Commit Graph

110 Commits

Author SHA1 Message Date
Aliaksandr Valialkin
c567a4353a lib/storage: take into account the requested time range when caching TSIDs for the given tag filters 2019-11-06 14:32:41 +02:00
Aliaksandr Valialkin
c6564c5d26 lib/storage: dump incorrectly sorted items on a single line; this should simplify error reporting 2019-11-05 18:41:50 +02:00
Aliaksandr Valialkin
a10c4cad85 lib/storage: return back finalPartsToMerge from 2 to 3 in order to prevent from excessive merges in old partitions 2019-11-05 17:28:57 +02:00
Aliaksandr Valialkin
e5b1fa0c38 lib/storage: separate the max inverted index scan loops per metric into fast and slow loops
Slow loops could require seeks and expensive regexp matching, while fast loops just scans
all the metricIDs for the given `tag=value` prefix. So these operations must have separate
max loops multiplier.
2019-11-05 17:28:57 +02:00
Aliaksandr Valialkin
f93c4f2493 lib/storage: skip repeated useless work when intersection of metricIDs with the given filter is too expensive
This should improve performance for query filters over big number of time series.
2019-11-05 14:35:55 +02:00
Aliaksandr Valialkin
f48e97263c lib/storage: reduce the maximum inverted index scans before giving up to label filters matching by metric name
The new value reduces the amount of wasted work during index scans over big number of time series.
2019-11-05 14:35:53 +02:00
Aliaksandr Valialkin
d2f688c550 lib/storage: try potentially faster tag filters at first, then apply slower tag filters
The fastest tag filters are non-negative non-regexp, since they are the most specific.
The slowest tag filters are negative regexp, since they require scanning
all the entries for the given label.
2019-11-05 14:35:48 +02:00
Aliaksandr Valialkin
2a38d30f93 lib/storage: pass pointer to MetricName in Fatalf, so it is properly detected as an interface with String() method
This fixes lint errors
2019-11-04 01:06:45 +02:00
Artem Navoiev
e05500cbd4 add unittests for bytesutil and storage (#221) 2019-11-04 00:57:24 +02:00
Aliaksandr Valialkin
f5fbc3ffd7 lib/{storage,uint64set}: add Set.Union() function and use it 2019-11-04 00:48:32 +02:00
Aliaksandr Valialkin
23e078261e lib/storage: tune the returned value from adjustMaxMetricsAdaptive 2019-11-04 00:45:28 +02:00
Aliaksandr Valialkin
386c349c8c lib/storage: remove interface conversion in hot path during block merging
This should improve merge speed a bit for parts with big number of small blocks.
2019-11-03 12:33:48 +02:00
Aliaksandr Valialkin
26ffc77622 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 02:27:19 +02:00
Aliaksandr Valialkin
6ab9c98a1e app/vmstorage: add -bigMergeConcurrency and -smallMergeConcurrency flags for tuning the maximum number of CPU cores used during merges 2019-10-31 16:17:29 +02:00
Aliaksandr Valialkin
6a22727676 lib/storage: optimize getMetricIDsForRecentHours for per-tenant lookups 2019-10-31 15:51:09 +02:00
Aliaksandr Valialkin
ca480915ca lib/storage: small cleanup in Storage.add 2019-10-31 14:30:22 +02:00
Aliaksandr Valialkin
a27e034a40 lib/storage: get parts to merge after applying the limit on the number of concurrent merges
This should reduce write amplification under high ingestion rate.
2019-10-30 00:09:44 +02:00
Aliaksandr Valialkin
5d2276dbf7 lib/{mergeset,storage}: limit the maximum number of concurrent merges; leave smaller number of parts during final merge 2019-10-29 12:45:37 +02:00
hanzai
52778da1f3 warns during rows addition (#214) 2019-10-20 23:38:51 +03:00
Aliaksandr Valialkin
78fc35c9b1 all: make fmt 2019-10-17 20:05:12 +03:00
Aliaksandr Valialkin
5b01b7fb01 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 18:27:49 +03:00
Aliaksandr Valialkin
661b8ede5b lib/storage: harden the check that the original items are sorted after mergeTagToMetricIDsRows fails to preserve sort order 2019-10-09 12:13:43 +03:00
Aliaksandr Valialkin
7f4a04ee6a lib/storage: typo fix in comment to maxRowsPerSmallPart. 2019-10-08 18:51:56 +03:00
Aliaksandr Valialkin
7e410e1412 lib/storage: add tests for mergeTagToMetricIDsRows and return the original items if the function breaks items` ordering.
This should save from data corruption issues revealed in the previous releases up to v1.28.0-beta5.
2019-10-08 16:35:39 +03:00
Aliaksandr Valialkin
d0b4590099 lib/storage: optimize TSID comparison 2019-09-26 14:20:02 +03:00
Aliaksandr Valialkin
95e3d648cb lib/storage: verify whether items are sorted in the end of call to mergeTagToMetricIDsRows
This should prevent from inverted index corruption if bug in mergeTagToMetricIDsRows is discovered.
2019-09-26 13:13:58 +03:00
Aliaksandr Valialkin
2b8358726f lib/storage: properly match labels against regexp with (?i) flag
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/161
2019-09-26 11:03:26 +03:00
Aliaksandr Valialkin
4e3871ac1e lib/storage: add missing break in removeDuplicateMetricIDs 2019-09-25 18:23:13 +03:00
Aliaksandr Valialkin
4468f9f966 lib/storage: remove duplicate MetricIDs in tag->metricIDs items before writing them into inverted index 2019-09-25 17:57:36 +03:00
Aliaksandr Valialkin
adc18c3ee6 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 13:48:24 +03:00
Aliaksandr Valialkin
de0e4eee2c 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 21:18:04 +03:00
Aliaksandr Valialkin
2212d0e421 lib/storage: typo fix: return dstData instead of data from mergeTagToMetricIDsRows 2019-09-24 19:32:58 +03:00
Aliaksandr Valialkin
9307de1b92 lib/storage: limit the number of metricIDs in tag->metricIDs row
This reduces the overhead on index and metaindex in lib/mergeset
2019-09-24 00:50:47 +03:00
Aliaksandr Valialkin
7734fc8012 lib/storage: share tsids across all the partSearch instances
This should reduce memory usage when big number of time series matches the given query.
2019-09-23 22:36:16 +03:00
Aliaksandr Valialkin
67a2bcb98a 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 20:46:33 +03:00
Aliaksandr Valialkin
d2ed8cb0b2 lib/storage: generate the first tag->metricIDs item in a mergeset block with a single metricID
The first item from each mergeset block goes into index (lib/mergeset.blockHeader),
so it must be short in order to reduce index size.
2019-09-22 19:37:50 +03:00
Aliaksandr Valialkin
7d13c31566 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 22:06:23 +03:00
Aliaksandr Valialkin
7e0c6d4ca6 lib/storage: optimize selecting all the metricIDs by scanning MetricID->TSID entries instead of tag->MetricID entries
The number of MetricID->TSID entries is smaller than the number of tag->MetricID entries
and MetricID->TSID entries are usually shorter than tag->MetricID entries.
This should improve performance when selecting all the metricIDs.
2019-09-20 11:57:57 +03:00
Aliaksandr Valialkin
89234f395d lib/storage: use sort.Sort instead of sort.slice in getSortedMetricIDs 2019-09-19 20:08:13 +03:00
Aliaksandr Valialkin
6e586fa09c lib/storage: skip duplicate call to intersectMetricIDsWithTagFilter on zero successful intersects 2019-09-19 17:51:10 +03:00
Aliaksandr Valialkin
c05885fb5f lib/storage: mark tag filter returning errFallbackToMetricNameMatch as useless
This will save CPU on subsequent calls for this filter
2019-09-18 19:11:44 +03:00
Aliaksandr Valialkin
db71c940ea lib/storage: properly construct keys for uselessTagFiltersCache and register useless negative tag filters there 2019-09-17 23:18:37 +03:00
Aliaksandr Valialkin
568ff61dcf lib/mergeset: dynamically calculate the maximum number of items per part, which can be cached in OS page cache 2019-09-09 11:42:45 +03:00
Aliaksandr Valialkin
2c2bd897dd lib/storage: remove duplicate tag keys on MetricName.Marshal call
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/172
2019-09-04 18:13:51 +03:00
Aliaksandr Valialkin
0b0153ba3d 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 15:08:44 +03:00
Aliaksandr Valialkin
604a4312f9 all: port to FreeBSD on GOARCH=amd64 2019-08-28 01:46:09 +03:00
Aliaksandr Valialkin
da07a6fb38 lib/storage: go fmt 2019-08-27 14:28:24 +03:00
Aliaksandr Valialkin
a63b69e9e2 lib/storage: report proper maxMetrics limit when more than -search.maxUniqueTimeseries series match the given filters 2019-08-27 14:21:31 +03:00
Aliaksandr Valialkin
82e813bad3 lib/storage: properly handle (?i) in the tag filter regexp
Fixes https://github.com/VictoriaMetrics/VictoriaMetrics/issues/161
2019-08-26 00:44:56 +03:00
Aliaksandr Valialkin
e2eac858b5 lib/storage: calculate the maximum number of rows per small part from -memory.allowedPercent
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/159

This simplifies error detection additionally to the `vm_rows_ignored_total` counters.
2019-08-25 15:29:09 +03:00