Aliaksandr Valialkin
ec3df0b913
app/vmselect/netstorage: improve scalability of blocks processing on systems with multiple CPU cores
...
Previously a single syncwg.WaitGroup was used for tracking the lifetime of processBlock callbacks
across all the per-vmstorage goroutines. This could be slow on systems with many CPU cores
because of inter-CPU synchronization overhead.
Use a separate per-vmstorage sync.WaitGroup instead in order to reduce inter-CPU synchronization overhead.
This should imrpove performance for heavy queries over big number of blocks on multi-CPU systems.
2022-08-11 21:37:24 +03:00
Aliaksandr Valialkin
1996e36cf0
app/vmselect/netstorage: prevent from calling processBlocks callback after the exit from ProcessBlocks function
...
This should prevent from panic at multi-level vmselect
when the top-level vmselect is configured with -replicationFactor > 1
2022-08-08 13:32:44 +03:00
Aliaksandr Valialkin
2635211bf4
app/vmselect/netstorage: properly detect and log timeout errors when querying vmstorage from vmselect
...
This change is based on https://github.com/VictoriaMetrics/VictoriaMetrics/pull/2937
Thanks to @isodude for the initial pull request.
2022-08-08 00:21:05 +03:00
Aliaksandr Valialkin
43185353bc
app/vmselect/netstorage: cleanup after 92630c1ab4
...
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/2896
2022-08-04 18:34:38 +03:00
Aliaksandr Valialkin
c81d2b4c18
app/vmselect/netstorage: initializes tsw.rowsProcessed before calling tsw.f, since tsw.f can modify r.Timestamps and r.Values lengths
2022-07-30 00:39:14 +03:00
Aliaksandr Valialkin
5ddae2e293
app/vmselect/netstorage: re-use random generator used for series shuffle in Result.RunParallel
...
This should reduce CPU usage needed for rand.Rand initialization
2022-07-30 00:31:00 +03:00
Aliaksandr Valialkin
3d4c312ba2
app/vmselect/netstorage: improve the speed of queries over big number of time series on multi-CPU system
...
Reduce inter-CPU communications when processing the query over big number of time series.
This should improve performance for queries over big number of time series
on systems with many CPU cores.
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/2896
Based on b596ac3745
2022-07-25 09:22:28 +03:00
Aliaksandr Valialkin
fbb403b5c0
app/vmselect/netstorage: optimize mergeSortBlocks() for the worst case when blocks contain interleaved samples
2022-07-12 12:30:24 +03:00
Aliaksandr Valialkin
c0af52228a
app/vmselect/netstorage: add benchmarks for mergeSortBlocks
...
This is a follow-up for 743ff84863
2022-07-11 12:53:46 +03:00
Aliaksandr Valialkin
d442ee4610
app/vmselect/netstorage: optimize mergeSortBlocks function
...
- Use binary search instead of linear scan when locating the run of smallest timestamps
in blocks with intersected time ranges. This should improve performance
when merging blocks with big number of samples
- Skip samples with duplicate timestamps. This should increase query performance
in cluster version of VictoriaMetrics with the enabled replication.
2022-07-09 00:35:38 +03:00
Aliaksandr Valialkin
195dccf678
app/vmselect: add ability to query vmselect from another vmselect
2022-07-06 13:19:45 +03:00
Aliaksandr Valialkin
cdd89d9cc2
app/vmselect: properly generate response for /api/v1/series
...
The response has been broken in 7d5d33fd71
2022-07-06 12:46:23 +03:00
Aliaksandr Valialkin
270e555f47
lib/vmselectapi: pass maxSuffixes arg to tagValueSuffixes RPC call
2022-07-06 12:46:22 +03:00
Aliaksandr Valialkin
f4df43f7cc
app/vmselect/netstorage: remove unused auth.Token arg
2022-07-06 12:46:21 +03:00
Aliaksandr Valialkin
78eeca6f0d
lib/vmselectapi: rename deleteMetrics to more correct deleteSeries
2022-07-06 12:46:21 +03:00
Aliaksandr Valialkin
daefb64f38
app/vmselect: expose additional histograms at /metrics page, which may help get more insights for the query workload
...
This commit is based on https://github.com/VictoriaMetrics/VictoriaMetrics/pull/2792
2022-06-28 20:18:31 +03:00
Aliaksandr Valialkin
7d5d33fd71
lib/storage: return marshaled metric names from SearchMetricNames
...
Previously SearchMetricNames was returning unmarshaled metric names.
This wasn't great for vmstorage, which should spend additional CPU time
for marshaling the metric names before sending them to vmselect.
While at it, remove possible duplicate metric names, which could occur when
multiple samples for new time series are ingested via concurrent requests.
Also sort the metric names before returning them to the client.
This simplifies debugging of the returned metric names across repeated requests to /api/v1/series
2022-06-28 18:16:32 +03:00
Aliaksandr Valialkin
399d4c36ae
app/vmselect: optimize /api/v1/series a bit for time ranges smaller than one day
2022-06-28 12:55:20 +03:00
Aliaksandr Valialkin
a667d339be
app/vmselect/netstorage/netstorage.go: group metrics in order to improve readability a bit
2022-06-27 14:00:24 +03:00
Aliaksandr Valialkin
08de733924
app/vmselect/netstorage: assume the response is full if up to -replicationFactor-1 vmstorage nodes are unavailable
...
This is a follow-up for ee5c502446https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1767
2022-06-27 12:21:26 +03:00
Aliaksandr Valialkin
bc9d704ef4
app/vmselect/netstorage: remove Get prefix from netstorage functions
...
This makes these function names more consistent with the server side
2022-06-27 00:37:49 +03:00
hagen1778
e40d015e9a
vmselect: make vm_partial_results_total consistent
...
Metrics `vm_partial_results_total` and `vm_requests_total` serving
the similar purpose, but contain inconsistent set of labels.
This change updates `vm_partial_results_total` labels to be consistent
with `vm_requests_total`.
The change breaks backward compatibility with assumption that
`vm_partial_results_total` wasn't widely used, since it is
not documented and absent in the alerts and dashboards.
Signed-off-by: hagen1778 <roman@victoriametrics.com>
2022-06-24 13:50:26 +02:00
Nikolay
ee5c502446
app/vmselect: fixes partial response with replicationFactor ( #2777 )
...
* app/vmselect: fixes partial response with replicationFactor
Allow partial response if it meets replicationFactor configured at vmselect
https://t.me/VictoriaMetrics_ru1/38490
* docs/CHANGELOG.md: document this change
Co-authored-by: Aliaksandr Valialkin <valyala@victoriametrics.com>
2022-06-23 20:17:24 +03:00
Aliaksandr Valialkin
dceca7e864
all: remove explicit "xxhash" name when importing github.com/cespare/xxhash/v2 package
...
This is a follow-up for fe2269b999
2022-06-21 20:27:30 +03:00
Aliaksandr Valialkin
b28c6febf9
app/{vminsert,vmselect}: add -vmstorageDialTimeout command-line flag for tuning the maximum time needed for establishing connections to vmstorage
...
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/711
2022-06-20 15:17:34 +03:00
Aliaksandr Valialkin
da1d1e83df
app/{vmselect,vmstorage}: properly pass seriesCountByLabelName and seriesCountByFocusLabelValue entries from vmstorage to vmselect
2022-06-16 10:44:29 +03:00
Aliaksandr Valialkin
ee9954082f
app/vmselect/netstorage: properly aggregate seriesCountByLabelName and seriesCountByFocusLabelValue obtained from multiple vmselect nodes at /api/v1/status/tsdb
2022-06-15 16:48:40 +03:00
Aliaksandr Valialkin
45fa9d798d
app/vmselect: accept focusLabel query arg at /api/v1/status/tsdb
2022-06-14 18:39:00 +03:00
Aliaksandr Valialkin
61e03f172b
app/vmselect: optimize /api/v1/labels and /api/v1/label/.../values handlers when match[] query arg is passed to them
2022-06-12 14:06:24 +03:00
Aliaksandr Valialkin
4a94cd81ce
app/vmselect: add optional limit query arg to /api/v1/labels and /api/v1/label_values endpoints
...
This arg allows limiting the number of sample values returned from these APIs
2022-06-10 10:24:07 +03:00
Aliaksandr Valialkin
a9ea3fee38
lib/querytracer: make it easier to use by passing trace context message to New and NewChild
...
The context message can be extended by calling Donef.
If there is no need to extend the message, then just call Done.
2022-06-08 21:16:12 +03:00
Aliaksandr Valialkin
2b343d8bd0
app: properly collect and merge /api/v1/status/tsdb info from vmstorage nodes
...
The collection has been broken in f2754c3e90https://github.com/VictoriaMetrics/VictoriaMetrics/issues/2233
2022-06-08 19:26:09 +03:00
Dmytro Kozlov
f2754c3e90
Cardinality explorer ( #2625 )
...
* Cardinality explorer
* vmui, vmselect: updated field name, added description to spinner
* make vmui-update
* updated const name, make vmui-update
* lib/storage: changes calculation for totalSeries values
* added static files
* wip
* wip
* wip
* wip
* docs/CHANGELOG.md: document cardinality explorer feature
See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/2233
Co-authored-by: f41gh7 <nik@victoriametrics.com>
Co-authored-by: Aliaksandr Valialkin <valyala@victoriametrics.com>
2022-06-08 18:54:27 +03:00
Aliaksandr Valialkin
c92bc5394f
app/vmselect/netstorage: properly read trace from vmstorage when it returns error message to vmselect
2022-06-01 14:35:00 +03:00
Aliaksandr Valialkin
afced37c0b
all: add initial support for query tracing
...
See https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#query-tracing
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1403
2022-06-01 02:31:44 +03:00
Aliaksandr Valialkin
a4a15a462b
app/vmselect/netstorage: bump RPC API versions for vmselect->vmstorage communications
...
This is a follow-up after b843f0e229
2022-04-08 12:36:04 +03:00
Aliaksandr Valialkin
b843f0e229
app/vmselect: add fine-grained limits for the number of returned/scanned time series for various APIs
2022-03-26 11:28:14 +02:00
Aliaksandr Valialkin
89ead3daca
app/vmselect/netstorage: report vmstorage errors to vmselect clients even if partial responses are allowed
...
If a vmstorage is reachable and returns an application-level error to vmselect,
then such error must be returned to the caller even if partial responses are allowed,
since it usually means cluster mis-configuration.
Partial responses may be returned only if some vmstorage nodes are temporarily unavailable.
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1941
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/678
2022-02-21 21:17:05 +02:00
Aliaksandr Valialkin
5f266370c5
all: follow-up after 4bdd10ab90
...
Properly use new bytesutil.Resize* functions
2022-02-01 17:49:28 +02:00
Aliaksandr Valialkin
6232eaa938
lib/bytesutil: split Resize() into ResizeNoCopy() and ResizeWithCopy() functions
...
Previously bytesutil.Resize() was copying the original byte slice contents to a newly allocated slice.
This wasted CPU cycles and memory bandwidth in some places, where the original slice contents wasn't needed
after slize resizing. Switch such places to bytesutil.ResizeNoCopy().
Rename the original bytesutil.Resize() function to bytesutil.ResizeWithCopy() for the sake of improved readability.
Additionally, allocate new slice with `make()` instead of `append()`. This guarantees that the capacity of the allocated slice
exactly matches the requested size. The `append()` could return a slice with bigger capacity as an optimization for further `append()` calls.
This could result in excess memory usage when the returned byte slice was cached (for instance, in lib/blockcache).
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/2007
2022-01-25 15:28:42 +02:00
Aliaksandr Valialkin
bc3923111b
lib/storage: return dedup interval in milliseconds from GetDedupInterval()
...
This removes duplicate .Milliseconds() calls after GetDedupInterval() calls.
2021-12-15 13:27:27 +02:00
Aliaksandr Valialkin
cdfe854c9b
lib/storage: explicitly pass dedupInterval to DeduplicateSamples() and deduplicateSamplesDuringMerge()
...
This improves the code readability and debuggability, since the output of these functions
stops depending on global state.
2021-12-14 20:52:29 +02:00
Aliaksandr Valialkin
a746fe8778
app/vmselect/promql: follow-up after 57b3320478
2021-09-24 01:25:04 +03:00
Aliaksandr Valialkin
7ad54041fe
app/{vminsert,vmselect}: automatically add missing port in -storageNode lists passed to vminsert and vmselect
...
This should simplify manual setup of the cluster according to https://docs.victoriametrics.com/Cluster-VictoriaMetrics.html#cluster-setup
2021-09-15 18:04:30 +03:00
Aliaksandr Valialkin
99004a6a40
app/vmselect/netstorage: unpack time series data in mostly local big chunks
...
This should improve performance on multi-CPU systems for queries selecting time series with big number of raw samples
2021-07-30 12:26:33 +03:00
Aliaksandr Valialkin
cbb81c2ce9
app/vmselect/netstorage: do not query Go maps with unsafe string keys, since this breaks in Go 1.17
2021-07-30 10:28:19 +03:00
Aliaksandr Valialkin
49bf3abf67
app/vmselect: follow-up for 626073bca8
...
* Rename -search.maxMetricsPointSearch to -search.maxSamplesPerQuery, so it is more consistent with the existing -search.maxSamplesPerSeries
* Move the -search.maxSamplesPerQuery from vmstorage to vmselect, so it could effectively limit the number of raw samples obtained from all the vmstorage nodes
* Document the -search.maxSamplesPerQuery in docs/CHANGELOG.md
2021-07-28 18:00:04 +03:00
Aliaksandr Valialkin
3921d8afae
app/vmselect: prevent from possible deadlock when f callback blocks inside RunParallel
2021-07-26 15:50:45 +03:00
Aliaksandr Valialkin
b92702f6d5
app/vmselect/netstorage: use more scalable algorithm for ditributing the work among among multiple channels on systems with big number of CPU cores
2021-07-16 00:35:36 +03:00
Aliaksandr Valialkin
5830ce2706
app/vmselect/netstorage: add -search.maxSamplesPerSeries command-line option for limiting the number of samples a query can process per each series
...
This should prevent from out of memory crashes like in https://github.com/VictoriaMetrics/VictoriaMetrics/issues/1067
2021-07-15 16:53:35 +03:00
