Commit graph

185 commits

Author SHA1 Message Date
Jeremy Meulemans 025c828976 Changed to open_head_chunks to address review.
Now incrementing numHeadChunks directly.
2017-02-17 07:10:13 -06:00
Jeremy Meulemans 074050b8c0 Updating for failed codeclimate check. 2017-02-16 18:04:28 -06:00
Jeremy Meulemans f70b52d0b6 Adding gauge for number of open head chunks.
Fixes #1710
2017-02-16 17:56:45 -06:00
beorn7 bed4934224 storage: One more persist error code path discovered
Also, in that code path, set chunkDescsOffset to 0 rather than -1 in
case of "dropped more chunks from persistence than from memory" so
that no other weird things happen before the series is quarantined for
good.
2017-02-09 11:51:40 +01:00
beorn7 8c8baaa558 storage: writeMemorySeries needs to return true for quarantined series
This is another fallout of my bug hunt.
2017-02-08 16:28:56 +01:00
beorn7 65dc8f44d3 storage: Test for errors returned by MaybePopulateLastTime 2017-02-01 23:43:58 +01:00
Brian Brazil f64c231dad Allow checkpoints and maintenance to happen concurrently. (#2321)
This is essential on larger Prometheus servers, as otherwise
checkpoints prevent sufficient persisting of chunks to disk.
2017-01-13 17:24:19 +00:00
Brian Brazil 1dcb7637f5 Add various persistence related metrics (#2333)
Add metrics around checkpointing and persistence

* Add a metric to say if checkpointing is happening,
and another to track total checkpoint time and count.

This breaks the existing prometheus_local_storage_checkpoint_duration_seconds
by renaming it to prometheus_local_storage_checkpoint_last_duration_seconds
as the former name is more appropriate for a summary.

* Add metric for last checkpoint size.

* Add metric for series/chunks processed by checkpoints.

For long checkpoints it'd be useful to see how they're progressing.

* Add metric for dirty series

* Add metric for number of chunks persisted per series.

You can get the number of chunks from chunk_ops,
but not the matching number of series. This helps determine
the size of the writes being made.

* Add metric for chunks queued for persistence

Chunks created includes both chunks that'll need persistence
and chunks read in for queries. This only includes chunks created
for persistence.

* Code review comments on new persistence metrics.
2017-01-11 15:11:19 +00:00
Mitsuhiro Tanda 7e369b9318 expose max memory chunks metrics (#2303)
* expose max memory chunks metrics
2016-12-27 18:34:07 +00:00
beorn7 253be23c00 storage: Sanity-check number of loaded chunk descs
Two cases:

- An unarchived metric must have at least one chunk desc loaded upon
  unarchival. Otherwise, the file is gone or has size 0, which is an
  inconsistency (because the series is still indexed in the archive
  index). Hence, quarantining is triggered.

- If loading the chunk descs of a series with a known chunkDescsOffset
  (i.e. != -1), the number of chunks loaded must be equal to
  chunkDescsOffset. If not, there is a data corruption. An error is
  returned, which leads to qurantining.

In any case, there is a guard added to not access the 1st element of
an empty chunkDescs slice. (That's what triggered the crashes in issue
2249.)  A time series with unknown chunkDescsOffset and no chunks in
memory and no chunks on disk either could trigger that case. I would
assume such a "null series" doesn't exist, but it's not entirely
unthinkable and unreasonable to happen (perhaps in future uses of the
storage). (Create a series, and then something tries to preload chunks
before the first sample is added.)
2016-12-13 23:19:39 +01:00
Fabian Reinartz 6703404cb4 Merge remote-tracking branch 'origin/release-1.2' 2016-11-01 16:35:22 +01:00
beorn7 c5bd178b93 Protect exported Querier interface method against negative time ranges 2016-11-01 15:05:01 +01:00
Fabian Reinartz 8fa18d564a storage: enhance Querier interface usage
This extracts Querier as an instantiateable and closeable object
rather than just defining extending methods of the storage interface.
This improves composability and allows abstracting query transactions,
which can be useful for transaction-level caches, consistent data views,
and encapsulating teardown.
2016-10-16 10:39:29 +02:00
Björn Rabenstein 1e2f03f668 Merge pull request #2005 from redbaron/microoptimise-matching
Microoptimise matching
2016-10-05 17:26:56 +02:00
Maxim Ivanov e6db9f8159 New fpsForLabelMatchers and seriesForLabelMatchers methods
These more specific methods have replaced `metricForLabelMatchers`
in cases where its  `map[fingerprint]metric` result type was
not necessary or was used as an intermediate step

Avoids duplicated calls to `seriesForRange` from
`QueryRange` and `QueryInstant` methods.
2016-10-05 15:15:54 +01:00
Julius Volz c9d4526428 Unpublish accidentally published series methods
There were some more accidentally published methods of the memorySeries
type which I didn't notice when reviewing https://github.com/prometheus/prometheus/pull/2011
2016-10-03 00:04:56 +02:00
Maxim Ivanov 4978a65495 Extract initial FP candidate build logic into candidateFPsForLabelMatchers method
No functional changes otherwise
2016-10-02 17:35:02 +01:00
Maxim Ivanov c048a0cde8 Add metrics to result after checking all matchers
Should be marginally faster and somewhat more GC friendly
2016-10-02 17:35:02 +01:00
Julius Volz c25f0de5ae Remove local.ZeroSample{,Pair}, use model definitions 2016-09-28 23:42:45 +02:00
Julius Volz 044ebce779 Review fixups. 2016-09-28 23:42:44 +02:00
Julius Volz d30a3c7c0f Fix accidental publishing of memorySeries.firstTime() 2016-09-26 13:25:27 +02:00
Julius Volz ab80ced756 storage: separate chunk package, publish more names
This is a followup to https://github.com/prometheus/prometheus/pull/2011.

This publishes more of the methods and other names of the chunk code and
moves the chunk code to its own package. There's some unavoidable
ugliness: the chunk and chunkDesc metrics are used by both packages, so
I had to move them to the chunk package. That isn't great, but I don't
see how to do it better without a larger redesign of everything. Same
for the evict requests and some other types.
2016-09-26 13:25:11 +02:00
Matthew Campbell 67d76e3a5d timeseries: store varbit encoded data into cassandra 2016-09-21 17:56:55 +02:00
Julius Volz c187308366 storage: Contextify storage interfaces.
This is based on https://github.com/prometheus/prometheus/pull/1997.

This adds contexts to the relevant Storage methods and already passes
PromQL's new per-query context into the storage's query methods.
The immediate motivation supporting multi-tenancy in Frankenstein, but
this could also be used by Prometheus's normal local storage to support
cancellations and timeouts at some point.
2016-09-19 16:29:07 +02:00
Julius Volz 3bfec97d46 Make the storage interface higher-level.
See discussion in
https://groups.google.com/forum/#!topic/prometheus-developers/bkuGbVlvQ9g

The main idea is that the user of a storage shouldn't have to deal with
fingerprints anymore, and should not need to do an individual preload
call for each metric. The storage interface needs to be made more
high-level to not expose these details.

This also makes it easier to reuse the same storage interface for remote
storages later, as fewer roundtrips are required and the fingerprint
concept doesn't work well across the network.

NOTE: this deliberately gets rid of a small optimization in the old
query Analyzer, where we dedupe instants and ranges for the same series.
This should have a minor impact, as most queries do not have multiple
selectors loading the same series (and at the same offset).
2016-07-25 13:59:22 +02:00
beorn7 fc6737b7fb storage: improve index lookups
tl;dr: This is not a fundamental solution to the indexing problem
(like tindex is) but it at least avoids utilizing the intersection
problem to the greatest possible amount.

In more detail:

Imagine the following query:

    nicely:aggregating:rule{job="foo",env="prod"}

While it uses a nicely aggregating recording rule (which might have a
very low cardinality), Prometheus still intersects the low number of
fingerprints for `{__name__="nicely:aggregating:rule"}` with the many
thousands of fingerprints matching `{job="foo"}` and with the millions
of fingerprints matching `{env="prod"}`. This totally innocuous query
is dead slow if the Prometheus server has a lot of time series with
the `{env="prod"}` label. Ironically, if you make the query more
complicated, it becomes blazingly fast:

    nicely:aggregating:rule{job=~"foo",env=~"prod"}

Why so? Because Prometheus only intersects with non-Equal matchers if
there are no Equal matchers. That's good in this case because it
retrieves the few fingerprints for
`{__name__="nicely:aggregating:rule"}` and then starts right ahead to
retrieve the metric for those FPs and checking individually if they
match the other matchers.

This change is generalizing the idea of when to stop intersecting FPs
and go into "retrieve metrics and check them individually against
remaining matchers" mode:

- First, sort all matchers by "expected cardinality". Matchers
  matching the empty string are always worst (and never used for
  intersections). Equal matchers are in general consider best, but by
  using some crude heuristics, we declare some better than others
  (instance labels or anything that looks like a recording rule).

- Then go through the matchers until we hit a threshold of remaining
  FPs in the intersection. This threshold is higher if we are already
  in the non-Equal matcher area as intersection is even more expensive
  here.

- Once the threshold has been reached (or we have run out of matchers
  that do not match the empty string), start with "retrieve metrics
  and check them individually against remaining matchers".

A beefy server at SoundCloud was spending 67% of its CPU time in index
lookups (fingerprintsForLabelPairs), serving mostly a dashboard that
is exclusively built with recording rules. With this change, it spends
only 35% in fingerprintsForLabelPairs. The CPU usage dropped from 26
cores to 18 cores. The median latency for query_range dropped from 14s
to 50ms(!). As expected, higher percentile latency didn't improve that
much because the new approach is _occasionally_ running into the worst
case while the old one was _systematically_ doing so. The 99th
percentile latency is now about as high as the median before (14s)
while it was almost twice as high before (26s).
2016-07-20 17:35:53 +02:00
beorn7 064b57858e Consistently use the Seconds() method for conversion of durations
This also fixes one remaining case of recording integral numbers
of seconds only for a metric, i.e. this will probably fix #1796.
2016-07-07 15:24:35 +02:00
Julius Volz 91401794fa storage: Make MemorySeriesStorage a public type
See https://twitter.com/fabxc/status/748032597876482048
2016-06-29 08:14:23 +02:00
Fabian Reinartz 425736a377 *: remove last remainers of non-second metrics 2016-06-23 17:50:39 +02:00
Julius Volz b7b6717438 Separate query interface out of local.Storage.
PromQL only requires a much narrower interface than local.Storage in
order to run queries. Narrower interfaces are easier to replace and
test, too.

We could also change the web interface to use local.Querier, except that
we'll probably use appending functions from there in the future.
2016-06-23 15:14:38 +02:00
beorn7 99881ded63 Make the number of fingerprint mutexes configurable
With a lot of series accessed in a short timeframe (by a query, a
large scrape, checkpointing, ...), there is actually quite a
significant amount of lock contention if something similar is running
at the same time.

In those cases, the number of locks needs to be increased.

On the same front, as our fingerprints don't have a lot of entropy, I
introduced some additional shuffling. With the current state, anly
changes in the least singificant bits of a FP would matter.
2016-06-02 19:18:00 +02:00
beorn7 b2ef4dc52d Correctly identify no-op appends if the value is NaN
This requires an updating of the vendored commen.model package, which
I will do once https://github.com/prometheus/common/pull/40 is merged.
2016-05-19 18:32:47 +02:00
beorn7 07a294ac15 Doc comment fixes 2016-04-26 01:05:56 +02:00
beorn7 20cba1ed8f Initialize metric vectors in memorySeriesStorage 2016-04-25 17:08:07 +02:00
beorn7 d566808d40 Bring back logging of discarded samples
But only on DEBUG level.

Also, count and report the two cases of out-of-order timestamps on the
one hand and same timestamp but different value on the other hand
separately.
2016-04-25 16:43:52 +02:00
beorn7 a90d645378 Checkpoint fingerprint mappings only upon shutdown
Before, we checkpointed after every newly detected fingerprint
collision, which is not a problem as long as collisions are
rare. However, with a sufficient number of metrics or particular
nature of the data set, there might be a lot of collisions, all to be
detected upon the first set of scrapes, and then the checkpointing
after each detection will take a quite long time (it's O(n²),
essentially).

Since we are rebuilding the fingerprint mapping during crash recovery,
the previous, very conservative approach didn't even buy us
anything. We only ever read from the checkpoint file after a clean
shutdown, so the only time we need to write the checkpoint file is
during a clean shutdown.
2016-04-15 01:03:28 +02:00
beorn7 199f309a39 Resurrect and rename invalid preload requests count metric.
It is now also used in label matching, so the name of the metric
changed from `prometheus_local_storage_invalid_preload_requests_total`
to `non_existent_series_matches_total'.
2016-03-13 11:54:24 +01:00
beorn7 e8c1f30ab2 Merge the parallel logic of getSeriesForRange and metricForFingerprint 2016-03-09 21:56:15 +01:00
beorn7 9445c7053d Add tests for range-limited label matching
While doing so, improve getSeriesForRange.
2016-03-09 21:01:03 +01:00
beorn7 47e3c90f9b Clean up error propagation
Only return an error where callers are doing something with it except
simply logging and ignoring.

All the errors touched in this commit flag the storage as dirty
anyway, and that fact is logged anyway. So most of what is being
removed here is just log spam.

As discussed earlier, the class of errors that flags the storage as
dirty signals fundamental corruption, no even bubbling up a one-time
warning to the user (e.g. about incomplete results) isn't helping much
because _anything_ happening in the storage has to be doubted from
that point on (and in fact retroactively into the past, too). Flagging
the storage dirty, and alerting on it (plus marking the state in the
web UI) is the only way I can see right now.

As a byproduct, I cleaned up the setDirty method a bit and improved
the logged errors.
2016-03-09 18:56:30 +01:00
beorn7 99854a84d7 Merge branch 'beorn7/storage6' into beorn7/storage7 2016-03-09 17:23:25 +01:00
beorn7 b343e65907 Merge branch 'beorn7/storage4' into beorn7/storage5
erge is necessary,
2016-03-09 17:14:42 +01:00
beorn7 d0a4477446 Merge branch 'beorn7/storage3' into beorn7/storage4
Conflicts:
	storage/local/preload.go
	storage/local/storage.go
	storage/local/storage_test.go
2016-03-09 17:13:16 +01:00
beorn7 55eddab25f Merge branch 'beorn7/storage2' into beorn7/storage3 2016-03-09 16:48:46 +01:00
beorn7 beb36df4bb De-flag preloadChunksForRange
Now there is preloadChunksForRange and preloadChunksForInstant in
both, the series and the storage.
2016-03-09 14:50:09 +01:00
beorn7 836f1db04c Improve MetricsForLabelMatchers
WIP: This needs more tests.

It now gets a from and through value, which it may opportunistically
use to optimize the retrieval. With possible future range indices,
this could be used in a very efficient way. This change merely applies
some easy checks, which should nevertheless solve the use case of
heavy rule evaluations on servers with a lot of series churn.

Idea is the following:

- Only archive series that are at least as old as the headChunkTimeout
  (which was already extremely unlikely to happen).

- Then maintain a high watermark for the last archival, i.e. no
  archived series has a sample more recent than that watermark.

- Any query that doesn't reach to a time before that watermark doesn't
  have to touch the archive index at all. (A production server at
  Soundcloud with the aforementioned series churn and heavy rule
  evaluations spends 50% of its CPU time in archive index
  lookups. Since rule evaluations usually only touch very recent
  values, most of those lookup should disappear with this change.)

- Federation with a very broad label matcher will profit from this,
  too.

As a byproduct, the un-needed MetricForFingerprint method was removed
from the Storage interface.
2016-03-09 00:25:59 +01:00
beorn7 fc7de5374a Quarantine series upon problem writing to the series file
This fixes https://github.com/prometheus/prometheus/issues/1059 , but
not in the obvious way (simply not updating the persist watermark,
because that's actually not that simple - we don't really know what
has gone wrong exactly). As any errors relevant here are most likely
caused by severe and unrecoverable problems with the series file,
Using the now quarantine feature is the right step. We don't really
have to be worried about any inconsistent state of the series because
it will be removed for good ASAP. Another plus is that we don't have
to declare the whole storage dirty anymore.
2016-03-03 13:15:02 +01:00
beorn7 0ea5801e47 Handle errors caused by data corruption more gracefully
This requires all the panic calls upon unexpected data to be converted
into errors returned. This pollute the function signatures quite
lot. Well, this is Go...

The ideas behind this are the following:

- panic only if it's a programming error. Data corruptions happen, and
  they are not programming errors.

- If we detect a data corruption, we "quarantine" the series,
  essentially removing it from the database and putting its data into
  a separate directory for forensics.

- Failure during writing to a series file is not considered corruption
  automatically. It will call setDirty, though, so that a
  crashrecovery upon the next restart will commence and check for
  that.

- Series quarantining and setDirty calls are logged and counted in
  metrics, but are hidden from the user of the interfaces in
  interface.go, whith the notable exception of Append(). The reasoning
  is that we treat corruption by removing the corrupted series, i.e. a
  query for it will return no results on its next call anyway, so
  return no results right now. In the case of Append(), we want to
  tell the user that no data has been appended, though.

Minor side effects:

- Now consistently using filepath.* instead of path.*.

- Introduced structured logging where I touched it. This makes things
  less consistent, but a complete change to structured logging would
  be out of scope for this PR.
2016-03-02 23:02:34 +01:00
beorn7 c740789ce3 Improve predict_linear
Fixes https://github.com/prometheus/prometheus/issues/1401

This remove the last (and in fact bogus) use of BoundaryValues.

Thus, a whole lot of unused (and arguably sub-optimal / ugly) code can
be removed here, too.
2016-02-25 12:10:55 +01:00
beorn7 4b503ed9a5 Merge branch 'master' into beorn7/storage2 2016-02-24 14:03:49 +01:00