prometheus

Commit Graph

Author	SHA1	Message	Date
Bjoern Rabenstein	74c143c4c9	Improve scraper shutdown time. - Stop target pools in parallel. - Stop individual scrapers in goroutines, too. - Timing tweaks. Change-Id: I9dff1ee18616694f14b04408eaf1625d0f989696	10 years ago
Bjoern Rabenstein	92156ee89d	Drain the newBaseLabels channel upon shutdown. This should help cut down shutdown times. Change-Id: I6e70a598a9e49aa6eeeb2034105b1bc6e9014324	10 years ago
Bjoern Rabenstein	6b37e47f9e	Remove unused metrics. Change-Id: Icf03ba4ce92a5e38daf12930f9661daba79c83bb	10 years ago
Bjoern Rabenstein	4447708c9f	Fix a race in target.go. Also, fix problems in shutdown. Starting serving and shutdown still has to be cleaned up properly. It's a mess. Change-Id: I51061db12064e434066446e6fceac32741c4f84c	10 years ago
Bjoern Rabenstein	e0a6cb281e	Fix the accept header. A '/' is a separator and has to be in a quoted string. Change-Id: If7a3a847f84f8f709074d05dc98b5b21e954030c	10 years ago
Brian Brazil	5edf689133	Stagger scrapes to spread out load. Change-Id: Ib141b271e4adfb817886871f86051c207b05cf35	10 years ago
Bjoern Rabenstein	1909686789	Make metrics exported by the Prometheus server itself more consistent. - Always spell out the time unit (e.g. milliseconds instead of ms). - Remove "_total" from the names of metrics that are not counters. - Make use of the "Namespace" and "Subsystem" fields in the options. - Removed the "capacity" facet from all metrics about channels/queues. These are all fixed via command line flags and will never change during the runtime of a process. Also, they should not be part of the same metric family. I have added separate metrics for the capacity of queues as convenience. (They will never change and are only set once.) - I left "metric_disk_latency_microseconds" unchanged, although that metric measures the latency of the storage device, even if it is not a spinning disk. "SSD" is read by many as "solid state disk", so it's not too far off. (It should be "solid state drive", of course, but "metric_drive_latency_microseconds" is probably confusing.) - Brian suggested to not mix "failure" and "success" outcome in the same metric family (distinguished by labels). For now, I left it as it is. We are touching some bigger issue here, especially as other parts in the Prometheus ecosystem are following the same principle. We still need to come to terms here and then change things consistently everywhere. Change-Id: If799458b450d18f78500f05990301c12525197d3	10 years ago
Brian Brazil	4a2b96f848	Remove backoff on scrape failure. Having metrics with variable timestamps inconsistently spaced when things fail will make it harder to write correct rules. Update status page, requires some refactoring to insert a function. Change-Id: Ie1c586cca53b8f3b318af8c21c418873063738a8	10 years ago
Julius Volz	1bb7074fec	Fix HTTP connection leak upon non-OK status. Change-Id: Ie7fbd7dcc089b8306b40631be3e3d736c23c1cd3	10 years ago
Bjoern Rabenstein	bacc31d5cc	Remove work-around that required copying all bytes of a scrape. Now that the subtle bug in matttproud/golang_protobuf_extensions is fixed, we do not need to copy the bytes of a scrape into a buffer first before starting to parse it. Change-Id: Ib73ecae16173ddd219cda56388a8f853332f8853	10 years ago
Bjoern Rabenstein	8956faeccb	Migrate to new client_golang. This change will only be submitted when the new client_golang has been moved to the new version. Change-Id: Ifceb59333072a08286a8ac910709a8ba2e3a1581	10 years ago
Bjoern Rabenstein	814e479723	Treat non-200 HTTP response as error. Change-Id: I2a9f3b47012b3c4839be53aa44c66d16dd41a24a	10 years ago
Brian Brazil	23255f1499	Fix negative Next Retrieval on status page. Change-Id: Ifa754034660a251fee71f166dbf057697ec4e872	11 years ago
Bjoern Rabenstein	64811caaec	Make Prometheus announce its new super-power: text format! Change-Id: Ia2ddfb28999c145e4d46c395381a9bf89d43148c	11 years ago
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	11 years ago
Julius Volz	d69b85e6c9	Add global label support via Ingesters.	11 years ago
Julius Volz	0003027dce	Add needed trailing spaces in logs.	11 years ago
Julius Volz	aa5d251f8d	Use github.com/golang/glog for all logging.	11 years ago
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.	11 years ago
Julius Volz	f8b20f30ac	Make retrieval work with client's new Ingester interface.	11 years ago
Julius Volz	3b970c5133	Add variable interpolation to notification messages. This includes required refactorings to enable replacing the http client (for testing) and moving the NotificationReq type definitions to the "notifications" package, so that this package doesn't need to depend on "rules" anymore and that it can instead use a representation of the required data which only includes the necessary fields.	11 years ago
Julius Volz	35ee2cd3cb	Add alertmanager notification support to Prometheus. Alert definitions now also have mandatory SUMMARY and DESCRIPTION fields that get sent along a firing alert to the alert manager.	12 years ago
Matt T. Proud	f7704af4f8	Code Review: Formatting comments.	12 years ago
Matt T. Proud	06b4a40661	Represent targets in a tabular interface. This commit represents a target group's endpoints in a tabular fashion for better differentiation of their state in a concise manner.	12 years ago
Matt T. Proud	e20e6980e9	Completely extract response payload for decoding. This commit forces the extraction framework to read the entire response payload into a buffer before attempting to decode it, for the underlying Protocol Buffer message readers do not block on partial messages.	12 years ago
Matt T. Proud	b8c7fd8c34	Include Accept header for telemetry request. This pull request introduces a HTTP Accept header to indicate a preference for Protocol Buffer-encoded messages.	12 years ago
Matt T. Proud	30b1cf80b5	WIP - Snapshot of Moving to Client Model.	12 years ago
Matt T. Proud	9cde48754b	Fix race conditions in TargetPool. The race condition detector found a few anomalies whereby a TargetPool could be read during a mutation. This has been fixed.	12 years ago
Julius Volz	081191afb8	Remember and display last scrape errors in web UI.	12 years ago
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.	12 years ago
Julius Volz	d8110fcd9c	Send sample arrays instead of single samples over channels.	12 years ago
Bernerd Schaefer	3929582892	Target uses HTTP transport with deadlines Instead of externally handling timeouts when scraping a target, we set timeouts on the HTTP connection. This ensures that we don't leak goroutines on timeouts. [fixes #181]	12 years ago
Matt T. Proud	a48ab34dd0	Refresh Prometheus client API usage. The client API has been updated per https://github.com/prometheus/client_golang/pull/9.	12 years ago
Julius Volz	d4ff85db5a	Add instance label to health (up) timeseries.	12 years ago
Julius Volz	ae316415fe	Add missing argument to Printf call.	12 years ago
Julius Volz	8c9e9632a8	Record scrape health timeseries per target.	12 years ago
Julius Volz	a1ba23038e	Fix scrape timestamps to reduce sample time jitter. We're currently timestamping samples with the time at the end of a scrape iteration. It makes more sense to use a timestamp from the beginning of the scrape for two reasons: a) this time is more relevant to the scraped values than the time at the end of the HTTP-GET + JSON decoding work. b) it reduces sample timestamp jitter if we measure at the beginning, and not at the completion of a scrape.	12 years ago
Johannes 'fish' Ziemke	14407a076a	Convert addresses pointing to localhost in status. Until now, targets pointing to localhost in the status view are linked to localhost, so you can't follow those links by clicking on them. This change converts the links to point to the hostname of the prometheus server. Before: <a href="http://localhost:9090/metrics.json">http://localhost:9090/metrics.json</a> After: <a href="http://hostname-of-prometheus-server:9090/metrics.json">http://localhost:9090/metrics.json</a>	12 years ago
Matt T. Proud	5a9417f80a	Include humanized target state strings. In the current /status implementation, we cannot divine what the target's state is but rather get an integer constant for it. This commit, stringifies the constants.	12 years ago
Julius Volz	f1fc7d717a	Allow replacing job targets via HTTP API. This roughly comprises the following changes: - index target pools by job instead of scrape interval - make targets within a pool exchangable while preserving existing health state for targets - allow exchanging targets via HTTP API (PUT) - show target lists in /status (experimental, for own debug use)	12 years ago
Julius Volz	047eb219e4	Fix target health state update. Right now, futureState is only used to give hints to the health scheduler, but nowhere is this future state persisted into the target's state field, so we don't actually track a target's state over time.	12 years ago
Julius Volz	5d55785936	Fix broken target scrape error propagation.	12 years ago
Matt T. Proud	ea54751431	Update import paths to new location. This repository moved from matttproud/prometheus to prometheus/prometheus, and all import paths need to be updated.	12 years ago
Matt T. Proud	f2ded515b7	Support versioned telemetry providers. client_golang was updated to support full label-oriented telemetry, which introduced interface incompatibilities with the previous version of Prometheus. To alleviate this, a general fetching and processing dispatching system has been created, which discriminates and processes according to the version of input.	12 years ago
Matt T. Proud	88d15373c5	Upgrade Prometheus to new API.	12 years ago
Julius Volz	80cdb0121d	Add support for configured job base labels.	12 years ago
Matt T. Proud	9752f1e61d	Refactor Target as interface for testability. Future tests around the ``TargetPool`` and ``TargetManager`` and friends will be a lot easier when the concrete behaviors of ``Target`` can be extracted out. Plus, each ``Target``, I suspect, will have its own resolution and query strategy.	12 years ago
Matt T. Proud	efe61c18fa	Refactor target scheduling to separate facility. ``Target`` will be refactored down the road to support various nuanced endpoint types. Thusly incorporating the scheduling behavior within it will be problematic. To that end, the scheduling behavior has been moved into a separate assistance type to improve conciseness and testability. ``make format`` was also run.	12 years ago
Julius Volz	56384bf42a	Add initial config and rule language implementation.	12 years ago
Matt T. Proud	52f52a7ee2	Include nascent instrumentation of stack.	12 years ago
Matt T. Proud	2922def8d0	Use the ``TargetManager`` for targets.	12 years ago
Julius Volz	45a3e0a182	Rename Target Frequency -> Interval.	12 years ago
Matt T. Proud	7a9777b4b5	Create ``TargetPool`` priority queue. ``TargetPool`` is a pool of targets pending scraping. For now, it uses the ``heap.Interface`` from ``container/heap`` to provide a priority queue for the system to scrape from the next target. It is my supposition that we'll use a model whereby we create a ``TargetPool`` for each scrape interval, into which ``Target`` instances are registered.	12 years ago

1 2 3 4

153 Commits (32a951ec89b2c90566a77213ed04a761f754dbb9)