Commit Graph

716 Commits

Author SHA1 Message Date
Aliaksandr Valialkin
443661a5da
lib/storage: properly free up resources from newTestStorage() by calling stopTestStorage() 2023-07-13 17:13:24 -07:00
Aliaksandr Valialkin
7094fa38bc
lib/storage: switch from global to per-day index for MetricName -> TSID mapping
Previously all the newly ingested time series were registered in global `MetricName -> TSID` index.
This index was used during data ingestion for locating the TSID (internal series id)
for the given canonical metric name (the canonical metric name consists of metric name plus all its labels sorted by label names).

The `MetricName -> TSID` index is stored on disk in order to make sure that the data
isn't lost on VictoriaMetrics restart or unclean shutdown.

The lookup in this index is relatively slow, since VictoriaMetrics needs to read the corresponding
data block from disk, unpack it, put the unpacked block into `indexdb/dataBlocks` cache,
and then search for the given `MetricName -> TSID` entry there. So VictoriaMetrics
uses in-memory cache for speeding up the lookup for active time series.
This cache is named `storage/tsid`. If this cache capacity is enough for all the currently ingested
active time series, then VictoriaMetrics works fast, since it doesn't need to read the data from disk.

VictoriaMetrics starts reading data from `MetricName -> TSID` on-disk index in the following cases:

- If `storage/tsid` cache capacity isn't enough for active time series.
  Then just increase available memory for VictoriaMetrics or reduce the number of active time series
  ingested into VictoriaMetrics.

- If new time series is ingested into VictoriaMetrics. In this case it cannot find
  the needed entry in the `storage/tsid` cache, so it needs to consult on-disk `MetricName -> TSID` index,
  since it doesn't know that the index has no the corresponding entry too.
  This is a typical event under high churn rate, when old time series are constantly substituted
  with new time series.

Reading the data from `MetricName -> TSID` index is slow, so inserts, which lead to reading this index,
are counted as slow inserts, and they can be monitored via `vm_slow_row_inserts_total` metric exposed by VictoriaMetrics.

Prior to this commit the `MetricName -> TSID` index was global, e.g. it contained entries sorted by `MetricName`
for all the time series ever ingested into VictoriaMetrics during the configured -retentionPeriod.
This index can become very large under high churn rate and long retention. VictoriaMetrics
caches data from this index in `indexdb/dataBlocks` in-memory cache for speeding up index lookups.
The `indexdb/dataBlocks` cache may occupy significant share of available memory for storing
recently accessed blocks at `MetricName -> TSID` index when searching for newly ingested time series.

This commit switches from global `MetricName -> TSID` index to per-day index. This allows significantly
reducing the amounts of data, which needs to be cached in `indexdb/dataBlocks`, since now VictoriaMetrics
consults only the index for the current day when new time series is ingested into it.

The downside of this change is increased indexdb size on disk for workloads without high churn rate,
e.g. with static time series, which do no change over time, since now VictoriaMetrics needs to store
identical `MetricName -> TSID` entries for static time series for every day.

This change removes an optimization for reducing CPU and disk IO spikes at indexdb rotation,
since it didn't work correctly - see https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1401 .

At the same time the change fixes the issue, which could result in lost access to time series,
which stop receving new samples during the first hour after indexdb rotation - see https://github.com/VictoriaMetrics/VictoriaMetrics/issues/2698

The issue with the increased CPU and disk IO usage during indexdb rotation will be addressed
in a separate commit according to https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1401#issuecomment-1553488685

This is a follow-up for 1f28b46ae9
2023-07-13 16:07:30 -07:00
Aliaksandr Valialkin
3b50b94f7a
lib/storage: fix possible test failure in TestStorageAddRowsConcurrent
The number of parts in the snapshot partition may be zero if concurrent goroutine just
started creating new partition, but didn't put data into it yet when the current
goroutine made a snapshot.
2023-07-13 15:03:45 -07:00
Aliaksandr Valialkin
152ca00fb8
docs/CHANGELOG.md: clarify description for https://github.com/VictoriaMetrics/VictoriaMetrics/issues/4336 bugfix
This is a follow-up for 5eb5df96e2
2023-07-06 17:09:03 -07:00
Aliaksandr Valialkin
aeac39cfd1
lib/storage: do not create flock.lock files at partition directories, since it is created at the Storage level 2023-06-19 22:48:37 -07:00
Nikolay
5eb5df96e2
lib/storage: creates parts.json on start-up if it not exists. (#4450)
* lib/storage: creates parts.json on start-up if it not exists.
It fixes migrations from versions below v1.90.0.
Previously parts.json was created only after successful merge.
But if merge was interruped for some reason (OOM or shutdown), parts.json wasn't created and partitions left after interruped merge weren't properly deleted.
Since VM cannot check if it must be removed or not.
https://github.com/VictoriaMetrics/VictoriaMetrics/issues/4336

* Apply suggestions from code review

Co-authored-by: Roman Khavronenko <roman@victoriametrics.com>

* Update lib/storage/partition.go

Co-authored-by: Roman Khavronenko <roman@victoriametrics.com>

---------

Co-authored-by: Roman Khavronenko <roman@victoriametrics.com>
2023-06-15 11:19:22 +02:00
Roman Khavronenko
f50f35a8e0
lib/storage: add comment for how mustBeDeleted field should be used (#4454)
Signed-off-by: hagen1778 <roman@victoriametrics.com>
2023-06-15 11:17:45 +02:00
Aliaksandr Valialkin
1f28b46ae9
lib/storage: revert the migration from global to per-day index for (MetricName -> TSID)
This reverts the following commits:
- e0e16a2d36
- 2ce02a7fe6

The reason for revert: the updated logic breaks assumptions made
when fixing https://github.com/VictoriaMetrics/VictoriaMetrics/issues/2698 .
For example, if a time series stop receiving new samples during the first
day after the indexdb rotation, there are chances that the time series
won't be registered in the new indexdb. This is OK until the next indexdb
rotation, since the time series is registered in the previous indexdb,
so it can be found during queries. But the time series will become invisible
for search after the next indexdb rotation, while its data is still there.

There is also incompletely solved issue with the increased CPU and disk IO resource
usage just after the indexdb rotation. There was an attempt to fix it, but it didn't fix
it in full, while introducing the issue mentioned above. See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1401

TODO: to find out the solution, which simultaneously solves the following issues:
- increased memory usage for setups high churn rate and long retention (e.g. what the reverted commit does)
- increased CPU and disk IO usage during indexdb rotation ( https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1401 )
- https://github.com/VictoriaMetrics/VictoriaMetrics/issues/2698

Possible solution - to create the new indexdb in one hour before the indexdb rotation
and to gradually pre-populate it with the needed index data during the last hour before indexdb rotation.
Then the new indexdb will contain all the needed data just after the rotation,
so it won't trigger increased CPU and disk IO.
2023-05-18 11:30:49 -07:00
Haleygo
1531d757ea fix lint check 2023-05-17 13:51:36 +02:00
Aliaksandr Valialkin
e0e16a2d36
lib/storage: follow-up after 2ce02a7fe6
- Document the change at docs/CHANGELOG.md
- Clarify comments for non-trivial code touched by the commit
- Improve the logic behind maybeCreateIndexes():
  - Correctly create per-day indexes if the indexdb rotation is performed during
    the first hour or the last hour of the day by UTC.
    Previously there was a possibility of missing index entries on that day.
  - Increase the duration for creating new indexes in the current indexdb for up to 22 hours
    after indexdb rotation. This should reduce the increased resource usage
    after indexdb rotation.
    It is safe to postpone index creation for the current day until the last hour
    of the current day after indexdb rotation by UTC, since the corresponding (date, ...)
    entries exist in the previous indexdb.
- Search for TSID by (date, MetricName) in both the current and the previous indexdb.
  Previously the search was performed only in the current indexdb. This could lead
  to excess creation of per-day indexes for the current day just after indexdb rotation.
- Search for (date, metricID) entries in both the current and the previous indexdb.
  Previously the search was performed only in the current indexdb. This could lead
  to excess creation of per-day indexes for the current day just after indexdb rotation.
2023-05-16 23:19:27 -07:00
Roman Khavronenko
2ce02a7fe6
lib/storage: introduce per-day MetricName=>TSID index (#4252)
The new index substitutes global MetricName=>TSID index
used for locating TSIDs on ingestion path.
For installations with high ingestion and churn rate, global
MetricName=>TSID index can grow enormously making
index lookups too expensive. This also results into bigger
than expected cache growth for indexdb blocks.

New per-day index supposed to be much smaller and more efficient.
This should improve ingestion speed and reliability during
re-routings in cluster.

The negative outcome could be occupied disk size, since
per-day index is more expensive comparing to global index.

Signed-off-by: hagen1778 <roman@victoriametrics.com>
2023-05-16 15:46:42 -07:00
Aliaksandr Valialkin
278278af95
lib/storage: reduce the unimportant logging during Storage start / stop
This should improve the visibility of potentially important logs
2023-05-16 15:14:21 -07:00
Aliaksandr Valialkin
09b403d38a
lib/{mergeset,storage}: make it clear that DebugFlush() doesn't store all the recently ingested data to disk
DebugFlush() makes sure that the recently ingested data becomes visible to search.

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/4272
2023-05-16 11:50:17 -07:00
Zakhar Bessarab
242050ba94
lib/storage: follow-up after a50d63c376 (#4289)
* lib/storage: follow-up after a50d63c376

- ensure retentionMsecs is rounded to day
- remove localTimeOffset in test as localOffset is ignored when using `UnixMilli`

Signed-off-by: Zakhar Bessarab <z.bessarab@victoriametrics.com>

* lib/storage: restore retention timezone offset effect on retention deadline

Signed-off-by: Zakhar Bessarab <z.bessarab@victoriametrics.com>

---------

Signed-off-by: Zakhar Bessarab <z.bessarab@victoriametrics.com>
2023-05-16 17:14:08 +02:00
Nikolay
8f4de6fa47
lib/storage: properly update link for entry at dateMetricID cache (#4258)
previously during sync for mutable and immutable cache parts, link for hotEntry with current date may be not properly updated
it corrupts cache for backfilling metrics and increased cpu load
2023-05-05 21:45:47 -07:00
Zakhar Bessarab
aca256735c
lib/storage: fix indexdb rotation infinite loop (#4249)
When using `retentionTimezoneOffset` and having local timezone being more than 4 hours different from UTC indexdb retention calculation could return negative value. This caused indexdb rotation to get in loop.
Fix calculation of offset to use `retentionTimezoneOffset` value properly and add test to cover all legit timezone configs.
See:
- https://github.com/VictoriaMetrics/VictoriaMetrics/issues/4207
- https://github.com/VictoriaMetrics/VictoriaMetrics/pull/4206

Signed-off-by: Zakhar Bessarab <z.bessarab@victoriametrics.com>
Co-authored-by: Nikolay <nik@victoriametrics.com>
2023-05-04 17:16:48 +02:00
Aliaksandr Valialkin
2a4c48c59d
lib/{mergeset,storage}: make mustReadPartNames() code more clear 2023-04-14 23:16:59 -07:00
Aliaksandr Valialkin
52006149b2
lib/storage: replace OpenStorage() with MustOpenStorage()
Callers of OpenStorage() log the returned error and exit.
The error logging and exit can be performed inside MustOpenStorage()
alongside with printing the stack trace for better debuggability.
This simplifies the code at caller side.
2023-04-14 23:02:40 -07:00
Aliaksandr Valialkin
2a2036160d
lib/storage: fix a bug, which prevents from reading pre-v1.90.0 parts
The bug has been introduced in c0b852d50d
2023-04-14 22:33:08 -07:00
Aliaksandr Valialkin
3727251910
lib/fs: add MustReadDir() function
Use fs.MustReadDir() instead of os.ReadDir() across the code in order to reduce the code verbosity.
The fs.MustReadDir() logs the error with the directory name and the call stack on error
before exit. This information should be enough for debugging the cause of the error.
2023-04-14 22:10:46 -07:00
Aliaksandr Valialkin
60d92894c5
lib/storage: validate rows in partition.AddRows() only during tests 2023-04-14 20:52:36 -07:00
Aliaksandr Valialkin
df619bdff0
all: consistently use fs.MustClose() for closing lock files 2023-04-14 20:14:21 -07:00
Aliaksandr Valialkin
2a3b19e1d2
lib/fs: convert CreateFlockFile to MustCreateFlockFile
Callers of CreateFlockFile log the returned err and exit.
It is better to log the error inside the MustCreateFlockFile together with the path
to the specified directory and the call stack. This simplifies
the code at the callers' side while leaving the debuggability at the same level.
2023-04-14 19:50:01 -07:00
Aliaksandr Valialkin
c0b852d50d
lib/{storage,mergeset}: convert InitFromFilePart to MustInitFromFilePart
Callers of InitFromFilePart log the error and exit.
It is better to log the error with the path to the part and the call stack
directly inside the MustInitFromFilePart() function.
This simplifies the code at callers' side while leaving the same level of debuggability.
2023-04-14 15:46:12 -07:00
Aliaksandr Valialkin
9183a439c7
lib/filestream: change Create() to MustCreate()
Callers of this function log the returned error and exit.
It is better logging the error together with the path to the filename
and call stack directly inside the function. This simplifies
the code at callers' side without reducing the level of debuggability
2023-04-14 15:12:48 -07:00
Aliaksandr Valialkin
5eb163a08a
lib/filestream: transform Open() -> MustOpen()
Callers of this function log the returned error and exit.
Let's log the error with the path to the filename and call stack
inside the function. This simplifies the code at callers' side
without reducing the level of debuggability.
2023-04-14 15:03:42 -07:00
Aliaksandr Valialkin
f341b7b3f8
lib/fs: substitute ReadFullData with MustReadData
Callers of ReadFullData() log the error and then exit.
So let's log the error with the path to the filename and the call stack
inside MustReadData(). This simplifies the code at callers' side,
while leaving the debuggability at the same level.
2023-04-14 14:39:29 -07:00
Aliaksandr Valialkin
bd6de6406a
lib/fs: improve error logging inside MustWriteData
Log the path to file on errors inside MustWriteData().
This improves debuggability of errors, which may occur inside MustWriteData().
2023-04-14 14:32:45 -07:00
Aliaksandr Valialkin
e0595af2bf
lib/{mergeset,storage}: remove isInMerge flag from parts only when they werent removed yet from the list of active parts
This prevents from possible panic during access to pw.p when it is set to nil at partWrapper.decRef() called inside swapSrcWithDstParts()
2023-04-14 00:08:11 -07:00
Aliaksandr Valialkin
9f8209d593
docs/CHANGELOG.md: run at least 4 background mergers on systems with less than 4 CPU cores
This reduces the probability of sudden spike in the number of small parts when all the background mergers
are busy with big merges.
2023-04-13 23:43:17 -07:00
Aliaksandr Valialkin
550d5c7ea4
lib/{mergeset,storage}: make sure that getFlushToDiskDeadline() takes into account only in-memory parts 2023-04-13 23:43:17 -07:00
Aliaksandr Valialkin
809fbaeaac
lib/fs: add Must prefix to CopyDirectory and CopyFile functions
Callers of these functions log the returned error and then exit.
Let's log the error with the call stack inside the function itself.
This simplifies the code at callers' side, while leaving the same
level of debuggability in case of errors.
2023-04-13 23:02:59 -07:00
Aliaksandr Valialkin
780abc3b3b
lib/fs: rename SymlinkRelative to MustSymlinkRelative
Callers of this function log the returned error and then exit.
Let's log the error with the call stack inside the function itself.
This simplifies the code at callers' side, while leaving the same
level of debuggability in case of errors.
2023-04-13 22:52:55 -07:00
Aliaksandr Valialkin
5f487ed996
lib/fs: rename HardLinkFiles to MustHardLinkFiles
Callers of this function log the returned error and then exit.
Let's log the error with the call stack inside the function itself.
This simplifies the code at callers' side, while leaving the same
level of debuggability in case of errors.
2023-04-13 22:48:07 -07:00
Aliaksandr Valialkin
30425ca81a
lib/fs: rename WriteFileAtomically to MustWriteAtomic
Callers of this function log the returned error and exit.
So let's just log the error with the given filepath and the call stack
inside the function itself and then exit. This simplifies the code
at callers' place while leaves the same level of debuggability in case of errors.
2023-04-13 22:41:15 -07:00
Aliaksandr Valialkin
036a7b7365
lib/fs: replace MkdirAllIfNotExist->MustMkdirIfNotExist and MkdirAllFailIfExist->MustMkdirFailIfExist
Callers of these functions log the returned error and then exit. The returned error already contains the path
to directory, which was failed to be created. So let's just log the error together with the call stack
inside these functions. This leaves the debuggability of the returned error at the same level
while allows simplifying the code at callers' side.

While at it, properly use MustMkdirFailIfExist instead of MustMkdirIfNotExist inside inmemoryPart.MustStoreToDisk().
It is expected that the inmemoryPart.MustStoreToDick() must fail if there is already a directory under the given path.
2023-04-13 22:11:59 -07:00
Aliaksandr Valialkin
344209e5e6
lib/fs: rename MustWriteFileAndSync to MustWriteSync in order to improve readability a bit
This is a follow-up for 2a8395be05
2023-04-13 21:43:32 -07:00
Aliaksandr Valialkin
b15c5961ab
lib/{mergeset,storage}: remove unused path field from blockStreamWriter
This is a follow-up after 42bba64aa7
2023-04-13 21:39:59 -07:00
Aliaksandr Valialkin
2a8395be05
lib/fs: replace WriteFileAndSync with MustWriteAndSync
When WriteFileAndSync fails, then the caller eventually logs the error message
and exits. The error message returned by WriteFileAndSync already contains the path
to the file, which couldn't be created. This information alongside the call stack
is enough for debugging the issue. So just use log.Panicf("FATAL: ...") inside MustWriteAndSync().
This simplifies error handling at caller side a bit.
2023-04-13 21:33:19 -07:00
Aliaksandr Valialkin
25f089de9d
lib/{mergeset,storage}: properly fsync part directory listing after writing in-memory part to disk
This is a follow-up after 42bba64aa7

Previously the part directory listing was fsync'ed implicitly inside partHeader.WriteMetadata()
by calling fs.WriteFileAtomically(). Now it must be fsync'ed explicitly.

There is no need in fsync'ing the parent directory, since it is fsync'ed by the caller
when updating parts.json file.
2023-04-13 21:19:04 -07:00
Aliaksandr Valialkin
42bba64aa7
lib/{mergeset,storage}: explicitly fsync the created part directory listing
Previously the created part directory listing was fsynced implicitly
when storing metadata.json file in it.

Also remove superflouous fsync for part directory listing,
which was called at blockStreamWriter.MustClose().
After that the metadata.json file is created, so an additional fsync
for the directory contents is needed.
2023-04-13 21:03:08 -07:00
Aliaksandr Valialkin
e1211a1187
app/vmstorage: deprecate -bigMergeConcurrency command-line flag
Improperly configured -bigMergeConcurrency command-line flag usually leads to uncontrolled
growth of unmerged parts, which, in turn, increases CPU usage and query durations.

So it is better deprecating this flag. In rare cases -smallMergeConcurrency command-line flag
can be used instead for controlling the concurrency of background merges.
2023-04-13 20:40:24 -07:00
Haleygo
0ad6010c91
fix sort pendingDateMetricsIDs (#4102) 2023-04-10 10:23:12 -07:00
Aliaksandr Valialkin
19b189e9b7
lib/storage: use shorter code after 03bde173b7 2023-04-02 21:35:52 -07:00
faceair
38fc55976e
lib/storage: fix reuse pendingMetricRow (#4049) 2023-04-02 21:35:50 -07:00
faceair
f3af8331ec
lib/storage: remove unused code (#4050) 2023-04-02 21:24:42 -07:00
Roman Khavronenko
27b958ba8b
lib/storage: check for free disk space before opening tables (#4035)
* lib/storage: check for free disk space before opening tables

We check for free disk space before call to `openTable`,
so `Storage` can be set to ReadOnly before mergeWorkers start.

Before the change, there was a chance that merges will start
even if Storage has to start in ReadOnly mode because of
`-storage.minFreeDiskSpaceBytes` limit.

https://github.com/VictoriaMetrics/VictoriaMetrics/issues/4023
Signed-off-by: hagen1778 <roman@victoriametrics.com>

* lib/storage: chore

Signed-off-by: hagen1778 <roman@victoriametrics.com>

* Update lib/storage/storage.go

---------

Signed-off-by: hagen1778 <roman@victoriametrics.com>
Co-authored-by: Aliaksandr Valialkin <valyala@victoriametrics.com>
2023-03-31 23:50:27 -07:00
Aliaksandr Valialkin
c8f2febaa1
lib/storage: consistently use OS-independent separator in file paths
This is needed for Windows support, which uses `\` instead of `/` as file separator

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/70
2023-03-25 14:33:58 -07:00
Aliaksandr Valialkin
b14d96618c
all: follow-up after 34634ec357
- Use windows.FlushFileBuffers() instead of windows.Fsync() at streamTracker.adviseDontNeed()
  for consistency with implementations for other architectures.
- Use filepath.Base() instead of filepath.Split(), since the dir part isn't used.
  This simplifies the code a bit.

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/70
2023-03-25 11:57:39 -07:00
Nikolay
34634ec357
lib/fs: adds memory map for windows (#3988)
This is a follow-up for 43b24164ef

* lib/fs: adds memory map for windows
it should improve performance for file reading

* lib/storage: replace '/' with os specific separator
it must fix an errors for windows

* lib/fs: mention windows fsync support

* lib/filestream: adds fdatasync for windows writes

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/70
2023-03-25 11:43:19 -07:00
Dmytro Kozlov
5c92022cc6
lib/storage: fix collect downsampling metrics (#489)
* lib/storage: fix downsampling

* lib/storage: update logic

* lib/storage: fix comments, removed unneeded check
2023-03-19 23:34:46 -07:00
Aliaksandr Valialkin
43b24164ef
all: add Windows build for VictoriaMetrics
This commit changes background merge algorithm, so it becomes compatible with Windows file semantics.

The previous algorithm for background merge:

1. Merge source parts into a destination part inside tmp directory.
2. Create a file in txn directory with instructions on how to atomically
   swap source parts with the destination part.
3. Perform instructions from the file.
4. Delete the file with instructions.

This algorithm guarantees that either source parts or destination part
is visible in the partition after unclean shutdown at any step above,
since the remaining files with instructions is replayed on the next restart,
after that the remaining contents of the tmp directory is deleted.

Unfortunately this algorithm doesn't work under Windows because
it disallows removing and moving files, which are in use.

So the new algorithm for background merge has been implemented:

1. Merge source parts into a destination part inside the partition directory itself.
   E.g. now the partition directory may contain both complete and incomplete parts.
2. Atomically update the parts.json file with the new list of parts after the merge,
   e.g. remove the source parts from the list and add the destination part to the list
   before storing it to parts.json file.
3. Remove the source parts from disk when they are no longer used.

This algorithm guarantees that either source parts or destination part
is visible in the partition after unclean shutdown at any step above,
since incomplete partitions from step 1 or old source parts from step 3 are removed
on the next startup by inspecting parts.json file.

This algorithm should work under Windows, since it doesn't remove or move files in use.
This algorithm has also the following benefits:

- It should work better for NFS.
- It fits object storage semantics.

The new algorithm changes data storage format, so it is impossible to downgrade
to the previous versions of VictoriaMetrics after upgrading to this algorithm.

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3236
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3821
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/70
2023-03-19 01:36:51 -07:00
Aliaksandr Valialkin
6460475e3b
lib/{mergeset,storage}: prevent from long wait time when creating a snapshot under high data ingestion rate
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3551
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/3873
2023-03-19 00:15:30 -07:00
Aliaksandr Valialkin
a26c6628fd
lib/{fs,mergeset,storage}: substitute os.Open()+os.File.Readdir() with os.ReadDir()
This simplifies code a bit
2023-03-17 21:03:37 -07:00
Zakhar Bessarab
6a5d236245
lib/storage: log original labels set when label value is truncated (#3952)
lib/storage: log original labels set when label value is truncated
2023-03-14 10:59:40 +01:00
Nikolay
927d9da270
lib/storage: correctly handle io.EOF error for pre-fetched metrics (#3946)
io.EOF shouldn't be returned from this function. It breaks all search
API logic and may result in empty query results.
2023-03-11 23:29:43 -08:00
Nikolay
6bfe9cc733
lib{mergset,storage}: prevent possible race condition with logging st… (#3900)
lib{mergset,storage}: prevent possible race condition with logging stats for merges

Previously partwrapper could be release by background process and reference for part may be invalid 
during logging stats. It will lead to panic at vmstorage
https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3897
2023-03-03 12:33:42 +01:00
Aliaksandr Valialkin
0d3f31f60e
lib/storage: follow-up for 39cdc546dd
- Use flag.Duration instead of flagutil.Duration for -snapshotCreateTimeout,
  since the flagutil.Duration is intended mostly for big durations, e.g. days, months and years,
  while the -snapshotCreateTimeout is usually smaller than one hour.
- Add links to https://docs.victoriametrics.com/#how-to-work-with-snapshots in docs/CHANGELOG.md,
  so readers could easily find the corresponding docs when reading the changelog.
- Properly remove all the created directories on unsuccessful attempt to create
  snapshot in Storage.CreateSnapshot().

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3551
2023-02-27 13:07:38 -08:00
Zakhar Bessarab
39cdc546dd
lib/storage: enhancements for snapshots process (#3873)
* lib/{fs,mergeset,storage}: skip `.must-remove.` dirs when creating snapshot (#3858)

* lib/{mergeset,storage}: add timeout configuration for snapshots creation, remove incomplete snapshots from storage

* docs: fix formatting

* app/vmstorage: add metrics to track status of snapshots

* app/vmstorage: use `vm_http_requests_total` metric for snapshot endpoints metrics, rename new flag to make name more clear

Signed-off-by: Zakhar Bessarab <z.bessarab@victoriametrics.com>

* app/vmstorage: update flag name in docs

Signed-off-by: Zakhar Bessarab <z.bessarab@victoriametrics.com>

* app/vmstorage: reflect new metrics names change in docs

Signed-off-by: Zakhar Bessarab <z.bessarab@victoriametrics.com>

---------

Signed-off-by: Zakhar Bessarab <z.bessarab@victoriametrics.com>
Co-authored-by: Aliaksandr Valialkin <valyala@victoriametrics.com>
2023-02-27 12:12:03 -08:00
Zakhar Bessarab
d8eaa511b0
lib/{fs,mergeset,storage}: skip .must-remove. dirs when creating snapshot (#3858) (#3867) 2023-02-24 12:38:42 -08:00
Oleksandr Redko
9fff48c3e3
app,lib: fix typos in comments (#3804) 2023-02-13 13:27:13 +01:00
Aliaksandr Valialkin
3ec8a4dc80
lib/{mergeset,storage}: allow at least 3 concurrent flushes during background merges on systems with 1 or 2 CPU cores
This should prevent from data ingestion slowdown and query performance degradation
on systems with small number of CPU cores (1 or 2), when big merge is performed.

This should help https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3790

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3337
2023-02-11 12:08:52 -08:00
Nikolay
9254e494f9
lib/storage: fixes finalDedup for backfilled data (#3737)
previously historical data backfilling may trigger force merge for previous month every hour
it consumes cpu, disk io and decrease cluster performance.
Following commit fixes it by applying deduplication for InMemoryParts
2023-02-01 09:54:21 -08:00
Nikolay
465a285324
lib/storage: properly release parts inMerge lock (#3711)
if storage doesn't have enough disk space, finalDedupWatcher holds inMerge lock for all parts and never release it until storage restart
2023-01-26 08:05:20 -08:00
Aliaksandr Valialkin
ba5a6c851c
lib/storage: use deterministic random generator in tests
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3683
2023-01-23 20:10:32 -08:00
Aliaksandr Valialkin
2ac530eb28
lib/{storage,mergeset}: wake up background merges as soon as there is a potential work for them
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3647
2023-01-18 01:10:18 -08:00
Aliaksandr Valialkin
b8409d6600
lib/{storage,mergeset}: do not run assisted merges when flushing pending samples to parts
Assisted merges are intended to be performed by goroutines, which accept the incoming samples,
in order to limit the data ingestion rate.

The worker, which converts pending samples to parts, shouldn't be penalized by assisted merges,
since this may result in increased number of pending rows as seen at https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3647#issuecomment-1385039142
when the assisted merge takes too much time.
2023-01-18 00:20:58 -08:00
Aliaksandr Valialkin
1ac025bbc9
lib/storage: use better naming for a function returning new []rawRows - newRawRowsBlock() -> newRawRows() 2023-01-18 00:01:03 -08:00
Aliaksandr Valialkin
09d7fa2737
lib/{mergeset,storage}: do not slow down concurrently executed queries during assisted merges
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3647
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3641
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/648
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/291
2023-01-16 14:31:52 -08:00
Aliaksandr Valialkin
2f3ddd4884
app/vmselect/promql: avoid memory allocations and copying from source timeseries to the returned result at timeseriesToResult() 2023-01-09 22:38:59 -08:00
Aliaksandr Valialkin
7afcca0c51
all: use metricsql.CompileRegexp instead of regexp.Compile for compiling regexps used in graphite queries
This should speed up repeated queries, since metricsql.CompileRegexp returns regexps from the cache
on subsequent calls for the same input regexp.
2023-01-09 21:43:08 -08:00
Aliaksandr Valialkin
41e00a0df7
lib/storage: simplify the fix from 488940502c
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3566
2023-01-07 01:04:43 -08:00
Dmytro Kozlov
488940502c
lib/storage: fix returning camelcase label names (#3608)
* lib/storage: fix returning camelcase label names

* doc: add change log

* Update docs/CHANGELOG.md

* Update docs/CHANGELOG.md

Co-authored-by: Aliaksandr Valialkin <valyala@victoriametrics.com>
2023-01-07 00:50:14 -08:00
Aliaksandr Valialkin
c63755c316
lib/writeconcurrencylimiter: improve the logic behind -maxConcurrentInserts limit
Previously the -maxConcurrentInserts was limiting the number of established client connections,
which write data to VictoriaMetrics. Some of these connections could be idle.
Such connections do not consume big amounts of CPU and RAM, so there is a little sense in limiting
the number of such connections. So now the -maxConcurrentInserts command-line option
limits the number of concurrently executed insert requests, not including idle connections.

It is recommended removing -maxConcurrentInserts command-line option, since the default value
for this option should work good for most cases.
2023-01-06 22:20:19 -08:00
Roman Khavronenko
5bdd880142
vmstorage: add more context to the flock acquiring msg (#3584)
See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3578

Signed-off-by: hagen1778 <roman@victoriametrics.com>

Signed-off-by: hagen1778 <roman@victoriametrics.com>
2023-01-05 18:30:42 -08:00
Aliaksandr Valialkin
1b16118e17
lib/{storage,mergeset}: tune the threshold for assisted merge
The https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3425#issuecomment-1359117221
reveals that CPU usage for incoming queries may significantly increase when the number
of in-memory parts becomes too big.

This commit reduces the maximum number of in-memory parts before starting the assisted merge
during data ingestion. This should reduce CPU usage for incoming queries,
since they need to inspect lower number of in-memory parts.

This should help https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3425
2022-12-28 14:39:24 -08:00
Aliaksandr Valialkin
4e55b67a44
lib/storage: clear the err if it is set to io.EOF when searching for the TSID by metricID
This is expected error after when recently added indexdb data isn't available for search yet
or wasn't flushed to disk after unclean shutdown of VictoriaMetrics.

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3515
2022-12-20 14:05:29 -08:00
Aliaksandr Valialkin
944effca54
lib/storage: do not check for the result returned by db.doExtDB() where this isn't necessary
This simplifies the code a bit
2022-12-19 13:23:13 -08:00
Aliaksandr Valialkin
6c98b56935
lib/storage: search for TSIDs for the given metricIDs in the previous indexdb if they aren't found in the current indexdb
The issue triggers after the indexdb rotation for time series, which stop receiving new samples.
This results in missing data for such time series in query responses.

This commit should address the https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3502

The issue has been introduced in 2dd93449d8
2022-12-19 12:03:09 -08:00
Aliaksandr Valialkin
dc0b08efb0
lib/storage: optimize partSearch.searchBHS() for common case when the TSID for the current block header is bigger or equal to the current tsid
This should help improving performance at https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3425
2022-12-19 10:28:03 -08:00
Aliaksandr Valialkin
057fb2120b
lib/storage: properly set buf capacity inside marshalMetricID
Previously it was always set to 0. In theory this could result into incorrect marshaling
of metricIDs.

The issue has been introduced in 5e4dfe50c6
2022-12-19 10:14:38 -08:00
Aliaksandr Valialkin
ad8852759d
lib/storage: skip missing tsids in the current block header by using binary search
This improves performance by up to 10x when big number of the requested TSIDs
are missing in the searched parts.

This should help https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3425
2022-12-14 22:06:51 -08:00
Aliaksandr Valialkin
4de9d35458
lib/flagutil/bytes.go: properly handle values bigger than 2GiB on 32-bit architectures
This fixes handling of values bigger than 2GiB for the following command-line flags:

- -storage.minFreeDiskSpaceBytes
- -remoteWrite.maxDiskUsagePerURL
2022-12-14 19:26:31 -08:00
Aliaksandr Valialkin
0d41d933e9
lib/mergeset: reduce the parts threshold before starting assisted merges
This should improve query speed in general case.

This is a follow-up for d1af6046c7
2022-12-13 09:13:49 -08:00
Aliaksandr Valialkin
d1af6046c7
lib/{mergeset,storage}: do not block small merges by pending big merges - assist with small merges instead
Blocked small merges may result into big number of small parts, which, in turn,
may result in increased CPU and memory usage during queries, since queries need to inspect
all the existing small parts.

The issue has been introduced in 8189770c50

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3337
2022-12-12 17:00:50 -08:00
Aliaksandr Valialkin
5b9e6b9d24
lib/storage: follow-up after 7c0ae3a86a
- Update docs at https://docs.victoriametrics.com/#deduplication
- Optimize the deduplication loop a bit

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3333
2022-12-08 18:16:57 -08:00
Roman Khavronenko
7c0ae3a86a
lib/storage: keep sample with the biggest value on timestamp conflict (#3421)
The change leaves raw sample with the biggest value for identical
timestamps per each `-dedup.minScrapeInterval` discrete interval
when the deduplication is enabled.

```
benchstat old.txt new.txt
name                                         old time/op    new time/op    delta
DeduplicateSamples/minScrapeInterval=1s-10      817ns ± 2%     832ns ± 3%      ~     (p=0.052 n=10+10)
DeduplicateSamples/minScrapeInterval=2s-10     1.56µs ± 1%    2.12µs ± 0%   +35.19%  (p=0.000 n=9+7)
DeduplicateSamples/minScrapeInterval=5s-10     1.32µs ± 3%    1.65µs ± 2%   +25.57%  (p=0.000 n=10+10)
DeduplicateSamples/minScrapeInterval=10s-10    1.13µs ± 2%    1.50µs ± 1%   +32.85%  (p=0.000 n=10+10)

name                                         old speed      new speed      delta
DeduplicateSamples/minScrapeInterval=1s-10   10.0GB/s ± 2%   9.9GB/s ± 3%      ~     (p=0.052 n=10+10)
DeduplicateSamples/minScrapeInterval=2s-10   5.24GB/s ± 1%  3.87GB/s ± 0%   -26.03%  (p=0.000 n=9+7)
DeduplicateSamples/minScrapeInterval=5s-10   6.22GB/s ± 3%  4.96GB/s ± 2%   -20.37%  (p=0.000 n=10+10)
DeduplicateSamples/minScrapeInterval=10s-10  7.28GB/s ± 2%  5.48GB/s ± 1%   -24.74%  (p=0.000 n=10+10)
```

https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3333
Signed-off-by: hagen1778 <roman@victoriametrics.com>

Signed-off-by: hagen1778 <roman@victoriametrics.com>
2022-12-08 18:06:11 -08:00
Aliaksandr Valialkin
d99d222f0a
lib/{storage,mergeset}: log the duration for flushing in-memory parts on graceful shutdown 2022-12-05 21:30:48 -08:00
Aliaksandr Valialkin
8189770c50
all: add -inmemoryDataFlushInterval command-line flag for controlling the frequency of saving in-memory data to disk
The main purpose of this command-line flag is to increase the lifetime of low-end flash storage
with the limited number of write operations it can perform. Such flash storage is usually
installed on Raspberry PI or similar appliances.

For example, `-inmemoryDataFlushInterval=1h` reduces the frequency of disk write operations
to up to once per hour if the ingested one-hour worth of data fits the limit for in-memory data.

The in-memory data is searchable in the same way as the data stored on disk.
VictoriaMetrics automatically flushes the in-memory data to disk on graceful shutdown via SIGINT signal.
The in-memory data is lost on unclean shutdown (hardware power loss, OOM crash, SIGKILL).

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3337
2022-12-05 15:16:14 -08:00
Aliaksandr Valialkin
544ea89f91
lib/{mergeset,storage}: add start background workers via startBackgroundWorkers() function 2022-12-04 00:01:04 -08:00
Aliaksandr Valialkin
33dda2809b
lib/mergeset: panic when too long item is passed to Table.AddItems() 2022-12-03 23:32:16 -08:00
Aliaksandr Valialkin
932c1f90ae
lib/storage: remove duplicate logging for filepath on errors 2022-12-03 23:15:22 -08:00
Aliaksandr Valialkin
044a304adb
lib/storage: pass a single arg - rowsPerBlock - to getCompressLevel() function instead of two args 2022-12-03 23:10:16 -08:00
Aliaksandr Valialkin
cb44976716
lib/{storage,mergeset}: use a single sync.WaitGroup for all background workers
This simplifies the code
2022-12-03 23:03:08 -08:00
Aliaksandr Valialkin
28e6d9e1ff
lib/storage: properly pass retentionMsecs to OpenStorage() at TestIndexDBRepopulateAfterRotation 2022-12-03 23:02:10 -08:00
Aliaksandr Valialkin
343c69fc15
lib/{mergeset,storage}: pass compressLevel to blockStreamWriter.InitFromInmemoryPart
This allows packing in-memory blocks with different compression levels
depending on its contents. This may save memory usage.
2022-12-03 22:46:48 -08:00
Aliaksandr Valialkin
f3e3a3daeb
lib/{mergeset,storage}: take into account byte slice capacity when returning the size of in-memory part
This results in more correct reporting of memory usage for in-memory parts
2022-12-03 22:30:36 -08:00
Aliaksandr Valialkin
45299efe22
lib/{storage,mergeset}: consistency rename: `flushRaw{Rows,Items} -> flushPending{Rows,Items} 2022-12-03 22:17:46 -08:00
Aliaksandr Valialkin
5ca58cc4fb
lib/storage: optimization: do not scan block for rows outside retention if it is covered by the retention 2022-12-03 22:14:12 -08:00
Aliaksandr Valialkin
152ac564ab
lib/storage: remove logging redundant path values in a single error message 2022-12-03 22:13:13 -08:00