522 Commits (eb651233ac7b831675620a865a2055c4c8810900)

Author	SHA1	Message	Date
Fabian Reinartz	eb651233ac	Merge pull request #2787 from prometheus/limit2 ... Rework sample limit to work for 2.0	8 years ago
Brian Brazil	37bc607e96	Rework sample limit to work for 2.0 ... Correctly update reported series. Increment prometheus_target_scrapes_exceeded_sample_limit_total. Add back unittests. Ignore stale markers when calculating sample limit. Fixes #2770	8 years ago
Fabian Reinartz	c6eed97c77	Merge pull request #2774 from prometheus/stalemem ... Fix staleness memory leak	8 years ago
Fabian Reinartz	bc7aff8cef	retrieval: extract scrape cache	8 years ago
Brian Brazil	72a276e7ed	Pass through storage errors in limitAppender.	8 years ago
Fabian Reinartz	a83014f53c	retrieval: fix memory leak and consumption for caches	8 years ago
Fabian Reinartz	3d8661b8d5	Add comment	8 years ago
Fabian Reinartz	43ca652217	retrieval: Don't allocate map on every scrape	8 years ago
Fabian Reinartz	d3f662f15e	Merge branch 'dev-2.0' into grobie/reduce-noisy-append-errors	8 years ago
Fabian Reinartz	d289dc55c3	storage: update TSDB	8 years ago
Brian Brazil	0920972f79	Initilise scraped sample map, and rename to series map.	8 years ago
Brian Brazil	bf38963118	Plumb through logger with target field to scrape loop.	8 years ago
Brian Brazil	d657d722dc	Log count of dupliates/out of order samples as warnings. ... Keep log of each sample as debug log.	8 years ago
Brian Brazil	8b9d3e7547	Put end of run staleness handler in seperate function. ... Improve log message.	8 years ago
Brian Brazil	d532272520	Add stalemarkers to synthetic series too when target stops.	8 years ago
Brian Brazil	b87d3ca9ea	Create stale markers when a target is stopped. ... When a target is no longer returned from SD stop() is called. However it may be recreated before the next scrape interval happens. So we wait to set stalemarkers until the scrape of the new target would have happened and been ingested, which is 2 scrape intervals. If we're shutting down the context will be cancelled, so return immediately rather than holding things up for potentially minutes waiting to safely set stalemarkers no newer than now. If the server starts immediately back up again all is well. If not, we're missing some stale markers.	8 years ago
Brian Brazil	95162ebc16	Add log messages for out of order samples	8 years ago
Brian Brazil	3c45400130	Don't fail scrape if one sample violates ordering. ... In Prometheus 1.x one sample that is out of order or that has a duplicate timestamp is discarded, and the rest of the scrape ingestion continues on. This will now also be true for 2.0.	8 years ago
Brian Brazil	fd5c5a50a3	Add stale markers on parse error. ... If we fail to parse the result of a scrape, we should treat that as a failed scrape and add stale markers.	8 years ago
Brian Brazil	c0c7e32e61	Treat a failed scrape as an empty scrape for staleness. ... If a target has died but is still in SD, we want the previously scraped values to go stale. This would also apply to brief blips.	8 years ago
Brian Brazil	850ea412ad	If an explicit timestamp is provided, bypass staleness.	8 years ago
Brian Brazil	a5cf25743c	Move stalness check into a function	8 years ago
Brian Brazil	5060a0fc51	Add unittests for ingestion stale NaNs	8 years ago
Brian Brazil	4f35952cf3	Inject a stale NaN when sample disappears between scrapes.	8 years ago
Brian Brazil	beaa7d5a43	Move consistent NaN logic into the parser.	8 years ago
Brian Brazil	76acf7b9b1	Ensure all the NaNs we ingest have the same bit pattern.	8 years ago
Brian Brazil	0eabed8048	Remove unused metric	8 years ago
Fabian Reinartz	76b3378190	retrieval: add missing scrape context cancelation	8 years ago
Tobias Schmidt	368206d2f5	Handle errSeriesDropped correctly ... If metrics_relabel_configs are used to drop metrics, an errSeriesDropped is returned. This shouldn't be used to return an error at the end of a append() call.	8 years ago
Fabian Reinartz	e829dbe2be	retrieval: comment out accept header again	8 years ago
Fabian Reinartz	73b8ff0ddc	Merge branch 'master' into dev-2.0	8 years ago
Matt Layher	5e4f5fb5ad	retrieval: make scrape timeout header consistent with others	8 years ago
Alexey Palazhchenko	17f15d024a	Small fixes. (#2578) ... Fix typos. Simplify with gofmt -s	8 years ago
Matt Layher	fe4b6693f7	retrieval: add Scrape-Timeout-Seconds header to each scrape request (#2565) ... Fixes #2508.	8 years ago
Fabian Reinartz	8ffc851147	Merge branch 'master' into dev-2.0	8 years ago
Julius Volz	947c83be3b	Sort targets by instance within a job ... Fixes https://github.com/prometheus/prometheus/issues/2536	8 years ago
Julius Volz	815762a4ad	Move retrieval.NewHTTPClient -> httputil.NewClientFromConfig	8 years ago
Fabian Reinartz	c389193b37	Merge branch 'master' into dev-2.0	8 years ago
Fabian Reinartz	5ec1efe622	retrieval: fix test	8 years ago
Fabian Reinartz	d9fb57cde4	*: Simplify []byte to string unsafe conversion	8 years ago
Fabian Reinartz	9304179ef7	Merge branch 'master' into dev-2.0	8 years ago
Erdem Agaoglu	8809735d7f	Setting User-Agent header (#2447)	8 years ago
Fabian Reinartz	cc0ff26f1f	retrieval: handle GZIP compression ourselves ... The automatic GZIP handling of net/http does not preserve buffers across requests and thus generates a lot of garbage. We handle GZIP ourselves to circumvent this.t	8 years ago
Fabian Reinartz	311e7b5069	storage/vendor: update to latest fabxc/tsdb	8 years ago
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.	8 years ago
Brian Brazil	34767c2221	Clone lset before relabelling. (#2386) ... We need to not change the lset passed into populateLabels, as that is kept around by the SDs. Fixes 2377	8 years ago
Fabian Reinartz	1d3cdd0d67	Merge branch 'master' into dev-2.0-rebase	8 years ago
Fabian Reinartz	035976b275	retrieval: handle not found error correctly	8 years ago
Fabian Reinartz	598e2f01c0	retrieval: don't erronously break appending	8 years ago
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.	8 years ago