go module updates

.gitignore

@@ -282,3 +282,5 @@ go.work.sum
 # Meta-internal CI
 skycastle/
 scrut/
+
+.claude/

charts/gcm/README.md

@@ -23,22 +23,18 @@ The chart is published to GHCR as an OCI artifact and versioned alongside GCM re
 
 ```shell
 helm install gcm oci://ghcr.io/facebookresearch/charts/gcm \
-  --set healthChecks.cluster=my-cluster \
-  --set healthChecks.sink=otel \
-  --set monitoring.sink=otel \
-  --set monitoring.cluster=my-cluster
+  -f <PATH/TO>/custom-values.yaml \
+  --namespace <namespace>
 ```
 
 **DCGM 3** (for older NVIDIA drivers R535/R525):
 
 ```shell
 helm install gcm oci://ghcr.io/facebookresearch/charts/gcm \
+  -f <PATH/TO>/custom-values.yaml \
+  --namespace <namespace> \
   --set monitoring.image.tag=dcgm3 \
   --set healthChecks.image.tag=dcgm3 \
-  --set healthChecks.cluster=my-cluster \
-  --set healthChecks.sink=otel \
-  --set monitoring.sink=otel \
-  --set monitoring.cluster=my-cluster
 ```
 
 To pin a specific chart version, add `--version X.Y.Z`.
@@ -48,11 +44,15 @@ Health checks and monitoring are independent — you can deploy either or both:
 ```shell
 # Health checks only
 helm install gcm oci://ghcr.io/facebookresearch/charts/gcm \
+  -f <PATH/TO>/custom-values.yaml \
+  --namespace <namespace> \
   --set monitoring.enabled=false \
   --set healthChecks.cluster=my-cluster
 
 # Monitoring only
 helm install gcm oci://ghcr.io/facebookresearch/charts/gcm \
+  -f <PATH/TO>/custom-values.yaml \
+  --namespace <namespace> \
   --set healthChecks.enabled=false \
   --set monitoring.sink=otel \
   --set monitoring.cluster=my-cluster
@@ -186,13 +186,17 @@ Sink-specific options can be passed via `sinkOpts` (OmegaConf dot-list syntax).
 ```shell
 # Monitoring: send GPU metrics to an OpenTelemetry collector
 helm install gcm oci://ghcr.io/facebookresearch/charts/gcm \
+  -f <PATH/TO>/custom-values.yaml \
+  --namespace <namespace> \
   --set monitoring.sink=otel \
   --set monitoring.cluster=my-cluster \
   --set monitoring.sinkOpts[0]=otel_endpoint=http://otel-collector:4318 \
   --set "monitoring.sinkOpts[1]=metric_resource_attributes={'environment': 'production'}"
 
 # Health checks: send results to an OpenTelemetry collector
 helm install gcm oci://ghcr.io/facebookresearch/charts/gcm \
+  -f <PATH/TO>/custom-values.yaml \
+  --namespace <namespace> \
   --set healthChecks.sink=otel \
   --set healthChecks.cluster=my-cluster \
   --set healthChecks.sinkOpts[0]=otel_endpoint=http://otel-collector:4318 \
@@ -207,6 +211,8 @@ For clusters that use **labels** instead of taints to identify GPU nodes, use `n
 
 ```shell
 helm install gcm oci://ghcr.io/facebookresearch/charts/gcm \
+  -f <PATH/TO>/custom-values.yaml \
+  --namespace <namespace> \
   --set monitoring.nodeSelector."nvidia\.com/gpu\.present"=true \
   --set healthChecks.nodeSelector."nvidia\.com/gpu\.present"=true
 ```

charts/gcm/values.yaml

@@ -5,8 +5,8 @@
 
 # Usage:
 #   helm install gcm oci://ghcr.io/facebookresearch/charts/gcm \
-#     -f charts/gcm/<CUSTOM-OVERRIDES>.yaml \
-#     --namespace monitoring
+#     -f <PATH/TO>/custom-values.yaml \
+#     --namespace <namespace>
 
 imagePullSecrets: []
 nameOverride: ""

shelper/go.mod

@@ -1,4 +1,4 @@
-module github.com/fairinternal/fair-cluster-monitoring/shelper
+module github.com/facebookresearch/gcm/shelper
 
 go 1.24.3
 

slurmprocessor/common.go

@@ -1,13 +1,13 @@
 // Copyright (c) Meta Platforms, Inc. and affiliates.
 // All rights reserved.
-package main
+package slurmprocessor
 
 import (
 	"context"
 	"log"
 	"strings"
 
-	shelper "github.com/fairinternal/fair-cluster-monitoring/shelper"
+	shelper "github.com/facebookresearch/gcm/shelper"
 	"go.opentelemetry.io/collector/component"
 	"go.opentelemetry.io/collector/consumer"
 	"go.opentelemetry.io/collector/pdata/pcommon"

slurmprocessor/config.go

@@ -1,6 +1,6 @@
 // Copyright (c) Meta Platforms, Inc. and affiliates.
 // All rights reserved.
-package main
+package slurmprocessor
 
 // Config Structure
 type Config struct {

slurmprocessor/config_test.go

@@ -1,6 +1,6 @@
 // Copyright (c) Meta Platforms, Inc. and affiliates.
 // All rights reserved.
-package main
+package slurmprocessor
 
 import (
 	"path"

slurmprocessor/factory.go

@@ -1,18 +1,17 @@
 // Copyright (c) Meta Platforms, Inc. and affiliates.
 // All rights reserved.
-package main
+package slurmprocessor
 
 import (
 	"context"
 	"log"
 
-	"github.com/open-telemetry/opentelemetry-collector-contrib/processor/attributesprocessor/internal/metadata"
 	"go.opentelemetry.io/collector/component"
 	"go.opentelemetry.io/collector/consumer"
 	"go.opentelemetry.io/collector/processor"
 	"go.opentelemetry.io/collector/processor/processorhelper"
 
-	shelper "github.com/fairinternal/fair-cluster-monitoring/shelper"
+	shelper "github.com/facebookresearch/gcm/shelper"
 )
 
 const (
@@ -25,9 +24,9 @@ func NewFactory() processor.Factory {
 	return processor.NewFactory(
 		component.MustNewType(typeStr),
 		createDefaultConfig,
-		processor.WithTraces(createTracesProcessor, metadata.TracesStability),
-		processor.WithMetrics(createMetricsProcessor, metadata.MetricsStability),
-		processor.WithLogs(createLogsProcessor, metadata.LogsStability),
+		processor.WithTraces(createTracesProcessor, component.StabilityLevelAlpha),
+		processor.WithMetrics(createMetricsProcessor, component.StabilityLevelAlpha),
+		processor.WithLogs(createLogsProcessor, component.StabilityLevelAlpha),
 	)
 }
 

slurmprocessor/go.mod

@@ -1,9 +1,9 @@
-module github.com/fairinternal/gpu-cluster-monitoring/slurmprocessor
+module github.com/facebookresearch/gcm/slurmprocessor
 
 go 1.24.3
 
 require (
-	github.com/open-telemetry/opentelemetry-collector-contrib/processor/attributesprocessor v0.126.0
+	github.com/facebookresearch/gcm/shelper v0.0.1
 	github.com/stretchr/testify v1.10.0
 	go.opentelemetry.io/collector/component v1.32.0
 	go.opentelemetry.io/collector/consumer v1.32.0
@@ -23,7 +23,6 @@ require (
 	github.com/cespare/xxhash/v2 v2.3.0 // indirect
 	github.com/davecgh/go-spew v1.1.1 // indirect
 	github.com/ebitengine/purego v0.8.3 // indirect
-	github.com/fairinternal/fair-cluster-monitoring/shelper v0.0.0-20250620180146-cf5a014efe9f // indirect
 	github.com/go-logr/logr v1.4.2 // indirect
 	github.com/go-logr/stdr v1.2.2 // indirect
 	github.com/go-ole/go-ole v1.2.6 // indirect

slurmprocessor/go.sum

@@ -12,8 +12,8 @@ github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/ebitengine/purego v0.8.3 h1:K+0AjQp63JEZTEMZiwsI9g0+hAMNohwUOtY0RPGexmc=
 github.com/ebitengine/purego v0.8.3/go.mod h1:iIjxzd6CiRiOG0UyXP+V1+jWqUXVjPKLAI0mRfJZTmQ=
-github.com/fairinternal/fair-cluster-monitoring/shelper v0.0.0-20250620180146-cf5a014efe9f h1:6O4bbLKO9n8m2myxE5oMk7+RAxGy9UYGDJlB/pWRzQM=
-github.com/fairinternal/fair-cluster-monitoring/shelper v0.0.0-20250620180146-cf5a014efe9f/go.mod h1:8iCqKvY1tift2boY06yo0PsgbhPwi/NSmyzNLRRZyMQ=
+github.com/facebookresearch/gcm/shelper v0.0.1 h1:QLRBEoZuI6dFX0AUvizC3j0bxrCQrmRiErtsgg1tV98=
+github.com/facebookresearch/gcm/shelper v0.0.1/go.mod h1:51syI2aPfL2BYW0zEYjblygcomw9SsMTte7LxgD+b9Q=
 github.com/felixge/httpsnoop v1.0.4 h1:NFTV2Zj1bL4mc9sqWACXbQFVBBg2W3GPvqp8/ESS2Wg=
 github.com/felixge/httpsnoop v1.0.4/go.mod h1:m8KPJKqk1gH5J9DgRY2ASl2lWCfGKXixSwevea8zH2U=
 github.com/foxboron/go-tpm-keyfiles v0.0.0-20250323135004-b31fac66206e h1:2jjYsGgM13xId2Ku+UGDQTO5It50LhT6lljiVJvBj1Y=
@@ -83,8 +83,6 @@ github.com/modern-go/reflect2 v1.0.2 h1:xBagoLtFs94CBntxluKeaWgTMpvLxC4ur3nMaC9G
 github.com/modern-go/reflect2 v1.0.2/go.mod h1:yWuevngMOJpCy52FWWMvUC8ws7m/LJsjYzDa0/r8luk=
 github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 h1:C3w9PqII01/Oq1c1nUAm88MOHcQC9l5mIlSMApZMrHA=
 github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822/go.mod h1:+n7T8mK8HuQTcFwEeznm/DIxMOiR9yIdICNftLE1DvQ=
-github.com/open-telemetry/opentelemetry-collector-contrib/processor/attributesprocessor v0.126.0 h1:ezG3TqbSnQG9JcaLMh0cTts/Jvek6mlj/WApOC3wQtE=
-github.com/open-telemetry/opentelemetry-collector-contrib/processor/attributesprocessor v0.126.0/go.mod h1:xbMS6tl+zIdD26RQXr6VdP2bDuBCBEdV6pC0WgNKiUI=
 github.com/pierrec/lz4/v4 v4.1.22 h1:cKFw6uJDK+/gfw5BcDL0JL5aBsAFdsIT18eRtLj7VIU=
 github.com/pierrec/lz4/v4 v4.1.22/go.mod h1:gZWDp/Ze/IJXGXf23ltt2EXimqmTUXEy0GFuRQyBid4=
 github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=

slurmprocessor/logs.go

@@ -1,12 +1,12 @@
 // Copyright (c) Meta Platforms, Inc. and affiliates.
 // All rights reserved.
-package main
+package slurmprocessor
 
 import (
 	"context"
 	"log"
 
-	shelper "github.com/fairinternal/fair-cluster-monitoring/shelper"
+	shelper "github.com/facebookresearch/gcm/shelper"
 	"go.opentelemetry.io/collector/component"
 	"go.opentelemetry.io/collector/consumer"
 	"go.opentelemetry.io/collector/pdata/plog"

slurmprocessor/metrics.go

@@ -1,12 +1,12 @@
 // Copyright (c) Meta Platforms, Inc. and affiliates.
 // All rights reserved.
-package main
+package slurmprocessor
 
 import (
 	"context"
 	"log"
 
-	shelper "github.com/fairinternal/fair-cluster-monitoring/shelper"
+	shelper "github.com/facebookresearch/gcm/shelper"
 	"go.opentelemetry.io/collector/component"
 	"go.opentelemetry.io/collector/consumer"
 	"go.opentelemetry.io/collector/pdata/pmetric"

slurmprocessor/traces.go

@@ -1,12 +1,12 @@
 // Copyright (c) Meta Platforms, Inc. and affiliates.
 // All rights reserved.
-package main
+package slurmprocessor
 
 import (
 	"context"
 	"log"
 
-	shelper "github.com/fairinternal/fair-cluster-monitoring/shelper"
+	shelper "github.com/facebookresearch/gcm/shelper"
 	"go.opentelemetry.io/collector/component"
 	"go.opentelemetry.io/collector/consumer"
 	"go.opentelemetry.io/collector/pdata/ptrace"

website/docs/GCM_Health_Checks/kubernetes_deployment.md

@@ -30,16 +30,20 @@ The recommended way to deploy on Kubernetes is via the [GCM Helm chart](https://
 
 ```shell
 helm install gcm oci://ghcr.io/facebookresearch/charts/gcm \
-  --set healthChecks.cluster=my-cluster \
-  --set healthChecks.sink=otel
+  -f <PATH/TO>/custom-values.yaml \
+  --namespace <namespace> \
+  --set monitoring.enabled=false \
+  --set healthChecks.enabled=true
 ```
 
 Or from source:
 
 ```shell
 helm install gcm charts/gcm \
-  --set healthChecks.cluster=my-cluster \
-  --set healthChecks.sink=otel
+  -f <PATH/TO>/custom-values.yaml \
+  --namespace <namespace> \
+  --set monitoring.enabled=false \
+  --set healthChecks.enabled=true
 ```
 
 See the [Helm chart README](https://github.com/facebookresearch/gcm/tree/main/charts/gcm/README.md) for full configuration options.

website/docs/GCM_Monitoring/kubernetes_deployment.md

@@ -29,16 +29,20 @@ The recommended way to deploy on Kubernetes is via the [GCM Helm chart](https://
 
 ```shell
 helm install gcm oci://ghcr.io/facebookresearch/charts/gcm \
-  --set monitoring.sink=otel \
-  --set monitoring.cluster=my-cluster
+  -f <PATH/TO>/custom-values.yaml \
+  --namespace <namespace> \
+  --set monitoring.enabled=true \
+  --set healthChecks.enabled=false
 ```
 
 Or from source:
 
 ```shell
 helm install gcm charts/gcm \
-  --set monitoring.sink=otel \
-  --set monitoring.cluster=my-cluster
+  -f <PATH/TO>/custom-values.yaml \
+  --namespace <namespace> \
+  --set monitoring.enabled=true \
+  --set healthChecks.enabled=false
 ```
 
 See the [Helm chart README](https://github.com/facebookresearch/gcm/tree/main/charts/gcm/README.md) for full configuration options.
@@ -57,7 +61,11 @@ See the [Helm chart README](https://github.com/facebookresearch/gcm/tree/main/ch
 ### Sending Metrics to OpenTelemetry
 
 ```shell
-helm install gcm oci://ghcr.io/facebookresearch/charts/gcm \
+helm install gcm oci://ghcr.io/facebookresearch/charts/gcm \ \
+  -f <PATH/TO>/custom-values.yaml \
+  --namespace <namespace> \
+  --set monitoring.enabled=true \
+  --set healthChecks.enabled=false \
   --set monitoring.sink=otel \
   --set monitoring.cluster=my-cluster \
   --set monitoring.extraEnv[0].name=OTEL_EXPORTER_OTLP_ENDPOINT \
@@ -67,7 +75,11 @@ helm install gcm oci://ghcr.io/facebookresearch/charts/gcm \
 Sink-specific options can also be passed via `monitoring.sinkOpts`:
 
 ```shell
-helm install gcm oci://ghcr.io/facebookresearch/charts/gcm \
+helm install gcm oci://ghcr.io/facebookresearch/charts/gcm \ \
+  -f <PATH/TO>/custom-values.yaml \
+  --namespace <namespace>
+  --set monitoring.enabled=true \
+  --set healthChecks.enabled=false \
   --set monitoring.sink=otel \
   --set monitoring.cluster=my-cluster \
   --set monitoring.sinkOpts[0]=otel_endpoint=http://otel-collector:4318 \