Currently, we determine the live vs. total snapshot size by listing all files in the snapshot directory,
and for each name, look it up in the base table directory and see if it exists there, and if so, if it's the same file
as in the snapshot by looking to the fstat data for the dev id and inode number.
However, we do not look the names in the staging directory so staging sstable
would skew the results as the will falsely contribute to the live size, since they
wouldn't be found in the base directory.
This change processes both the staging directory and base table directory
and keeps the file capacity in a map, indexed by the files inode number, allowing us to easily
detect hard links and be resilient against concurrent move of files from the staging sub-directory
back into the base table directory.
Fixes#27635
* Minor issue, no backport required
Closesscylladb/scylladb#27636
* github.com:scylladb/scylladb:
table: get_snapshot_details: add FIXME comments
table: get_snapshot_details: lookup entries also in the staging directory
table: get_snapshot_details: optimize using the entry number_of_links
table: get_snapshot_details: continue loop for manifest and schema entries
table: get_snapshot_details: use directory_lister
Ref https://github.com/scylladb/seastar/pull/3163
We can optimize the stat calls we use here by
using open_directory to open the snapshot,
base, and staging directory once, and using statat
calls for the relative name instead of the full
blown file_stat that needs to traverse the whole
path prefix for every call (the dirents are likely
to be cached, but still why waste cpu cycles on that
over and over again).
Signed-off-by: Benny Halevy <bhalevy@scylladb.com>
If the number_of_linkes equals 1, we can be sure that
the file exists only in the snapshot directory so there is no need
to look it up in the data directory.
Signed-off-by: Benny Halevy <bhalevy@scylladb.com>
Now that we're using a simple loop in the coroutine just continue
the loop for files we want to ignore.
Signed-off-by: Benny Halevy <bhalevy@scylladb.com>
It is more efficient to use the coroutine generator
to list the directory.
Brewing changes in seastar would make the generator buffered
as well as adding an extended generation that would
return the file stat data for each entry, that would become
useful in the next patch that optimizes the algorithm by
considering the entry's link count.
Signed-off-by: Benny Halevy <bhalevy@scylladb.com>
Currently, we first print the json contents into a stringstream buffer
and then we write it as a whole to the manifest.json file output stream.
This is not scalable and may cause large allocation for large enough number
of files.
Fixes#24216
Signed-off-by: Benny Halevy <bhalevy@scylladb.com>
Closesscylladb/scylladb#27542
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
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.
Can potentially lead to unnecessary abort.
compaction_groups() and for_each_compaction_group() can throw.
Co-authored-by: bhalevy <20910904+bhalevy@users.noreply.github.com>
The distributed_loader::get_sstables_from_object_store() method accepts an endpoint parameter and internally wants to get storage type for that endpoint (s3 or gcs). This is needed to construct storage_options object to create an sstable object.
To get the type, the method scans db::config option, but there's much simpler way to get one.
Code cleanup, no need to backport
Closesscylladb/scylladb#27381
* github.com:scylladb/scylladb:
sstables_loader: Provide endpoint type for get_sstables_from_object_store()
storage_manager: Introduce get_endpoint_type() method
storage_manager: Split get_endpoint_client()
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
We store the per-shard chunk count in a uint64_t vector
global_offset, and then convert the counts to offsets with
a prefix sum:
```c++
// [1, 2, 3, 0] --> [0, 1, 3, 6]
std::exclusive_scan(global_offset.begin(), global_offset.end(), global_offset.begin(), 0, std::plus());
```
However, std::exclusive_scan takes the accumulator type from the
initial value, 0, which is an int, instead of from the range being
iterated, which is of uint64_t.
As a result, the prefix sum is computed as a 32-bit integer value. If
it exceeds 0x8000'0000, it becomes negative. It is then extended to
64 bits and stored. The result is a huge 64-bit number. Later on
we try to find an sstable with this chunk and fail, crashing on
an assertion.
An example of the failure can be seen here: https://godbolt.org/z/6M8aEbo57
The fix is simple: the initial value is passed as uint64_t instead of int.
Fixes https://github.com/scylladb/scylladb/issues/27417Closesscylladb/scylladb#27418
SELECT * FROM MUTATION_FRAGMENTS() queries have a transformed schema
(mutation-fragment schema), which is a superset of that of the queried
table's. The mutation fragment schema represents position_in_partition
of mutation fragments expressed as clustering columns. This presents
some challenges, as some position_in_partition fields are null for some
positions. This was solved by setting these clustering keys components
to bytes{}. In the process, a mistake was made: when the clustering key
is missing in the position_in_partition, the position_weight is also set
to bytes{}. This is not correct, it is possible for some positions to
have no key but to still have a position_weight. An example is
position_in_partition::before_all_clustered_rows().
Fix this by always filling in the position_weight for positions which
have region() == clustered, instead of the earlier condition on the key
presence.
This is a minor bug affecting range tombstone changes at the two
extremes: position_in_partition::{before,after}_all_clustered_rows(). In
both cases, the position_weight can be deduced by a human looking at the
results, based on the position of the range tombstone change, relative
to other fragments.
Currently the method scans db::config to find one. It has some
drawbacks. First, it's not very nice. Second, it needs to handle the
case when the endpoint is missing, while it relally never is. Third, the
type in config entry is not necessarily set.
It's nicer to get the type from storage manager.
Signed-off-by: Pavel Emelyanov <xemul@scylladb.com>
This PR adds support for limiting the maximum shares allocated to a
compaction scheduling class by the compaction controller. It introduces
a new configuration parameter, compaction_max_shares, which, when set
to a non zero value, will cap the shares allocated to compaction jobs.
This PR also exposes the shares computed by the compaction controller
via metrics, for observability purposes.
Fixes https://github.com/scylladb/scylladb/issues/9431
Enhancement. No need to backport.
NOTE: Replaces PR https://github.com/scylladb/scylladb/pull/26696
Ran a test in which the backlog raised the need for max shares (normalized backlog above normalization_factor), and played with different values for new option compaction_max_shares to see it works (500, 1000, 2000, 250, 50)
Closesscylladb/scylladb#27024
* github.com:scylladb/scylladb:
db/config: introduce new config parameter `compaction_max_shares`
compaction_manager:config: introduce max_shares
compaction_controller: add configurable maximum shares
compaction_controller: introduce `set_max_shares()`
Add a method to dynamically adjust the maximum output of control points
in the compaction controller. This is required for supporting runtime
configuration of the maximum shares allocated to the compaction process
by the controller.
Signed-off-by: Lakshmi Narayanan Sreethar <lakshmi.sreethar@scylladb.com>
Signed-off-by: Raphael S. Carvalho <raphaelsc@scylladb.com>
Add precompiled header support to CMakeLists.txt and configure.py -
it improves compilation time by approximately 10%.
New header `stdafx.hh` is added, don't include it manually -
the compiler will include it for you. The header contains includes from
external libraries used by Scylla - seastar, standard library,
linux headers and zlib.
The feature is enabled by default, use CMake option `Scylla_USE_PRECOMPILED_HEADER`
or configure.py --disable-precompiled-header to disable.
The feature should be disabled, when trying to check headers - otherwise
you might get false negatives on missing includes from seastar / abseil and so on.
Note: following configuration needs to be added to ccache.conf:
sloppiness = pch_defines,time_macros,include_file_mtime,include_file_ctime
Closesscylladb/scylladb#26617
Currently sstables_manager keeps a reference on global db::config to configure itself. Most of other services use their own specific configs with much less data on-board for the same purposes (e.g. #24841, #19051 and #23705 did same for other services) This PR applies this approach to sstables_manager as well.
Mostly it moves various values from db::config onto newly introduced struct sstables_manager::config, but it also adds specific tracking of sstable_file_io_extensions and patches tools/scylla-sstable not to use sstables_manager as "proxy" object to get db::config from along its calls.
Shuffling components dependencies, no need to backport
Closesscylladb/scylladb#27021
* github.com:scylladb/scylladb:
sstables_manager: Drop db::config from sstables_manager
tools/sstable: Make shard_of_with_tablets use db::config argument
tools/sstable: Add db::config& to all operations
tools/sstable: Get endpoints from storage manager
sstables_manager: Hold sstable IO extensions on it
sstables: Manager helper to grab file io extensions
sstables_manager: Move default format on config
sstables_manager: Move enable_sstable_data_integrity_check on config
sstables_manager: Move data_file_directories on config
sstables_manager: Move components_memory_reclaim_threshold on config
sstables_manager: Move column_index_auto_scale_threshold on config
sstables_manager: Move column_index_size on config
sstables_manager: Move sstable_summary_ratio on config
sstables_manager: Move enable_sstable_key_validation on config
sstables_manager: Move available_memory on config
code: Introduce sstables_manager::config
sstables: Patch get_local_directories() to work on vector of paths
code: Rename sstables_manager::config() into db_config()
Consider the following:
1) single-key read starts, blocks on replica e.g. waiting for memory.
2) the same replica is migrated away
3) single-key read expires, coordinator abandons it, releases erm.
4) migration advances to cleanup stage, barrier doesn't wait on
timed-out read
5) compaction group of the replica is deallocated on cleanup
6) that single-key resumes, but doesn't find sstable set (post cleanup)
7) with abort-on-internal-error turned on, node crashes
It's fine for abandoned (= timed out) reads to fail, since the
coordinator is gone.
For active reads (non timed out), the barrier will wait for them
since their coordinator holds erm.
This solution consists of failing reads which underlying tablet
replica has been cleaned up, by just converting internal error
to plain exception.
Fixes#26229.
Signed-off-by: Raphael S. Carvalho <raphaelsc@scylladb.com>
Closesscylladb/scylladb#27078
This patch adds a metric for pre-compression size of sstable files.
This patch adds a per-table metric
`scylla_column_family_total_disk_space_before_compression`,
which measures the hypothetical total size of sstables on disk,
if Data.db was replaced with an uncompressed equivalent.
As for the implementation:
Before the patch, tables and sstable sets are already tracking their total physical file size.
Whenever sstables are added or removed, the size delta is propagated from the sstable up through sstable sets into table_stats.
To implement the new metric, we turn the size delta that is getting passed around from a one-dimensional to a two-dimensional value, which includes both the physical and the pre-compression size.
New functionality, no backport needed.
Closesscylladb/scylladb#26996
* github.com:scylladb/scylladb:
replica/table: add a metric for hypothetical total file size without compression
replica/table: keep track of total pre-compression file size
Currently manager holds a reference on db::config and when sstables IO
extensions are needed it grabs them from this config. Since db::config
is going to be removed from sstables manager, it should either keep
track of all config extensions, or only those that it needs. This patch
makes the latter choice and keeps reference to sstable_file_io_ext. on
manager. The reference is passed as constructor argument, not via
manager config, but it's a random choice, no specific reason why not
putting it on config itself.
Signed-off-by: Pavel Emelyanov <xemul@scylladb.com>
It's explicitly `me` type by default, but places that can write sstables
override it with db::config value: replica::database, tests and scylla
sstable tool.
Live-updateable, so use updateable_value<> type.
Signed-off-by: Pavel Emelyanov <xemul@scylladb.com>
Set its default value to the one from db/config.cc. Only
replica::database may want to re-configure it. Also not live-updateable.
Signed-off-by: Pavel Emelyanov <xemul@scylladb.com>
Set its default value to the one from db/config.cc. Only the
replica::database and tests may want to re-configure it.
This one is live-updateable, so use updateable_value<> type.
Signed-off-by: Pavel Emelyanov <xemul@scylladb.com>
This PR enables integrity check of both checksum and digest for repair/streaming.
In the past, streaming readers only verified the checksum of compressed SSTables.
This change extends the checks to include the digest and the checksum (CRC) for both compressed and uncompressed SSTables. These additional checks require reading the digest and CRC components from disk, which may cause some I/O overhead. For uncompressed SSTables, this involves loading and computing checksums and digest from the data, while for compressed SSTables - where checksums are already verified inline - the only extra cost is reading and verifying the digest.If the reader range doesn't cover the full SSTable, the digest is not loaded and check is skipped.
To support testing of these changes, a new option was added to the random_mutation_generator that allows disabling compression.
Several new test cases were added to verify that the repair_reader correctly detects corruption. These tests corrupt digest or data component of an SSTable and confirm that the system throws the expected `malformed_sstable_exception`.
Backport is not required, it is an improvement
Refs #21776Closesscylladb/scylladb#26444
* github.com:scylladb/scylladb:
boost/repair_test: add repair reader integrity verification test cases
test/lib: allow to disable compression in random_mutation_generator
sstables: Skip checksum and digest reads for unlinked SSTables
table: enable integrity checks for streaming reader
table: Add integrity option to table::make_sstable_reader()
sstables: Add integrity option to create_single_key_sstable_reader
Set its default value to the one from db/config.cc. Only the
replica::database may want to re-configure it.
This one is live-updateable, so use updateable_value<> type.
Signed-off-by: Pavel Emelyanov <xemul@scylladb.com>
Set its default value to the one from db/config.cc. Only
replica::database may want to re-configure it. Also not live-updateable.
Signed-off-by: Pavel Emelyanov <xemul@scylladb.com>
Set its default value to the one from db/config.cc. Only
replica::database may want to re-configure it. Also not live-updateable.
Signed-off-by: Pavel Emelyanov <xemul@scylladb.com>
Make it OFF by default and update only those callers, that may have it
ON -- the replica::database, tests and scylla-sstable tool.
Also not live-updateable, so plain bool.
Signed-off-by: Pavel Emelyanov <xemul@scylladb.com>
Currently, this parameter is passed to sstables_manager as explicit
constructor argument.
Also, it's not live-updateable, so a plain size_t type for it.
Signed-off-by: Pavel Emelyanov <xemul@scylladb.com>
This is specific configuration for sstables_manager. All places that
construct sstables manager are updated to provide config to it. For now
the config is empty and exists alongside with db::config. Further
patches will populate the former config with data and the latter config
will be eventually removed.
Signed-off-by: Pavel Emelyanov <xemul@scylladb.com>
This patch adds a per-table metric
`scylla_column_family_total_disk_space_before_compression`,
which measures the hypothetical total size of sstables on disk,
if Data.db was replaced with an uncompressed equivalent.
Every table and sstable set keeps track of the total file size
of contained sstables.
Due to a feature request, we also want to keep track of the hypothetical
file size if Data files were uncompressed, to add a metric that
shows the compression ratio of sstables.
We achieve this by replacing the relevant `uint_64 bytes_on_disk`
counters everywhere with a struct that contains both the actual
(post-compression) size and the hypothetical pre-compression size.
This patch isn't supposed to change any observable behavior.
In the next patch, we will use these changes to add a new metric.
When applying a counter mutation, use apply_on_shards to apply the
mutation on all write shards, similarly to the way other mutations are
applied in the storage proxy. Previously the mutation was applied only
on the current shard which is the read shard.
This is needed to respect the write_both stages of intranode migration
where we need to apply the mutation on both the old and the new shards.
Refactor the counter update to split the functions and have them called
by the storage proxy to prepare for a later change.
Previously in mutate_counter the storage proxy calls the replica
function apply_counter_update that does a few things:
1. checks that the operation can be done: check timeout, disk utilization
2. acquire counter locks
3. do read-modify-write and transform the counter mutation
4. apply the mutation in the replica
In this commit we change it so that these functions are split and called
from the storage proxy, so that we have better control from the storage
proxy when we change it later to work across multiple shards. For
example, we will want to acquire locks on multiple shards, transform it
on one shard, and then apply the mutation on multiple shards.
After the change it works as follows in storage proxy:
1. acquire counter locks
2. call replica prepare to check the operation and transform the mutation
3. call replica apply to apply the transformed mutation
Add a RAII guard for counter update that holds the counter locks and the
table operation, and extract the creation of the guard to a separate
function.
This prepares it for a later change where we will want to obtain the
guard externally from the storage proxy.
The compaction manager backlog is exposed via metrics, but if static
shares are set, the backlog is never calculated. As a result, there is
no way to determine the backlog and if the static shares need
adjustment. Fix that by calculating backlog even when static shares are
set.
Fixes#26287
Signed-off-by: Lakshmi Narayanan Sreethar <lakshmi.sreethar@scylladb.com>
Closesscylladb/scylladb#26778
This change adds the ability to move tablets sizes in load_stats after a tablet migration or table resize (split/merge). This is needed because the size based load balancer needs to have tablet size data which is as accurate as possible, in order to work on fresh tablet size distribution and issue correct tablet migrations.
This is the second part of the size based load balancing changes:
- First part for tablet size collection via load_stats: #26035
- Second part reconcile load_stats: #26152
- The third part for load_sketch changes: #26153
- The fourth part which performs tablet load balancing based on tablet size: #26254
This is a new feature and backport is not needed.
Closesscylladb/scylladb#26152
* github.com:scylladb/scylladb:
load_balancer: load_stats reconcile after tablet migration and table resize
load_stats: change data structure which contains tablet sizes
