-
Notifications
You must be signed in to change notification settings - Fork 576
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Prepare for migration to new runtime metrics (#5747)
Part of #5655 This is a refactoring to prepare for the implementation of the new runtime metrics. It: * Adds support for `OTEL_GO_X_DEPRECATED_RUNTIME_METRICS`, which can be set to `true` or `false` to enable/disable the existing runtime metrics. It initially defaults to `true` while the new metrics are under development. * Moves the existing runtime metrics implementation to its own internal package, deprecatedruntime, to clearly separate it from the new metrics being added, and to make the eventual removal easier. This does not change any of the metrics generated, or the public API surface of the runtime metrics package.
- Loading branch information
Showing
9 changed files
with
456 additions
and
268 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,22 @@ | ||
| // Copyright The OpenTelemetry Authors | ||
| // SPDX-License-Identifier: Apache-2.0 | ||
|
|
||
| // Package deprecatedruntime implements the deprecated runtime metrics for OpenTelemetry. | ||
| // | ||
| // The metric events produced are: | ||
| // | ||
| // runtime.go.cgo.calls - Number of cgo calls made by the current process | ||
| // runtime.go.gc.count - Number of completed garbage collection cycles | ||
| // runtime.go.gc.pause_ns (ns) Amount of nanoseconds in GC stop-the-world pauses | ||
| // runtime.go.gc.pause_total_ns (ns) Cumulative nanoseconds in GC stop-the-world pauses since the program started | ||
| // runtime.go.goroutines - Number of goroutines that currently exist | ||
| // runtime.go.lookups - Number of pointer lookups performed by the runtime | ||
| // runtime.go.mem.heap_alloc (bytes) Bytes of allocated heap objects | ||
| // runtime.go.mem.heap_idle (bytes) Bytes in idle (unused) spans | ||
| // runtime.go.mem.heap_inuse (bytes) Bytes in in-use spans | ||
| // runtime.go.mem.heap_objects - Number of allocated heap objects | ||
| // runtime.go.mem.heap_released (bytes) Bytes of idle spans whose physical memory has been returned to the OS | ||
| // runtime.go.mem.heap_sys (bytes) Bytes of heap memory obtained from the OS | ||
| // runtime.go.mem.live_objects - Number of live objects is the number of cumulative Mallocs - Frees | ||
| // runtime.uptime (ms) Milliseconds since application was initialized | ||
| package deprecatedruntime // import "go.opentelemetry.io/contrib/instrumentation/runtime/internal/deprecatedruntime" |
282 changes: 282 additions & 0 deletions
282
instrumentation/runtime/internal/deprecatedruntime/runtime.go
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,282 @@ | ||
| // Copyright The OpenTelemetry Authors | ||
| // SPDX-License-Identifier: Apache-2.0 | ||
|
|
||
| package deprecatedruntime // import "go.opentelemetry.io/contrib/instrumentation/runtime/internal/deprecatedruntime" | ||
|
|
||
| import ( | ||
| "context" | ||
| goruntime "runtime" | ||
| "sync" | ||
| "time" | ||
|
|
||
| "go.opentelemetry.io/otel/metric" | ||
| ) | ||
|
|
||
| // Runtime reports the work-in-progress conventional runtime metrics specified by OpenTelemetry. | ||
| type runtime struct { | ||
| minimumReadMemStatsInterval time.Duration | ||
| meter metric.Meter | ||
| } | ||
|
|
||
| // Start initializes reporting of runtime metrics using the supplied config. | ||
| func Start(meter metric.Meter, minimumReadMemStatsInterval time.Duration) error { | ||
| r := &runtime{ | ||
| meter: meter, | ||
| minimumReadMemStatsInterval: minimumReadMemStatsInterval, | ||
| } | ||
| return r.register() | ||
| } | ||
|
|
||
| func (r *runtime) register() error { | ||
| startTime := time.Now() | ||
| uptime, err := r.meter.Int64ObservableCounter( | ||
| "runtime.uptime", | ||
| metric.WithUnit("ms"), | ||
| metric.WithDescription("Milliseconds since application was initialized"), | ||
| ) | ||
| if err != nil { | ||
| return err | ||
| } | ||
|
|
||
| goroutines, err := r.meter.Int64ObservableUpDownCounter( | ||
| "process.runtime.go.goroutines", | ||
| metric.WithDescription("Number of goroutines that currently exist"), | ||
| ) | ||
| if err != nil { | ||
| return err | ||
| } | ||
|
|
||
| cgoCalls, err := r.meter.Int64ObservableUpDownCounter( | ||
| "process.runtime.go.cgo.calls", | ||
| metric.WithDescription("Number of cgo calls made by the current process"), | ||
| ) | ||
| if err != nil { | ||
| return err | ||
| } | ||
|
|
||
| _, err = r.meter.RegisterCallback( | ||
| func(ctx context.Context, o metric.Observer) error { | ||
| o.ObserveInt64(uptime, time.Since(startTime).Milliseconds()) | ||
| o.ObserveInt64(goroutines, int64(goruntime.NumGoroutine())) | ||
| o.ObserveInt64(cgoCalls, goruntime.NumCgoCall()) | ||
| return nil | ||
| }, | ||
| uptime, | ||
| goroutines, | ||
| cgoCalls, | ||
| ) | ||
| if err != nil { | ||
| return err | ||
| } | ||
|
|
||
| return r.registerMemStats() | ||
| } | ||
|
|
||
| func (r *runtime) registerMemStats() error { | ||
| var ( | ||
| err error | ||
|
|
||
| heapAlloc metric.Int64ObservableUpDownCounter | ||
| heapIdle metric.Int64ObservableUpDownCounter | ||
| heapInuse metric.Int64ObservableUpDownCounter | ||
| heapObjects metric.Int64ObservableUpDownCounter | ||
| heapReleased metric.Int64ObservableUpDownCounter | ||
| heapSys metric.Int64ObservableUpDownCounter | ||
| liveObjects metric.Int64ObservableUpDownCounter | ||
|
|
||
| // TODO: is ptrLookups useful? I've not seen a value | ||
| // other than zero. | ||
| ptrLookups metric.Int64ObservableCounter | ||
|
|
||
| gcCount metric.Int64ObservableCounter | ||
| pauseTotalNs metric.Int64ObservableCounter | ||
| gcPauseNs metric.Int64Histogram | ||
|
|
||
| lastNumGC uint32 | ||
| lastMemStats time.Time | ||
| memStats goruntime.MemStats | ||
|
|
||
| // lock prevents a race between batch observer and instrument registration. | ||
| lock sync.Mutex | ||
| ) | ||
|
|
||
| lock.Lock() | ||
| defer lock.Unlock() | ||
|
|
||
| if heapAlloc, err = r.meter.Int64ObservableUpDownCounter( | ||
| "process.runtime.go.mem.heap_alloc", | ||
| metric.WithUnit("By"), | ||
| metric.WithDescription("Bytes of allocated heap objects"), | ||
| ); err != nil { | ||
| return err | ||
| } | ||
|
|
||
| if heapIdle, err = r.meter.Int64ObservableUpDownCounter( | ||
| "process.runtime.go.mem.heap_idle", | ||
| metric.WithUnit("By"), | ||
| metric.WithDescription("Bytes in idle (unused) spans"), | ||
| ); err != nil { | ||
| return err | ||
| } | ||
|
|
||
| if heapInuse, err = r.meter.Int64ObservableUpDownCounter( | ||
| "process.runtime.go.mem.heap_inuse", | ||
| metric.WithUnit("By"), | ||
| metric.WithDescription("Bytes in in-use spans"), | ||
| ); err != nil { | ||
| return err | ||
| } | ||
|
|
||
| if heapObjects, err = r.meter.Int64ObservableUpDownCounter( | ||
| "process.runtime.go.mem.heap_objects", | ||
| metric.WithDescription("Number of allocated heap objects"), | ||
| ); err != nil { | ||
| return err | ||
| } | ||
|
|
||
| // FYI see https://github.com/golang/go/issues/32284 to help | ||
| // understand the meaning of this value. | ||
| if heapReleased, err = r.meter.Int64ObservableUpDownCounter( | ||
| "process.runtime.go.mem.heap_released", | ||
| metric.WithUnit("By"), | ||
| metric.WithDescription("Bytes of idle spans whose physical memory has been returned to the OS"), | ||
| ); err != nil { | ||
| return err | ||
| } | ||
|
|
||
| if heapSys, err = r.meter.Int64ObservableUpDownCounter( | ||
| "process.runtime.go.mem.heap_sys", | ||
| metric.WithUnit("By"), | ||
| metric.WithDescription("Bytes of heap memory obtained from the OS"), | ||
| ); err != nil { | ||
| return err | ||
| } | ||
|
|
||
| if ptrLookups, err = r.meter.Int64ObservableCounter( | ||
| "process.runtime.go.mem.lookups", | ||
| metric.WithDescription("Number of pointer lookups performed by the runtime"), | ||
| ); err != nil { | ||
| return err | ||
| } | ||
|
|
||
| if liveObjects, err = r.meter.Int64ObservableUpDownCounter( | ||
| "process.runtime.go.mem.live_objects", | ||
| metric.WithDescription("Number of live objects is the number of cumulative Mallocs - Frees"), | ||
| ); err != nil { | ||
| return err | ||
| } | ||
|
|
||
| if gcCount, err = r.meter.Int64ObservableCounter( | ||
| "process.runtime.go.gc.count", | ||
| metric.WithDescription("Number of completed garbage collection cycles"), | ||
| ); err != nil { | ||
| return err | ||
| } | ||
|
|
||
| // Note that the following could be derived as a sum of | ||
| // individual pauses, but we may lose individual pauses if the | ||
| // observation interval is too slow. | ||
| if pauseTotalNs, err = r.meter.Int64ObservableCounter( | ||
| "process.runtime.go.gc.pause_total_ns", | ||
| // TODO: nanoseconds units | ||
| metric.WithDescription("Cumulative nanoseconds in GC stop-the-world pauses since the program started"), | ||
| ); err != nil { | ||
| return err | ||
| } | ||
|
|
||
| if gcPauseNs, err = r.meter.Int64Histogram( | ||
| "process.runtime.go.gc.pause_ns", | ||
| // TODO: nanoseconds units | ||
| metric.WithDescription("Amount of nanoseconds in GC stop-the-world pauses"), | ||
| ); err != nil { | ||
| return err | ||
| } | ||
|
|
||
| _, err = r.meter.RegisterCallback( | ||
| func(ctx context.Context, o metric.Observer) error { | ||
| lock.Lock() | ||
| defer lock.Unlock() | ||
|
|
||
| now := time.Now() | ||
| if now.Sub(lastMemStats) >= r.minimumReadMemStatsInterval { | ||
| goruntime.ReadMemStats(&memStats) | ||
| lastMemStats = now | ||
| } | ||
|
|
||
| o.ObserveInt64(heapAlloc, int64(memStats.HeapAlloc)) | ||
| o.ObserveInt64(heapIdle, int64(memStats.HeapIdle)) | ||
| o.ObserveInt64(heapInuse, int64(memStats.HeapInuse)) | ||
| o.ObserveInt64(heapObjects, int64(memStats.HeapObjects)) | ||
| o.ObserveInt64(heapReleased, int64(memStats.HeapReleased)) | ||
| o.ObserveInt64(heapSys, int64(memStats.HeapSys)) | ||
| o.ObserveInt64(liveObjects, int64(memStats.Mallocs-memStats.Frees)) | ||
| o.ObserveInt64(ptrLookups, int64(memStats.Lookups)) | ||
| o.ObserveInt64(gcCount, int64(memStats.NumGC)) | ||
| o.ObserveInt64(pauseTotalNs, int64(memStats.PauseTotalNs)) | ||
|
|
||
| computeGCPauses(ctx, gcPauseNs, memStats.PauseNs[:], lastNumGC, memStats.NumGC) | ||
|
|
||
| lastNumGC = memStats.NumGC | ||
|
|
||
| return nil | ||
| }, | ||
| heapAlloc, | ||
| heapIdle, | ||
| heapInuse, | ||
| heapObjects, | ||
| heapReleased, | ||
| heapSys, | ||
| liveObjects, | ||
|
|
||
| ptrLookups, | ||
|
|
||
| gcCount, | ||
| pauseTotalNs, | ||
| ) | ||
| if err != nil { | ||
| return err | ||
| } | ||
| return nil | ||
| } | ||
|
|
||
| func computeGCPauses( | ||
| ctx context.Context, | ||
| recorder metric.Int64Histogram, | ||
| circular []uint64, | ||
| lastNumGC, currentNumGC uint32, | ||
| ) { | ||
| delta := int(int64(currentNumGC) - int64(lastNumGC)) | ||
|
|
||
| if delta == 0 { | ||
| return | ||
| } | ||
|
|
||
| if delta >= len(circular) { | ||
| // There were > 256 collections, some may have been lost. | ||
| recordGCPauses(ctx, recorder, circular) | ||
| return | ||
| } | ||
|
|
||
| length := uint32(len(circular)) | ||
|
|
||
| i := lastNumGC % length | ||
| j := currentNumGC % length | ||
|
|
||
| if j < i { // wrap around the circular buffer | ||
| recordGCPauses(ctx, recorder, circular[i:]) | ||
| recordGCPauses(ctx, recorder, circular[:j]) | ||
| return | ||
| } | ||
|
|
||
| recordGCPauses(ctx, recorder, circular[i:j]) | ||
| } | ||
|
|
||
| func recordGCPauses( | ||
| ctx context.Context, | ||
| recorder metric.Int64Histogram, | ||
| pauses []uint64, | ||
| ) { | ||
| for _, pause := range pauses { | ||
| recorder.Record(ctx, int64(pause)) | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,38 @@ | ||
| # Feature Gates | ||
|
|
||
| The runtime package contains a feature gate used to ease the migration | ||
| from the [previous runtime metrics conventions] to the new [OpenTelemetry Go | ||
| Runtime conventions]. | ||
|
|
||
| Note that the new runtime metrics conventions are still experimental, and may | ||
| change in backwards incompatible ways as feedback is applied. | ||
|
|
||
| ## Features | ||
|
|
||
| - [Include Deprecated Metrics](#include-deprecated-metrics) | ||
|
|
||
| ### Include Deprecated Metrics | ||
|
|
||
| Once new experimental runtime metrics are added, they will be produced | ||
| **in addition to** the existing runtime metrics. Users that migrate right away | ||
| can disable the old runtime metrics: | ||
|
|
||
| ```console | ||
| export OTEL_GO_X_DEPRECATED_RUNTIME_METRICS=false | ||
| ``` | ||
|
|
||
| In a later release, the deprecated runtime metrics will stop being produced by | ||
| default. To temporarily re-enable the deprecated metrics: | ||
|
|
||
| ```console | ||
| export OTEL_GO_X_DEPRECATED_RUNTIME_METRICS=true | ||
| ``` | ||
|
|
||
| After two additional releases, the deprecated runtime metrics will be removed, | ||
| and setting the environment variable will no longer have any effect. | ||
|
|
||
| The value set must be the case-insensitive string of `"true"` to enable the | ||
| feature, and `"false"` to disable the feature. All other values are ignored. | ||
|
|
||
| [previous runtime metrics conventions]: go.opentelemetry.io/contrib/instrumentation/runtime/internal/deprecatedruntime | ||
| [OpenTelemetry Go Runtime conventions]: https://github.com/open-telemetry/semantic-conventions/blob/main/docs/runtime/go-metrics.md |
Oops, something went wrong.