config: blobStorage: # Please also set the other keys to connect to your blob storage. See configuration section. enabled: true settings: redisRunsExpirySeconds: "3600"# ttl:# enabled: true# ttl_period_seconds:# longlived: "7776000" # 90 days (default is 400 days)# shortlived: "604800" # 7 days (default is 14 days)frontend: deployment: replicas: 4 # OR enable autoscaling to this level (example below)# autoscaling:# enabled: true# maxReplicas: 4# minReplicas: 2platformBackend: deployment: replicas: 20 # OR enable autoscaling to this level (example below)# autoscaling:# enabled: true# maxReplicas: 20# minReplicas: 8## Note that we are actively working on improving performance of this service to reduce the number of replicas.queue: deployment: replicas: 160 # OR enable autoscaling to this level (example below)# autoscaling:# enabled: true# maxReplicas: 160# minReplicas: 40backend: deployment: replicas: 5 # OR enable autoscaling to this level (example below)# autoscaling:# enabled: true# maxReplicas: 5# minReplicas: 3## Ensure your Redis cache is at least 200 GBredis: external: enabled: true existingSecretName: langsmith-redis-secret # Set the connection url for your external Redis instance (200+ GB)clickhouse: statefulSet: persistence: # This may depend on your configured TTL (see config section). # We recommend 600Gi for every shortlived TTL day if operating at this scale constantly. size: 4200Gi # This assumes 7 days TTL and operating a this scale constantly. resources: requests: cpu: "10" memory: "32Gi" limits: cpu: "16" memory: "48Gi"commonEnv: - name: "CLICKHOUSE_ASYNC_INSERT_WAIT_PCT_FLOAT" value: "0"
config: blobStorage: # Please also set the other keys to connect to your blob storage. See configuration section. enabled: truefrontend: deployment: replicas: 2queue: deployment: replicas: 6 # OR enable autoscaling to this level (example below)# autoscaling:# enabled: true# maxReplicas: 6# minReplicas: 4backend: deployment: replicas: 40 # OR enable autoscaling to this level (example below)# autoscaling:# enabled: true# maxReplicas: 40# minReplicas: 16# We strongly recommend setting up a replicated clickhouse cluster for this load.# Update these values as needed to connect to your replicated clickhouse cluster.clickhouse: external: # If using a 3 node replicated setup, each replica in the cluster should have resource requests of 8+ cores and 16+ GB memory, and resource limit of 12 cores and 32 GB memory. enabled: true host: langsmith-ch-clickhouse-replicated.default.svc.cluster.local port: "8123" nativePort: "9000" user: "default" password: "password" database: "default" cluster: "replicated"
config: blobStorage: # Please also set the other keys to connect to your blob storage. See configuration section. enabled: true settings: redisRunsExpirySeconds: "3600"frontend: deployment: replicas: 2queue: deployment: replicas: 10 # OR enable autoscaling to this level (example below)# autoscaling:# enabled: true# maxReplicas: 10# minReplicas: 5backend: deployment: replicas: 16 # OR enable autoscaling to this level (example below)# autoscaling:# enabled: true# maxReplicas: 16# minReplicas: 8redis: statefulSet: resources: requests: memory: 13Gi limits: memory: 13Gi # -- For external redis instead use something like below -- # external: # enabled: true # connectionUrl: "<URL>" OR existingSecretName: "<SECRET-NAME>"clickhouse: statefulSet: persistence: # This may depend on your configured TTL. # We recommend 60Gi for every shortlived TTL day if operating at this scale constantly. size: 420Gi # This assumes 7 days TTL and operating a this scale constantly. resources: requests: cpu: "16" memory: "24Gi" limits: cpu: "28" memory: "40Gi"commonEnv: - name: "CLICKHOUSE_ASYNC_INSERT_WAIT_PCT_FLOAT" value: "0"
config: blobStorage: # Please also set the other keys to connect to your blob storage. See configuration section. enabled: true settings: redisRunsExpirySeconds: "3600"# ttl:# enabled: true# ttl_period_seconds:# longlived: "7776000" # 90 days (default is 400 days)# shortlived: "604800" # 7 days (default is 14 days)frontend: deployment: replicas: 4 # OR enable autoscaling to this level (example below)# autoscaling:# enabled: true# maxReplicas: 4# minReplicas: 2platformBackend: deployment: replicas: 20 # OR enable autoscaling to this level (example below)# autoscaling:# enabled: true# maxReplicas: 20# minReplicas: 8## Note that we are actively working on improving performance of this service to reduce the number of replicas.queue: deployment: replicas: 160 # OR enable autoscaling to this level (example below)# autoscaling:# enabled: true# maxReplicas: 160# minReplicas: 40backend: deployment: replicas: 50 # OR enable autoscaling to this level (example below)# autoscaling:# enabled: true# maxReplicas: 50# minReplicas: 20## Ensure your Redis cache is at least 200 GBredis: external: enabled: true existingSecretName: langsmith-redis-secret # Set the connection url for your external Redis instance (200+ GB)# We strongly recommend setting up a replicated clickhouse cluster for this load.# Update these values as needed to connect to your replicated clickhouse cluster.clickhouse: external: # If using a 3 node replicated setup, each replica in the cluster should have resource requests of 14+ cores and 24+ GB memory, and resource limit of 20 cores and 48 GB memory. enabled: true host: langsmith-ch-clickhouse-replicated.default.svc.cluster.local port: "8123" nativePort: "9000" user: "default" password: "password" database: "default" cluster: "replicated"commonEnv: - name: "CLICKHOUSE_ASYNC_INSERT_WAIT_PCT_FLOAT" value: "0"
确保 Kubernetes 集群配置了足够的资源以扩展到建议的大小。部署后,Kubernetes 集群中的所有 pod 都应处于 `Running` 状态。卡在 `Pending` 状态的 pod 可能表明您已达到节点池限制或需要更大的节点。此外,确保部署在集群上的任何 ingress 控制器都能够处理所需的负载,以防止瓶颈。