Commit Graph

317 Commits (027d8968d57463924146fd57c6057d0d00e0f492)

Author SHA1 Message Date
Julius Volz 740d448983 Use custom timestamp type for sample timestamps and related code.
So far we've been using Go's native time.Time for anything related to sample
timestamps. Since the range of time.Time is much bigger than what we need, this
has created two problems:

- there could be time.Time values which were out of the range/precision of the
  time type that we persist to disk, therefore causing incorrectly ordered keys.
  One bug caused by this was:

  https://github.com/prometheus/prometheus/issues/367

  It would be good to use a timestamp type that's more closely aligned with
  what the underlying storage supports.

- sizeof(time.Time) is 192, while Prometheus should be ok with a single 64-bit
  Unix timestamp (possibly even a 32-bit one). Since we store samples in large
  numbers, this seriously affects memory usage. Furthermore, copying/working
  with the data will be faster if it's smaller.

*MEMORY USAGE RESULTS*
Initial memory usage comparisons for a running Prometheus with 1 timeseries and
100,000 samples show roughly a 13% decrease in total (VIRT) memory usage. In my
tests, this advantage for some reason decreased a bit the more samples the
timeseries had (to 5-7% for millions of samples). This I can't fully explain,
but perhaps garbage collection issues were involved.

*WHEN TO USE THE NEW TIMESTAMP TYPE*
The new clientmodel.Timestamp type should be used whenever time
calculations are either directly or indirectly related to sample
timestamps.

For example:
- the timestamp of a sample itself
- all kinds of watermarks
- anything that may become or is compared to a sample timestamp (like the timestamp
  passed into Target.Scrape()).

When to still use time.Time:
- for measuring durations/times not related to sample timestamps, like duration
  telemetry exporting, timers that indicate how frequently to execute some
  action, etc.

*NOTE ON OPERATOR OPTIMIZATION TESTS*
We don't use operator optimization code anymore, but it still lives in
the code as dead code. It still has tests, but I couldn't get all of them to
pass with the new timestamp format. I commented out the failing cases for now,
but we should probably remove the dead code soon. I just didn't want to do that
in the same change as this.

Change-Id: I821787414b0debe85c9fffaeb57abd453727af0f
2013-12-03 09:11:28 +01:00
Julius Volz 6b7de31a3c Upgrade to LevelDB 1.14.0 to fix LevelDB bugs.
This tentatively fixes https://github.com/prometheus/prometheus/issues/368 due
to an upstream bugfix in snapshotted LevelDB iterator handling, which got fixed
in LevelDB 1.14.0:

https://code.google.com/p/leveldb/issues/detail?id=200

Change-Id: Ib0cc67b7d3dc33913a1c16736eff32ef702c63bf
2013-12-03 09:07:15 +01:00
Julius Volz db015de65b Comment and "go fmt" fixups in compaction tests.
Change-Id: Iaa0eda6a22a5caa0590bae87ff579f9ace21e80a
2013-10-30 17:06:17 +01:00
Julius Volz 51408bdfe8 Merge changes I3ffeb091,Idffefea4
* changes:
  Add chunk sanity checking to dumper tool.
  Add compaction regression tests.
2013-10-24 13:58:14 +02:00
Julius Volz 2162e57784 Merge "Fix watermarker default time / LevelDB key ordering bug." 2013-10-24 13:57:48 +02:00
Julius Volz 5e18255920 Merge "Fix chunk corruption compaction bug." 2013-10-24 13:57:31 +02:00
Julius Volz eb461a707d Add chunk sanity checking to dumper tool.
Also, move codecs/filters to common location so they can be used in subsequent
test.

Change-Id: I3ffeb09188b8f4552e42683cbc9279645f45b32e
2013-10-23 01:06:49 +02:00
Julius Volz 6ea22f2bf9 Add compaction regression tests.
This adds regression tests that catch the two error cases reported in

  https://github.com/prometheus/prometheus/issues/367

It also adds a commented-out test case for the crash in

  https://github.com/prometheus/prometheus/issues/368

but there's no fix for the latter crash yet.

Change-Id: Idffefea4ed7cc281caae660bcad2e3c13ec3bd17
2013-10-23 01:06:28 +02:00
Conor Hennessy 9a48010cec Add a check for metrics directory existence.
Previously on startup the program would just quit without stating
explicitly why.

Change-Id: I833b85eb74d2dd27cdc3f0f2e65d7bb1c42caa39
2013-10-22 20:54:34 +02:00
Julius Volz b5f6e3c90c Fix watermarker default time / LevelDB key ordering bug.
This fixes part 2) of https://github.com/prometheus/prometheus/issues/367
(uninitialized time.Time mapping to a higher LevelDB key than "normal"
timestamps).

Change-Id: Ib079974110a7b7c4757948f81fc47d3d29ae43c9
2013-10-21 14:32:21 +02:00
Julius Volz a1a97ed064 Fix chunk corruption compaction bug.
This fixes part 1) of https://github.com/prometheus/prometheus/issues/367 (the
storing of samples with the wrong fingerprint into a compacted chunk, thus
corrupting it).

Change-Id: I4c36d0d2e508e37a0aba90b8ca2ecc78ee03e3f1
2013-10-21 14:30:22 +02:00
Matt T. Proud 86fcbe5bde Retain DTO on each cycle.
Change-Id: Ifc6f68f98eacb01097771d0dbf043c98bba1d518
2013-09-05 10:14:34 +02:00
Matt T. Proud 4a87c002e8 Update low-level i'faces to reflect wireformats.
This commit fixes a critique of the old storage API design, whereby
the input parameters were always as raw bytes and never Protocol
Buffer messages that encapsulated the data, meaning every place a
read or mutation was conducted needed to manually perform said
translations on its own.  This is taxing.

Change-Id: I4786938d0d207cefb7782bd2bd96a517eead186f
2013-09-04 17:13:58 +02:00
Matt T. Proud 7910f6e863 Prevent total storage locking during memory flush.
While a hack, this change should allow us to serve queries
expeditiously during a flush operation.

Change-Id: I9a483fd1dd2b0638ab24ace960df08773c4a5079
2013-08-29 11:33:38 +02:00
Matt T. Proud 12d5e6ca5a Curation should not starve user-interactive ops.
The background curation should be staggered to ensure that disk
I/O yields to user-interactive operations in a timely manner. The
lack of routine prioritization necessitates this.

Change-Id: I9b498a74ccd933ffb856e06fedc167430e521d86
2013-08-26 19:40:55 +02:00
Matt T. Proud 2b42fd0068 Snapshot of no more frontier.
Change-Id: Icd52da3f52bfe4529829ea70b4865ed7c9f6c446
2013-08-23 17:13:58 +02:00
Matt T. Proud 7db518d3a0 Abstract high watermark cache into standard LRU.
Conflicts:
	storage/metric/memory.go
	storage/metric/tiered.go
	storage/metric/watermark.go

Change-Id: Iab2aedbd8f83dc4ce633421bd4a55990fa026b85
2013-08-19 12:26:55 +02:00
Matt T. Proud d74c2c54d4 Interfacification of stream.
Move the stream to an interface, for a number of additional changes
around it are underway.

Conflicts:
	storage/metric/memory.go

Change-Id: I4a5fc176f4a5274a64ebdb1cad52600954c463c3
2013-08-16 17:35:21 +02:00
Matt T. Proud c262907fec Kill interface cruft.
These pieces were never used and should be thusly removed.

Change-Id: I8dd151ec4c40b6d3ccffad1bb9b8b75a92e9ee37
2013-08-15 11:39:07 +02:00
Matt T. Proud b23acccea8 Kill AppendSample interface definition.
AppendSample will be repcated with AppendSamples, which will take
advantage of bulks appends.  This is a necessary step for indexing
pipeline decoupling.

Change-Id: Ia83811a87bcc89973d3b64d64b85a28710253ebc
2013-08-15 11:35:50 +02:00
Matt T. Proud aaaf3367d6 Include forgotten imports.
This fixes the build.

Change-Id: Id132f4342adb9ed20116191086f157ca7f7cf515
2013-08-14 18:52:55 +02:00
Matt T. Proud acf91f38bd Build layered indexers.
The indexers will be extracted in a short while and wrapped accordingly with
these types.

Change-Id: I4d1abda4e46117210babad5aa0d42f9ca1f6594f
2013-08-14 13:32:53 +02:00
Matt T. Proud 972e856d9b Kill the curation state channel.
The use of the channels for curation state were always unidiomatic.

Change-Id: I1cb1d7175ebfb4faf28dff84201066278d6a0d92
2013-08-13 17:20:22 +02:00
Matt T. Proud 1ceb25b701 Publication of LevelDBMetricPersistence Fields.
This will enable us to break down the onerous construction method.

Change-Id: Ia89337ba39d6745af6757180af2485ec8a990a3b
2013-08-13 00:36:12 +02:00
Julius Volz 0003027dce Add needed trailing spaces in logs. 2013-08-12 18:22:48 +02:00
Julius Volz aa5d251f8d Use github.com/golang/glog for all logging. 2013-08-12 17:54:36 +02:00
Matt T. Proud a5141e4d0a Depointerize storage conf. and chain ingester.
The storage builders need to work with the assumption that they have
a copy of the underlying configuration data if any mutations are made.
2013-08-12 17:07:03 +02:00
Matt T. Proud 820e551988 Code Review: Nits. 2013-08-07 13:29:10 +02:00
Matt T. Proud a3bf2efdd5 Replace index writes with wrapped interface.
This commit is the first of several and should not be regarded as the
desired end state for these cleanups.  What this one does it, however,
is wrap the query index writing behind an interface type that can be
injected into the storage stack and have its lifecycle managed
separately as needed.  It also would mean we can swap out underlying
implementations to support remote indexing, buffering, no-op indexing
very easily.

In the future, most of the individual index interface members in the
tiered storage will go away in favor of agents that can query and
resolve what they need from the datastore without the user knowing
how and why they work.
2013-08-07 12:15:48 +02:00
Matt T. Proud 52664f701a Hot Fix: Use extracted time. 2013-08-06 14:18:02 +02:00
Matt T. Proud 38dac35b3e Code Review: Short name consistency. 2013-08-06 12:38:35 +02:00
Matt T. Proud a00f18d78b Code Review: Manual re-alignment. 2013-08-06 12:23:06 +02:00
Matt T. Proud cc989c68e1 Replace direct curation table access with wrapper. 2013-08-06 12:02:52 +02:00
Matt T. Proud 07ac921aec Code Review: First pass. 2013-08-05 17:31:49 +02:00
Matt T. Proud d8792cfd86 Extract HighWatermarking.
Clean up the rest.
2013-08-05 11:03:03 +02:00
Matt T. Proud f4669a812c Extract index storage into separate types. 2013-08-04 15:31:52 +02:00
Matt T. Proud 772d3d6b11 Consolidate LevelDB storage construction.
There are too many parameters to constructing a LevelDB storage
instance for a construction method, so I've opted to take an
idiomatic approach of embedding them in a struct for easier
mediation and versioning.
2013-08-03 17:25:03 +02:00
Julius Volz e3415e953f Add notifications telemetry. 2013-07-31 12:40:56 +02:00
juliusv 927435d68e Merge pull request #333 from prometheus/round-time
Round time to nearest second in memory storage.
2013-07-16 05:52:31 -07:00
Julius Volz 5d88e8cc45 Round time to nearest second in memory storage.
When samples get flushed to disk, they lose sub-second precision anyways. By
already dropping sub-second precision, data fetched from memory vs. disk will
behave the same. Later, we should consider also storing a more compact
representation than time.Time in memory if we're not going to use its full
precision.
2013-07-16 14:51:54 +02:00
Matt T. Proud f7704af4f8 Code Review: Formatting comments. 2013-07-15 15:12:01 +02:00
Julius Volz a76a797f3f Always treat series without watermarks as too old.
Current series always get watermarks written out upon append now. This
drops support for old series without any watermarks by always reporting
them as too old (stale) during queries.
2013-06-27 17:10:06 +02:00
Julius Volz d2da21121c Implement getValueRangeAtIntervalOp for faster range queries.
This also short-circuits optimize() for now, since it is complex to implement
for the new operator, and ops generated by the query layer already fulfill the
needed invariants. We should still investigate later whether to completely
delete operator optimization code or extend it to support
getValueRangeAtIntervalOp operators.
2013-06-26 18:10:36 +02:00
Julius Volz e7f049c85b Fix expunging of empty memory series (loop var pointerization bug) 2013-06-26 18:00:47 +02:00
Julius Volz baa5b07829 Fix condition for dropping empty memory series. 2013-06-25 17:57:35 +02:00
Matt T. Proud 30b1cf80b5 WIP - Snapshot of Moving to Client Model. 2013-06-25 15:52:42 +02:00
juliusv 42198c1f1c Merge pull request #311 from prometheus/fix/watermarking/on-first-write
Ensure new metrics are watermarked early.
2013-06-25 03:13:58 -07:00
Matt T. Proud 4137c75523 Shrink default LRU cache sizes.
Observing Prometheus in production confirms we can lower these values
safely.
2013-06-24 12:09:16 +02:00
Matt T. Proud ecb9c7bb9d Code Review: Swap ordering of elements. 2013-06-21 21:17:50 +02:00
Matt T. Proud 5daa0a09ea Code Review: Swap ordering of watermark getting.
A test for Julius.
2013-06-21 18:34:08 +02:00
Matt T. Proud ee840904d2 Code Review: !Before -> After. 2013-06-21 18:26:40 +02:00
Matt T. Proud 2d5de99fbf Regard in-memory series as new.
This commit ensures that series that exist only in-memory and not
on-disk are not regarded as too old for operation exclusion.
2013-06-21 18:26:39 +02:00
Matt T. Proud 81c406630a Merge pull request #312 from prometheus/fix/sample-append-logging
Log correct sample count when appending to disk.
2013-06-21 08:55:51 -07:00
Matt T. Proud a1a23fbaf8 Ensure new metrics are watermarked early.
With the checking of fingerprint freshness to cull stale metrics
from queries, we should write watermarks early to aid in more
accurate responses.
2013-06-21 16:38:46 +02:00
Julius Volz ba8c122147 Log correct sample count when appending to disk. 2013-06-21 12:23:27 +02:00
Julius Volz f2b4067b7b Speedup and clean up operation optimization. 2013-06-20 03:01:13 +02:00
Julius Volz 008bc09da8 Move check for empty memory series to separate method. 2013-06-19 14:19:53 +02:00
Julius Volz 16364eda37 Drop empty series from memory after flushing. 2013-06-19 12:14:23 +02:00
Julius Volz 71199e2c93 Cache disk fingerprint->metric lookups in memory. 2013-06-18 14:08:58 +02:00
Matt T. Proud a73f061d3c Persist solely Protocol Buffers.
An design question was open for me in the beginning was whether to
serialize other types to disk, but Protocol Buffers quickly won out,
which allows us to drop support for other types.  This is a good
start to cleaning up a lot of cruft in the storage stack and
can let us eventually decouple the various moving parts into
separate subsystems for easier reasoning.

This commit is not strictly required, but it is a start to making
the rest a lot more enjoyable to interact with.
2013-06-08 11:02:35 +02:00
juliusv 95400cb785 Merge pull request #290 from prometheus/fix/go-vet
Minor "go tool vet" cleanups
2013-06-07 06:52:48 -07:00
Julius Volz 558281890b Minor "go tool vet" cleanups 2013-06-07 15:34:41 +02:00
juliusv 615972dd01 Merge pull request #288 from prometheus/fix/curator/fallthrough-compaction-ordering
Fix fallthrough compaction value ordering.
2013-06-07 05:46:15 -07:00
Matt T. Proud 86f63b078b Fix fallthrough compaction value ordering.
We discovered a regression whereby data chunks could be appended out
of order if the fallthrough case was hit.
2013-06-07 14:41:00 +02:00
Julius Volz 7b9ee95030 Minor LevelDB watermark handling cleanups. 2013-06-06 23:56:31 +02:00
Julius Volz 84741b227d Use LRU cache to avoid querying stale series. 2013-06-06 23:56:19 +02:00
Julius Volz f98853d7b7 Fix type error in watermark list handling. 2013-06-06 23:56:14 +02:00
Matt T. Proud ef1d5fd8a2 Introduce semaphores for tiered storage.
This commit wraps the tiered storage access componnets in semaphores,
since we can handle several concurrent memory reads.
2013-06-06 18:16:18 +02:00
Matt T. Proud 819045541e Code Review: Make double-drain a panic. 2013-06-06 12:40:06 +02:00
Matt T. Proud e217a9fb41 Race Work: Make memory arena locks more coarse.
We can optimize these as needed later.
2013-06-06 12:08:20 +02:00
Matt T. Proud beaaf386e7 Add storage state guards and transition callbacks.
To ensure that we access tiered storage in the proper way, we have
guards now.
2013-06-06 11:52:09 +02:00
Matt T. Proud abb5353ade Merge pull request #283 from prometheus/feature/storage/consult-watermark
Include LRU cache for fingerprint watermarks.
2013-06-06 02:33:45 -07:00
Matt T. Proud 2c3df44af6 Ensure database access waits until it is started.
This commit introduces a channel message to ensure serving
state has been reached with the storage stack before anything attempts
to use it.
2013-06-06 10:42:21 +02:00
Matt T. Proud cbe2f3a7b1 Include LRU cache for fingerprint watermarks. 2013-06-06 10:13:18 +02:00
Julius Volz 51689d965d Add debug timers to instant and range queries.
This adds timers around several query-relevant code blocks. For now, the
query timer stats are only logged for queries initiated through the UI.
In other cases (rule evaluations), the stats are simply thrown away.

My hope is that this helps us understand where queries spend time,
especially in cases where they sometimes hang for unusual amounts of
time.
2013-06-05 18:32:54 +02:00
Matt T. Proud 8339a189cb Code Review: Fix seriesPresent scope.
The seriesPresent scope should be constrained to the scope of a
scanJob, since this is keyed to given series.
2013-06-04 13:16:59 +02:00
Matt T. Proud fe41ce0b19 Conditionalize disk initializations.
This commit conditionalizes the creation of the diskFrontier and
seriesFrontier along with the iterator such that they are provisioned
once something is actually required from disk.
2013-06-04 12:53:57 +02:00
Julius Volz a8468a2e5e Fix reversed disk flush cutoff behavior. 2013-05-28 16:14:30 +02:00
Julius Volz eb1f956909 Revert "Revert "Ensure that all extracted samples are added to view.""
This reverts commit 4b30fb86b4.
2013-05-28 14:36:03 +02:00
Matt T. Proud 4b30fb86b4 Revert "Ensure that all extracted samples are added to view."
This reverts commit 008314b5a8. By
running an automated git bisection described in
https://gist.github.com/matttproud-soundcloud/22a371a8d2cba382ea64
this commit was found.
2013-05-23 13:36:22 +02:00
Julius Volz 750f862d9a Use GetBoundaryValues() for non-counter deltas. 2013-05-22 19:13:47 +02:00
Julius Volz f2b48b8c4a Make getValuesAtIntervalOp consume all chunk data in one pass.
This is mainly a small performance improvement, since we skip past the last
extracted time immediately if it was also the last sample in the chunk, instead
of trying to extract non-existent values before the chunk end again and again
and only gradually approaching the end of the chunk.
2013-05-22 18:14:45 +02:00
Julius Volz 83d60bed89 extractValuesAroundTime() code simplification. 2013-05-22 18:14:45 +02:00
Julius Volz 008314b5a8 Ensure that all extracted samples are added to view.
The current behavior only adds those samples to the view that are extracted by
the last pass of the last processed op and throws other ones away. This is a
bug. We need to append all samples that are extracted by each op pass.

This also makes view.appendSamples() take an array of samples.
2013-05-22 18:14:37 +02:00
Matt T. Proud b586801830 Code Review: Fix to-disk queue infinite growth.
We discovered a bug while manually testing this branch on a live
instance, whereby the to-disk queue was never actually dumped to
disk.
2013-05-22 17:59:53 +02:00
Matt T. Proud 285a8b701b Code Review: Extend lock. 2013-05-22 17:59:53 +02:00
Matt T. Proud 2526ab8c81 Code Review: Extend lock scope for appending. 2013-05-22 17:59:53 +02:00
Matt T. Proud f994482d15 Code Review: Avenues for future improvemnet noted. 2013-05-22 17:59:53 +02:00
Matt T. Proud 298a90c143 Code Review: Initial arena size name. 2013-05-22 17:59:53 +02:00
Matt T. Proud c07abf8521 Initial move away from skiplist. 2013-05-22 17:59:53 +02:00
Matt T. Proud 74a66fd938 Spawn grouping of fingerprints with free semaphore.
The previous implementation spawned N goroutines to group samples
together and would not start work until the semaphore unblocked.
While this didn't leak, it polluted the scheduling space.  Thusly,
the routine only starts after a semaphore has been acquired.
2013-05-21 16:11:35 +02:00
Julius Volz 5b105c77fc Repointerize fingerprints. 2013-05-21 14:28:14 +02:00
Matt T. Proud ec5b5bae28 Fuck you, Travis. 2013-05-21 09:42:00 +02:00
Matt T. Proud e5ac91222b Benchmark memory arena; simplify map generation.
The one-off keys have been replaced with ``model.LabelPair``, which is
indexable.  The performance impact is negligible, but it represents
a cognitive simplification.
2013-05-21 09:39:12 +02:00
juliusv 360477f66c Merge pull request #257 from prometheus/feature/better-memory-behaviors
Pointerize memorySeriesArena.
2013-05-16 07:36:40 -07:00
Matt T. Proud e1f20de2e9 Pointerize memorySeriesArena. 2013-05-16 17:09:28 +03:00
Matt T. Proud 8f4c7ece92 Destroy naked returns in half of corpus.
The use of naked return values is frowned upon.  This is the first
of two bulk updates to remove them.
2013-05-16 10:53:25 +03:00
Matt T. Proud 4e0c932a4f Simplify Encoder's encoding signature.
The reality is that if we ever try to encode a Protocol Buffer and it
fails, it's likely that such an error is ultimately not a runtime error
and should be fixed forthwith.  Thusly, we should rename
``Encoder.Encode`` to ``Encoder.MustEncode`` and drop the error return
value.
2013-05-16 00:54:18 +03:00
juliusv 516101f015 Merge pull request #250 from prometheus/refactor/drop-unused-storage-setting
Drop unused writeMemoryInterval
2013-05-14 08:45:59 -07:00
juliusv 9ff00b651d Merge pull request #251 from prometheus/fix/memory-metric-mutability
Fix GetMetricForFingerprint() metric mutability.
2013-05-14 08:12:45 -07:00