Enable some additioal Go runtime metrics in order to observe additional
performance data.
Enables a number of new metrics:
```
HELP go_gc_cycles_automatic_gc_cycles_total Count of completed GC cycles generated by the Go runtime.
HELP go_gc_cycles_forced_gc_cycles_total Count of completed GC cycles forced by the application.
HELP go_gc_cycles_total_gc_cycles_total Count of all completed GC cycles.
HELP go_gc_gogc_percent Heap size target percentage configured by the user, otherwise 100. This value is set by the GOGC environment variable, and the runtime/debug.SetGCPercent function.
HELP go_gc_gomemlimit_bytes Go runtime memory limit configured by the user, otherwise math.MaxInt64. This value is set by the GOMEMLIMIT environment variable, and the runtime/debug.SetMemoryLimit function.
HELP go_gc_heap_allocs_by_size_bytes Distribution of heap allocations by approximate size. Bucket counts increase monotonically. Note that this does not include tiny objects as defined by /gc/heap/tiny/allocs:objects, only tiny blocks.
HELP go_gc_heap_allocs_bytes_total Cumulative sum of memory allocated to the heap by the application.
HELP go_gc_heap_allocs_objects_total Cumulative count of heap allocations triggered by the application. Note that this does not include tiny objects as defined by /gc/heap/tiny/allocs:objects, only tiny blocks.
HELP go_gc_heap_frees_by_size_bytes Distribution of freed heap allocations by approximate size. Bucket counts increase monotonically. Note that this does not include tiny objects as defined by /gc/heap/tiny/allocs:objects, only tiny blocks.
HELP go_gc_heap_frees_bytes_total Cumulative sum of heap memory freed by the garbage collector.
HELP go_gc_heap_frees_objects_total Cumulative count of heap allocations whose storage was freed by the garbage collector. Note that this does not include tiny objects as defined by /gc/heap/tiny/allocs:objects, only tiny blocks.
HELP go_gc_heap_goal_bytes Heap size target for the end of the GC cycle.
HELP go_gc_heap_live_bytes Heap memory occupied by live objects that were marked by the previous GC.
HELP go_gc_heap_objects_objects Number of objects, live or unswept, occupying heap memory.
HELP go_gc_heap_tiny_allocs_objects_total Count of small allocations that are packed together into blocks. These allocations are counted separately from other allocations because each individual allocation is not tracked by the runtime, only their block. Each block is already accounted for in allocs-by-size and frees-by-size.
HELP go_gc_limiter_last_enabled_gc_cycle GC cycle the last time the GC CPU limiter was enabled. This metric is useful for diagnosing the root cause of an out-of-memory error, because the limiter trades memory for CPU time when the GC's CPU time gets too high. This is most likely to occur with use of SetMemoryLimit. The first GC cycle is cycle 1, so a value of 0 indicates that it was never enabled.
HELP go_gc_pauses_seconds Deprecated. Prefer the identical /sched/pauses/total/gc:seconds.
HELP go_gc_scan_globals_bytes The total amount of global variable space that is scannable.
HELP go_gc_scan_heap_bytes The total amount of heap space that is scannable.
HELP go_gc_scan_stack_bytes The number of bytes of stack that were scanned last GC cycle.
HELP go_gc_scan_total_bytes The total amount space that is scannable. Sum of all metrics in /gc/scan.
HELP go_gc_stack_starting_size_bytes The stack size of new goroutines.
HELP go_sched_gomaxprocs_threads The current runtime.GOMAXPROCS setting, or the number of operating system threads that can execute user-level Go code simultaneously.
HELP go_sched_goroutines_goroutines Count of live goroutines.
HELP go_sched_latencies_seconds Distribution of the time goroutines have spent in the scheduler in a runnable state before actually running. Bucket counts increase monotonically.
HELP go_sched_pauses_stopping_gc_seconds Distribution of individual GC-related stop-the-world stopping latencies. This is the time it takes from deciding to stop the world until all Ps are stopped. This is a subset of the total GC-related stop-the-world time (/sched/pauses/total/gc:seconds). During this time, some threads may be executing. Bucket counts increase monotonically.
HELP go_sched_pauses_stopping_other_seconds Distribution of individual non-GC-related stop-the-world stopping latencies. This is the time it takes from deciding to stop the world until all Ps are stopped. This is a subset of the total non-GC-related stop-the-world time (/sched/pauses/total/other:seconds). During this time, some threads may be executing. Bucket counts increase monotonically.
HELP go_sched_pauses_total_gc_seconds Distribution of individual GC-related stop-the-world pause latencies. This is the time from deciding to stop the world until the world is started again. Some of this time is spent getting all threads to stop (this is measured directly in /sched/pauses/stopping/gc:seconds), during which some threads may still be running. Bucket counts increase monotonically.
HELP go_sched_pauses_total_other_seconds Distribution of individual non-GC-related stop-the-world pause latencies. This is the time from deciding to stop the world until the world is started again. Some of this time is spent getting all threads to stop (measured directly in /sched/pauses/stopping/other:seconds). Bucket counts increase monotonically.
```
Signed-off-by: SuperQ <superq@gmail.com>
This is about native histograms (not yet supported) and staleness
markers (for which OpenMetrics support isn't even planned).
Signed-off-by: beorn7 <beorn@grafana.com>
Up until this point, if a scrape was done with the protobuf format Prometheus would always try to ingest native histograms even with the feature flag disabled. This causes problems with other feature-flags that depend on the protobuf format, like 'created-timestamp-zero-ingestion'. This commit decouples native histogram parsing from ingestion, making sure ingestion only happens when the 'native-histogram' feature-flag is enabled.
Signed-off-by: Arthur Silva Sens <arthur.sens@coralogix.com>
Currently, running promtool tsdb analyze with the --extended flag
will cause an 'index out of range' error if running it
against a block that does not have any native histogram chunks.
This change ensures that promtool won't try to display data that doesn't exist.
Signed-off-by: Will Hegedus <whegedus@linode.com>
use it in loadDataAsQueryable to make sure the RO Head doesn't truncate or cut new chunks in data/chunks_head/.
add a -sandbox-dir-root flag to "promtool tsdb dump/dump-openmetrics" to control the root of that sandbox dirrectory.
Signed-off-by: machine424 <ayoubmrini424@gmail.com>
Using testify outside of unit tests results in panics rather than a
useful error for the user.
Fixes#13703
Signed-off-by: David Leadbeater <dgl@dgl.cx>
This closes the loop, as the output can be fed into "tsdb create-blocks-from openmetrics"
Native histograms are not supported.
Signed-off-by: machine424 <ayoubmrini424@gmail.com>
For instance `require.NoError` will print the unexpected error; we don't
need to include it in the message.
Signed-off-by: Bryan Boreham <bjboreham@gmail.com>
Optimize histogram iterators
Histogram iterators allocate new objects in the AtHistogram and
AtFloatHistogram methods, which makes calculating rates over long
ranges expensive.
In #13215 we allowed an existing object to be reused
when converting an integer histogram to a float histogram. This commit follows
the same idea and allows injecting an existing object in the AtHistogram and
AtFloatHistogram methods. When the injected value is nil, iterators allocate
new histograms, otherwise they populate and return the injected object.
The commit also adds a CopyTo method to Histogram and FloatHistogram which
is used in the BufferedIterator to overwrite items in the ring instead of making
new copies.
Note that a specialized HPoint pool is needed for all of this to work
(`matrixSelectorHPool`).
---------
Signed-off-by: Filip Petkovski <filip.petkovsky@gmail.com>
Co-authored-by: George Krajcsovits <krajorama@users.noreply.github.com>
SD Managers take over responsibility for SD metrics registration
---------
Signed-off-by: Paulin Todev <paulin.todev@gmail.com>
Signed-off-by: Björn Rabenstein <github@rabenste.in>
Co-authored-by: Björn Rabenstein <github@rabenste.in>
Enable automatic detection of memory limits and configure GOMEMLIMIT to
match.
* Also includes a flag to allow controlling the reserved ratio.
Signed-off-by: SuperQ <superq@gmail.com>
Conditions are ANDed inside the same matcher but matchers are ORed
Including unit tests for "promtool tsdb dump".
Refactor some matchers scraping utils.
Signed-off-by: machine424 <ayoubmrini424@gmail.com>
Add `query analyze` command to promtool
This command analyzes the buckets of classic and native histograms,
based on data queried from the Prometheus query API, i.e. it
doesn't require direct access to the TSDB files.
Signed-off-by: Jeanette Tan <jeanette.tan@grafana.com>
---------
Signed-off-by: Jeanette Tan <jeanette.tan@grafana.com>
Digging around the TSDB code and I've found that this flag is unused so
let's remove it.
Signed-off-by: Giedrius Statkevičius <giedrius.statkevicius@vinted.com>
