Aliaksandr Valialkin
87179c6839
lib/{storage,mergeset}: fix unaligned 64-bit atomic operation
panic for 32-bit architectures
...
The panic has been introduced in 56b6b893ce
2021-04-27 16:41:32 +03:00
Aliaksandr Valialkin
56b6b893ce
lib/mergeset: split rows ingestion among multiple shards
...
This improves rows ingestion on systems with many CPU cores by reducing lock contention.
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1244
Thanks to @waldoweng for the original idea and draft implementation at https://github.com/VictoriaMetrics/VictoriaMetrics/pull/1243
2021-04-27 15:36:34 +03:00
Aliaksandr Valialkin
bbebdf9ba1
lib/{storage,mergeset}: remove empty directories on startup. Such directories can be left after unclean shutdown on NFS storage
...
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1142
2021-04-22 13:02:44 +03:00
Aliaksandr Valialkin
636c55b526
lib/mergeset: reduce memory usage for inmemoryBlock by using more compact items representation
...
This also should reduce CPU time spent by GC, since inmemoryBlock.items don't have pointers now,
so GC doesn't need visiting them.
2021-02-21 22:06:47 +02:00
Aliaksandr Valialkin
48656dcc38
lib/{mergeset,storage}: allow merging smaller number of small parts
...
While this may increase CPU and disk IO usage needed for background merge,
this also recudes CPU usage during queries in production. This is because
such queries tend to read recently added data and it is better to have lower number
of parts for such data in order to reduce CPU usage.
This partially reverts ebf8da3730
2021-02-21 21:28:36 +02:00
Aliaksandr Valialkin
cb311bb156
lib/{mergeset,storage}: do not use pools for indexBlock and inmemoryBlock during their caching, since this results in higher memory usage in production without any performance gains
2021-02-21 21:18:59 +02:00
Aliaksandr Valialkin
ce99b48a9a
Revert "lib/mergeset: tune lifetime for entries inside block caches"
...
This reverts commit 458c89324d
.
Production testing revealed zero improvements for memory usage with reduced lifetime for entries in block caches.
2021-02-17 20:42:21 +02:00
Aliaksandr Valialkin
458c89324d
lib/mergeset: tune lifetime for entries inside block caches
...
This should reduce memory usage in general case without significant CPU usage increase
2021-02-16 18:11:51 +02:00
Aliaksandr Valialkin
2824856691
lib/mergeset: clarify comments in the code a bit
2021-02-16 18:02:57 +02:00
Aliaksandr Valialkin
7faa762021
lib/mergeset: remove unused code after a4140de9e6
2021-02-16 13:40:09 +02:00
Aliaksandr Valialkin
0a69122d81
lib/mergeset: remove dead code left after a4140de9e6
2021-02-09 16:33:52 +02:00
Aliaksandr Valialkin
a4140de9e6
lib/mergeset: unconditionally cache indexdb blocks
...
Production workloads show that indexdb blocks must be cached unconditionally for reducing CPU usage.
This shouldn't increase memory usage too much, since unused blocks are removed from the cache every two minutes.
2021-02-09 00:47:50 +02:00
Aliaksandr Valialkin
cb96a1865b
app/vmstorage: export missing vm_cache_size_bytes
metrics for indexdb and data caches
2021-02-09 00:47:00 +02:00
faceair
b638c1eed5
lib/mergeset: add missing shouldCacheBlock ( #1019 )
2021-01-15 11:46:01 +02:00
Aliaksandr Valialkin
ebf8da3730
lib/{storage,mergeset}: tune background merge process in order to reduce CPU usage and disk IO usage
2020-12-18 20:01:08 +02:00
Aliaksandr Valialkin
4146fc4668
all: properly handle CPU limits set on the host system/container
...
This can reduce memory usage on systems with enabled CPU limits.
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/946
2020-12-08 21:07:29 +02:00
Aliaksandr Valialkin
1c669a69a8
lib/mergeset: tune the number of rawItemsBlocks to merge at once
...
512 blocks give higher ingestion performance and slightly lower memory usage
2020-11-25 21:52:52 +02:00
Aliaksandr Valialkin
7119f294f3
lib/mergeset: help GC by removing refereces to slices in inmemoryBlock.Reset
2020-11-25 21:19:43 +02:00
Aliaksandr Valialkin
78d2715d04
all: spelling fix: superflouos->superfluous. This is a follow-up for 0acdab3ab9
2020-11-24 12:42:22 +02:00
Aliaksandr Valialkin
f765985947
lib/fs: replace fs.OpenReaderAt with fs.MustOpenReaderAt
...
All the callers for fs.OpenReaderAt expect that the file will be opened.
So it is better to log fatal error inside fs.MustOpenReaderAt instead of leaving this to the caller.
2020-11-23 09:57:21 +02:00
Aliaksandr Valialkin
ae91a6883c
lib/{storage,mergeset}: clean cached index blocks and inmemory blocks more aggressively
...
Previously such blocks were cleaned after they weren't accessed during 10 minutes.
Now they are cleaned after one minute of missing access. This should reduce memory usage in general case.
2020-11-04 17:04:04 +02:00
Aliaksandr Valialkin
8beb0da6ad
lib/{mergeset,storage}: compare errors with errors.Is()
2020-09-17 03:03:02 +03:00
Aliaksandr Valialkin
067d7c1ea1
lib/{mergeset,storage}: code prettifying
2020-09-17 02:06:31 +03:00
Aliaksandr Valialkin
00b1659dde
lib: dump compressed block contents on error during decompression
...
This should improve detecting root cause for https://github.com/facebook/zstd/issues/2222
2020-08-15 14:44:33 +03:00
Aliaksandr Valialkin
e7959094f6
lib/storage: remove prioritizing of merging small parts over merging big parts, since it doesn't work as expected
...
The prioritizing could lead to big merge starvation, which could end up in too big number of parts that must be merged into big parts.
Multiple big merges may be initiated after the migration from v1.39.0 or v1.39.1. It is OK - these merges should be finished soon,
which should return CPU and disk IO usage to normal levels.
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/648
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/618
2020-07-30 19:57:27 +03:00
Aliaksandr Valialkin
6f05c4d351
lib/storage: improve prioritizing of data ingestion over querying
...
Prioritize also small merges over big merges.
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/291
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/648
2020-07-23 13:23:36 +03:00
Aliaksandr Valialkin
9224ede54f
lib/mergeset: properly calculate global metrics in UpdateStats()
...
Previously these metrics could be calculated multiple times for multiple mergeset.Table instances.
2020-07-23 00:35:13 +03:00
Aliaksandr Valialkin
d5dddb0953
all: use %w instead of %s for wrapping errors in fmt.Errorf
...
This will simplify examining the returned errors such as httpserver.ErrorWithStatusCode .
See https://blog.golang.org/go1.13-errors for details.
2020-06-30 23:05:11 +03:00
Aliaksandr Valialkin
0eacea1de1
lib/{storage,mergeset}: further tuning of compression levels depending on block size
...
This should improve performance for querying newly added data, since it can be unpacked faster.
2020-05-15 13:24:37 +03:00
Aliaksandr Valialkin
f9f3afb6af
lib/mergeset: tune compression levels in order to improve ingestion performance a bit
2020-05-15 13:24:37 +03:00
Aliaksandr Valialkin
0afd48d2ee
lib: extract common code for returning fast unix timestamp into lib/fasttime
2020-05-14 23:02:07 +03:00
Aliaksandr Valialkin
42866fa754
lib/{storage,mergeset}: return dst on error from unmarshalBlockHeaders, so it could be reused
2020-05-14 15:32:07 +03:00
Aliaksandr Valialkin
606585f7be
lib/{storage,mergeset}: cleanup: remove unused partSearch.indexBlockReuse
2020-05-14 14:03:03 +03:00
Aliaksandr Valialkin
7d73623c69
lib/{storage,mergeset}: make sure that requests
and misses
cache counters never go down
2020-04-10 14:45:01 +03:00
Aliaksandr Valialkin
7836ad8907
lib/mergeset: skip createing temporary part objects when merging source inmemory parts
...
This should reduce CPU usage when adding new entries to inverted index.
This should alos prevent from creating stalled cleaner goroutines for the created temporary parts,
since they were never closed.
This should fix the following issue: https://github.com/VictoriaMetrics/VictoriaMetrics/issues/316 .
2020-02-13 14:09:32 +02:00
Aliaksandr Valialkin
eceaf13e5e
lib/{storage,mergeset}: use time.Ticker instead of time.Timer where appropriate
...
It has been appeared that time.Timer was used in places where time.Ticker must be used instead.
This could result in blocked goroutines as in the https://github.com/VictoriaMetrics/VictoriaMetrics/issues/316 .
2020-02-13 13:10:07 +02:00
Aliaksandr Valialkin
ad8af629bb
all: rename ReadAt* to MustReadAt* in order to dont clash with io.ReaderAt
2020-01-30 15:08:58 +02:00
Aliaksandr Valialkin
5bb9ccb6bf
lib/mergeset: properly update lastAccesstime
in indexBlockCache entries
...
This is a follow-up for 6665f10e7b
2020-01-29 21:20:47 +02:00
Aliaksandr Valialkin
680080887d
all: consistently log durations in seconds with millisecond precision
...
This should improve logs readability
2020-01-22 18:28:27 +02:00
Aliaksandr Valialkin
6665f10e7b
lib/{mergeset,storage}: properly update lastAccessTime
in index and data block cache entries
2020-01-20 14:59:47 +02:00
Aliaksandr Valialkin
893b62c682
lib/{mergeset,storage}: fix uint64 counters alignment for 32-bit architectures (GOARCH=386, GOARCH=arm)
2020-01-14 22:47:04 +02:00
Aliaksandr Valialkin
7830c10eb2
lib/{storage,mergeset}: gradually remove stale entries from block cache and index caches
...
This should reduce memory usage in the long run when old blocks and indexes
aren't accessed anymore.
2020-01-14 21:38:44 +02:00
Aliaksandr Valialkin
3c076544bf
app/vmselect/promql: allow negative offsets
...
Updates https://github.com/prometheus/prometheus/issues/6282
2019-12-11 01:00:23 +02:00
Aliaksandr Valialkin
0ed9258545
lib/{mergeset,storage}: log info message when both source and destination part paths from txn are missing during startup
...
This is expected condition after unclean shutdown (OOM, hard reset, `kill -9`) on NFS disk.
2019-12-09 15:44:53 +02:00
Aliaksandr Valialkin
72345eb5bd
lib/{mergeset,storage}: make sure pending transaction deletions are finished before and after runTransactions
call.
...
`runTransactions` call issues async deletions for transaction files. The previously issued transaction deletions
can race with the next call to `runTransactions`. Prevent this by waiting until all the pending transaction
deletions are funished in the beginning of `runTransactions`. Also make sure that all the pending transaction
deletions are finished before returning from `runTransactions`.
2019-12-04 21:40:30 +02:00
Aliaksandr Valialkin
638a5cbb16
lib/{mergeset,storage}: remove transaction files only after the mentioned dirs are really removed
...
This should fix the issue on NFS when incompletely removed dirs may be left
after unclean shutdown (OOM, kill -9, hard reset, etc.), while the corresponding transaction
files are already removed.
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/162
2019-12-02 21:36:31 +02:00
Aliaksandr Valialkin
c62399eb3e
lib/{storage,mergeset}: create missing partition directories after restoring from backups
...
Backup tools could skip empty directories. So re-create such directories on the first run.
2019-11-02 02:27:11 +02:00
Aliaksandr Valialkin
2e2eff90d5
lib/{mergeset,storage}: limit the maximum number of concurrent merges; leave smaller number of parts during final merge
2019-10-29 12:45:28 +02:00
Aliaksandr Valialkin
97ce4e03a5
all: add support for GOARCH=386 and fix all the issues related to 32-bit architectures such as GOARCH=arm
...
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/212
2019-10-17 18:23:23 +03:00
Aliaksandr Valialkin
fdc5cfd838
lib/mergeset: reduce the maximum number of cached blocks, since there are reports on OOMs due to too big caches
...
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/189
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/195
2019-09-30 12:25:40 +03:00
Aliaksandr Valialkin
aebc45ad26
lib/{mergeset,storage}: do not cache inverted index blocks containing tag->metricIDs
items
...
This should reduce the amounts of used RAM during queries with filters over big number of time series.
2019-09-25 14:02:15 +03:00
Aliaksandr Valialkin
b986516fbe
lib/storage: create and use lib/uint64set
instead of map[uint64]struct{}
...
This should improve inverted index search performance for filters matching big number of time series,
since `lib/uint64set.Set` is faster than `map[uint64]struct{}` for both `Add` and `Has` calls.
See the corresponding benchmarks in `lib/uint64set`.
2019-09-24 21:17:55 +03:00
Aliaksandr Valialkin
4e26ad869b
lib/{storage,mergeset}: verify PrepareBlock callback results
...
Do not touch the first and the last item passed to PrepareBlock
in order to preserve sort order of mergeset blocks.
2019-09-23 20:43:13 +03:00
Aliaksandr Valialkin
0772191975
lib/mergeset: detect whether we are in test by executable suffix
2019-09-22 23:12:15 +03:00
Aliaksandr Valialkin
0686ac52c3
lib/{storage,mergeset}: merge tag->metricID
rows into tag->metricIDs
rows for common tag
values
...
This should improve lookup performance if the same `label=value` pair exists
in big number of time series.
This should also reduce memory usage for mergeset data cache, since `tag->metricIDs` rows
occupy less space than the original `tag->metricID` rows.
2019-09-20 22:06:41 +03:00
Aliaksandr Valialkin
00cfb2d2b9
lib/mergeset: rename misleading mergeSmallParts to mergeExistingParts
2019-09-19 21:48:20 +03:00
Aliaksandr Valialkin
37dc223e25
lib/mergeset: use sort.IsSorted instead of sort.SliceIsSorted in inmemoryBlock.isSorted in order to reduce memory allocations
2019-09-19 20:13:08 +03:00
Aliaksandr Valialkin
51a21c7d4b
lib/mergeset: fill partHeader.firstItem on first block flush
2019-09-19 17:48:09 +03:00
Aliaksandr Valialkin
0c8057924f
lib/mergeset: properly check for sorted block headers
...
Fix a typo for https://github.com/VictoriaMetrics/VictoriaMetrics/issues/181
2019-09-13 21:59:29 +03:00
Aliaksandr Valialkin
bad53e4207
lib/mergeset: dynamically calculate the maximum number of items per part, which can be cached in OS page cache
2019-09-11 14:53:45 +03:00
Aliaksandr Valialkin
e1d76ec1f3
lib/storage: invalidate tagFilters -> TSIDS
cache when newly added index data becomes visible to search
...
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/163
2019-08-29 15:08:35 +03:00
Aliaksandr Valialkin
9196c085a7
all: port to FreeBSD on GOARCH=amd64
2019-08-28 01:19:23 +03:00
Aliaksandr Valialkin
0967683ae9
lib: move common code for creating flock.lock file into fs.CreateFlockFile
2019-08-13 01:45:46 +03:00
Aliaksandr Valialkin
5d8d110010
lib/fs: atomically create file with the given contents on WriteFileAtomically
...
This should prevent from `transaction` and `metadata.json` files corruption
on unclean shutdown such as OOM, `kill -9`, power loss, etc.
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/148
2019-08-12 15:02:55 +03:00
Aliaksandr Valialkin
1fe6d784d8
all: consistency renaming: bytesSize -> sizeBytes
2019-07-10 00:47:36 +03:00
Aliaksandr Valialkin
56c154f45b
all: add vm_data_size_bytes
metrics for easy monitoring of on-disk data size and on-disk inverted index size
2019-07-04 19:42:30 +03:00
Aliaksandr Valialkin
a41955863a
lib/mergeset: make fmt
2019-06-29 14:25:26 +03:00
Aliaksandr Valialkin
0c88afa386
lib/mergeset: speed up binarySearchKey by skipping the first item during binary search
2019-06-29 13:45:49 +03:00
Aliaksandr Valialkin
af2ceaaa0b
lib/storage: mention source parts on merge error
...
This should improve determining broken source part.
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/76
2019-06-24 14:08:43 +03:00
Aliaksandr Valialkin
419197ba08
lib/fs: consolidate *RemoveAll* funcs into a single MustRemoveAll func
...
The func syncs parent dir in order to persist directory removal
in the event of power loss
2019-06-12 01:53:46 +03:00
Aliaksandr Valialkin
935bfd7a18
lib/fs: consistency renaming SyncPath -> MustSyncPath, since it doesnt return error
2019-06-11 23:13:49 +03:00
Aliaksandr Valialkin
20fc0e0e54
lib/{storage,mergeset}: sync filenames inside part when finalizing the part
...
Fixes https://github.com/VictoriaMetrics/VictoriaMetrics/issues/63
2019-06-11 21:51:13 +03:00
Aliaksandr Valialkin
ac7b186f13
all: try hard removing directory with contents
...
Fixes https://github.com/VictoriaMetrics/VictoriaMetrics/issues/61
2019-06-11 01:57:59 +03:00
Aliaksandr Valialkin
54fb8b21f9
all: fix misspellings
2019-05-25 21:51:11 +03:00
Aliaksandr Valialkin
1836c415e6
all: open-sourcing single-node version
2019-05-23 00:18:06 +03:00