Commit graph

1147 commits

Author SHA1 Message Date
Tom Wilkie b8217720ac Review feedback.
Signed-off-by: Tom Wilkie <tom.wilkie@gmail.com>
2018-06-19 13:03:01 +01:00
Corentin Chary db9dbeeaec federation: nil pointer deference when using remove read
```
level=error ts=2018-06-13T07:19:04.515149169Z caller=stdlib.go:89 component=web caller="http: panic serving [::1" msg="]:56202: runtime error: invalid memory address or nil pointer dereference"
level=error ts=2018-06-13T07:19:04.516199547Z caller=stdlib.go:89 component=web caller="http: panic serving [::1" msg="]:56204: runtime error: invalid memory address or nil pointer dereference"
level=error ts=2018-06-13T07:19:04.51717692Z caller=stdlib.go:89 component=web caller="http: panic serving [::1" msg="]:56206: runtime error: invalid memory address or nil pointer dereference"
level=error ts=2018-06-13T07:19:04.564952878Z caller=stdlib.go:89 component=web caller="http: panic serving [::1" msg="]:56208: runtime error: invalid memory address or nil pointer dereference"
level=error ts=2018-06-13T07:19:04.566575791Z caller=stdlib.go:89 component=web caller="http: panic serving [::1" msg="]:56210: runtime error: invalid memory address or nil pointer dereference"
level=error ts=2018-06-13T07:19:04.567106063Z caller=stdlib.go:89 component=web caller="http: panic serving [::1" msg="]:56212: runtime error: invalid memory address or nil pointer dereference"
```

When remove read is enabled, federation will call `q.Select(nil, mset...)`
which will break remote reads because it currently doesn't handle empty
SelectParams.

Signed-off-by: Corentin Chary <c.chary@criteo.com>
2018-06-19 13:03:01 +01:00
Brian Brazil 78efdc6d6b
Avoid infinite loop on duplicate NaN values. (#4275)
Fixes #4254

NaNs don't equal themselves, so a duplicate NaN would
always hit the break statement and never get popped.

We should not be returning multiple data point for the same
timestamp, so don't compare values at all.

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>
2018-06-18 17:34:08 +01:00
Tom Wilkie 0b189b2da9 Review feedback.
Signed-off-by: Tom Wilkie <tom.wilkie@gmail.com>
2018-06-18 17:21:12 +01:00
Corentin Chary 530107f8ef federation: nil pointer deference when using remove read
```
level=error ts=2018-06-13T07:19:04.515149169Z caller=stdlib.go:89 component=web caller="http: panic serving [::1" msg="]:56202: runtime error: invalid memory address or nil pointer dereference"
level=error ts=2018-06-13T07:19:04.516199547Z caller=stdlib.go:89 component=web caller="http: panic serving [::1" msg="]:56204: runtime error: invalid memory address or nil pointer dereference"
level=error ts=2018-06-13T07:19:04.51717692Z caller=stdlib.go:89 component=web caller="http: panic serving [::1" msg="]:56206: runtime error: invalid memory address or nil pointer dereference"
level=error ts=2018-06-13T07:19:04.564952878Z caller=stdlib.go:89 component=web caller="http: panic serving [::1" msg="]:56208: runtime error: invalid memory address or nil pointer dereference"
level=error ts=2018-06-13T07:19:04.566575791Z caller=stdlib.go:89 component=web caller="http: panic serving [::1" msg="]:56210: runtime error: invalid memory address or nil pointer dereference"
level=error ts=2018-06-13T07:19:04.567106063Z caller=stdlib.go:89 component=web caller="http: panic serving [::1" msg="]:56212: runtime error: invalid memory address or nil pointer dereference"
```

When remove read is enabled, federation will call `q.Select(nil, mset...)`
which will break remote reads because it currently doesn't handle empty
SelectParams.

Signed-off-by: Corentin Chary <c.chary@criteo.com>
2018-06-18 17:21:12 +01:00
Andreas Auernhammer 37d1bcf495 limit size of POST requests against remote read endpoint (#4239)
This commit fixes a denial-of-service issue of the remote
read endpoint. It limits the size of the POST request body
to 32 MB such that clients cannot write arbitrary amounts
of data to the server memory.

Fixes #4238

Signed-off-by: Andreas Auernhammer <aead@mail.de>
2018-06-08 08:19:20 +01:00
Fabian Reinartz fe80dddbc4
Merge pull request #4210 from bboreham/log-remote-name
Add queue name to logger for remote writes
2018-06-04 15:49:39 +02:00
Brian Brazil dd6781add2 Optimise PromQL (#3966)
* Move range logic to 'eval'

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Make aggregegate range aware

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* PromQL is statically typed, so don't eval to find the type.

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Extend rangewrapper to multiple exprs

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Start making function evaluation ranged

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Make instant queries a special case of range queries

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Eliminate evalString

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Evaluate range vector functions one series at a time

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Make unary operators range aware

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Make binops range aware

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Pass time to range-aware functions.

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Make simple _over_time functions range aware

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Reduce allocs when working with matrix selectors

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Add basic benchmark for range evaluation

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Reuse objects for function arguments

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Do dropmetricname and allocating output vector only once.

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Add range-aware support for range vector functions with params

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Optimise holt_winters, cut cpu and allocs by ~25%

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Make rate&friends range aware

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Make more functions range aware. Document calling convention.

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Make date functions range aware

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Make simple math functions range aware

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Convert more functions to be range aware

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Make more functions range aware

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Specialcase timestamp() with vector selector arg for range awareness

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Remove transition code for functions

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Remove the rest of the engine transition code

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Remove more obselete code

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Remove the last uses of the eval* functions

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Remove engine finalizers to prevent corruption

The finalizers set by matrixSelector were being called
just before the value they were retruning to the pool
was then being provided to the caller. Thus a concurrent query
could corrupt the data that the user has just been returned.

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Add new benchmark suite for range functinos

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Migrate existing benchmarks to new system

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Expand promql benchmarks

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Simply test by removing unused range code

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* When testing instant queries, check range queries too.

To protect against subsequent steps in a range query being
affected by the previous steps, add a test that evaluates
an instant query that we know works again as a range query
with the tiimestamp we care about not being the first step.

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Reuse ring for matrix iters. Put query results back in pool.

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Reuse buffer when iterating over matrix selectors

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Unary minus should remove metric name

Cut down benchmarks for faster runs.

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Reduce repetition in benchmark test cases

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Work series by series when doing normal vectorSelectors

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Optimise benchmark setup, cuts time by 60%

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Have rangeWrapper use an evalNodeHelper to cache across steps

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Use evalNodeHelper with functions

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Cache dropMetricName within a node evaluation.

This saves both the calculations and allocs done by dropMetricName
across steps.

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Reuse input vectors in rangewrapper

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Reuse the point slices in the matrixes input/output by rangeWrapper

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Make benchmark setup faster using AddFast

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Simplify benchmark code.

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Add caching in VectorBinop

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Use xor to have one-level resultMetric hash key

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Add more benchmarks

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Call Query.Close in apiv1

This allows point slices allocated for the response data
to be reused by later queries, saving allocations.

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Optimise histogram_quantile

It's now 5-10% faster with 97% less garbage generated for 1k steps

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Make the input collection in rangeVector linear rather than quadratic

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Optimise label_replace, for 1k steps 15x fewer allocs and 3x faster

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Optimise label_join, 1.8x faster and 11x less memory for 1k steps

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Expand benchmarks, cleanup comments, simplify numSteps logic.

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Address Fabian's comments

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Comments from Alin.

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Address jrv's comments

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Remove dead code

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Address Simon's comments.

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Rename populateIterators, pre-init some sizes

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Handle case where function has non-matrix args first

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Split rangeWrapper out to rangeEval function, improve comments

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Cleanup and make things more consistent

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Make EvalNodeHelper public

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>

* Fabian's comments.

Signed-off-by: Brian Brazil <brian.brazil@robustperception.io>
2018-06-04 15:47:45 +02:00
Bryan Boreham 3277aeefaa Add queue name to logger for remote writes
More than one remote_write destination can be configured, in which
case it's essential to know which one each log message refers to.

Signed-off-by: Bryan Boreham <bjboreham@gmail.com>
2018-06-01 13:04:00 +00:00
Tom Wilkie b58199bf12 Review feedback.
Signed-off-by: Tom Wilkie <tom.wilkie@gmail.com>
2018-05-29 11:35:43 +01:00
Tom Wilkie 3353bbd018 Add proper unclean shutdown handling with a cancellable context.
Signed-off-by: Tom Wilkie <tom.wilkie@gmail.com>
2018-05-29 09:51:29 +01:00
Tom Wilkie e51d6c4b6c Make remote flush deadline a command line param.
Signed-off-by: Tom Wilkie <tom.wilkie@gmail.com>
2018-05-23 15:06:01 +01:00
Tom Wilkie a6c353613a Make the flush deadline configurable.
Signed-off-by: Tom Wilkie <tom.wilkie@gmail.com>
2018-05-23 15:04:36 +01:00
Tom Wilkie aa17263edd Remove WaitGroup and extra goroutine.
Signed-off-by: Tom Wilkie <tom.wilkie@gmail.com>
2018-05-23 15:04:34 +01:00
Tom Wilkie f3c61f8bb2 Only give remote queues 1 minute to flush samples on shutdown.
Signed-off-by: Tom Wilkie <tom.wilkie@gmail.com>
2018-05-23 15:04:32 +01:00
Tom Wilkie ba418780be Dedupe samples in the mergeIterator.
Signed-off-by: Tom Wilkie <tom.wilkie@gmail.com>
2018-05-23 12:15:47 +01:00
Henri DF 2952387ed1 Pass query hints down into remote read query proto (#4122)
Signed-off-by: Henri DF <henridf@gmail.com>
2018-05-08 09:48:13 +01:00
Adam Shannon 809881d7f5 support reading basic_auth password_file for HTTP basic auth (#4077)
Issue: https://github.com/prometheus/prometheus/issues/4076

Signed-off-by: Adam Shannon <adamkshannon@gmail.com>
2018-04-25 18:19:06 +01:00
Mario Trangoni 464e747f1e fix some comments typos (#4059) 2018-04-08 10:51:54 +01:00
ferhat elmas ec8e4d8a7c all: remove unnecessary type conversions (#3992)
excep promql due to not to create conflict with #3966.
2018-03-21 09:25:22 +00:00
Tom Wilkie 02a154ced6
Merge pull request #3941 from prometheus/3809-correctly-stop-timer
Correctly stop the timer used in the remote write path.
2018-03-13 09:05:52 +00:00
Tom Wilkie dc860e7d0e Fix nit. 2018-03-12 16:48:51 +00:00
Tom Wilkie 390b018c90 Test sample timeout delivery. 2018-03-12 15:35:43 +00:00
Tom Wilkie 22d820ef8e Review feedback. 2018-03-12 14:27:48 +00:00
Brian Brazil a8c22c85cc
Correctly handle pruning wraparound after ring expansion (#3942)
Fixes #3939
2018-03-12 13:16:59 +00:00
Tom Wilkie f8c9d375b6 Correctly stop the timer used in the remote write path. 2018-03-09 12:00:26 +00:00
ferhat elmas ffa673f7d8 General simplifications (#3887)
Another try as in #1516
2018-02-26 07:58:10 +00:00
Fabian Reinartz 7ccd4b39b8 *: implement query params
This adds a parameter to the storage selection interface which allows
query engine(s) to pass information about the operations surrounding a
data selection.
This can for example be used by remote storage backends to infer the
correct downsampling aggregates that need to be provided.
2018-02-13 12:17:22 +01:00
Tom Wilkie a730083cbf
Merge pull request #3731 from bboreham/reuse-timer
Re-use timer in remote storage queue
2018-02-05 10:54:08 +01:00
Krasi Georgiev b75428ec19 rename package retrieve to scrape
no fucnctinal changes just renaming retrieval to scrape
2018-02-01 09:55:07 +00:00
Tom Wilkie 3dc5b8eef5 Use sub benchmarks. 2018-01-29 11:37:48 +00:00
Tom Wilkie da29c09dca Some benchmarks for the mergeSeries set. 2018-01-26 11:01:59 +00:00
Tom Wilkie 749781edf3 Also, don't make a mergeSeriesSet if there is only one SeriesSet. 2018-01-25 11:17:16 +00:00
Tom Wilkie 48e39068bd Don't allocate a mergeSeries if there is only one series to merge. 2018-01-25 11:11:55 +00:00
Bryan Boreham 8a4535e6ad Re-use timer instead of creating new ones on every sample
The docs for `time.After()` note that "The underlying Timer is not
recovered by the garbage collector until the timer fires".
2018-01-24 12:36:29 +00:00
Tom Wilkie f2c5399e39
Merge pull request #3561 from twiedenbein/master
fixed bug with initialization of queueconfig
2018-01-17 12:24:58 +00:00
Shubheksha Jalan 0471e64ad1 Use shared types from the common repo (#3674)
* refactor: use shared types from common repo, remove util/config

* vendor: add common/config

* fix nit
2018-01-11 16:10:25 +01:00
Shubheksha Jalan ec94df49d4 Refactor SD configuration to remove config dependency (#3629)
* refactor: move targetGroup struct and CheckOverflow() to their own package

* refactor: move auth and security related structs to a utility package, fix import error in utility package

* refactor: Azure SD, remove SD struct from config

* refactor: DNS SD, remove SD struct from config into dns package

* refactor: ec2 SD, move SD struct from config into the ec2 package

* refactor: file SD, move SD struct from config to file discovery package

* refactor: gce, move SD struct from config to gce discovery package

* refactor: move HTTPClientConfig and URL into util/config, fix import error in httputil

* refactor: consul, move SD struct from config into consul discovery package

* refactor: marathon, move SD struct from config into marathon discovery package

* refactor: triton, move SD struct from config to triton discovery package, fix test

* refactor: zookeeper, move SD structs from config to zookeeper discovery package

* refactor: openstack, remove SD struct from config, move into openstack discovery package

* refactor: kubernetes, move SD struct from config into kubernetes discovery package

* refactor: notifier, use targetgroup package instead of config

* refactor: tests for file, marathon, triton SD - use targetgroup package instead of config.TargetGroup

* refactor: retrieval, use targetgroup package instead of config.TargetGroup

* refactor: storage, use config util package

* refactor: discovery manager, use targetgroup package instead of config.TargetGroup

* refactor: use HTTPClient and TLS config from configUtil instead of config

* refactor: tests, use targetgroup package instead of config.TargetGroup

* refactor: fix tagetgroup.Group pointers that were removed by mistake

* refactor: openstack, kubernetes: drop prefixes

* refactor: remove import aliases forced due to vscode bug

* refactor: move main SD struct out of config into discovery/config

* refactor: rename configUtil to config_util

* refactor: rename yamlUtil to yaml_config

* refactor: kubernetes, remove prefixes

* refactor: move the TargetGroup package to discovery/

* refactor: fix order of imports
2017-12-29 21:01:34 +01:00
Ed Schouten bb724f1bef Deprecate DeduplicateSeriesSet() in favor of NewMergeSeriesSet().
Federation makes use of dedupedSeriesSet to merge SeriesSets for every
query into one output stream. If many match[] arguments are provided,
many dedupedSeriesSet objects will get chained. This has the downside of
causing a potential O(n*k) running time, where n is the number of series
and k the number of match[] arguments.

In the mean time, the storage package provides a mergeSeriesSet that
accomplishes the same with an O(n*log(k)) running time by making use of
a binary heap. Let's just get rid of dedupedSeriesSet and change all
existing callers to use mergeSeriesSet.
2017-12-10 19:51:20 +01:00
Tom Wiedenbein 937ac8c060
fixed bug with initialization of queueconfig
QueueConfigs would only ever initialize to the default settings, and would not pick up their respective values from YAML.
2017-12-08 02:11:45 -08:00
Fabian Reinartz 83cd270ea4 *: adapt to storage interface changes 2017-11-23 19:05:04 +01:00
Tobias Schmidt 7098c56474 Add remote read filter option
For special remote read endpoints which have only data for specific
queries, it is desired to limit the number of queries sent to the
configured remote read endpoint to reduce latency and performance
overhead.
2017-11-13 23:30:01 +01:00
Tobias Schmidt 434f0374f7 Refactor remote storage querier handling
* Decouple remote client from ReadRecent feature.
* Separate remote read filter into a small, testable function.
* Use storage.Queryable interface to compose independent
  functionalities.
2017-11-13 23:19:15 +01:00
Tobias Schmidt 9b0091d487 Add storage.Queryable and storage.QueryableFunc
In order to compose different querier implementations more easily, this
change introduces a separate storage.Queryable interface grouping the
query (Querier) function of the storage.

Furthermore, it adds a QueryableFunc type to ease writing very simple
queryable implementations.
2017-11-13 20:19:37 +01:00
Julius Volz 9f10c63cff
Fix remote read labelset corruption (#3456)
The labelsets returned from remote read are mutated in higher levels
(like seriesFilter.Labels()) and since the concreteSeriesSet didn't
return a copy, the external mutation affected the labelset in the
concreteSeries itself. This resulted in bizarre bugs where local and
remote series would show with identical label sets in the UI, but not be
deduplicated, since internally, a series might come to look like:

{__name__="node_load5", instance="192.168.1.202:12090", job="node_exporter", node="odroid", node="odroid"}

(note the repetition of the last label)
2017-11-12 00:47:47 +01:00
Krasi Georgiev 5d8f93a22a now using only github.com/gogo/protobuf
bumped all grpc-gateway packages to v1.2.2
updated and run  the denproto.sh script
2017-11-02 11:31:57 +00:00
Fabian Reinartz 30e777d10d tsdb: default too small max block duration 2017-10-30 12:09:56 +01:00
Tom Wilkie 48a7a00a38 Fast path the merge querier (#3358)
* Fast path the merge querier such that it is completely removed from query path when there is no remote storage.

* Add NoopQuerier

* Add copyright notice.

* Avoid global, use a function.
2017-10-27 13:29:05 +02:00
Tom Wilkie 0e572686db Revert "Bypass the fanout storage merging if no remote storage is configured." 2017-10-26 16:09:39 +01:00
Tom Wilkie 1af3ef431d s/TestRemoveLabels/TestSeriesSetFilter/ 2017-10-26 13:50:39 +01:00
Tom Wilkie 9c3c98e8de Revert "Port 'Don't disable HTTP keep-alives for remote storage connections.' to 2.0 (see #3173)"
This reverts commit 0997191b18.
2017-10-26 13:43:48 +01:00
Tom Wilkie 746752b946 Merge external labels in order. 2017-10-26 11:44:49 +01:00
Tom Wilkie 6e4d4ea402 Initialise some counters in remote storage API. 2017-10-26 11:09:45 +01:00
Tom Wilkie 2ae04d0e79 Add license header. 2017-10-26 11:09:16 +01:00
Tom Wilkie e8c264e47a Add comment. 2017-10-26 11:09:16 +01:00
Tom Wilkie ee011d906d Port remote read server to 2.0. 2017-10-26 11:09:14 +01:00
Bryan Boreham 0997191b18 Port 'Don't disable HTTP keep-alives for remote storage connections.' to 2.0 (see #3173)
Removes configurability introduced in #3160 in favour of hard-coding,
per advice from @brian-brazil.
2017-10-26 11:08:33 +01:00
Tom Wilkie 56820726fa Move a couple of the encoding/decoding functions into codec.go 2017-10-26 11:08:33 +01:00
Conor Broderick 08b7328669 Port Metric name validation to 2.0 (see #2975) 2017-10-26 11:08:33 +01:00
Tom Wilkie 8fe0212ff7 Port 'Make queue manager configurable.' to 2.0, see #2991 2017-10-26 11:08:33 +01:00
Tom Wilkie 3760f56c0c remote: Expose ClientConfig type (see #3165) 2017-10-26 11:08:33 +01:00
Tom Wilkie 16f71a7723 Port codec.go over form 1.8 branch. 2017-10-26 11:08:33 +01:00
Fabian Reinartz e53040e2ac Merge pull request #3339 from tomwilkie/3065-remote-read-bypass
Bypass the fanout storage merging if no remote storage is configured.
2017-10-26 09:14:26 +02:00
Fabian Reinartz bf56ad4233 Merge branch 'master' into master 2017-10-26 09:06:12 +02:00
Paul Gier c4c3205d76 storage/tsdb: check that max block duration is larger than min
If the user accidentally sets the max block duration smaller than the min,
the current error is not informative.  This change just performs the check
earlier and improves the error message.
2017-10-25 19:24:49 -05:00
Fabian Reinartz ce63a5a855 Merge pull request #3352 from prometheus/rc2
Cut v2.0.0-rc.2
2017-10-25 20:39:39 +02:00
Thibault Chataigner fc4406201e Tsdb StartTime : Use a simplier way to compute StartTime 2017-10-25 17:41:00 +02:00
Julius Volz 099df0c5f0 Migrate "golang.org/x/net/context" -> "context" (#3333)
In some places, where ctxhttp or gRPC are concerned, we still need to use the
old contexts.
2017-10-24 21:21:42 -07:00
Tom Wilkie 4bbef0ec30 Bypass the fanout storage merging if no remote storage is configured. 2017-10-23 21:34:53 +01:00
Fabian Reinartz a57ea79660 Close index reader properly 2017-10-23 21:59:18 +02:00
Julius Volz c3d6abc8e6 Fix some lint errors (#3334)
I left the promql ones and some others untouched as I remember that @fabxc
prefers them that way.
2017-10-23 14:57:30 +01:00
Julius Volz 2846d62573 Fix staticcheck issue in test (#3331)
staticcheck fails with:
storage/remote/read_test.go:199:27: do not pass a nil Context, even if a function permits it; pass context.TODO if you are unsure about which Context to use (SA1012)
2017-10-23 11:51:48 +01:00
Brian Brazil 4a50f547c8 removeLabels needs a pointer to work. (#3326) 2017-10-21 08:29:03 +01:00
Thibault Chataigner bf4a279a91 Remote storage reads based on oldest timestamp in primary storage (#3129)
Currently all read queries are simply pushed to remote read clients.
This is fine, except for remote storage for wich it unefficient and
make query slower even if remote read is unnecessary.
So we need instead to compare the oldest timestamp in primary/local
storage with the query range lower boundary. If the oldest timestamp
is older than the mint parameter, then there is no need for remote read.
This is an optionnal behavior per remote read client.

Signed-off-by: Thibault Chataigner <t.chataigner@criteo.com>
2017-10-18 12:08:14 +01:00
Julius Volz 9ef8518b37 Remove "package remote" garbage from license headers (#3304) 2017-10-17 02:26:38 +01:00
Tobias Schmidt 721050c6cb Update prometheus/tsdb dependency 2017-10-16 15:36:25 +02:00
Julius Volz 33c1171b9c Don't add anchoring to exported Value matcher field
Instead, just make the anchoring part of the internal regex. This helps because
some users will want to read back the `Value` field and expect it to be the
same as the input value (e.g. some tests in Cortex), or use the value in
another context which is already expected to add its own anchoring, leading to
superfluous double anchoring (such as when we translate matchers into remote
read request matchers).
2017-10-10 10:10:21 -07:00
Brian Brazil 73dc96e7f5 Fix leak of ticker in remote storage queue manager. 2017-10-09 19:44:03 +01:00
Brian Brazil ee88f0d222 Ensure all values are used or _ 2017-10-09 19:44:03 +01:00
Brian Brazil 37ec2d5283 Fix off by one error in concreteSeriesSet (#3262) 2017-10-09 13:37:58 +01:00
Marc Sluiter 6a633eece1 Added go-conntrack for monitoring http connections (#3241)
Added metrics for in- and outgoing traffic with go-conntrack.
2017-10-06 11:22:19 +01:00
Julius Volz f7e8348a88 Re-add contexts to storage.Storage.Querier() (#3230)
* Re-add contexts to storage.Storage.Querier()

These are needed when replacing the storage by a multi-tenant
implementation where the tenant is stored in the context.

The 1.x query interfaces already had contexts, but they got lost in 2.x.

* Convert promql.Engine to use native contexts
2017-10-04 21:04:15 +02:00
Fabian Reinartz 7b02bfee0a web: start web handler while TSDB is starting up 2017-09-20 15:03:19 +02:00
Fabian Reinartz d21f149745 *: migrate to go-kit/log 2017-09-08 22:01:51 +05:30
Fabian Reinartz 0efecea6d4 Adapt storage APIs to uint64 references 2017-09-07 14:14:41 +02:00
Fabian Reinartz 0c81d5f719 storage: instantiate correct block ranges 2017-08-24 12:36:07 +02:00
Fabian Reinartz 2037778d14 vendor: update TSDB 2017-08-10 14:51:02 +02:00
Tom Wilkie b11bc8ae24 Fix some comments. 2017-08-01 11:19:35 +01:00
Tom Wilkie ec999ff397 Prevent number of remote write shards from going negative.
This can happen in the situation where the system scales up the number of shards massively (to deal with some backlog), then scales it down again as the number of samples sent during the time period is less than the number received.
2017-07-19 16:32:09 +01:00
Tom Wilkie a09acdcc5b Make concreteSeriersIterator behave. 2017-07-13 18:33:08 +01:00
Tom Wilkie 994a7f27d6 Propagate errors through mergeSeriesSet correctly. 2017-07-13 15:02:01 +01:00
Tom Wilkie 2e0d8487e3 Return zeros if At() is called after Next() returns false. 2017-07-13 14:40:29 +01:00
Tom Wilkie 014bd31a86 Remove unnecessary whitespace changes, add comment. 2017-07-13 11:26:46 +01:00
Tom Wilkie 98ac07f86a Add unit test for the merging on the read path. 2017-07-13 11:05:38 +01:00
Tom Wilkie b568ace7ce Move protos to ./prompb 2017-07-12 22:06:35 +01:00
Tom Wilkie 96e25adc8d Introduce 'primary' storage in fanout, and have Add return the ref from the primary.
Also, ensure all append batches are rolled back when a commit or rollback fails.
2017-07-12 15:51:05 +01:00
Tom Wilkie db8128ceeb Add label set as first parameter to AddFast, ingored by TSDB adapter. 2017-07-12 15:20:12 +01:00
Tom Wilkie 2dda5775e3 Initial port of remote storage to v2. 2017-07-12 12:27:57 +01:00
Fabian Reinartz 16464c3a33 Merge pull request #2910 from prometheus/adminapi
Admin API
2017-07-11 17:15:49 +02:00
Fabian Reinartz ccf9e62972 *: add admin grpc API 2017-07-10 09:14:14 +02:00
Goutham Veeramachaneni 243419c007 Return tsdb.ErrOutOfBounds as storage.ErrOutOfBounds
Signed-off-by: Goutham Veeramachaneni <cs14btech11014@iith.ac.in>
2017-07-06 14:18:31 +02:00
Goutham Veeramachaneni 3069bd3996 Handle scrapes with OutOfBounds metrics better
fixes #2894

Signed-off-by: Goutham Veeramachaneni <goutham@boomerangcommerce.com>
2017-07-04 11:24:13 +02:00
Goutham Veeramachaneni d407bd150c Consolidate the duration params in CLI
* All CLI params moved to model.Duration

Signed-off-by: Goutham Veeramachaneni <cs14btech11014@iith.ac.in>
2017-06-16 20:20:57 +05:30
Goutham Veeramachaneni baf5b0f0fc Fix error where we look into the future. (#2829)
* Fix error where we look into the future.

So currently we are adding values that are in the future for an older
timestamp. For example, if we have [(1, 1), (150, 2)] we will end up
showing [(1, 1), (2,2)].

Further it is not advisable to call .At() after Next() returns false.

Signed-off-by: Goutham Veeramachaneni <cs14btech11014@iith.ac.in>

* Retuen early if done

Signed-off-by: Goutham Veeramachaneni <cs14btech11014@iith.ac.in>

* Handle Seek() where we reach the end of iterator

Signed-off-by: Goutham Veeramachaneni <cs14btech11014@iith.ac.in>

* Simplify code

Signed-off-by: Goutham Veeramachaneni <cs14btech11014@iith.ac.in>
2017-06-13 07:22:27 +02:00
Brian Brazil c02c25d5ba Allow peeking back further in buffer. 2017-05-24 14:27:17 +01:00
Fabian Reinartz d289dc55c3 storage: update TSDB 2017-05-22 11:53:08 +02:00
Fabian Reinartz 9b175d48cb Add flag to disable TSDB lock file 2017-05-09 12:56:51 +02:00
Fabian Reinartz 0f3110487d Merge remote-tracking branch 'origin/dev-2.0' into dev-2.0 2017-04-27 10:25:04 +02:00
Fabian Reinartz 37deb21c45 vendor: remove unused dependency and last ref to fabxc/tsdb 2017-04-27 10:23:34 +02:00
Brian Brazil 5c9a6ce747 Add license to files.
This should fix CI for dev-2.0.
2017-04-19 13:46:22 +01:00
Fabian Reinartz 8ffc851147 Merge branch 'master' into dev-2.0 2017-04-04 15:17:56 +02:00
Fabian Reinartz cfb2a7f1d5 vendor: sync organisation migration of tsdb 2017-04-04 11:33:51 +02:00
Fabian Reinartz bbcf20ba01 web: deduplicate series in federation 2017-04-04 11:20:23 +02:00
Fabian Reinartz 4e41987bcb storage: add deduplication function
This adds a function to deduplicate two series sets given that duplicate
series have equivalent data points.
2017-04-04 11:07:21 +02:00
Björn Rabenstein 50e4f49b7e Merge pull request #2561 from prometheus/beorn7/storage2
storage: Evict unused chunk.Descs in crash recovery
2017-04-04 00:05:03 +02:00
beorn7 08fc6cbd39 storage: Evict unused chunk.Descs in crash recovery
This is in line with the v1.5 change in paradigm to not keep
chunk.Descs without chunks around after a series maintenance.

It's mainly motivated by avoiding excessive amounts of RAM usage
during crash recovery.

The code avoids to create memory time series with zero chunk.Descs as
that is prone to trigger weird effects. (Series maintenance would
archive series with zero chunk.Descs, but we cannot do that here
because the archive indices still have to be checked.)
2017-04-04 00:04:22 +02:00
Björn Rabenstein 1c6240fc40 Merge pull request #2559 from prometheus/beorn7/storage
storage: Replace fpIter by sortedFPs
2017-04-03 16:56:21 +02:00
beorn7 d284ffab03 storage: Replace fpIter by sortedFPs
The fpIter was kind of cumbersome to use and required a lock for each
iteration (which wasn't even needed for the iteration at startup after
loading the checkpoint).

The new implementation here has an obvious penalty in memory, but it's
only 8 byte per series, so 80MiB for a beefy server with 10M memory
time series (which would probably need ~100GiB RAM, so the memory
penalty is only 0.1% of the total memory need).

The big advantage is that now series maintenance happens in order,
which leads to the time between two maintenances of the same series
being less random. Ideally, after each maintenance, the next
maintenance would tackle the series with the largest number of
non-persisted chunks. That would be quite an effort to find out or
track, but with the approach here, the next maintenance will tackle
the series whose previous maintenance is longest ago, which is a good
approximation.

While this commit won't change the _average_ number of chunks
persisted per maintenance, it will reduce the mean time a given chunk
has to wait for its persistence and thus reduce the steady-state
number of chunks waiting for persistence.

Also, the map iteration in Go is non-deterministic but not truly
random. In practice, the iteration appears to be somewhat "bucketed".
You can often observe a bunch of series with similar duration since
their last maintenance, i.e. you see batches of series with similar
number of chunks persisted per maintenance. If that batch is
relatively young, a whole lot of series are maintained with very few
chunks to persist. (See screenshot in PR for a better explanation.)
2017-04-03 15:34:46 +02:00
Tobias Schmidt eac36d123e Fix unstable fanin test (#2558) 2017-04-03 13:02:15 +02:00
Julius Volz 5a896033e3 Add remote read external label handling (#2555)
* Add remote read external label handling

This implements rule 1 and 2 from
https://docs.google.com/document/d/188YauRgfF0J4CYMigLsVNN34V_kUwKnApBs2dQMfBbs/edit

* Use more descriptive example labels in read test

* Add comment for querier.addExternalLabels()

* Make argument naming in removeLabels() more generic
2017-04-02 17:48:15 +02:00
Björn Rabenstein e63d079b59 Merge pull request #2527 from prometheus/beorn7/storage
storage: Evict chunks and calculate persistence pressure...
2017-03-27 14:49:42 +02:00
Julius Volz b5b0e00923 Merge pull request #2499 from prometheus/remote-read
Remote Read
2017-03-27 14:43:44 +02:00
beorn7 434ab2a6a3 storage: Evict chunks and calculate persistence pressure based on target heap size
This is a fairly easy attempt to dynamically evict chunks based on the
heap size. A target heap size has to be set as a command line flage,
so that users can essentially say "utilize 4GiB of RAM, and please
don't OOM".

The -storage.local.max-chunks-to-persist and
-storage.local.memory-chunks flags are deprecated by this
change. Backwards compatibility is provided by ignoring
-storage.local.max-chunks-to-persist and use
-storage.local.memory-chunks to set the new
-storage.local.target-heap-size to a reasonable (and conservative)
value (both with a warning).

This also makes the metrics intstrumentation more consistent (in
naming and implementation) and cleans up a few quirks in the tests.

Answers to anticipated comments:

There is a chance that Go 1.9 will allow programs better control over
the Go memory management. I don't expect those changes to be in
contradiction with the approach here, but I do expect them to
complement them and allow them to be more precise and controlled. In
any case, once those Go changes are available, this code has to be
revisted.

One might be tempted to let the user specify an estimated value for
the RSS usage, and then internall set a target heap size of a certain
fraction of that. (In my experience, 2/3 is a fairly safe bet.)
However, investigations have shown that RSS size and its relation to
the heap size is really really complicated. It depends on so many
factors that I wouldn't even start listing them in a commit
description. It depends on many circumstances and not at least on the
risk trade-off of each individual user between RAM utilization and
probability of OOMing during a RAM usage peak. To not add even more to
the confusion, we need to stick to the well-defined number we also use
in the targeting here, the sum of the sizes of heap objects.
2017-03-27 14:33:50 +02:00
beorn7 96a303b348 storage: Use staleness delta as head chunk timeout
Currently, if a series stops to exist, its head chunk will be kept
open for an hour. That prevents it from being persisted. Which
prevents it from being evicted. Which prevents the series from being
archived.

Most of the time, once no sample has been added to a series within the
staleness limit, we can be pretty confident that this series will not
receive samples anymore. The whole chain as described above can be
started after 5m instead of 1h. In the relaxed case, this doesn't
change a lot as the head chunk timeout is only checked during series
maintenance, and usually, a series is only maintained every six
hours. However, there is the typical scenario where a large service is
deployed, the deoply turns out to be bad, and then it is deployed
again within minutes, and quite quickly the number of time series has
tripled. That's the point where the Prometheus server is stressed and
switches (rightfully) into rushed mode. In that mode, time series are
processed as quickly as possible, but all of that is in vein if all of
those recently ended time series cannot be persisted yet for another
hour. In that scenario, this change will help most, and it's exactly
the scenario where help is most desperately needed.
2017-03-26 23:44:50 +02:00
Julius Volz 3f23aa2cc7 Add headers to indicate remote read/write version
Also add Content-Type header.
2017-03-24 17:39:51 +01:00
Julius Volz 8fda83ea12 Make rules only read local data 2017-03-21 00:50:04 +01:00
Julius Volz 94acd3f1d8 Add fanin tests and fix uncovered bugs 2017-03-21 00:08:17 +01:00
Julius Volz 9b33cfc457 Fix/unify context-based remote storage timeouts 2017-03-20 14:17:06 +01:00
Julius Volz 815762a4ad Move retrieval.NewHTTPClient -> httputil.NewClientFromConfig 2017-03-20 14:17:04 +01:00
Fabian Reinartz 397f001ac5 Merge branch 'master' into dev-2.0 2017-03-20 14:12:11 +01:00
Julius Volz eb14678a25 Make remote read/write use config.HTTPClientConfig 2017-03-20 13:37:50 +01:00
Julius Volz 406b65d0dc Rename remote.Storage to remote.Writer 2017-03-20 13:15:28 +01:00
Julius Volz 02395a224d [WIP] Remote Read 2017-03-20 13:13:44 +01:00
Julius Volz 40e41a4776 Merge pull request #2494 from tomwilkie/remote-write-sharding
Dynamically reshard the QueueManager based on observed load.
2017-03-20 12:45:17 +01:00
Fabian Reinartz b586781283 *: update tsdb vendoring and add retention flag 2017-03-17 16:06:04 +01:00
beorn7 48d221c11e storage: Fix typo in comment 2017-03-16 11:49:41 +01:00
Fabian Reinartz 0ecd205794 promql: Use buffer pool for matrix allocations 2017-03-14 10:57:34 +01:00
Tom Wilkie 75bb0f3253 Review feedback 2017-03-13 21:24:49 +00:00
Tom Wilkie 77cce900b8 Fix tests 2017-03-13 15:21:59 +00:00
Tom Wilkie b48799a01e Add license stanza 2017-03-13 14:50:15 +00:00
Tom Wilkie 9d22f030cf Dynamically reshard the QueueManager based on observed load. 2017-03-13 14:41:16 +00:00
Fabian Reinartz 8a8eb12985 storage/tsdb: don't use partitioned DB. 2017-03-07 11:51:30 +01:00
Fabian Reinartz 9eb1d6c927 remote: take code from master 2017-03-07 11:43:32 +01:00
Fabian Reinartz 9304179ef7 Merge branch 'master' into dev-2.0 2017-03-02 08:16:58 +01:00
Fabian Reinartz 4397b4d508 *: pass Prometheus registry into storage 2017-02-28 09:33:14 +01:00
Tom Wilkie 1ab893c6ec Limit 'discarding sample' logs to 1 every 10s (#2446)
* Limit 'discarding sample' logs to 1 every 10s

* Include the vendored library

* Review feedback
2017-02-23 19:20:39 +01:00
Julius Volz 2f39dbc8b3 Rename StorageQueueManager -> QueueManager 2017-02-21 21:45:43 +01:00
Julius Volz e9476b35d5 Re-add multiple remote writers
Each remote write endpoint gets its own set of relabeling rules.

This is based on the (yet-to-be-merged)
https://github.com/prometheus/prometheus/pull/2419, which removes legacy
remote write implementations.
2017-02-20 13:23:12 +01:00
Björn Rabenstein 089dc1076b Merge pull request #2435 from jmeulemans/open-chunks-gauge
Adding gauge for number of open head chunks.
2017-02-17 16:02:06 +01:00
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
Julius Volz beb3c4b389 Remove legacy remote storage implementations
This removes legacy support for specific remote storage systems in favor
of only offering the generic remote write protocol. An example bridge
application that translates from the generic protocol to each of those
legacy backends is still provided at:

documentation/examples/remote_storage/remote_storage_bridge

See also https://github.com/prometheus/prometheus/issues/10

The next step in the plan is to re-add support for multiple remote
storages.
2017-02-14 17:52:05 +01:00
beorn7 d771185a43 storage: Fix chunkIndexToStartSeek calculation
With a high enough shrink ratio and enough chunks to persist, the
cutoff point could be _outside_ of the file, which wreaks havoc in the
storage.
2017-02-10 11:42:59 +01:00
beorn7 73bd5e4dff Merge branch 'beorn7/storage' into beorn7/storage3 2017-02-09 14:44:10 +01:00
beorn7 46a0837816 storage: Fix offset returned by dropAndPersistChunks
This is another corner-case that was previously never exercised
because the rewriting of a series file was never prevented by the
shrink ratio.

Scenario: There is an existing series on disk, which is archived. If a
new sample comes in for that file, a new chunk in memory is created,
and the chunkDescsOffset is set to -1. If series maintenance happens
before the series has at least one chunk to persist _and_ an
insufficient chunks on disk is old enough for purging (so that the
shrink ratio kicks in), dropAndPersistChunks would return 0, but it
should return the chunk length of the series file.
2017-02-09 14:35:07 +01:00
beorn7 9d12204da5 Merge branch 'release-1.5' 2017-02-09 13:11:53 +01:00
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 242d8edcb5 Merge branch 'release-1.5' 2017-02-08 17:28:09 +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
Mitsuhiro Tanda be8b1eb656 storage: optimize dropping chunks by using minShrinkRatio (#2397)
storage: prevent unnecessary chunk header reading if minShrinkRatio > 0
2017-02-07 17:33:54 +01:00
beorn7 2363a90adc storage: Do not throw away fully persisted memory series in checkpointing 2017-02-06 17:39:59 +01:00
Fabian Reinartz ea3ba338dd main: add flags for new storage 2017-02-05 18:22:06 +01:00
beorn7 244a65fb29 storage: Increase persist watermark before calling append
The append call may reuse cds, and thus change its len.
(In practice, this wouldn't happen as cds should have len==cap.
Still, the previous order of lines was problematic.)
2017-02-05 02:25:09 +01:00
beorn7 75282b27ba storage: Added checks for invariants 2017-02-04 23:40:22 +01:00
beorn7 31e9db7f0c storage: Simplify evictChunkDesc method 2017-02-04 22:29:37 +01:00
Fabian Reinartz 5772f1a7ba retrieval/storage: adapt to new interface
This simplifies the interface to two add methods for
appends with labels or faster reference numbers.
2017-02-02 13:05:46 +01:00
beorn7 65dc8f44d3 storage: Test for errors returned by MaybePopulateLastTime 2017-02-01 23:43:58 +01:00
beorn7 752fac60ae storage: Remove race condition from TestLoop 2017-02-01 23:43:58 +01:00
beorn7 4ccfc93dcf storage: Set shrink ratio in the constructor. 2017-02-01 15:37:16 +01:00
beorn7 b2f086c6c4 storage: Expose bug of not setting the shrink ratio in the contstructor 2017-02-01 15:37:10 +01:00
Brian Brazil c1b547a90e Only checkpoint chunkdescs and series that need persisting. (#2340)
This decreases checkpoint size by not checkpointing things
that don't actually need checkpointing.

This is fully compatible with the v2 checkpoint format,
as it makes series appear as though the only chunksdescs
in memory are those that need persisting.
2017-01-17 00:59:38 +00:00
Fabian Reinartz c691895a0f retrieval: cache series references, use pkg/textparse
With this change the scraping caches series references and only
allocates label sets if it has to retrieve a new reference.
pkg/textparse is used to do the conditional parsing and reduce
allocations from 900B/sample to 0 in the general case.
2017-01-16 12:03:57 +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
Fabian Reinartz ad9bc62e4c storage: extend appender and adapt it 2017-01-13 14:48:01 +01:00
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
Fabian Reinartz 304cae9928 tsdb: Use PartitionedDB constructor 2017-01-06 12:34:54 +01:00
Brian Brazil f9e581907a Make index queue bigger. (#2322)
When a large Prometheus starts up fresh it can take many minutes
to warmup and clear out the index queue. A larger queue means less
blocking, bigger batches and cuts down startup time by ~50%.
2017-01-05 17:57:42 +00:00
Fabian Reinartz bc20d93f0a storage: rename iterator value getters to At() 2017-01-02 13:33:37 +01:00
Fabian Reinartz 7322c46b8e storage: add mock iterator for test 2016-12-30 10:45:56 +01:00
Fabian Reinartz f8fc1f5bb2 *: migrate ingestion to new batch Appender 2016-12-29 11:03:56 +01:00
Fabian Reinartz 71fe0c58a8 promql: misc fixes 2016-12-28 11:32:15 +01:00
Mitsuhiro Tanda 7e369b9318 expose max memory chunks metrics (#2303)
* expose max memory chunks metrics
2016-12-27 18:34:07 +00:00
Fabian Reinartz fecf9532b9 *: fix misc compile errors 2016-12-25 11:42:57 +01:00
Fabian Reinartz 622ece6273 *: fix recording tests, migrate matcher types 2016-12-25 11:12:57 +01:00
Fabian Reinartz 0492ddbd4d *: fully decouple tsdb, add new storage interfaces 2016-12-25 01:43:22 +01:00
Fabian Reinartz d17b5be48a storage/metric: remove package 2016-12-25 00:42:52 +01:00
Fabian Reinartz 8b84ee5ee6 storage: remove old storage
This removes all old storage files and only keeps interfaces
to still allow the code to compile.
2016-12-22 23:33:32 +01:00
Fabian Reinartz 11a731ba82 remote: remove hard-coded remote storages
This commit removes the flag-configured remote storage integrations
in favor of the generic remote write path.
2016-12-22 23:17:35 +01:00
Brian Brazil 93b70ee4ea Evict chunk descs of all unloaded chunks during maintenance. (#2297)
Keeping these around has two problems:
1) Each desc takes 64 bytes, 10 of them is 640B. This is a lot of
overhead on a 1024 byte chunk.
2) It can take well over a week to reach a point where this and thus
Prometheus memory usage as a whole enters steady state. This makes RAM
estimation very hard for users, and makes it difficult to investigate
things like memory fragmentation.

Instead we'll wipe them during each memory series maintenance cycle, and
if a query pulls them in they'll hang around as cache until the next
cycle.
2016-12-22 13:49:03 +00:00
Brian Brazil 1b8a474612 Don't clone the metric if there's no remote writes.
The metric clone can't be further optimised, and is a
non-trivial memory allocation cost so fast path it
if there's no remote writes configured.
2016-12-21 11:34:48 +00:00
Tristan Colgate 30be8e0b8a ignore dotfiles in data directory 2016-12-15 11:48:23 +00:00
Björn Rabenstein 45570e5972 Merge pull request #2277 from prometheus/beorn7/storage2
storage: Sanity-check number of loaded chunk descs
2016-12-14 02:59:10 +01:00
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
Björn Rabenstein 5f0c0e43cf Merge pull request #2276 from prometheus/beorn7/storage
storage: Catch data corruption that leads to division by zero
2016-12-13 23:13:39 +01:00
beorn7 837c029b16 storage: Fix linter issue
Go style tries to avoid indented `else` blocks.
2016-12-13 19:05:30 +01:00
beorn7 4719482f5f storage: Make tests go-vet and golint clean 2016-12-13 17:07:27 +01:00
beorn7 485ac8dff7 storage: Verify validity of byte length when unmarshalling (double)delta chunks
This makes sure a division-by-zero crash cannot happen in the Len()
method.

Fixes #2773
2016-12-13 17:07:27 +01:00
tattsun e714079cf2 storage: fix error message (#2270)
* storage: add error message
2016-12-09 22:36:27 +00:00
Christopher M. Luciano 148b006e25 Clarify error message when Prometheus data dir finds unexpected files 2016-12-05 10:51:57 -05:00
Julius Volz 127332c56f Merge pull request #2168 from tomwilkie/chunk-len
Add call to estimate number of samples in a chunk to the API
2016-11-17 23:13:50 -08:00
Tom Wilkie 585878cdb2 Add call to estimate number of samples in a chunk to the API 2016-11-17 19:09:59 +00:00
Björn Rabenstein 036715370f Merge pull request #2184 from huydx/master
Fix possible memory leak by defer inside loop
2016-11-14 15:26:39 +01:00
huydx c999902761 Fix possible memory leak by defer inside loop 2016-11-14 14:08:08 +09:00
Fabian Reinartz 856de30c09 Check error before defer closing
If an error is returned the file might be nil and a Close call
would cause a panic.
2016-11-13 18:16:02 +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
beorn7 5b16d6bd6e Merge branch 'release-1.2' 2016-10-31 00:06:23 +01:00
beorn7 876e5da4f8 Add guard against non-monotonic samples in series
This can only happen due to data corruption.
2016-10-25 14:59:33 +02:00
Dominik Schulz 182e17958a Trivial spelling corrections and a small comment. 2016-10-18 20:14:38 +02:00
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
beorn7 719508752b Re-add counting of evict chunk ops and decrementing NumMemChunks
Also, modify test to expose the regression.
2016-10-10 16:30:10 +02:00
Julius Volz cb02f017ee Clean up some doc comments 2016-10-06 21:53:40 +02:00
Julius Volz c212ef0326 Add Chunk.Utilization() methods
When using the chunking code in other projects (both Weave Prism and
ChronixDB ingester), you sometimes want to know how well you are
utilizing your chunks when closing/storing them.
2016-10-06 16:31:59 +02:00
Julius Volz c7932aa009 Remove gRPC leftovers in protobuf definitions 2016-10-05 17:31:04 +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
Brian Brazil 6e8f87a37f Merge pull request #2047 from prometheus/write-relabel
Add support for remote write relabelling.
2016-10-05 07:47:49 +01:00
Brian Brazil 77605649a9 Add support for remote write relabelling.
Switch back to a single remote writer, as we were only ever meant to
have one and the relabel semantics are clearer that way.
2016-10-05 07:43:19 +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
Maxim Ivanov bedc0eda1f Added BenchmarkQueryRange 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
Julius Volz 42c05dd3a2 Merge pull request #2011 from mattkanwisher/chuck-public
Make Chunk and ChunkIterator public for reuse
2016-09-23 14:45:35 +02:00
beorn7 ca98382943 Avoid defer in seriesMap.get
This is related to https://github.com/golang/go/issues/14939 .
It's probably the only occurrence where it matters.
2016-09-22 17:50:58 +02:00
Matthew Campbell 67d76e3a5d timeseries: store varbit encoded data into cassandra 2016-09-21 17:56:55 +02:00
Tom Wilkie 4520e12440 Add HTTP Basic Auth & TLS support to the generic write path. (#1957)
* Add config, HTTP Basic Auth and TLS support to the generic write path.

- Move generic write path configuration to the config file
- Factor out config.TLSConfig -> tlf.Config translation
- Support TLSConfig for generic remote storage
- Rename Run to Start, and make it non-blocking.
- Dedupe code in httputil for TLS config.
- Make remote queue metrics global.
2016-09-19 22:47:51 +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
Maxim Ivanov bdc53098fc Avoid having contended mutexes on same cacheline
CPUs have to serialise write access to a single cache line
effectively reducing level of possible parallelism. Placing
mutexes on different cache lines avoids this problem.

Most gains will be seen on NUMA servers where CPU interconnect
traffic is especially expensive

Before:
go test . -run none -bench BenchmarkFingerprintLocker
BenchmarkFingerprintLockerParallel-4   	 2000000	       932 ns/op
BenchmarkFingerprintLockerSerial-4     	30000000	        49.6 ns/op

After:
go test . -run none -bench BenchmarkFingerprintLocker
BenchmarkFingerprintLockerParallel-4   	 3000000	       569 ns/op
BenchmarkFingerprintLockerSerial-4     	30000000	        51.0 ns/op
2016-09-18 23:32:55 +01:00
Julius Volz 5f5a78e807 Merge pull request #1974 from prometheus/disable-local-storage
Allow disabling local storage.
2016-09-17 18:40:01 +02:00
Tom Wilkie d83879210c Switch back to protos over HTTP, instead of GRPC.
My aim is to support the new grpc generic write path in Frankenstein.  On the surface this seems easy - however I've hit a number of problems that make me think it might be better to not use grpc just yet.

The explanation of the problems requires a little background.  At weave, traffic to frankenstein need to go through a couple of services first, for SSL and to be authenticated.  So traffic goes:

    internet -> frontend -> authfe -> frankenstein

- The frontend is Nginx, and adds/removes SSL.  Its done this way for legacy reasons, so the certs can be managed in one place, although eventually we imagine we'll merge it with authfe.  All traffic from frontend is sent to authfe.
- Authfe checks the auth tokens / cookie etc and then picks the service to forward the RPC to.
- Frankenstein accepts the reads and does the right thing with them.

First problem I hit was Nginx won't proxy http2 requests - it can accept them, but all calls downstream are http1 (see https://trac.nginx.org/nginx/ticket/923).  This wasn't such a big deal, so it now looks like:

    internet --(grpc/http2)--> frontend --(grpc/http1)--> authfe --(grpc/http1)--> frankenstein

Next problem was golang grpc server won't accept http1 requests (see https://groups.google.com/forum/#!topic/grpc-io/JnjCYGPMUms).  It is possible to link a grpc server in with a normal go http mux, as long as the mux server is serving over SSL, as the golang http client & server won't do http2 over anything other than an SSL connection.  This would require making all our service to service comms SSL.  So I had a go a writing a grpc http1 server, and got pretty far.  But is was a bit of a mess.

So finally I thought I'd make a separate grpc frontend for this, running in parallel with the frontend/authfe combo on a different port - and first up I'd need a grpc reverse proxy.  Ideally we'd have some nice, generic reverse proxy that only knew about a map from service names -> downstream service, and didn't need to decode & re-encode every request as it went through.  It seems like this can't be done with golang's grpc library - see https://github.com/mwitkow/grpc-proxy/issues/1.

And then I was surprised to find you can't do grpc from browsers! See http://www.grpc.io/faq/ - not important to us, but I'm starting to question why we decided to use grpc in the first place?

It would seem we could have most of the benefits of grpc with protos over HTTP, and this wouldn't preclude moving to grpc when its a bit more mature?  In fact, the grcp FAQ even admits as much:

> Why is gRPC better than any binary blob over HTTP/2?
> This is largely what gRPC is on the wire.
2016-09-15 23:21:54 +01:00
Tobias Schmidt 29ced0090f Fix common english misspellings 2016-09-14 23:23:28 -04:00
Tobias Schmidt e2c12dcdb5 Add missing error check in persistence test 2016-09-14 23:16:47 -04:00
Tobias Schmidt 8f3b62bfe4 Simplify struct initialization 2016-09-14 23:13:27 -04:00
Julius Volz b24e5d63bc Add noop local storage engine.
This adds a flag -storage.local.engine which allows turning off local
storage in Prometheus. Instead of adding if-conditions and nil checks to
all parts of Prometheus that deal with Prometheus's local storage
(including the web interface), disabling local storage simply means
replacing the normal local storage with a noop version that throws
samples away and returns empty query results. We also don't add the noop
storage to the fanout appender to decrease internal overhead.

Instead of returning empty results, an alternate behavior could be to
return errors on any query that point out that the local storage is
disabled. Not sure which one is more preferable, so I went with the
empty result option for now.
2016-09-14 13:18:05 +02:00
Fabian Reinartz 22296dcb85 storage: clarify sample/matcher relation in docs 2016-09-12 11:19:36 +02:00
Fabian Reinartz cc6f988a5e storage: fix Querier interface documentation 2016-09-12 10:48:54 +02:00
Fabian Reinartz 7bd7e63f97 storage: fix struct alignment issue in test
The uint64 `numCalls` ends up being not word-aligned on certain architectures,
which makes atomic reads/writes panic.
2016-09-11 00:32:57 +02:00
nghialv 7655038184 fix typo 2016-09-08 19:01:32 +09:00
Tom Wilkie d41d91388f Update for new generic remote storage. 2016-08-30 17:43:29 +02:00
Tom Wilkie a6931b71e8 Rationalise retrieval metrics so we have the state (success/failed) on both samples and batches, in a consistent fashion.
Also, report total queue capacity of all queues, i.e. capacity * shards.
2016-08-30 17:42:42 +02:00
Tom Wilkie ece12bff93 Shard/parrallelise samples by fingerprint in StorageQueueManager
By splitting the single queue into multiple queues and flushing each individual queue in serially (and all queues in parallel), we can guarantee to preserve the order of timestampsin samples sent to downstream systems.
2016-08-30 17:42:36 +02:00
Julius Volz fe29e87824 Merge pull request #1930 from prometheus/generic-write-grpc
Generic write via gRPC
2016-08-30 17:28:48 +02:00
Julius Volz aa3f2b7216 Generic write cleanups and changes.
- fold metric name into labels
- return initialization errors back to main
- add snappy compression
- better context handling
- pre-allocation of labels
- remove generic naming
- other cleanups
2016-08-30 17:24:48 +02:00
Brian Brazil 36d2c4bd0b Add generic write path using grpc.
This uses a new proto format, with scope for multiple samples per
timeseries in future. This will allow users to pump samples out to
whatever they like without having to change the core Prometheus code.

There's also an example receiver to save users figuring out the
boilerplate themselves.
2016-08-30 17:19:18 +02:00
Dan Milstein ec064c96f6 Add field names to table-driven test fixtures 2016-08-30 07:57:39 -04:00
Dan Milstein ac8788aca6 Convert to table-driven test and inline helper func 2016-08-30 07:57:39 -04:00
Dan Milstein f50f656a66 Fix double-delta unmarshaling to respect actual min header size
Turns out its valid to have an overall chunk which is smaller than the
full doubleDeltaHeaderBytes size -- if it has a single sample, it
doesn't fill the whole header.  Updated unmarshalling check to respect
this.
2016-08-30 07:57:39 -04:00
Dan Milstein b815956341 Catch errors when unmarshalling delta/doubleDelta encoded chunks
This is (hopefully) a fix for #1653

Specifically, this makes it so that if the length for the stored
delta/doubleDelta is somehow corrupted to be too small, the attempt to
unmarshal will return an error.

The current (broken) behavior is to return a malformed chunk, which can
then lead to a panic when there is an attempt to read header values.

The referenced issue proposed creating chunks with a minimum length -- I
instead opted to just error on the attempt to unmarshal, since I'm not
clear on how it could be safe to proceed when the length is
incorrect/unknown.

The issue also talked about possibly "quarantining series", but I don't
know the surrounding code well enough to understand how to make that
happen.
2016-08-30 07:57:39 -04:00
Matt Bostock e618af5d0b Storage: Add crash recovery metric 'started_dirty'
...to indicate when crash recovery was invoked during Prometheus
startup.

Fixes #1918.
2016-08-27 21:41:06 +02:00
Dan Milstein 764ceaa939 Add timeout to test, cap waiting at 1 second 2016-08-24 11:30:38 -04:00
Dan Milstein 007907b410 Fix one of the tests for a remote storage QueueManager
Specifically, the TestSpawnNotMoreThanMaxConcurrentSendsGoroutines was failing on a fresh checkout of master.

The test had a race condition -- it would only pass if one of the
spawned goroutines happened to very quickly pull a set of samples off an
internal queue.

This patch rewrites the test so that it deterministically waits until
all samples have been pulled off that queue.  In case of errors, it also
now reports on the difference between what it expected and what it found.

I verified that, if the code under test is deliberately broken, the test
successfully reports on that.
2016-08-23 16:26:33 -04:00
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
Dmitry Vorobev 273e457da4 web: return status code and error message for config resource 2016-07-15 10:15:24 +02:00
Björn Rabenstein 0622304244 Merge pull request #1798 from prometheus/beorn7/storage2
Crash recovery: Fix an edge case.
2016-07-13 16:53:18 +02:00
beorn7 2a75b15328 Crash recovery: Fix an edge case.
If the chunks of a series in the checkpoint are all older then the
latest chunk on disk, the head chunk is persisted and therefore has to
be declared closed.

It would be great to have a test for this, but that would require more
plumbing, subject of #447.
2016-07-07 16:17:38 +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
Jan van Valburg 68f3df49d0 stoarge: fix 'access denied' error on Windows
On Windows, it is not possible to rename or delete a file that is
currerntly open. This change closes the file in dropAndPersistChunks
before it tries to delete it, or rename the temporary file to it.
2016-06-21 11:21:20 +02:00
beorn7 b274c7aaa7 Update doc comments 2016-06-03 12:34:01 +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
Tobias Schmidt 4c439b4b45 Merge pull request #1646 from prometheus/beorn7/valuecomparison
Correctly identify no-op appends if the value is NaN
2016-05-20 10:38:05 -04:00
beorn7 a308c76292 Improve TestAppendOutOfOrder
It did not test the returned error so far.
Also, add tests for the NaN case broken before
https://github.com/prometheus/common/pull/40
2016-05-20 13:46:33 +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
Dmitry Vorobev bd2a770015 storage/remote: Spawn not more than "maxConcurrentSends" goroutines. 2016-05-19 16:15:04 +02:00
Dmitry Savintsev 7fdb62c253 fix several minor golint style issues 2016-05-11 14:26:18 +02:00
Steve Durrheimer 399d5c6375
Make version informations consistent between prometheus components 2016-05-05 22:33:18 +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 db16acd7fb Never drop a still open head chunk. 2016-04-15 19:18:40 +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
Jonathan Boulle 38098f8c95 Add missing license headers
Prometheus is Apache 2 licensed, and most source files have the
appropriate copyright license header, but some were missing it without
apparent reason. Correct that by adding it.
2016-04-13 16:08:22 +02:00
Fabian Reinartz a18639dc2d Merge pull request #1454 from prometheus/beorn7/fix-test
Give TestEvictAndLoadChunkDescs more time to actually evict
2016-04-08 14:58:01 +02:00
Tobias Schmidt e82ef154ee Remove unused code leftovers 2016-04-02 20:20:55 -04:00
beorn7 d09ca03e10 Work around compiler bug
Benchmarks don't show any significant changes.
2016-03-29 17:05:28 +02:00
beorn7 507f550cd4 Merge branch 'master' into beorn7/storage7 2016-03-24 14:21:28 +01:00
beorn7 865d16f870 Rename Gorilla into varbit 2016-03-23 16:30:41 +01:00
Julius Volz d3b53bd7f0 Fix comment about Graphite mapping of dimensions. 2016-03-23 00:38:32 +01:00
beorn7 4b574e8a61 Switch chunk encoding to type 2 where it was hardcoded type 1 before
The chunk encoding was hardcoded there because it mostly doesn't
matter what encoding is chosen in that test. Since type 1 is
battle-hardened enough, I'm switching to type 2 here so that we can
catch unexpected problems as a byproduct. My expectation is that the
chunk encoding doesn't matter anyway, as said, but then "unexpected
problems" contains the word "unexpected".
2016-03-20 23:32:20 +01:00
beorn7 c72979e3ed Remove a redundancy from Gorilla-style chunks
So far, the last sample in a chunk was saved twice. That's required
for adding more samples as we need to know the last sample added to
add more samples without iterating through the whole chunk. However,
once the last sample was added to the chunk before it's full, there is
no need to save it twice. Thus, the very last sample added to a chunk
can _only_ be saved in the header fields for the last sample. The
chunk has to be identifiable as closed, then. This information has
been added to the flags byte.
2016-03-20 23:09:48 +01:00
beorn7 b6dbb826ae Improve fuzz testing and fix a bug exposed
This improves fuzz testing in two ways:

(1) More realistic time stamps. So far, the most common case in
practice was very rare in the test: Completely regular increases of
the timestamp.

(2) Verify samples by scanning through the whole relevant section of
the series.

For Gorilla-like chunks, this showed two things:

(1) With more regularly increasing time stamps, BenchmarkFuzz is
essentially as fast as with the traditional chunks:

```
BenchmarkFuzzChunkType0-8              2         972514684 ns/op        83426196 B/op    2500044 allocs/op
BenchmarkFuzzChunkType1-8              2         971478001 ns/op        82874660 B/op    2512364 allocs/op
BenchmarkFuzzChunkType2-8              2         999339453 ns/op        76670636 B/op    2366116 allocs/op
```

(2) There was a bug related to when and how the chunk footer is
overwritten to make use for the last sample. This wasn't exposed by
random access as the last sample of a chunk is retrieved from the
values in the header in that case.
2016-03-20 17:21:28 +01:00
beorn7 9d8fbbe822 Review improvements 2016-03-17 17:31:56 +01:00
beorn7 8cdced3850 Implement Gorilla-inspired chunk encoding
This is not a verbatim implementation of the Gorilla encoding.  First
of all, it could not, even if we wanted, because Prometheus has a
different chunking model (constant size, not constant time).  Second,
this adds a number of changes that improve the encoding in general or
at least for the specific use case of Prometheus (and are partially
only possible in the context of Prometheus). See comments in the code
for details.
2016-03-17 14:47:08 +01:00
beorn7 8e64e8dfca Fix return statement. 2016-03-17 14:43:00 +01:00
Björn Rabenstein 98c8560851 Merge pull request #1477 from prometheus/beorn7/storage7
Solve the series churn problem...
2016-03-17 14:39:28 +01:00
beorn7 e7ac9c6863 Improvments based on review
- Moved returns into the default section of switch statement that can
  only happen then.

- Fix typo.
2016-03-17 14:37:24 +01:00
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 5e4fa96719 Merge branch 'beorn7/storage5' into beorn7/storage6 2016-03-09 17:21:32 +01:00