragma once
@@ -63,8 +91,6 @@ public:
 ///
 class authorizer {
 public:
-    using ptr_type = std::unique_ptr<authorizer>;
-
    virtual ~authorizer() = default;

    virtual future<> start() = 0;
--- a/auth/common.cc
+++ b/auth/common.cc
@@ -1,19 +1,31 @@
 /*
- * Copyright (C) 2017-present ScyllaDB
+ * Copyright (C) 2017 ScyllaDB
 */

 /*
- * SPDX-License-Identifier: AGPL-3.0-or-later
+ * This file is part of Scylla.
+ *
+ * Scylla is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Scylla is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Scylla.  If not, see <http://www.gnu.org/licenses/>.
 */

-#include <seastar/core/coroutine.hh>
 #include "auth/common.hh"

 #include <seastar/core/shared_ptr.hh>

 #include "cql3/query_processor.hh"
 #include "cql3/statements/create_table_statement.hh"
-#include "replica/database.hh"
+#include "database.hh"
 #include "schema_builder.hh"
 #include "service/migration_manager.hh"
 #include "timeout_config.hh"
@@ -22,9 +34,9 @@ namespace auth {

 namespace meta {

-constinit const std::string_view AUTH_KS("system_auth");
-constinit const std::string_view USERS_CF("users");
-constinit const std::string_view AUTH_PACKAGE_NAME("org.apache.cassandra.auth.");
+constexpr std::string_view AUTH_KS("system_auth");
+constexpr std::string_view USERS_CF("users");
+constexpr std::string_view AUTH_PACKAGE_NAME("org.apache.cassandra.auth.");

 }

@@ -33,13 +45,15 @@ static logging::logger auth_log("auth");
 // Func must support being invoked more than once.
 future<> do_after_system_ready(seastar::abort_source& as, seastar::noncopyable_function<future<>()> func) {
    struct empty_state { };
-    return exponential_backoff_retry::do_until_value(1s, 1min, as, [func = std::move(func)] {
-        return func().then_wrapped([] (auto&& f) -> std::optional<empty_state> {
-            if (f.failed()) {
-                auth_log.debug("Auth task failed with error, rescheduling: {}", f.get_exception());
-                return { };
-            }
-            return { empty_state() };
+    return delay_until_system_ready(as).then([&as, func = std::move(func)] () mutable {
+        return exponential_backoff_retry::do_until_value(1s, 1min, as, [func = std::move(func)] {
+            return func().then_wrapped([] (auto&& f) -> std::optional<empty_state> {
+                if (f.failed()) {
+                    auth_log.debug("Auth task failed with error, rescheduling: {}", f.get_exception());
+                    return { };
+                }
+                return { empty_state() };
+            });
        });
    }).discard_result();
 }
@@ -49,9 +63,10 @@ static future<> create_metadata_table_if_missing_impl(
        cql3::query_processor& qp,
        std::string_view cql,
        ::service::migration_manager& mm) {
-    assert(this_shard_id() == 0); // once_among_shards makes sure a function is executed on shard 0 only
-
-    auto db = qp.db();
+    static auto ignore_existing = [] (seastar::noncopyable_function<future<>()> func) {
+        return futurize_invoke(std::move(func)).handle_exception_type([] (exceptions::already_exists_exception& ignored) { });
+    };
+    auto& db = qp.db();
    auto parsed_statement = cql3::query_processor::parse_statement(cql);
    auto& parsed_cf_statement = static_cast<cql3::statements::raw::cf_statement&>(*parsed_statement);

@@ -66,14 +81,9 @@ static future<> create_metadata_table_if_missing_impl(
    schema_builder b(schema);
    b.set_uuid(uuid);
    schema_ptr table = b.build();
-
-    if (!db.has_schema(table->ks_name(), table->cf_name())) {
-        auto group0_guard = co_await mm.start_group0_operation();
-        auto ts = group0_guard.write_timestamp();
-        try {
-            co_return co_await mm.announce(co_await mm.prepare_new_column_family_announcement(table, ts), std::move(group0_guard));
-        } catch (exceptions::already_exists_exception&) {}
-    }
+    return ignore_existing([&mm, table = std::move(table)] () {
+        return mm.announce_new_column_family(table, false);
+    });
 }

 future<> create_metadata_table_if_missing(
@@ -84,12 +94,12 @@ future<> create_metadata_table_if_missing(
    return futurize_invoke(create_metadata_table_if_missing_impl, table_name, qp, cql, mm);
 }

-future<> wait_for_schema_agreement(::service::migration_manager& mm, const replica::database& db, seastar::abort_source& as) {
+future<> wait_for_schema_agreement(::service::migration_manager& mm, const database& db, seastar::abort_source& as) {
    static const auto pause = [] { return sleep(std::chrono::milliseconds(500)); };

    return do_until([&db, &as] {
        as.check();
-        return db.get_version() != replica::database::empty_version;
+        return db.get_version() != database::empty_version;
    }, pause).then([&mm, &as] {
        return do_until([&mm, &as] {
            as.check();
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Piotr Sarna	fcb349b026	tests: add tests for per-role timeouts The test cases verify that setting timeout parameters per-role works and is validated.	2020-11-27 12:43:53 +01:00
Piotr Sarna	28c558af95	docs: add a paragaph about per-role parameters This paragraph is also the first one in newly crated roles.md, which should be later filled with more information about roles.	2020-11-27 12:43:53 +01:00
Piotr Sarna	83b47ae394	cql3: add validating per-role timeout options Per-role timeout options are now validated when set: - they should represent a valid duration - the duration should have millisecond granularity, since the timeout clock does not support micro/nanoseconds.	2020-11-27 12:37:27 +01:00
Piotr Sarna	391d1f2b21	client_state: add updating per-role params Per-role parameters (currently: read_timeout and write_timeout) are now updated when a new connection is established. Also, the changes are immediately propagated for the connection which sent the CREATE ROLE/ALTER ROLE statement. The other connections which have the changed role are currently not immediately reloaded. It can be done in the future if needed, but all sessions with given roles should be tracked, or, alternatively, all sessions should be iterated and changed.	2020-11-27 12:37:27 +01:00
Piotr Sarna	137a8a0161	auth: add options support to password authenticator Custom options will be used later to provide per-role timeouts and other useful parameters.	2020-11-27 12:37:17 +01:00
Piotr Sarna	c473cb4a2d	treewide: remove timeout config from query options Timeout config is now stored in each connection, so there's no point in tracking it inside each query as well. This patch removes timeout_config from query_options and follows by removing now unnecessary parameters of many functions and constructors.	2020-11-26 17:56:55 +01:00
Piotr Sarna	98fac66361	cql3: use timeout config from client state instead of query options ... in batch statement, in order to be able to remove the timeout from query options later.	2020-11-26 17:55:29 +01:00
Piotr Sarna	2cbeb3678f	cql3: use timeout config from client state instead of query options ... in modification statement, in order to be able to remove the timeout from query options later.	2020-11-26 17:55:29 +01:00
Piotr Sarna	d61e1fd174	cql3: use timeout config from client state instead of query options ... in select statement, in order to be able to remove the timeout from query options later.	2020-11-26 17:55:29 +01:00
Piotr Sarna	f31ac0a8ca	service: add timeout config to client state Future patches will use this per-connection timeout config to allow setting different timeouts for each session, based on roles.	2020-11-26 17:55:14 +01:00