This pull request introduces a new caching mechanism for client options in the Alternator and transport layers, refactors how client metadata is stored and accessed, and extends the `system.clients` virtual table to surface richer client information. The changes improve efficiency by deduplicating commonly used strings (like driver names/versions and client options), and ensure that client data is handled in a way that's safe for cross-shard access. Additionally, the test suite and virtual table schema are updated to reflect the new client options data.
**Caching and client metadata refactoring:**
* The largest and most repeatable items in the connection state before this PR were a `driver_name` and a `driver_version` which were stored as an `sstring` object which means that the corresponding memory consumption was 16 bytes per each such value at least (the smallest size of the `seastar`'s `sstring` object) **per-connection**. In reality the driver name is usually longer than 15 characters, e.g. "ScyllaDB Python Driver" is 23 characters and this is not the longest driver name there is. In such cases the actual memory usage of a corresponding `sstring` object jumps to 8 + 4 + 1 + (string length, 23 in our example) + 1.
So, for "ScyllaDB Python Driver" it would be 37 bytes (in reality it would be a bit more due to natural alignment of other allocations since the `contents` size is not well aligned (13 bytes), but let's ignore this for now).
* These bytes add up quickly as there are more connections and, sometimes we are talking about millions of connections per-shard.
* Using a smart pointer (`lw_shared_ptr`) referencing a corresponding cached value will effectively reduce the per-connection memory usage to be 8 bytes (a size of a pointer on 64-bit CPU platform) for each such value. While storing a corresponding `sstring` value only once.
* This will would reduce the "variable" (per-connection) memory usage by **at least 50%**. And in case of "ScyllaDB Python Driver" driver version - by 78%!
* And all this for a price of a single `loading_shared_values` object **per-shard** (implements a hash table) and a minor overhead for each value **stored** in it.
* Introduced a new cache type (`client_options_cache_type`) for deduplicating and sharing client option strings, and refactored `client_data`, `client_state`, and related classes to use `foreign_ptr<std::unique_ptr<client_data>>` and cached entry types for fields like driver name, driver version, and client options. (`client_data.hh`, `service/client_state.hh`, `alternator/server.hh`, `alternator/controller.hh`, `transport/controller.hh`, `transport/protocol_server.hh`) [[1]](diffhunk://#diff-664a3b19e905481bdf8eb3843fc4d34691067bb97ab11cfd6e652e74aac51d9fR33-R36) [[2]](diffhunk://#diff-664a3b19e905481bdf8eb3843fc4d34691067bb97ab11cfd6e652e74aac51d9fL40-R56) [[3]](diffhunk://#diff-daadce1a2de3667511e59558f3a8f077b5ee30a14bcc6a99d588db90d0fcd2bdL105-R107) [[4]](diffhunk://#diff-daadce1a2de3667511e59558f3a8f077b5ee30a14bcc6a99d588db90d0fcd2bdL154-R182) [[5]](diffhunk://#diff-5fce246edf5abffb2351bd02e2eb1e9850880f7a00607ccaa90c3eee7ef57c6bL91-R92) [[6]](diffhunk://#diff-5fce246edf5abffb2351bd02e2eb1e9850880f7a00607ccaa90c3eee7ef57c6bL110-R111) [[7]](diffhunk://#diff-31730ba8e7374f784a88dc27c1512291cf73b7f24e08768f7466a3c8cfcc7a1aL96-R96) [[8]](diffhunk://#diff-19a97c0247cc08155ee49b277e43859ca32d6ef8cbff0ed7368ec5fa19e0a11eL172-R172) [[9]](diffhunk://#diff-eea7e2db5d799a25e717a72ac8ce5842bd4adb72b694d38d8f47166d9cd926faL356-R356) [[10]](diffhunk://#diff-d0b4ec3a144bbc5dc993866cf0b940850a457ff6156064f7e2b4b10ad0a95fefL80-R80) [[11]](diffhunk://#diff-4293b94c444d9bd5ecd17ce7eda8c00685d35ecf6e07f844efc91a91bbe85be1L46-R48)
* Updated the methods for setting and getting driver name, driver version, and client options in `client_state` to be asynchronous and use the new cache. (`service/client_state.hh`, `service/client_state.cc`) [[1]](diffhunk://#diff-daadce1a2de3667511e59558f3a8f077b5ee30a14bcc6a99d588db90d0fcd2bdL154-R182) [[2]](diffhunk://#diff-99634aae22e2573f38b4e2f050ed2ac4f8173ff27f0ae8b3609d1f0cc1aeb775R347-R362)
**Virtual table and API enhancements:**
* Extended the `system.clients` virtual table schema and implementation to include a new `client_options` column (a map of option key/value pairs), and updated the table population logic to use the new cached types and foreign pointers. (`db/virtual_tables.cc`) [[1]](diffhunk://#diff-05f7bff3edb39fb8759c90b445e860189f2f30e04717ed58bae42716082af3d1R752) [[2]](diffhunk://#diff-05f7bff3edb39fb8759c90b445e860189f2f30e04717ed58bae42716082af3d1L769-R770) [[3]](diffhunk://#diff-05f7bff3edb39fb8759c90b445e860189f2f30e04717ed58bae42716082af3d1L809-R816) [[4]](diffhunk://#diff-05f7bff3edb39fb8759c90b445e860189f2f30e04717ed58bae42716082af3d1L828-R879)
**API and interface changes:**
* Changed the signatures of `get_client_data` methods throughout the codebase to return vectors of `foreign_ptr<std::unique_ptr<client_data>>` instead of plain `client_data` objects, to ensure safe cross-shard access. (`alternator/controller.hh`, `alternator/controller.cc`, `alternator/server.hh`, `alternator/server.cc`, `transport/controller.hh`, `transport/protocol_server.hh`) [[1]](diffhunk://#diff-31730ba8e7374f784a88dc27c1512291cf73b7f24e08768f7466a3c8cfcc7a1aL96-R96) [[2]](diffhunk://#diff-19a97c0247cc08155ee49b277e43859ca32d6ef8cbff0ed7368ec5fa19e0a11eL172-R172) [[3]](diffhunk://#diff-5fce246edf5abffb2351bd02e2eb1e9850880f7a00607ccaa90c3eee7ef57c6bL110-R111) [[4]](diffhunk://#diff-a7e2cda866c03a75afcf3b087de1c1dcd2e7aa996214db67f9a11ed6451e596dL988-R995) [[5]](diffhunk://#diff-eea7e2db5d799a25e717a72ac8ce5842bd4adb72b694d38d8f47166d9cd926faL356-R356) [[6]](diffhunk://#diff-d0b4ec3a144bbc5dc993866cf0b940850a457ff6156064f7e2b4b10ad0a95fefL80-R80) [[7]](diffhunk://#diff-4293b94c444d9bd5ecd17ce7eda8c00685d35ecf6e07f844efc91a91bbe85be1L46-R48)
**Testing and validation:**
* Updated the Python test for the `system.clients` table to verify the new `client_options` column and its contents, ensuring that driver name and version are present in the options map. (`test/cqlpy/test_virtual_tables.py`) [[1]](diffhunk://#diff-6dd8bd4a6a82cd642252a29dc70726f89a46ceefb991c3e63fc67e283f323f03R79) [[2]](diffhunk://#diff-6dd8bd4a6a82cd642252a29dc70726f89a46ceefb991c3e63fc67e283f323f03R88-R90)
Closesscylladb/scylladb#25746
* github.com:scylladb/scylladb:
transport/server: declare a new "CLIENT_OPTIONS" option as supported
service/client_state and alternator/server: use cached values for driver_name and driver_version fields
system.clients: add a client_options column
controller: update get_client_data to use foreign_ptr for client_data
This patch consists of a few smaller follow-ups to the view building worker:
- catch general execption in staging task registrator
- remove unnecessary CV broadcast
- don't pollute function context with conditionally compiled variable
- avoid creating a copy of tasks map
- fix some typos
Refs https://github.com/scylladb/scylladb/issues/25929
Refs https://github.com/scylladb/scylladb/pull/26897
This PR doesn't fix any bugs but recently we're backporting some PRs to 2025.4, so let's also backport this one to avoid painful conflicts.
Closesscylladb/scylladb#26558
* github.com:scylladb/scylladb:
docs/dev/view-building-coordinator: fix typos
db/view/view_building_worker: remove unnnecessary empty lines
db/view/view_building_worker: fix typo
db/view/view_building_worker: avoid creating a copy of tasks map
db/view/view_building_worker: wrap conditionally compiled code in a scope
db/view/view_building_worker: remove unnecessary CV broadcast
db/view/view_building_worker: catch general execption in staging task registrator
Optimize memory usage changing types of driver_name and driver_version be
a reference to a cached value instead of an sstring.
These fields very often have the same value among different connections hence
it makes sense to cache these values and use references to them instead of duplicating
such strings in each connection state.
Signed-off-by: Vlad Zolotarov <vladz@scylladb.com>
This new column is going to contain all OPTIONS sent in the
STARTUP frame of the corresponding CQL session.
The new column has a `frozen<map<text, text>>` type, and
we are also optimizing the amount of required memory for storing
corresponding keys and values by caching them on each shard level.
Signed-off-by: Vlad Zolotarov <vladz@scylladb.com>
get_client_data() is used to assemble `client_data` objects from each connection
on each CPU in the context of generation of the `system.clients` virtual table data.
After collected, `client_data` objects were std::moved and arranged into a
different structure to match the table's sorting requirements.
This didn't allow having not-cross-shard-movable objects as fields in the `client_data`,
e.g. lw_shared_ptr objects.
Since we are planning to add such fields to `client_data` in following patches this patch
is solving the limitation above by making get_client_data() return `foreign_ptr<std::unique_ptr<client_data>>`
objects instead of naked `client_data` ones.
Signed-off-by: Vlad Zolotarov <vladz@scylladb.com>
Make the removenode operation go through the `left_token_ring` state, similar to decommission. This ensures that when removenode completes, all nodes in the cluster are aware of the topology change through a global token metadata barrier.
Previously, removenode would skip the `left_token_ring` state and go directly from `write_both_read_new` to `left` state. This meant that when the operation completed, some nodes might not yet know about the topology change, potentially causing issues with subsequent data plane requests.
Key changes:
- Both decommission and removenode now transition to `left_token_ring` state in the `write_both_read_new` handler
- In `left_token_ring` state, only decommissioning nodes receive the shutdown RPC (removed nodes are already dead)
- Updated documentation to reflect that both operations use this state
This change improves consistency guarantees for removenode operations by ensuring cluster-wide awareness before completion.
The change is protected by "REMOVENODE_WITH_LEFT_TOKEN_RING" feature flag to also support mixed clusters during e.g. upgrade.
Fixes: scylladb/scylladb#25530
No backport: This fixes and issue found in tests. It can theoretically happen in production too, but wasn't reported in any customer issue, so a backport is not needed.
Closesscylladb/scylladb#26931
* https://github.com/scylladb/scylladb:
topology: make removenode use left_token_ring state for global barrier
topology: allow removing nodes not having tokens
features: add feature flag for removenode via left token ring
For the changes to go through the left_token_ring state when
REMOVENODE_WITH_LEFT_TOKEN_RING feature is enabled, we need to allow
removing nodes to not have any tokens (similarly to decommissioning
nodes, which use the same sequence of states).
This means the tests also need to change to allow for this new behavior
- it can temporarily happen that a removing node has no tokens but is
still part of Raft group 0 (so there may be a temporary mismatch between
the token ring and group 0 membership).
Therefore, the `check_token_ring_and_group0_consistency` function is
replaced by `wait_for_token_ring_and_group0_consistency`, which waits
up to 30 seconds for consistency to be reached.
Currently the formatter converts it to json and then tries to emit into
the output context with the "...{{}}" format string. The intent was to
have the "...{<json text>}" output. However, the double curly brace in
format string means "print a curly brace", so the output of the above
formatting is "...{}", literally.
Fix by keeping a single curly brace. The "<json text>" thing will have
its own surrounding curly braces.
Fixes#27718
Signed-off-by: Pavel Emelyanov <xemul@scylladb.com>
Closesscylladb/scylladb#27687
If a keyspace has a numeric replication factor in a DC and rf < #racks,
then the replicas of tablets in this keyspace can be distributed among
all racks in the DC (different for each tablet). With rack list, we need all
tablet replicas to be placed on the same racks. Hence, the conversion
requires tablet co-location.
After this series, the conversion can be done using ALTER KEYSPACE
statement. The statement that does this conversion in any DC is not
allowed to change a rf in any DC. So, if we have dc1 and dc2 with 3 racks
each and a keyspace ks then with a single ALTER KEYSPACE we can do:
- {dc1 : 2} -> {dc1 : [r1, r2]};
- {dc1 : 2, dc2: 2} -> {dc1 : [r1, r2], dc2: [r2,r3]};
- {dc1 : 2, dc2: 2} -> {dc1 : [r1, r2], dc2: 2}
- {dc1 : 2} -> {dc1 : 2, dc2 : [r1]}
But we cannot do:
- {dc1 : 2} -> {dc1 : [r1, r2, r3]};
- {dc1 : 1, dc2 : [r1, r2] → dc1: [r1], dc2: [r1].
In order to do the co-locations rf change request is paused. Tablet
load balancer examines the paused rf change requests and schedules
necessary tablet migrations. During the process of co-location, no other
cross-rack migration is allowed.
Load balancer checks whether any paused rf change request is
ready to be resumed. If so, it puts the request back to global topology
request queue.
While an rf change request for a keyspace is running, any other rf change
of this keyspace will fail.
Fixes: #26398.
New feature, no backport
Closesscylladb/scylladb#27279
* github.com:scylladb/scylladb:
test: add est_rack_list_conversion_with_two_replicas_in_rack
test: test creating tablet_rack_list_colocation_plan
test: add test_numeric_rf_to_rack_list_conversion test
tasks: service: add global_topology_request_virtual_task
cql3: statements: allow altering from numeric rf to rack list
service: topology_coordinator: pause keyspace_rf_change request
service: implement make_rack_list_colocation_plan
service: add tablet_rack_list_colocation_plan
cql3: reject concurrent alter of the same keyspace
test: check paused rf change requests persistence
db: service: add paused_rf_change_requests to system.topology
service: pass topology and system_keyspace to load_balancer ctor
service: tablet_allocator: extract load updates
service: tablet_allocator: extract ensure_node
tasks, system_keyspace: Introduce get_topology_request_entry_opt()
node_ops: Drop get_pending_ids()
node_ops: Drop redundant get_status_helper()
Add a service::topo::global_topology_request_virtual_task, which
covers the replication factor changes.
Currently, the global_topology_request_virtual_task can be aborted
only if it is paused.
The progress of the rf change isn't counted.
In the following changes, we allow to alter from numeric rf to rack list.
Before the alter, two tablets of the same keyspace can have replicas
on different racks. To switch to rack list, we need to co-locate
the replicas. It will be achieved by pausing the keyspace_rf_change
and scheduling migrations.
We need to persist the ids of requests that are paused. A new column -
paused_rf_change_requests is added to system.topology table.
In this commit no data is kept in the new column.
`system.client_routes` is a system table that sets the target address and ports for each `host_id`, for one or more connection (e.g., Private Link) represented by `connection_id`. Cloud will write the table via REST, and drivers will read it via CQL to override values obtained from `system.local` and `system.peers`.
This patch series contains:
- Introduction of `CLIENT_ROUTES` feature flag.
- Implementation of raft-based `system.client_routes` table
- Implementation of `v2/client-routes` POST/DELETE/GET endpoints
- Implementation of new `CLIENT_ROUTES_CHANGE` event that is sent to drivers when `system.client_routes` is changed
- New tests that verifies the aforementioned features
Ref: scylladb/scylla-enterprise#5699
For now, no automatic backport. However, the changes are planned to be release on `2025.4` either as a backport or a private build.
Closesscylladb/scylladb#27323
* https://github.com/scylladb/scylladb:
docs: describe CLIENT_ROUTES_CHANGE extension
test: add test for CLIENT_ROUTES event
service: transport: add CLIENT_ROUTES_CHANGE event
test: add cluster tests for client routes
test: add API tests for client_routes endpoints
test: add `timeout` parameter to `delete` in RESTClient
test: allow json_body in send
api: implement client_routes endpoints
api: add client_routes.json
service: main: add client_routes_service
db: add system.client_routes table
gms: add CLIENT_ROUTES feature
Fixes#26744
If a segment to replay is broken such that the main header is not zero, but still broken, we throw header_checksum_error. This was not handled in replayer, which grouped this into the "user error/fundamental problem" category.
However, assuming we allow for "real" disk corruption, this should really be treated same as data corruption, i.e. reported data loss, not failure to start up.
The `test_one_big_mutation_corrupted_on_startup` test accidentally sometimes provoked this issue, by doing random file wrecking, which on rare occasions provoked this, and thus failed test due to scylla not starting up, instead of losing data as expected.
Closesscylladb/scylladb#27556
* github.com:scylladb/scylladb:
test::cluster::dtest::tools::files: Remove file
commitlog_replay: Handle fully corrupt files same as partial corruption.
test::pylib::suite::base: Split options.name test specifier only once
Fix multiple cases where the captured `std::exception_ptr` has been re-thrown via simple `throw eptr;`, which results in losing the original exception type and details.
Resolved at various places found by clang-tidy:
1. db::schema_applier
When applying schema changes, the previous implementation attempted to handle exceptions by catching and rethrowing them, but did so incorrectly: using `throw ex` with a `std::exception_ptr` loses the original exception type and details.
However, in this case, explicit exception handling is unnecessary. The only reason for catching was to ensure `ap.destroy()` is called before propagating the exception. This can be more cleanly and safely achieved using Seastar's `.finally()` continuation, which guarantees cleanup regardless of success or failure.
2. directories
The `std::exception_ptr()` has been captured for logging and then again re-thrown incorrectly via `throw ex;`. We could use `std::rethrow_exception()` here instead, but it seems to be simpler to just use regular `throw;` to rethrow the original exception, and only use the `std::current_exception()` for logging (which is a pattern used in other places as well).
3. storage_service
Here the exception has been re-thrown incorrectly in a coroutine. There it is best to use the `co_await coroutine::return_exception_ptr` to propagate exception more efficiently in a coroutine-friendly manner.
Fixes: SCYLLADB-94
Refs: scylladb/scylladb#27501
No backport: This fixes an error logging issue, that isn't a production problem by itself (only found in test), therefore not backporting to older branches.
Closesscylladb/scylladb#27613
* https://github.com/scylladb/scylladb:
db: schema_applier: improve exception-safe cleanup
directories: fix exception rethrowing
storage_service: use coroutine-friendly exception propagation in join_node_response_handler
Introduce `system.client_routes`, a system table that sets the target
address and ports for each `host_id`, for one or more connections
(e.g., Private Link) represented by `connection_id`. Cloud will write
the table via REST, and drivers will read it via CQL to override
values obtained from `system.local` and `system.peers`.
The table is Raft-managed to provide consistent replication across
nodes.
Schema overview: each row is identified by `(connection_id, host_id)`
and describes where clients should connect: `address` and one or more of
`port`, `tls_port`, `alternator_port`, `alternator_https_port`.
`host_id` is a UUID (just as in ScyllaDB) but `connection_id` can be
any string to accept formats of all cloud providers. `address` is
also a regular string because it can represent either an IP address or
a domain. Ports are optional in the sense that at least one of
the four must be provided.
Ref: scylladb/scylla-enterprise#5699
The batchlog table contains an entry for each logged batch that is processed by the local node as coordinator. These entries are typically very short lived, they are inserted when the batch is processed and deleted immediately after the batch is successfully applied.
When a table has `tombstone_gc = {'mode': 'repair'}` enabled, every repair has to flush all hints and batchlogs, so that we can be certain that there is no live data in any of these, older than the last repair. Since batches can contain member queries from any number of tables, the whole batchlog has to be flushed, even if repair-mode tombstone-gc is enabled for a single table.
Flushing the batchlog table happens by doing a batchlog replay. This involves reading the entire content of this table, and attempting to replay+delete any live entries (that are old enough to be replayed). Under normal operating circumstances, 99%+ of the content of the batchlog table is partition tombstones. Because of this, scanning the content of this table has to process thousands to millions of tombstones. This was observed to require up to 20 minutes to finish, causing repairs to slow down to a crawl, as the batchlog-flush has to be repeated at the end of the repair of each token-range.
When trying to address this problem, the first idea was that we should expedite the garbage-collection of these accumulated tombstones. This experiment failed, see https://github.com/scylladb/scylladb/pull/23752. The commitlog proved to be an impossible to bypass barrier, preventing quick garbage-collection of tombstones. So long as a single commit-log segment is alive, holding content from the batchlog table, all tombstones written after are blocked from GC.
The second approach, represented by this PR, is to not rely in tombstone GC to reduce the tombstone amount. Instead restructure the table such that a single higher-order tombstone can be used to shadow and allow for the eviction of the myriads of individual batchlog entry tombstones. This is realized by reorganizing the batchlog table such that individual batches are rows, not partitions.
This new schema is introduced by the new `system.batchlog_v2` table, introduced by this PR:
CREATE TABLE system.batchlog_v2 (
version int,
stage int,
shard int,
written_at timestamp,
id uuid,
data blob,
PRIMARY KEY ((version, stage, shard), written_at, id));
The new schema organization has the following goals:
1) Make post-replay batchlog cleanup possible with a simple range-tombstone. This allows dropping the individual dead batchlog entries, as they are shadowed by a higher level tombstone. This enables dropping tombstones without tombstone GC.
2) To make the above possible, introduce the stage key component: batchlog entries that fail the first replay attempt, are moved to the failed_replay stage, so the initial stage can be cleaned up safely.
3) Spread out the data among Scylla shards, via the batchlog shard column.
4) Make batchlog entries ordered by the batchlog create time (id). This allows for selecting batchlogs to replay, without post-filtering of batchlogs that are too young to be replayed.
Fixes: https://github.com/scylladb/scylladb/issues/23358
This is an improvement, normally not a backport-candidate. We might override this and backport to allow wider use of `tombstone_gc: {'mode': 'repair'}`.
Closesscylladb/scylladb#26671
* github.com:scylladb/scylladb:
db/config: change batchlog_replay_cleanup_after_replays default to 1
test/boost/batchlog_manager_test: add test for batchlog cleanup
replica/mutation_dump: always set position weight for clustering positions
service/storage_proxy: s/batch_replay_throw/storage_proxy_fail_replay_batch/
test/lib: introduce error_injection.hh
utils/error_injection: add debug log to disable() and disable_all()
test/lib/cql_test_env: forward config to batchlog
test/lib/cql_test_env: add batch type to execute_batch()
test/lib/cql_assertions: add with_size(predicate) overload
test/lib/cql_assertions: add source location to fail messages
test/lib/cql_assertions: columns_assertions: add assert_for_columns_of_each_row()
test/lib/cql_assertions: rows_assertions::assert_for_columns_of_row(): add index bound check
test/lib/cql_assertions: columns_assertions: add T* with_typed_column() overload
db/batchlog_manager: config: s/write_timeout/reply_timeot/
db,service: switch to system.batchlog_v2
db/system_keyspace: introduce system.batchlog_v2
service,db: extract generation of batchlog delete mutation
service,db: extract get_batchlog_mutation_for() from storage-proxy
db/batchlog_manager: only consider propagation delay with tombstone-gc=repair
db/batchlog_manager: don't drop entire batch if one mutations' table was dropped
data_dictionary: table: add get_truncation_time()
db/batchlog_manager: batch(): replace map_reduce() with simple loop
db/batchlog_manager: finish coroutinizing replay_all_failed_batches
db/batchlog_manager: improve replayAllFailedBatches logs
When applying schema changes, the previous implementation attempted to
handle exceptions by catching and rethrowing them, but did so
incorrectly: using `throw ex` with a `std::exception_ptr` loses the
original exception type and details. The correct approach is to use
`std::rethrow_exception()`.
However, in this case, explicit exception handling is unnecessary. The
only reason for catching was to ensure `ap.destroy()` is called before
propagating the exception. This can be more cleanly and safely achieved
using Seastar's `.finally()` continuation, which guarantees cleanup
regardless of success or failure.
This change removes the manual try/catch/rethrow and uses `.finally()`
to ensure proper cleanup, letting exceptions propagate naturally and
preserving their type and information.
Fixes: SCYLLADB-94
Refs: scylladb/scylladb#27501
This reverts commit 8192f45e84.
The merge exposed a bug where truncate (via drop) fails and causes Raft
errors, leading to schema inconsistencies across nodes. This results in
test_table_drop_with_auto_snapshot failures with 'Keyspace test does not exist'
errors.
The specific problematic change was in commit 19b6207f which modified
truncate_table_on_all_shards to set use_sstable_identifier = true. This
causes exceptions during truncate that are not properly handled, leading
to Raft applier fiber stopping and nodes losing schema synchronization.
This reverts commit faad0167d7. It causes
a regression in
test_two_tablets_concurrent_repair_and_migration_repair_writer_level
in debug mode (with ~5%-10% probability).
Fixes#27510.
Closesscylladb/scylladb#27560
Fixes#26744
If a segment to replay is broken such that the main header is not zero,
but still broken, we throw header_checksum_error. This was not handled in
replayer, which grouped this into the "user error/fundamental problem"
category. However, assuming we allow for "real" disk corruption, this should
really be treated same as data corruption, i.e. reported data loss, not
failure to start up.
The `test_one_big_mutation_corrupted_on_startup` test accidentally sometimes
provoked this issue, by doing random file wrecking, which on rare occasions
provoked this, and thus failed test due to scylla not starting up, instead
of loosing data as expected.
Changed test to consistently cause this exact error instead.
With the introduction of rack-lists and the reliance of materialized views on them, the `get_view_natural_endpoint` function can be greatly simplified. When using tablets, instead of doing any index-matching, we can now pair base tables with views only in the same rack.
In this series we remove no longer needed code and reorganize the needed code for better clarity.
After the changes, the `get_view_natural_endpoint` function goes down from 245 lines to 85 lines, while the whole pairing-related text goes down from 346 lines to 239 lines.
Fixes https://github.com/scylladb/scylladb/issues/26313Closesscylladb/scylladb#27383
* github.com:scylladb/scylladb:
mv: replace the simple/complex rack-aware pairing with exact rack matching
mv: split out vnode pairing code from get_view_natural_endpoint
mv: unify self-pairing and rack-aware pairing into one bool
mv: remove the workaround for left nodes when sending view updates
This patch adds tablet repair progress report support so that the user
could use the /task_manager/task_status API to query the progress.
In order to support this, a new system table is introduced to record the
user request related info, i.e, start of the request and end of the
request.
The progress is accurate when tablet split or merge happens in the
middle of the request, since the tokens of the tablet are recorded when
the request is started and when repair of each tablet is finished. The
original tablet repair is considered as finished when the finished
ranges cover the original tablet token ranges.
After this patch, the /task_manager/task_status API will report correct
progress_total and progress_completed.
Fixes#22564Fixes#26896Closesscylladb/scylladb#26924
This change adds a new option to the REST api and correspondingly, to scylla nodetool: use_sstable_identifier.
When set, we use the sstable identifier, if available, to name each sstable in the snapshots directory
and the manifest.json file, rather than using the sstable generation.
This can be used by the user (e.g. Scylla Manager) for global deduplication with tablets, where an sstable
may be migrated across shards or across nodes, and in this case, its generation may change, but its
sstable identifier remains sstable.
Currently, Scylla manager uses the sstable generation to detect sstables that are already backed up to
object storage and exist in previous backed up snapshots.
Historically, the sstable generation was guaranteed to be unique only per table per node,
so the dedup code currently checks for deduplication in the node scope.
However, with tablet migration, sstables are renamed when migrated to a different shard,
i.e. their generation changes, and they may be renamed when migrated to another node,
but even if they are not, the dedup logic still assumes uniqueness only within a node.
To address both cases, we keep the sstable_id stable throughout the sstable life cycle (since 3a12ad96c7).
Given the globally unique sstable identifier, scylla manager can now detect duplicate sstables
in a wider scope. This can be cluster-wide, but we practically need only rack-wide deduplication
or dc-wide, as tablets are migrated across racks only in rare occasions (like when converting from a
numerical replication factor to a rack list containing a subset of the available racks in a datacenter).
Fixes#27181
* New feature, no backport required
Closesscylladb/scylladb#27184
* github.com:scylladb/scylladb:
database: truncate_table_on_all_shards: set use_sstable_identifier to true
nodetool: snapshot: add --use-sstable-identifier option
api: storage_service: take_snapshot: add use_sstable_identifier option
test: database_test: add snapshot_use_sstable_identifier_works
test: database_test: snapshot_works: add validate_manifest
sstable: write_scylla_metadata: add random_sstable_identifier error injection
table: snapshot_on_all_shards: take snapshot_options
sstable: add get_format getter
sstable: snapshot: add use_sstable_identifier option
db: snapshot_ctl: snapshot_options: add use_sstable_identifier options
db: snapshot_ctl: move skip_flush to struct snapshot_options
Large reserves in allocating_section can cause stalls. We already log
reserve increase, but we don't know which table it belongs to:
lsa - LSA allocation failure, increasing reserve in section 0x600009f94590 to 128 segments;
Allocating sections used for updating row cache on memtable flush are
notoriously problematic. Each table has its own row_cache, so its own
allocating_section(s). If we attached table name to those sections, we
could identify which table is causing problems. In some issues we
suspected system.raft, but we can't be sure.
This patch allows naming allocating_sections for the purpose of
identifying them in such log messages. I use abstract_formatter for
this purpose to avoid the cost of formatting strings on the hot path
(e.g. index_reader). And also to avoid duplicating strings which are
already stored elsewhere.
Fixes#25799Closesscylladb/scylladb#27470
Range tombstones are represented as entry attributes, which applies to
the interval between entries. So if a range tombstone covers many
rows, to apply it we have to update all covered entries. In some
workloads that could be many entries, even the whole cache. Before
the patch, we did this update without preemption, which can cause
reactor stalls in such workloads.
This scenario is already covered by mvcc_tests,
e.g. test_apply_to_incomplete_respects_continuity. And I verified that
the new preemption point is hit in the test.
perf-row-cache-update results show no significant stalls anymore (max
2ms scheduling delay, instead of previous 1.5 s):
Generated 1124195 rows
Memtable fill took 4179.457520 [ms], {count: 8295, 99%: 0.654949 [ms], max: 32.817176 [ms]}
Draining...
took 0.000616 [ms]
cache: 2506/2948 [MB], memtable: 781/1024 [MB], alloc/comp: 1051/662 [MB] (amp: 0.630)
update: 2874.157471 [ms], preemption: {count: 26650, 99%: 1.131752 [ms], max: 2.068762 [ms]}, cache: 3027/3973 [MB], alloc/comp: 3951/2424 [MB] (amp: 0.614), pr/me/dr 1124195/0/0
Fixes#23479Fixes#2578Closesscylladb/scylladb#27469
* github.com:scylladb/scylladb:
cache, mvcc: Preempt cache update when applying range tombstone from memtable
partition_snapshot_row_cursor: Clarify non-obvious semantic difference of range_tombstone()
perf-row-cache-update: Add scenario with large tombstone covering many rows
We switched to using v3 schema tables (in system_schema keyspace) in
2017, in 9eb91bc30b.
So no system should have the old schema any more.
No need to run legacy_schema_migrator on boot.
Closesscylladb/scylladb#27420
The code creates a local variable, so it's better to wrap it in a local
scope, to the conditionally compiled variable doesn't pollute the
external scope.
After scylladb/scylladb#26897 was merged, the worker doesn't use the
view building state machine CV to manage lifetime of batches, so the
broadcast is not needed.
In case of general exception in `view_building_worker::create_staging_sstable_tasks()`,
catch it, print it with error level and sleep 1s before retrying.
This will allow for the registrator to retry its work in case of failure
and it should be easier to detect any bugs in the method.
The PRUNE MATERALIZED VIEW statement is performed as follows:
1. Perform a range scan of the view table from the view replicas based
on the ranges specified in the statement.
2. While reading the paged scan above, for each view row perform a read
from all base replicas at the corresponding primary key. If a discrepancy
is detected, delete the row in the view table.
When reading multiple rows, this is very slow because for each view row
we need to performe a single row query on multiple replicas.
In this patch we add an option to speed this up by performing many of the
single base row reads concurrently, at the concurrency specified in the
USING CONCURRENCY clause.
Aside from the unit test, I checked manually on a 3-node cluster with 10M rows, using vnodes. There were actually no ghost rows in the test, but we still had to iterate over all view rows and read the corresponding base rows. And actual ghost rows, if there are any, should be a tiny fraction of all rows. I compared concurrencies 1,2,10,100 and the results were:
* Pruning with concurrency 1 took total 1416 seconds
* Pruning with concurrency 2 took total 731 seconds
* Pruning with concurrency 10 took total 234 seconds
* Pruning with concurrency 100 took total 171 seconds
So after a concurrency of 10 or so we're hitting diminishing returns (at least in this setup). At that point we may be no longer bottlenecked by the reads, but by CPU on the shard that's handling the PRUNE
Fixes https://github.com/scylladb/scylladb/issues/27070Closesscylladb/scylladb#27097
* github.com:scylladb/scylladb:
mv: allow setting concurrency in PRUNE MATERIALIZED VIEW
cql: add CONCURRENCY to the USING clause
To be used for naming sstables in the snapshot by their
sstable identifiers rather than their generation, to
facilitate global deduplication of sstables in backup.
Signed-off-by: Benny Halevy <bhalevy@scylladb.com>
This patch adds separate group for vector search parameters in the
documentation and fixes small typos and formatting.
Fixes: SCYLLADB-77.
Closesscylladb/scylladb#27385
Even though that `view_building_coordinator::work_on_view_building` has
an `if` at the very beginning which checks whether the currently
processed base table is set, it only prints a message and continues
executing the rest of the function regardless of the result of the
check. However, some of the logic in the function assumes that the
currently processed base table field is set and tries to access the
value of the field. This can lead to the view building coordinator
accessing a disengaged optional, which is undefined behavior.
Fix the function by adding the clearly missing `co_await` to the check.
A regression test is added which checks that the view building state
observer - a different fiber which used to print a weird message due to
erroneus view building coordinator behavior - does not print a warning.
Fixes: scylladb/scylladb#27363Closesscylladb/scylladb#27373
Now that batchlog cleanup is cheap, on account of memtable flush on the
system.batchlog table garbage-collecting tombstones (previous patch), we
can afford to do cleanup on each replay, keeping the memtable size small
and more importantly -- the amount of tombstones in the memtable small.
Although the value of this item is indeed derived from the write timeout
config, the name doesn't reflect what it is used for. Change it to
reflect it better.
New batchlogs are written to the batchlog_v2 table and replay also uses
the v2 table.
The content of system.batchlog is attempted to be migrated to
system.batchlog_v2 after each start of the batchlog_manager service.
The migration is retried on each replay if it fails. This is reduntant
but simple.
Batchlog cleanup now doesn't involve flushing memtables, the only
remaining user of replica/database.hh is gone, so the include is
dropped.
Rearranges the system.batchlog schema as follows:
CREATE TABLE system.batchlog_v2 (
version int,
stage int,
shard int,
written_at timestamp,
id uuid,
data blob,
PRIMARY KEY ((version, stage, shard), written_at, id));
With the following goals:
1) Make post-replay batchlog cleanup possible with a simple
range-tombstone. This allows dropping the individual dead batchlog
entries, as they are shadowed by a higher level tombstone. This
enables dropping tombstones without tombstone GC.
2) To make the above possible, introduce the stage key component:
batchlog entries that fail the first replay attempt, are moved to the
failed_replay stage, so the initial stage can be cleaned up safely.
3) Spread out the data among Scylla shards, via the batchlog shard
column.
4) Make batchlog entries ordered by the batchlog create time (id). This
allows for selecting batchlogs to replay, without post-filtering of
batchlogs that are too young to be replayed.
Don't build batchlog delete mutations in storage-proxy code. Move this
code into db/batchlog_manager.cc, exposed via db/batchlog.hh.
This serves multiple goals:
1) Concentrates low-level batchlog related logic in
db/batchlog_manager.cc
2) Reduce current and future code duplication.
3) Make future changes to this logic easier.
Don't build batchlog mutations in storage-proxy code. Move this code
into db/batchlog_manager.cc, exposed via db/batchlog.hh.
This serves multiple goals:
1) Concentrates low-level batchlog related logic in
db/batchlog_manager.cc
2) Reduce current and future code duplication.
2) Make future changes to this logic easier.
Just skip the mutation(s) whose tables were dropped instead.
Use the newly introduced data_dictionary::table::get_truncation_time()
to avoid looking up real table object.
The map_reduce achieves no concurrency, both map and reduce are
synchronous. It only achieves two redundant lookups for the table and
hard-to-read code. Convert it into a simple loop. Preserve the
stall-protection by adding a maybe_yield() to the loop.
