Support gcsfuse-generic and any machine-type in pods

GoogleCloudPlatform · Aug 6, 2024 · ce59323 · ce59323
1 parent 8360569
commit ce59323
Show file tree

Hide file tree

Showing 4 changed files with 46 additions and 10 deletions.
diff --git a/...trics/scripts/testing_on_gke/examples/dlio/unet3d-loading-test/templates/dlio-tester.yaml b/...trics/scripts/testing_on_gke/examples/dlio/unet3d-loading-test/templates/dlio-tester.yaml
@@ -32,11 +32,11 @@ spec:
  image: {{ .Values.image }}
  resources:
  limits:
- cpu: "100"
- memory: 400Gi
+ cpu: {{ .Values.resourceLimits.cpu }}
+ memory: {{ .Values.resourceLimits.memory }}
  requests:
- cpu: "50"
- memory: 300Gi
+ cpu: {{ .Values.resourceRequests.cpu }}
+ memory: {{ .Values.resourceRequests.memory }}
  env:
  - name: RDMAV_FORK_SAFE
  value: "1"
@@ -86,6 +86,10 @@ spec:
  ++workload.reader.read_threads={{ .Values.dlio.readThreads }} \
  ++workload.output.folder=/logs/{{ .Values.dlio.numFilesTrain }}-{{ .Values.dlio.recordLength }}-{{ .Values.dlio.batchSize }}/{{ .Values.scenario }}
 
+ {{ if eq .Values.scenario "gcsfuse-generic"}}
+ echo "{{ .Values.gcsfuse.mountOptions }}" > /logs/{{ .Values.dlio.numFilesTrain }}-{{ .Values.dlio.recordLength }}-{{ .Values.dlio.batchSize }}/{{ .Values.scenario }}/gcsfuse_mount_options
+ {{ end }}
+
  gsutil -m cp -R /logs gs://{{ .Values.bucketName }}/logs/$(date +"%Y-%m-%d-%H-%M")
  volumeMounts:
  - name: dshm
@@ -103,6 +107,13 @@ spec:
  - name: data-vol
  {{- if eq .Values.scenario "local-ssd" }}
  emptyDir: {}
+ {{- else if eq .Values.scenario "gcsfuse-generic" }}
+ csi:
+ driver: gcsfuse.csi.storage.gke.io
+ volumeAttributes:
+ bucketName: {{ .Values.bucketName }}
+ gcsfuseLoggingSeverity: "info"
+ mountOptions: "{{ .Values.gcsfuse.mountOptions }}"
  {{- else if eq .Values.scenario "gcsfuse-file-cache" }}
  csi:
  driver: gcsfuse.csi.storage.gke.io

diff --git a/perfmetrics/scripts/testing_on_gke/examples/dlio/unet3d-loading-test/values.yaml b/perfmetrics/scripts/testing_on_gke/examples/dlio/unet3d-loading-test/values.yaml
@@ -22,6 +22,13 @@ bucketName: gke-dlio-test-data
 scenario: local-ssd
 nodeType: n2-standard-96
 
+resourceLimits:
+ cpu: 0
+ memory: 0
+resourceRequests:
+ cpu: 0
+ memory: 0
+
 dlio:
  numFilesTrain: 500000
  recordLength: 102400
@@ -34,3 +41,4 @@ gcsfuse:
  metadataTypeCacheCapacity: "-1"
  fileCacheCapacity: "-1"
  fileCacheForRangeRead: "true"
+ mountOptions: "implicit-dirs"
diff --git a/perfmetrics/scripts/testing_on_gke/examples/fio/loading-test/templates/fio-tester.yaml b/perfmetrics/scripts/testing_on_gke/examples/fio/loading-test/templates/fio-tester.yaml
@@ -36,8 +36,8 @@ spec:
  cpu: {{ .Values.resourceLimits.cpu }}
  memory: {{ .Values.resourceLimits.memory }}
  requests:
- cpu: "30"
- memory: 300Gi
+ cpu: {{ .Values.resourceRequests.cpu }}
+ memory: {{ .Values.resourceRequests.memory }}
  command:
  - "/bin/sh"
  - "-c"
@@ -110,7 +110,7 @@ spec:
  pause_in_seconds=20
  block_size={{ .Values.fio.blockSize }}
  file_size={{ .Values.fio.fileSize }}
- num_of_threads=50
+ num_of_threads={{ .Values.fio.numThreads }}
  workload_dir=/data
 
  # Cleaning the pagecache, dentries and inode cache before the starting the workload.
@@ -126,6 +126,11 @@ spec:
 
  echo "Run fio tests..."
  mkdir -p /data/fio-output/{{ .Values.scenario }}/$read_type
+
+ {{ if eq .Values.scenario "gcsfuse-generic" }}
+ echo "{{ .Values.gcsfuse.mountOptions }}" > /data/fio-output/{{ .Values.scenario }}/$read_type/gcsfuse_mount_options
+ {{ end }}
+
  for i in $(seq $epoch); do
 
  echo "[Epoch ${i}] start time:" `date +%s`
@@ -164,6 +169,13 @@ spec:
  - name: data-vol
  {{- if eq .Values.scenario "local-ssd" }}
  emptyDir: {}
+ {{- else if eq .Values.scenario "gcsfuse-generic" }}
+ csi:
+ driver: gcsfuse.csi.storage.gke.io
+ volumeAttributes:
+ bucketName: {{ .Values.bucketName }}
+ # gcsfuseLoggingSeverity: "info"
+ mountOptions: "{{ .Values.gcsfuse.mountOptions }}"
  {{- else if eq .Values.scenario "gcsfuse-file-cache" }}
  csi:
  driver: gcsfuse.csi.storage.gke.io

diff --git a/perfmetrics/scripts/testing_on_gke/examples/fio/loading-test/values.yaml b/perfmetrics/scripts/testing_on_gke/examples/fio/loading-test/values.yaml
@@ -23,18 +23,23 @@ scenario: local-ssd
 nodeType: n2-standard-96
 
 resourceLimits:
- cpu: 100
- memory: 400Gi
+ cpu: 0
+ memory: 0
+resourceRequests:
+ cpu: 0
+ memory: 0
 
 fio:
  readType: read
  fileSize: 64K
  blockSize: 64K
  filesPerThread: "20000"
+ numThreads: "50"
 
 gcsfuse:
  metadataCacheTTLSeconds: "6048000"
  metadataStatCacheCapacity: "-1"
  metadataTypeCacheCapacity: "-1"
  fileCacheCapacity: "-1"
- fileCacheForRangeRead: "true"
+ fileCacheForRangeRead: "true"
+ mountOptions: "implicit-dirs"