Undo all cnames in prod

.config/hakari.toml

@@ -4,7 +4,7 @@
 hakari-package = "workspace_hack"
 
 # Format for `workspace-hack = ...` lines in other Cargo.tomls. Requires cargo-hakari 0.9.8 or above.
-dep-format-version = "4"
+dep-format-version = "3"
 
 # Setting workspace.resolver = "2" in the root Cargo.toml is HIGHLY recommended.
 # Hakari works much better with the new feature resolver.

.github/PULL_REQUEST_TEMPLATE/release-pr.md

@@ -10,7 +10,6 @@
 <!-- List everything that should be done **before** release, any issues / setting changes / etc -->
 
 ### Checklist after release
-- [ ] Make sure instructions from PRs included in this release and labeled `manual_release_instructions` are executed (either by you or by people who wrote them).
 - [ ] Based on the merged commits write release notes and open a PR into `website` repo ([example](https://github.com/neondatabase/website/pull/219/files))
 - [ ] Check [#dev-production-stream](https://neondb.slack.com/archives/C03F5SM1N02) Slack channel
 - [ ] Check [stuck projects page](https://console.neon.tech/admin/projects?sort=last_active&order=desc&stuck=true)

.github/actions/allure-report/action.yml

@@ -45,12 +45,12 @@ runs:
       shell: bash -euxo pipefail {0}
       run: |
         if [ "${{ inputs.action }}" != "store" ] && [ "${{ inputs.action }}" != "generate" ]; then
-          echo >&2 "Unknown inputs.action type '${{ inputs.action }}'; allowed 'generate' or 'store' only"
+          echo 2>&1 "Unknown inputs.action type '${{ inputs.action }}'; allowed 'generate' or 'store' only"
           exit 1
         fi
 
         if [ -z "${{ inputs.test_selection }}" ] && [ "${{ inputs.action }}" == "store" ]; then
-          echo >&2 "inputs.test_selection must be set for 'store' action"
+          echo 2>&1 "inputs.test_selection must be set for 'store' action"
           exit 2
         fi
 

.github/actions/download/action.yml

@@ -37,7 +37,7 @@ runs:
             echo 'SKIPPED=true' >> $GITHUB_OUTPUT
             exit 0
           else
-            echo >&2 "Neither s3://${BUCKET}/${PREFIX}/${FILENAME} nor its version from previous attempts exist"
+            echo 2>&1 "Neither s3://${BUCKET}/${PREFIX}/${FILENAME} nor its version from previous attempts exist"
             exit 1
           fi
         fi

.github/actions/neon-branch-create/action.yml

@@ -58,7 +58,7 @@ runs:
         done
 
         if [ -z "${branch_id}" ] || [ "${branch_id}" == "null" ]; then
-          echo >&2 "Failed to create branch after 10 attempts, the latest response was: ${branch}"
+          echo 2>&1 "Failed to create branch after 10 attempts, the latest response was: ${branch}"
           exit 1
         fi
 
@@ -122,7 +122,7 @@ runs:
         done
 
         if [ -z "${password}" ] || [ "${password}" == "null" ]; then
-          echo >&2 "Failed to reset password after 10 attempts, the latest response was: ${reset_password}"
+          echo 2>&1 "Failed to reset password after 10 attempts, the latest response was: ${reset_password}"
           exit 1
         fi
 

.github/actions/neon-branch-delete/action.yml

@@ -48,7 +48,7 @@ runs:
         done
 
         if [ -z "${branch_id}" ] || [ "${branch_id}" == "null" ]; then
-          echo >&2 "Failed to delete branch after 10 attempts, the latest response was: ${deleted_branch}"
+          echo 2>&1 "Failed to delete branch after 10 attempts, the latest response was: ${deleted_branch}"
           exit 1
         fi
       env:

.github/actions/run-python-test-set/action.yml

@@ -202,7 +202,7 @@ runs:
         prefix: latest
 
     - name: Create Allure report
-      if: ${{ !cancelled() }}
+      if: success() || failure()
       uses: ./.github/actions/allure-report
       with:
         action: store

.github/actions/upload/action.yml

@@ -23,7 +23,7 @@ runs:
         mkdir -p $(dirname $ARCHIVE)
 
         if [ -f ${ARCHIVE} ]; then
-          echo >&2 "File ${ARCHIVE} already exist. Something went wrong before"
+          echo 2>&1 "File ${ARCHIVE} already exist. Something went wrong before"
           exit 1
         fi
 
@@ -33,10 +33,10 @@ runs:
         elif [ -f ${SOURCE} ]; then
           time tar -cf ${ARCHIVE} --zstd ${SOURCE}
         elif ! ls ${SOURCE} > /dev/null 2>&1; then
-          echo >&2 "${SOURCE} does not exist"
+          echo 2>&1 "${SOURCE} does not exist"
           exit 2
         else
-          echo >&2 "${SOURCE} is neither a directory nor a file, do not know how to handle it"
+          echo 2>&1 "${SOURCE} is neither a directory nor a file, do not know how to handle it"
           exit 3
         fi
 

.github/ansible/prod.ap-southeast-1.hosts.yaml

@@ -17,7 +17,7 @@ storage:
           kind: "LayerAccessThreshold"
           period: "10m"
           threshold: &default_eviction_threshold "24h"
-        evictions_low_residence_duration_metric_threshold: *default_eviction_threshold
+      evictions_low_residence_duration_metric_threshold: *default_eviction_threshold
       remote_storage:
         bucket_name: "{{ bucket_name }}"
         bucket_region: "{{ bucket_region }}"

.github/ansible/prod.eu-central-1.hosts.yaml

@@ -17,7 +17,7 @@ storage:
           kind: "LayerAccessThreshold"
           period: "10m"
           threshold: &default_eviction_threshold "24h"
-        evictions_low_residence_duration_metric_threshold: *default_eviction_threshold
+      evictions_low_residence_duration_metric_threshold: *default_eviction_threshold
       remote_storage:
         bucket_name: "{{ bucket_name }}"
         bucket_region: "{{ bucket_region }}"

.github/ansible/prod.us-east-1.hosts.yaml

@@ -1,50 +0,0 @@
-storage:
-  vars:
-    bucket_name: neon-prod-storage-us-east-1
-    bucket_region: us-east-1
-    console_mgmt_base_url: http://neon-internal-api.aws.neon.tech
-    broker_endpoint: http://storage-broker-lb.theta.us-east-1.internal.aws.neon.tech:50051
-    pageserver_config_stub:
-      pg_distrib_dir: /usr/local
-      metric_collection_endpoint: http://neon-internal-api.aws.neon.tech/billing/api/v1/usage_events
-      metric_collection_interval: 10min
-      disk_usage_based_eviction:
-        max_usage_pct: 85 # TODO: decrease to 80 after all pageservers are below 80
-        min_avail_bytes: 0
-        period: "10s"
-      tenant_config:
-        eviction_policy:
-          kind: "LayerAccessThreshold"
-          period: "10m"
-          threshold: &default_eviction_threshold "24h"
-        evictions_low_residence_duration_metric_threshold: *default_eviction_threshold
-      remote_storage:
-        bucket_name: "{{ bucket_name }}"
-        bucket_region: "{{ bucket_region }}"
-        prefix_in_bucket: "pageserver/v1"
-    safekeeper_s3_prefix: safekeeper/v1/wal
-    hostname_suffix: ""
-    remote_user: ssm-user
-    ansible_aws_ssm_region: us-east-1
-    ansible_aws_ssm_bucket_name: neon-prod-storage-us-east-1
-    console_region_id: aws-us-east-1
-    sentry_environment: production
-
-  children:
-    pageservers:
-      hosts:
-        pageserver-0.us-east-1.aws.neon.tech:
-          ansible_host: i-085222088b0d2e0c7
-        pageserver-1.us-east-1.aws.neon.tech:
-          ansible_host: i-0969d4f684d23a21e
-        pageserver-2.us-east-1.aws.neon.tech:
-          ansible_host: i-05dee87895da58dad
-
-    safekeepers:
-      hosts:
-        safekeeper-0.us-east-1.aws.neon.tech:
-          ansible_host: i-04ce739e88793d864
-        safekeeper-1.us-east-1.aws.neon.tech:
-          ansible_host: i-0e9e6c9227fb81410
-        safekeeper-2.us-east-1.aws.neon.tech:
-          ansible_host: i-072f4dd86a327d52f

.github/ansible/prod.us-east-2.hosts.yaml

@@ -17,7 +17,7 @@ storage:
           kind: "LayerAccessThreshold"
           period: "10m"
           threshold: &default_eviction_threshold "24h"
-        evictions_low_residence_duration_metric_threshold: *default_eviction_threshold
+      evictions_low_residence_duration_metric_threshold: *default_eviction_threshold
       remote_storage:
         bucket_name: "{{ bucket_name }}"
         bucket_region: "{{ bucket_region }}"

.github/ansible/prod.us-west-2.hosts.yaml

@@ -17,7 +17,7 @@ storage:
           kind: "LayerAccessThreshold"
           period: "10m"
           threshold: &default_eviction_threshold "24h"
-        evictions_low_residence_duration_metric_threshold: *default_eviction_threshold
+      evictions_low_residence_duration_metric_threshold: *default_eviction_threshold
       remote_storage:
         bucket_name: "{{ bucket_name }}"
         bucket_region: "{{ bucket_region }}"
@@ -34,7 +34,7 @@ storage:
     pageservers:
       hosts:
         pageserver-0.us-west-2.aws.neon.tech:
-          ansible_host: i-0d9f6dfae0e1c780d
+          ansible_host: i-0d9f6dfae0e1c780d 
         pageserver-1.us-west-2.aws.neon.tech:
           ansible_host: i-0c834be1dddba8b3f
         pageserver-2.us-west-2.aws.neon.tech:
@@ -49,5 +49,5 @@ storage:
         safekeeper-1.us-west-2.aws.neon.tech:
           ansible_host: i-074682f9d3c712e7c
         safekeeper-2.us-west-2.aws.neon.tech:
-          ansible_host: i-042b7efb1729d7966
-
+          ansible_host: i-042b7efb1729d7966 
+          

.github/ansible/staging.eu-central-1.hosts.yaml

@@ -1,47 +0,0 @@
-storage:
-  vars:
-    bucket_name: neon-dev-storage-eu-central-1
-    bucket_region: eu-central-1
-    # We only register/update storage in one preview console and manually copy to other instances
-    console_mgmt_base_url: http://neon-internal-api.helium.aws.neon.build
-    broker_endpoint: http://storage-broker-lb.alpha.eu-central-1.internal.aws.neon.build:50051
-    pageserver_config_stub:
-      pg_distrib_dir: /usr/local
-      metric_collection_endpoint: http://neon-internal-api.helium.aws.neon.build/billing/api/v1/usage_events
-      metric_collection_interval: 10min
-      disk_usage_based_eviction:
-        max_usage_pct: 80
-        min_avail_bytes: 0
-        period: "10s"
-      tenant_config:
-        eviction_policy:
-          kind: "LayerAccessThreshold"
-          period: "20m"
-          threshold: &default_eviction_threshold "20m"
-      evictions_low_residence_duration_metric_threshold: *default_eviction_threshold
-      remote_storage:
-        bucket_name: "{{ bucket_name }}"
-        bucket_region: "{{ bucket_region }}"
-        prefix_in_bucket: "pageserver/v1"
-    safekeeper_s3_prefix: safekeeper/v1/wal
-    hostname_suffix: ""
-    remote_user: ssm-user
-    ansible_aws_ssm_region: eu-central-1
-    ansible_aws_ssm_bucket_name: neon-dev-storage-eu-central-1
-    console_region_id: aws-eu-central-1
-    sentry_environment: staging
-
-  children:
-    pageservers:
-      hosts:
-        pageserver-0.eu-central-1.aws.neon.build:
-          ansible_host: i-011f93ec26cfba2d4
-
-    safekeepers:
-      hosts:
-        safekeeper-0.eu-central-1.aws.neon.build:
-          ansible_host: i-0ff026d27babf8ddd
-        safekeeper-1.eu-central-1.aws.neon.build:
-          ansible_host: i-03983a49ee54725d9
-        safekeeper-2.eu-central-1.aws.neon.build:
-          ansible_host: i-0bd025ecdb61b0db3

.github/ansible/staging.eu-west-1.hosts.yaml

@@ -17,7 +17,7 @@ storage:
           kind: "LayerAccessThreshold"
           period: "20m"
           threshold: &default_eviction_threshold "20m"
-        evictions_low_residence_duration_metric_threshold: *default_eviction_threshold
+      evictions_low_residence_duration_metric_threshold: *default_eviction_threshold
       remote_storage:
         bucket_name: "{{ bucket_name }}"
         bucket_region: "{{ bucket_region }}"

.github/ansible/staging.us-east-2.hosts.yaml

@@ -17,7 +17,7 @@ storage:
           kind: "LayerAccessThreshold"
           period: "20m"
           threshold: &default_eviction_threshold "20m"
-        evictions_low_residence_duration_metric_threshold: *default_eviction_threshold
+      evictions_low_residence_duration_metric_threshold: *default_eviction_threshold
       remote_storage:
         bucket_name: "{{ bucket_name }}"
         bucket_region: "{{ bucket_region }}"
@@ -48,6 +48,8 @@ storage:
       hosts:
         safekeeper-0.us-east-2.aws.neon.build:
           ansible_host: i-027662bd552bf5db0
+        safekeeper-1.us-east-2.aws.neon.build:
+          ansible_host: i-0171efc3604a7b907
         safekeeper-2.us-east-2.aws.neon.build:
           ansible_host: i-0de0b03a51676a6ce
         safekeeper-99.us-east-2.aws.neon.build:

.github/helm-values/dev-eu-central-1-alpha.neon-storage-broker.yaml

@@ -1,52 +0,0 @@
-# Helm chart values for neon-storage-broker
-podLabels:
-  neon_env: staging
-  neon_service: storage-broker
-
-# Use L4 LB
-service:
-  # service.annotations -- Annotations to add to the service
-  annotations:
-    service.beta.kubernetes.io/aws-load-balancer-type: external  # use newer AWS Load Balancer Controller
-    service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
-    service.beta.kubernetes.io/aws-load-balancer-scheme: internal  # deploy LB to private subnet
-    # assign service to this name at external-dns
-    external-dns.alpha.kubernetes.io/hostname: storage-broker-lb.alpha.eu-central-1.internal.aws.neon.build
-  # service.type -- Service type
-  type: LoadBalancer
-  # service.port -- broker listen port
-  port: 50051
-
-ingress:
-  enabled: false
-
-metrics:
-  enabled: false
-
-extraManifests:
-  - apiVersion: operator.victoriametrics.com/v1beta1
-    kind: VMServiceScrape
-    metadata:
-      name: "{{ include \"neon-storage-broker.fullname\" . }}"
-      labels:
-        helm.sh/chart: neon-storage-broker-{{ .Chart.Version }}
-        app.kubernetes.io/name: neon-storage-broker
-        app.kubernetes.io/instance: neon-storage-broker
-        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
-        app.kubernetes.io/managed-by: Helm
-      namespace: "{{ .Release.Namespace }}"
-    spec:
-      selector:
-        matchLabels:
-          app.kubernetes.io/name: "neon-storage-broker"
-      endpoints:
-        - port: broker
-          path: /metrics
-          interval: 10s
-          scrapeTimeout: 10s
-      namespaceSelector:
-        matchNames:
-          - "{{ .Release.Namespace }}"
-
-settings:
-  sentryEnvironment: "staging"

.github/helm-values/dev-eu-west-1-zeta.neon-proxy-scram.yaml

@@ -7,13 +7,13 @@ deploymentStrategy:
     maxSurge: 100%
     maxUnavailable: 50%
 
-# Delay the kill signal by 5 minutes (5 * 60)
+# Delay the kill signal by 7 days (7 * 24 * 60 * 60)
 # The pod(s) will stay in Terminating, keeps the existing connections
 # but doesn't receive new ones
 containerLifecycle:
   preStop:
     exec:
-      command: ["/bin/sh", "-c", "sleep 300"]
+      command: ["/bin/sh", "-c", "sleep 604800"]
 terminationGracePeriodSeconds: 604800
 
 image:
@@ -23,7 +23,6 @@ settings:
   authBackend: "console"
   authEndpoint: "http://neon-internal-api.aws.neon.build/management/api/v2"
   domain: "*.eu-west-1.aws.neon.build"
-  otelExporterOtlpEndpoint: "https://otel-collector.zeta.eu-west-1.internal.aws.neon.build"
   sentryEnvironment: "staging"
   wssPort: 8443
   metricCollectionEndpoint: "http://neon-internal-api.aws.neon.build/billing/api/v1/usage_events"

.github/helm-values/dev-us-east-2-beta.neon-proxy-link.yaml

@@ -9,7 +9,6 @@ settings:
   authEndpoint: "https://console.stage.neon.tech/authenticate_proxy_request/"
   uri: "https://console.stage.neon.tech/psql_session/"
   domain: "pg.neon.build"
-  otelExporterOtlpEndpoint: "https://otel-collector.beta.us-east-2.internal.aws.neon.build"
   sentryEnvironment: "staging"
   metricCollectionEndpoint: "http://neon-internal-api.aws.neon.build/billing/api/v1/usage_events"
   metricCollectionInterval: "1min"

.github/helm-values/dev-us-east-2-beta.neon-proxy-scram-legacy.yaml

@@ -1,22 +1,6 @@
 # Helm chart values for neon-proxy-scram.
 # This is a YAML-formatted file.
 
-deploymentStrategy:
-  type: RollingUpdate
-  rollingUpdate:
-    maxSurge: 100%
-    maxUnavailable: 50%
-
-# Delay the kill signal by 5 minutes (5 * 60)
-# The pod(s) will stay in Terminating, keeps the existing connections
-# but doesn't receive new ones
-containerLifecycle:
-  preStop:
-    exec:
-      command: ["/bin/sh", "-c", "sleep 300"]
-terminationGracePeriodSeconds: 604800
-
-
 image:
   repository: neondatabase/neon
 
@@ -24,7 +8,6 @@ settings:
   authBackend: "console"
   authEndpoint: "http://neon-internal-api.aws.neon.build/management/api/v2"
   domain: "*.cloud.stage.neon.tech"
-  otelExporterOtlpEndpoint: "https://otel-collector.beta.us-east-2.internal.aws.neon.build"
   sentryEnvironment: "staging"
   wssPort: 8443
   metricCollectionEndpoint: "http://neon-internal-api.aws.neon.build/billing/api/v1/usage_events"

.github/helm-values/dev-us-east-2-beta.neon-proxy-scram.yaml

@@ -7,16 +7,15 @@ deploymentStrategy:
     maxSurge: 100%
     maxUnavailable: 50%
 
-# Delay the kill signal by 5 minutes (5 * 60)
+# Delay the kill signal by 7 days (7 * 24 * 60 * 60)
 # The pod(s) will stay in Terminating, keeps the existing connections
 # but doesn't receive new ones
 containerLifecycle:
   preStop:
     exec:
-      command: ["/bin/sh", "-c", "sleep 300"]
+      command: ["/bin/sh", "-c", "sleep 604800"]
 terminationGracePeriodSeconds: 604800
 
-
 image:
   repository: neondatabase/neon
 
@@ -25,7 +24,6 @@ settings:
   authEndpoint: "http://neon-internal-api.aws.neon.build/management/api/v2"
   domain: "*.us-east-2.aws.neon.build"
   extraDomains: ["*.us-east-2.postgres.zenith.tech", "*.us-east-2.retooldb-staging.com"]
-  otelExporterOtlpEndpoint: "https://otel-collector.beta.us-east-2.internal.aws.neon.build"
   sentryEnvironment: "staging"
   wssPort: 8443
   metricCollectionEndpoint: "http://neon-internal-api.aws.neon.build/billing/api/v1/usage_events"

.github/helm-values/preview-template.neon-proxy-scram.yaml

@@ -1,67 +0,0 @@
-# Helm chart values for neon-proxy-scram.
-# This is a YAML-formatted file.
-
-deploymentStrategy:
-  type: RollingUpdate
-  rollingUpdate:
-    maxSurge: 100%
-    maxUnavailable: 50%
-
-image:
-  repository: neondatabase/neon
-
-settings:
-  authBackend: "console"
-  authEndpoint: "http://neon-internal-api.${PREVIEW_NAME}.aws.neon.build/management/api/v2"
-  domain: "*.cloud.${PREVIEW_NAME}.aws.neon.build"
-  sentryEnvironment: "staging"
-  wssPort: 8443
-  metricCollectionEndpoint: "http://neon-internal-api.${PREVIEW_NAME}.aws.neon.build/billing/api/v1/usage_events"
-  metricCollectionInterval: "1min"
-
-# -- Additional labels for neon-proxy pods
-podLabels:
-  neon_service: proxy-scram
-  neon_env: test
-  neon_region: ${PREVIEW_NAME}.eu-central-1
-
-
-exposedService:
-  annotations:
-    service.beta.kubernetes.io/aws-load-balancer-type: external
-    service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
-    service.beta.kubernetes.io/aws-load-balancer-scheme: internet-facing
-    external-dns.alpha.kubernetes.io/hostname: cloud.${PREVIEW_NAME}.aws.neon.build
-  httpsPort: 443
-
-#metrics:
-#  enabled: true
-#  serviceMonitor:
-#    enabled: true
-#    selector:
-#      release: kube-prometheus-stack
-
-extraManifests:
-  - apiVersion: operator.victoriametrics.com/v1beta1
-    kind: VMServiceScrape
-    metadata:
-      name: "{{ include \"neon-proxy.fullname\" . }}"
-      labels:
-        helm.sh/chart: neon-proxy-{{ .Chart.Version }}
-        app.kubernetes.io/name: neon-proxy
-        app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
-        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
-        app.kubernetes.io/managed-by: Helm
-      namespace: "{{ .Release.Namespace }}"
-    spec:
-      selector:
-        matchLabels:
-          app.kubernetes.io/name: "neon-proxy"
-      endpoints:
-        - port: http
-          path: /metrics
-          interval: 10s
-          scrapeTimeout: 10s
-      namespaceSelector:
-        matchNames:
-          - "{{ .Release.Namespace }}"

.github/helm-values/prod-ap-southeast-1-epsilon.neon-proxy-scram.yaml

@@ -7,13 +7,13 @@ deploymentStrategy:
     maxSurge: 100%
     maxUnavailable: 50%
 
-# Delay the kill signal by 5 minutes (5 * 60)
+# Delay the kill signal by 7 days (7 * 24 * 60 * 60)
 # The pod(s) will stay in Terminating, keeps the existing connections
 # but doesn't receive new ones
 containerLifecycle:
   preStop:
     exec:
-      command: ["/bin/sh", "-c", "sleep 300"]
+      command: ["/bin/sh", "-c", "sleep 604800"]
 terminationGracePeriodSeconds: 604800
 
 
@@ -24,7 +24,7 @@ settings:
   authBackend: "console"
   authEndpoint: "http://neon-internal-api.aws.neon.tech/management/api/v2"
   domain: "*.ap-southeast-1.aws.neon.tech"
-  extraDomains: ["*.ap-southeast-1.retooldb.com", "*.ap-southeast-1.postgres.vercel-storage.com"]
+#  extraDomains: ["*.ap-southeast-1.retooldb.com", "*.ap-southeast-1.postgres.vercel-storage.com"]
   sentryEnvironment: "production"
   wssPort: 8443
   metricCollectionEndpoint: "http://neon-internal-api.aws.neon.tech/billing/api/v1/usage_events"

.github/helm-values/prod-eu-central-1-gamma.neon-proxy-scram.yaml

@@ -7,13 +7,13 @@ deploymentStrategy:
     maxSurge: 100%
     maxUnavailable: 50%
 
-# Delay the kill signal by 5 minutes (5 * 60)
+# Delay the kill signal by 7 days (7 * 24 * 60 * 60)
 # The pod(s) will stay in Terminating, keeps the existing connections
 # but doesn't receive new ones
 containerLifecycle:
   preStop:
     exec:
-      command: ["/bin/sh", "-c", "sleep 300"]
+      command: ["/bin/sh", "-c", "sleep 604800"]
 terminationGracePeriodSeconds: 604800
 
 
@@ -24,7 +24,7 @@ settings:
   authBackend: "console"
   authEndpoint: "http://neon-internal-api.aws.neon.tech/management/api/v2"
   domain: "*.eu-central-1.aws.neon.tech"
-  extraDomains: ["*.eu-central-1.retooldb.com", "*.eu-central-1.postgres.vercel-storage.com"]
+#  extraDomains: ["*.eu-central-1.retooldb.com", "*.eu-central-1.postgres.vercel-storage.com"]
   sentryEnvironment: "production"
   wssPort: 8443
   metricCollectionEndpoint: "http://neon-internal-api.aws.neon.tech/billing/api/v1/usage_events"

.github/helm-values/prod-us-east-1-theta.neon-proxy-scram.yaml

@@ -1,69 +0,0 @@
-# Helm chart values for neon-proxy-scram.
-# This is a YAML-formatted file.
-
-deploymentStrategy:
-  type: RollingUpdate
-  rollingUpdate:
-    maxSurge: 100%
-    maxUnavailable: 50%
-
-# Delay the kill signal by 5 minutes (5 * 60)
-# The pod(s) will stay in Terminating, keeps the existing connections
-# but doesn't receive new ones
-containerLifecycle:
-  preStop:
-    exec:
-      command: ["/bin/sh", "-c", "sleep 300"]
-terminationGracePeriodSeconds: 604800
-
-image:
-  repository: neondatabase/neon
-
-settings:
-  authBackend: "console"
-  authEndpoint: "http://neon-internal-api.aws.neon.tech/management/api/v2"
-  domain: "*.us-east-1.aws.neon.tech"
-  # *.us-east-1.retooldb.com hasn't been delegated yet.
-  extraDomains: ["*.us-east-1.postgres.vercel-storage.com"]
-  sentryEnvironment: "production"
-  wssPort: 8443
-  metricCollectionEndpoint: "http://neon-internal-api.aws.neon.tech/billing/api/v1/usage_events"
-  metricCollectionInterval: "10min"
-
-podLabels:
-  neon_service: proxy-scram
-  neon_env: prod
-  neon_region: us-east-1
-
-exposedService:
-  annotations:
-    service.beta.kubernetes.io/aws-load-balancer-type: external
-    service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
-    service.beta.kubernetes.io/aws-load-balancer-scheme: internet-facing
-    external-dns.alpha.kubernetes.io/hostname: us-east-1.aws.neon.tech
-  httpsPort: 443
-
-extraManifests:
-  - apiVersion: operator.victoriametrics.com/v1beta1
-    kind: VMServiceScrape
-    metadata:
-      name: "{{ include \"neon-proxy.fullname\" . }}"
-      labels:
-        helm.sh/chart: neon-proxy-{{ .Chart.Version }}
-        app.kubernetes.io/name: neon-proxy
-        app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
-        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
-        app.kubernetes.io/managed-by: Helm
-      namespace: "{{ .Release.Namespace }}"
-    spec:
-      selector:
-        matchLabels:
-          app.kubernetes.io/name: "neon-proxy"
-      endpoints:
-        - port: http
-          path: /metrics
-          interval: 10s
-          scrapeTimeout: 10s
-      namespaceSelector:
-        matchNames:
-          - "{{ .Release.Namespace }}"

.github/helm-values/prod-us-east-1-theta.neon-storage-broker.yaml

@@ -1,52 +0,0 @@
-# Helm chart values for neon-storage-broker
-podLabels:
-  neon_env: production
-  neon_service: storage-broker
-
-# Use L4 LB
-service:
-  # service.annotations -- Annotations to add to the service
-  annotations:
-    service.beta.kubernetes.io/aws-load-balancer-type: external  # use newer AWS Load Balancer Controller
-    service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
-    service.beta.kubernetes.io/aws-load-balancer-scheme: internal  # deploy LB to private subnet
-    # assign service to this name at external-dns
-    external-dns.alpha.kubernetes.io/hostname: storage-broker-lb.theta.us-east-1.internal.aws.neon.tech
-  # service.type -- Service type
-  type: LoadBalancer
-  # service.port -- broker listen port
-  port: 50051
-
-ingress:
-  enabled: false
-
-metrics:
-  enabled: false
-
-extraManifests:
-  - apiVersion: operator.victoriametrics.com/v1beta1
-    kind: VMServiceScrape
-    metadata:
-      name: "{{ include \"neon-storage-broker.fullname\" . }}"
-      labels:
-        helm.sh/chart: neon-storage-broker-{{ .Chart.Version }}
-        app.kubernetes.io/name: neon-storage-broker
-        app.kubernetes.io/instance: neon-storage-broker
-        app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
-        app.kubernetes.io/managed-by: Helm
-      namespace: "{{ .Release.Namespace }}"
-    spec:
-      selector:
-        matchLabels:
-          app.kubernetes.io/name: "neon-storage-broker"
-      endpoints:
-        - port: broker
-          path: /metrics
-          interval: 10s
-          scrapeTimeout: 10s
-      namespaceSelector:
-        matchNames:
-          - "{{ .Release.Namespace }}"
-
-settings:
-  sentryEnvironment: "production"

.github/helm-values/prod-us-east-2-delta.neon-proxy-scram.yaml

@@ -7,13 +7,13 @@ deploymentStrategy:
     maxSurge: 100%
     maxUnavailable: 50%
 
-# Delay the kill signal by 5 minutes (5 * 60)
+# Delay the kill signal by 7 days (7 * 24 * 60 * 60)
 # The pod(s) will stay in Terminating, keeps the existing connections
 # but doesn't receive new ones
 containerLifecycle:
   preStop:
     exec:
-      command: ["/bin/sh", "-c", "sleep 300"]
+      command: ["/bin/sh", "-c", "sleep 604800"]
 terminationGracePeriodSeconds: 604800
 
 
@@ -24,7 +24,7 @@ settings:
   authBackend: "console"
   authEndpoint: "http://neon-internal-api.aws.neon.tech/management/api/v2"
   domain: "*.us-east-2.aws.neon.tech"
-  extraDomains: ["*.us-east-2.retooldb.com", "*.us-east-2.postgres.vercel-storage.com"]
+#  extraDomains: ["*.us-east-2.retooldb.com", "*.us-east-2.postgres.vercel-storage.com"]
   sentryEnvironment: "production"
   wssPort: 8443
   metricCollectionEndpoint: "http://neon-internal-api.aws.neon.tech/billing/api/v1/usage_events"

.github/helm-values/prod-us-west-2-eta.neon-proxy-scram-legacy.yaml

@@ -7,13 +7,13 @@ deploymentStrategy:
     maxSurge: 100%
     maxUnavailable: 50%
 
-# Delay the kill signal by 5 minutes (5 * 60)
+# Delay the kill signal by 7 days (7 * 24 * 60 * 60)
 # The pod(s) will stay in Terminating, keeps the existing connections
 # but doesn't receive new ones
 containerLifecycle:
   preStop:
     exec:
-      command: ["/bin/sh", "-c", "sleep 300"]
+      command: ["/bin/sh", "-c", "sleep 604800"]
 terminationGracePeriodSeconds: 604800
 
 

.github/helm-values/prod-us-west-2-eta.neon-proxy-scram.yaml

@@ -7,13 +7,13 @@ deploymentStrategy:
     maxSurge: 100%
     maxUnavailable: 50%
 
-# Delay the kill signal by 5 minutes (5 * 60)
+# Delay the kill signal by 7 days (7 * 24 * 60 * 60)
 # The pod(s) will stay in Terminating, keeps the existing connections
 # but doesn't receive new ones
 containerLifecycle:
   preStop:
     exec:
-      command: ["/bin/sh", "-c", "sleep 300"]
+      command: ["/bin/sh", "-c", "sleep 604800"]
 terminationGracePeriodSeconds: 604800
 
 
@@ -24,7 +24,7 @@ settings:
   authBackend: "console"
   authEndpoint: "http://neon-internal-api.aws.neon.tech/management/api/v2"
   domain: "*.us-west-2.aws.neon.tech"
-  extraDomains: ["*.us-west-2.retooldb.com", "*.us-west-2.postgres.vercel-storage.com"]
+#  extraDomains: ["*.us-west-2.retooldb.com", "*.us-west-2.postgres.vercel-storage.com"]
   sentryEnvironment: "production"
   wssPort: 8443
   metricCollectionEndpoint: "http://neon-internal-api.aws.neon.tech/billing/api/v1/usage_events"

.github/workflows/benchmarking.yml

@@ -30,7 +30,7 @@ defaults:
 
 concurrency:
   # Allow only one workflow per any non-`main` branch.
-  group: ${{ github.workflow }}-${{ github.ref_name }}-${{ github.ref_name == 'main' && github.sha || 'anysha' }}
+  group: ${{ github.workflow }}-${{ github.ref }}-${{ github.ref == 'refs/heads/main' && github.sha || 'anysha' }}
   cancel-in-progress: true
 
 jobs:
@@ -42,7 +42,7 @@ jobs:
       DEFAULT_PG_VERSION: 14
       TEST_OUTPUT: /tmp/test_output
       BUILD_TYPE: remote
-      SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref_name == 'main' ) }}
+      SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref == 'refs/heads/main' ) }}
       PLATFORM: "neon-staging"
 
     runs-on: [ self-hosted, us-east-2, x64 ]
@@ -92,7 +92,7 @@ jobs:
         api_key: ${{ secrets.NEON_STAGING_API_KEY }}
 
     - name: Create Allure report
-      if: ${{ !cancelled() }}
+      if: success() || failure()
       uses: ./.github/actions/allure-report
       with:
         action: generate
@@ -174,7 +174,7 @@ jobs:
       DEFAULT_PG_VERSION: 14
       TEST_OUTPUT: /tmp/test_output
       BUILD_TYPE: remote
-      SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref_name == 'main' ) }}
+      SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref == 'refs/heads/main' ) }}
       PLATFORM: ${{ matrix.platform }}
 
     runs-on: [ self-hosted, us-east-2, x64 ]
@@ -226,7 +226,7 @@ jobs:
             CONNSTR=${{ secrets.BENCHMARK_RDS_POSTGRES_CONNSTR }}
             ;;
           *)
-            echo >&2 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-reuse', 'neon-captest-new', 'neon-captest-freetier', 'rds-aurora', or 'rds-postgres'"
+            echo 2>&1 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-reuse', 'neon-captest-new', 'neon-captest-freetier', 'rds-aurora', or 'rds-postgres'"
             exit 1
             ;;
         esac
@@ -282,7 +282,7 @@ jobs:
         api_key: ${{ secrets.NEON_STAGING_API_KEY }}
 
     - name: Create Allure report
-      if: ${{ !cancelled() }}
+      if: success() || failure()
       uses: ./.github/actions/allure-report
       with:
         action: generate
@@ -305,7 +305,7 @@ jobs:
     #
     # *_CLICKBENCH_CONNSTR: Genuine ClickBench DB with ~100M rows
     # *_CLICKBENCH_10M_CONNSTR: DB with the first 10M rows of ClickBench DB
-    if: ${{ !cancelled() }}
+    if: success() || failure()
     needs: [ generate-matrices, pgbench-compare ]
 
     strategy:
@@ -317,7 +317,7 @@ jobs:
       DEFAULT_PG_VERSION: 14
       TEST_OUTPUT: /tmp/test_output
       BUILD_TYPE: remote
-      SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref_name == 'main' ) }}
+      SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref == 'refs/heads/main' ) }}
       PLATFORM: ${{ matrix.platform }}
 
     runs-on: [ self-hosted, us-east-2, x64 ]
@@ -356,7 +356,7 @@ jobs:
             CONNSTR=${{ secrets.BENCHMARK_RDS_POSTGRES_CLICKBENCH_10M_CONNSTR }}
             ;;
           *)
-            echo >&2 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-reuse', 'rds-aurora', or 'rds-postgres'"
+            echo 2>&1 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-reuse', 'rds-aurora', or 'rds-postgres'"
             exit 1
             ;;
         esac
@@ -379,7 +379,7 @@ jobs:
         BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
 
     - name: Create Allure report
-      if: ${{ !cancelled() }}
+      if: success() || failure()
       uses: ./.github/actions/allure-report
       with:
         action: generate
@@ -401,7 +401,7 @@ jobs:
     # We might change it after https://github.com/neondatabase/neon/issues/2900.
     #
     # *_TPCH_S10_CONNSTR: DB generated with scale factor 10 (~10 GB)
-    if: ${{ !cancelled() }}
+    if: success() || failure()
     needs: [ generate-matrices, clickbench-compare ]
 
     strategy:
@@ -413,7 +413,7 @@ jobs:
       DEFAULT_PG_VERSION: 14
       TEST_OUTPUT: /tmp/test_output
       BUILD_TYPE: remote
-      SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref_name == 'main' ) }}
+      SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref == 'refs/heads/main' ) }}
       PLATFORM: ${{ matrix.platform }}
 
     runs-on: [ self-hosted, us-east-2, x64 ]
@@ -452,7 +452,7 @@ jobs:
             CONNSTR=${{ secrets.BENCHMARK_RDS_POSTGRES_TPCH_S10_CONNSTR }}
             ;;
           *)
-            echo >&2 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-reuse', 'rds-aurora', or 'rds-postgres'"
+            echo 2>&1 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-reuse', 'rds-aurora', or 'rds-postgres'"
             exit 1
             ;;
         esac
@@ -475,7 +475,7 @@ jobs:
         BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
 
     - name: Create Allure report
-      if: ${{ !cancelled() }}
+      if: success() || failure()
       uses: ./.github/actions/allure-report
       with:
         action: generate
@@ -491,7 +491,7 @@ jobs:
         SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
 
   user-examples-compare:
-    if: ${{ !cancelled() }}
+    if: success() || failure()
     needs: [ generate-matrices, tpch-compare ]
 
     strategy:
@@ -503,7 +503,7 @@ jobs:
       DEFAULT_PG_VERSION: 14
       TEST_OUTPUT: /tmp/test_output
       BUILD_TYPE: remote
-      SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref_name == 'main' ) }}
+      SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref == 'refs/heads/main' ) }}
       PLATFORM: ${{ matrix.platform }}
 
     runs-on: [ self-hosted, us-east-2, x64 ]
@@ -542,7 +542,7 @@ jobs:
             CONNSTR=${{ secrets.BENCHMARK_USER_EXAMPLE_RDS_POSTGRES_CONNSTR }}
             ;;
           *)
-            echo >&2 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-reuse', 'rds-aurora', or 'rds-postgres'"
+            echo 2>&1 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-reuse', 'rds-aurora', or 'rds-postgres'"
             exit 1
             ;;
         esac
@@ -565,7 +565,7 @@ jobs:
         BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
 
     - name: Create Allure report
-      if: ${{ !cancelled() }}
+      if: success() || failure()
       uses: ./.github/actions/allure-report
       with:
         action: generate

.github/workflows/build_and_test.yml

@@ -13,7 +13,7 @@ defaults:
 
 concurrency:
   # Allow only one workflow per any non-`main` branch.
-  group: ${{ github.workflow }}-${{ github.ref_name }}-${{ github.ref_name == 'main' && github.sha || 'anysha' }}
+  group: ${{ github.workflow }}-${{ github.ref }}-${{ github.ref == 'refs/heads/main' && github.sha || 'anysha' }}
   cancel-in-progress: true
 
 env:
@@ -368,7 +368,7 @@ jobs:
           build_type: ${{ matrix.build_type }}
           test_selection: performance
           run_in_parallel: false
-          save_perf_report: ${{ github.ref_name == 'main' }}
+          save_perf_report: ${{ github.ref == 'refs/heads/main' }}
         env:
           VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
           PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
@@ -541,7 +541,7 @@ jobs:
     container:
       image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/base:pinned
       options: --init
-    needs: [ promote-images, tag ]
+    needs: [ push-docker-hub, tag ]
     steps:
       - name: Set PR's status to pending and request a remote CI test
         run: |
@@ -584,7 +584,8 @@ jobs:
   neon-image:
     runs-on: [ self-hosted, gen3, large ]
     needs: [ tag ]
-    container: gcr.io/kaniko-project/executor:v1.9.2-debug
+    # https://github.com/GoogleContainerTools/kaniko/issues/2005
+    container: gcr.io/kaniko-project/executor:v1.7.0-debug
     defaults:
       run:
         shell: sh -eu {0}
@@ -596,32 +597,11 @@ jobs:
           submodules: true
           fetch-depth: 0
 
-      - name: Configure ECR and Docker Hub login
-        run: |
-          DOCKERHUB_AUTH=$(echo -n "${{ secrets.NEON_DOCKERHUB_USERNAME }}:${{ secrets.NEON_DOCKERHUB_PASSWORD }}" | base64)
-          echo "::add-mask::${DOCKERHUB_AUTH}"
-
-          cat <<-EOF > /kaniko/.docker/config.json
-            {
-              "auths": {
-                "https://index.docker.io/v1/": {
-                  "auth": "${DOCKERHUB_AUTH}"
-                }
-              },
-              "credHelpers": {
-                "369495373322.dkr.ecr.eu-central-1.amazonaws.com": "ecr-login"
-              }
-            }
-          EOF
+      - name: Configure ECR login
+        run: echo "{\"credsStore\":\"ecr-login\"}" > /kaniko/.docker/config.json
 
       - name: Kaniko build neon
-        run:
-          /kaniko/executor --reproducible --snapshot-mode=redo --skip-unused-stages --cache=true
-                           --cache-repo 369495373322.dkr.ecr.eu-central-1.amazonaws.com/cache
-                           --context .
-                           --build-arg GIT_VERSION=${{ github.sha }}
-                           --destination 369495373322.dkr.ecr.eu-central-1.amazonaws.com/neon:${{needs.tag.outputs.build-tag}}
-                           --destination neondatabase/neon:${{needs.tag.outputs.build-tag}}
+        run: /kaniko/executor --reproducible --snapshotMode=redo --skip-unused-stages --cache=true --cache-repo 369495373322.dkr.ecr.eu-central-1.amazonaws.com/cache --context . --build-arg GIT_VERSION=${{ github.sha }} --destination 369495373322.dkr.ecr.eu-central-1.amazonaws.com/neon:${{needs.tag.outputs.build-tag}}
 
       # Cleanup script fails otherwise - rm: cannot remove '/nvme/actions-runner/_work/_temp/_github_home/.ecr': Permission denied
       - name: Cleanup ECR folder
@@ -672,7 +652,7 @@ jobs:
   compute-tools-image:
     runs-on: [ self-hosted, gen3, large ]
     needs: [ tag ]
-    container: gcr.io/kaniko-project/executor:v1.9.2-debug
+    container: gcr.io/kaniko-project/executor:v1.7.0-debug
     defaults:
       run:
         shell: sh -eu {0}
@@ -681,41 +661,18 @@ jobs:
       - name: Checkout
         uses: actions/checkout@v1 # v3 won't work with kaniko
 
-      - name: Configure ECR and Docker Hub login
-        run: |
-          DOCKERHUB_AUTH=$(echo -n "${{ secrets.NEON_DOCKERHUB_USERNAME }}:${{ secrets.NEON_DOCKERHUB_PASSWORD }}" | base64)
-          echo "::add-mask::${DOCKERHUB_AUTH}"
-
-          cat <<-EOF > /kaniko/.docker/config.json
-            {
-              "auths": {
-                "https://index.docker.io/v1/": {
-                  "auth": "${DOCKERHUB_AUTH}"
-                }
-              },
-              "credHelpers": {
-                "369495373322.dkr.ecr.eu-central-1.amazonaws.com": "ecr-login"
-              }
-            }
-          EOF
+      - name: Configure ECR login
+        run: echo "{\"credsStore\":\"ecr-login\"}" > /kaniko/.docker/config.json
 
       - name: Kaniko build compute tools
-        run:
-          /kaniko/executor --reproducible --snapshot-mode=redo --skip-unused-stages --cache=true
-                           --cache-repo 369495373322.dkr.ecr.eu-central-1.amazonaws.com/cache
-                           --context .
-                           --build-arg GIT_VERSION=${{ github.sha }}
-                           --dockerfile Dockerfile.compute-tools
-                           --destination 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-tools:${{needs.tag.outputs.build-tag}}
-                           --destination neondatabase/compute-tools:${{needs.tag.outputs.build-tag}}
+        run: /kaniko/executor --reproducible --snapshotMode=redo --skip-unused-stages --cache=true --cache-repo 369495373322.dkr.ecr.eu-central-1.amazonaws.com/cache --context . --build-arg GIT_VERSION=${{ github.sha }} --dockerfile Dockerfile.compute-tools --destination 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-tools:${{needs.tag.outputs.build-tag}}
 
-      # Cleanup script fails otherwise - rm: cannot remove '/nvme/actions-runner/_work/_temp/_github_home/.ecr': Permission denied
       - name: Cleanup ECR folder
         run: rm -rf ~/.ecr
 
   compute-node-image:
     runs-on: [ self-hosted, gen3, large ]
-    container: gcr.io/kaniko-project/executor:v1.9.2-debug
+    container: gcr.io/kaniko-project/executor:v1.7.0-debug
     needs: [ tag ]
     strategy:
       fail-fast: false
@@ -732,36 +689,12 @@ jobs:
           submodules: true
           fetch-depth: 0
 
-      - name: Configure ECR and Docker Hub login
-        run: |
-          DOCKERHUB_AUTH=$(echo -n "${{ secrets.NEON_DOCKERHUB_USERNAME }}:${{ secrets.NEON_DOCKERHUB_PASSWORD }}" | base64)
-          echo "::add-mask::${DOCKERHUB_AUTH}"
-
-          cat <<-EOF > /kaniko/.docker/config.json
-            {
-              "auths": {
-                "https://index.docker.io/v1/": {
-                  "auth": "${DOCKERHUB_AUTH}"
-                }
-              },
-              "credHelpers": {
-                "369495373322.dkr.ecr.eu-central-1.amazonaws.com": "ecr-login"
-              }
-            }
-          EOF
+      - name: Configure ECR login
+        run: echo "{\"credsStore\":\"ecr-login\"}" > /kaniko/.docker/config.json
 
       - name: Kaniko build compute node with extensions
-        run:
-          /kaniko/executor --reproducible --snapshot-mode=redo --skip-unused-stages --cache=true
-                           --cache-repo 369495373322.dkr.ecr.eu-central-1.amazonaws.com/cache
-                           --context .
-                           --build-arg GIT_VERSION=${{ github.sha }}
-                           --build-arg PG_VERSION=${{ matrix.version }}
-                           --dockerfile Dockerfile.compute-node
-                           --destination 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-${{ matrix.version }}:${{needs.tag.outputs.build-tag}}
-                           --destination neondatabase/compute-node-${{ matrix.version }}:${{needs.tag.outputs.build-tag}}
+        run: /kaniko/executor --reproducible --snapshotMode=redo --skip-unused-stages --cache=true --cache-repo 369495373322.dkr.ecr.eu-central-1.amazonaws.com/cache  --context . --build-arg GIT_VERSION=${{ github.sha }} --build-arg PG_VERSION=${{ matrix.version }} --dockerfile Dockerfile.compute-node --destination 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-${{ matrix.version }}:${{needs.tag.outputs.build-tag}}
 
-      # Cleanup script fails otherwise - rm: cannot remove '/nvme/actions-runner/_work/_temp/_github_home/.ecr': Permission denied
       - name: Cleanup ECR folder
         run: rm -rf ~/.ecr
 
@@ -853,8 +786,41 @@ jobs:
     runs-on: [ self-hosted, gen3, small ]
     needs: [ tag, test-images, vm-compute-node-image ]
     container: golang:1.19-bullseye
-    # Don't add if-condition here.
-    # The job should always be run because we have dependant other jobs that shouldn't be skipped
+    if: github.event_name != 'workflow_dispatch'
+
+    steps:
+      - name: Install Crane & ECR helper
+        if: |
+          (github.ref_name == 'main' || github.ref_name == 'release') &&
+          github.event_name != 'workflow_dispatch'
+        run: |
+          go install github.com/google/go-containerregistry/cmd/crane@31786c6cbb82d6ec4fb8eb79cd9387905130534e # v0.11.0
+          go install github.com/awslabs/amazon-ecr-credential-helper/ecr-login/cli/docker-credential-ecr-login@69c85dc22db6511932bbf119e1a0cc5c90c69a7f # v0.6.0
+
+      - name: Configure ECR login
+        run: |
+          mkdir /github/home/.docker/
+          echo "{\"credsStore\":\"ecr-login\"}" > /github/home/.docker/config.json
+
+      - name: Add latest tag to images
+        if: |
+          (github.ref_name == 'main' || github.ref_name == 'release') &&
+          github.event_name != 'workflow_dispatch'
+        run: |
+          crane tag 369495373322.dkr.ecr.eu-central-1.amazonaws.com/neon:${{needs.tag.outputs.build-tag}} latest
+          crane tag 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-tools:${{needs.tag.outputs.build-tag}} latest
+          crane tag 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v14:${{needs.tag.outputs.build-tag}} latest
+          crane tag 369495373322.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-v14:${{needs.tag.outputs.build-tag}} latest
+          crane tag 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v15:${{needs.tag.outputs.build-tag}} latest
+          crane tag 369495373322.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-v15:${{needs.tag.outputs.build-tag}} latest
+
+      - name: Cleanup ECR folder
+        run: rm -rf ~/.ecr
+
+  push-docker-hub:
+    runs-on: [ self-hosted, dev, x64 ]
+    needs: [ promote-images, tag ]
+    container: golang:1.19-bullseye
 
     steps:
       - name: Install Crane & ECR helper
@@ -867,27 +833,31 @@ jobs:
           mkdir /github/home/.docker/
           echo "{\"credsStore\":\"ecr-login\"}" > /github/home/.docker/config.json
 
-      - name: Copy vm-compute-node images to Docker Hub
-        run: |
-          crane pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-v14:${{needs.tag.outputs.build-tag}} vm-compute-node-v14
-          crane pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-v15:${{needs.tag.outputs.build-tag}} vm-compute-node-v15
+      - name: Pull neon image from ECR
+        run: crane pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/neon:${{needs.tag.outputs.build-tag}} neon
 
-      - name: Add latest tag to images
-        if: |
-          (github.ref_name == 'main' || github.ref_name == 'release') &&
-           github.event_name != 'workflow_dispatch'
-        run: |
-          crane tag 369495373322.dkr.ecr.eu-central-1.amazonaws.com/neon:${{needs.tag.outputs.build-tag}} latest
-          crane tag 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-tools:${{needs.tag.outputs.build-tag}} latest
-          crane tag 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v14:${{needs.tag.outputs.build-tag}} latest
-          crane tag 369495373322.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-v14:${{needs.tag.outputs.build-tag}} latest
-          crane tag 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v15:${{needs.tag.outputs.build-tag}} latest
-          crane tag 369495373322.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-v15:${{needs.tag.outputs.build-tag}} latest
+      - name: Pull compute tools image from ECR
+        run: crane pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-tools:${{needs.tag.outputs.build-tag}} compute-tools
+
+      - name: Pull compute node v14 image from ECR
+        run: crane pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v14:${{needs.tag.outputs.build-tag}} compute-node-v14
+
+      - name: Pull vm compute node v14 image from ECR
+        run: crane pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-v14:${{needs.tag.outputs.build-tag}} vm-compute-node-v14
+
+      - name: Pull compute node v15 image from ECR
+        run: crane pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v15:${{needs.tag.outputs.build-tag}} compute-node-v15
+
+      - name: Pull vm compute node v15 image from ECR
+        run: crane pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-v15:${{needs.tag.outputs.build-tag}} vm-compute-node-v15
+
+      - name: Pull rust image from ECR
+        run: crane pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned rust
 
       - name: Push images to production ECR
         if: |
           (github.ref_name == 'main' || github.ref_name == 'release') &&
-           github.event_name != 'workflow_dispatch'
+          github.event_name != 'workflow_dispatch'
         run: |
           crane copy 369495373322.dkr.ecr.eu-central-1.amazonaws.com/neon:${{needs.tag.outputs.build-tag}} 093970136003.dkr.ecr.eu-central-1.amazonaws.com/neon:latest
           crane copy 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-tools:${{needs.tag.outputs.build-tag}} 093970136003.dkr.ecr.eu-central-1.amazonaws.com/compute-tools:latest
@@ -902,12 +872,28 @@ jobs:
           echo "" > /github/home/.docker/config.json
           crane auth login -u ${{ secrets.NEON_DOCKERHUB_USERNAME }} -p ${{ secrets.NEON_DOCKERHUB_PASSWORD }} index.docker.io
 
-      - name: Push vm-compute-node to Docker Hub
-        run: |
-          crane push vm-compute-node-v14 neondatabase/vm-compute-node-v14:${{needs.tag.outputs.build-tag}}
-          crane push vm-compute-node-v15 neondatabase/vm-compute-node-v15:${{needs.tag.outputs.build-tag}}
+      - name: Push neon image to Docker Hub
+        run: crane push neon neondatabase/neon:${{needs.tag.outputs.build-tag}}
 
-      - name: Push latest tags to Docker Hub
+      - name: Push compute tools image to Docker Hub
+        run: crane push compute-tools neondatabase/compute-tools:${{needs.tag.outputs.build-tag}}
+
+      - name: Push compute node v14 image to Docker Hub
+        run: crane push compute-node-v14 neondatabase/compute-node-v14:${{needs.tag.outputs.build-tag}}
+
+      - name: Push vm compute node v14 image to Docker Hub
+        run: crane push vm-compute-node-v14 neondatabase/vm-compute-node-v14:${{needs.tag.outputs.build-tag}}
+
+      - name: Push compute node v15 image to Docker Hub
+        run: crane push compute-node-v15 neondatabase/compute-node-v15:${{needs.tag.outputs.build-tag}}
+
+      - name: Push vm compute node v15 image to Docker Hub
+        run: crane push vm-compute-node-v15 neondatabase/vm-compute-node-v15:${{needs.tag.outputs.build-tag}}
+
+      - name: Push rust image to Docker Hub
+        run: crane push rust neondatabase/rust:pinned
+
+      - name: Add latest tag to images in Docker Hub
         if: |
           (github.ref_name == 'main' || github.ref_name == 'release') &&
           github.event_name != 'workflow_dispatch'
@@ -927,7 +913,7 @@ jobs:
     container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/ansible:pinned
     # We need both storage **and** compute images for deploy, because control plane picks the compute version based on the storage version.
     # If it notices a fresh storage it may bump the compute version. And if compute image failed to build it may break things badly
-    needs: [ promote-images, tag, regress-tests ]
+    needs: [ push-docker-hub, tag, regress-tests ]
     if: |
       contains(github.event.pull_request.labels.*.name, 'deploy-test-storage') &&
       github.event_name != 'workflow_dispatch'
@@ -961,7 +947,7 @@ jobs:
   deploy:
     runs-on: [ self-hosted, gen3, small ]
     container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/ansible:latest
-    needs: [ promote-images, tag, regress-tests ]
+    needs: [ push-docker-hub, tag, regress-tests ]
     if: ( github.ref_name == 'main' || github.ref_name == 'release' ) && github.event_name != 'workflow_dispatch'
     steps:
       - name: Fix git ownership
@@ -998,7 +984,7 @@ jobs:
     container:
       image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
       options: --init
-    needs: [ promote-images, tag, regress-tests ]
+    needs: [ push-docker-hub, tag, regress-tests ]
     if: github.ref_name == 'release' && github.event_name != 'workflow_dispatch'
     steps:
       - name: Promote compatibility snapshot for the release
@@ -1021,7 +1007,7 @@ jobs:
 
             S3_KEY=$(aws s3api list-objects-v2 --bucket ${BUCKET} --prefix ${OLD_PREFIX} | jq -r '.Contents[].Key' | grep ${FILENAME} | sort --version-sort | tail -1 || true)
             if [ -z "${S3_KEY}" ]; then
-              echo >&2 "Neither s3://${BUCKET}/${OLD_PREFIX}/${FILENAME} nor its version from previous attempts exist"
+              echo 2>&1 "Neither s3://${BUCKET}/${OLD_PREFIX}/${FILENAME} nor its version from previous attempts exist"
               exit 1
             fi
 

.github/workflows/deploy-dev.yml

@@ -48,8 +48,7 @@ jobs:
         shell: bash
     strategy:
       matrix:
-        # TODO(sergey): Fix storage deploy in eu-central-1
-        target_region: [ eu-west-1, us-east-2]
+        target_region: [ eu-west-1, us-east-2 ]
     environment:
       name: dev-${{ matrix.target_region }}
     steps:
@@ -134,53 +133,6 @@ jobs:
   
       - name: Cleanup helm folder
         run: rm -rf ~/.cache
-
-  deploy-preview-proxy-new:
-    runs-on: [ self-hosted, gen3, small ]
-    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/ansible:pinned
-    if: inputs.deployProxy
-    defaults:
-      run:
-        shell: bash
-    strategy:
-      matrix:
-        include:
-          - target_region:  eu-central-1
-            target_cluster: dev-eu-central-1-alpha
-    environment:
-      name: dev-${{ matrix.target_region }}
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          submodules: true
-          fetch-depth: 0
-          ref: ${{ inputs.branch }}
-  
-      - name: Configure AWS Credentials
-        uses: aws-actions/configure-aws-credentials@v1-node16
-        with:
-          role-to-assume: arn:aws:iam::369495373322:role/github-runner
-          aws-region: eu-central-1
-          role-skip-session-tagging: true
-          role-duration-seconds: 1800
-  
-      - name: Configure environment
-        run: |
-          helm repo add neondatabase https://neondatabase.github.io/helm-charts
-          aws --region ${{ matrix.target_region }} eks update-kubeconfig --name  ${{ matrix.target_cluster }}
-  
-      - name: Re-deploy preview proxies
-        run: |
-          DOCKER_TAG=${{ inputs.dockerTag }}
-          for PREVIEW_NAME in helium argon krypton xenon radon oganesson hydrogen nitrogen oxygen fluorine chlorine; do
-            export PREVIEW_NAME
-            envsubst <.github/helm-values/preview-template.neon-proxy-scram.yaml >preview-${PREVIEW_NAME}.neon-proxy-scram.yaml
-            helm upgrade neon-proxy-scram-${PREVIEW_NAME} neondatabase/neon-proxy --namespace neon-proxy-${PREVIEW_NAME} --create-namespace --install --atomic -f preview-${PREVIEW_NAME}.neon-proxy-scram.yaml --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
-          done
-
-      - name: Cleanup helm folder
-        run: rm -rf ~/.cache
   
   deploy-storage-broker-new:
     runs-on: [ self-hosted, gen3, small ]
@@ -196,8 +148,6 @@ jobs:
             target_cluster: dev-us-east-2-beta
           - target_region:  eu-west-1
             target_cluster: dev-eu-west-1-zeta
-          - target_region:  eu-central-1
-            target_cluster: dev-eu-central-1-alpha
     environment:
       name: dev-${{ matrix.target_region }}
     steps:

.github/workflows/deploy-prod.yml

@@ -49,7 +49,7 @@ jobs:
         shell: bash
     strategy:
       matrix:
-        target_region: [ us-east-2, us-west-2, eu-central-1, ap-southeast-1, us-east-1 ]
+        target_region: [ us-east-2, us-west-2, eu-central-1, ap-southeast-1 ]
     environment:
       name: prod-${{ matrix.target_region }}
     steps:
@@ -97,10 +97,6 @@ jobs:
             target_cluster: prod-ap-southeast-1-epsilon
             deploy_link_proxy: false
             deploy_legacy_scram_proxy: false
-          - target_region: us-east-1
-            target_cluster: prod-us-east-1-theta
-            deploy_link_proxy: false
-            deploy_legacy_scram_proxy: false
     environment:
       name: prod-${{ matrix.target_region }}
     steps:
@@ -151,8 +147,6 @@ jobs:
             target_cluster: prod-eu-central-1-gamma
           - target_region: ap-southeast-1
             target_cluster: prod-ap-southeast-1-epsilon
-          - target_region: us-east-1
-            target_cluster: prod-us-east-1-theta
     environment:
       name: prod-${{ matrix.target_region }}
     steps:

.github/workflows/neon_extra_builds.yml

@@ -12,7 +12,7 @@ defaults:
 
 concurrency:
   # Allow only one workflow per any non-`main` branch.
-  group: ${{ github.workflow }}-${{ github.ref_name }}-${{ github.ref_name == 'main' && github.sha || 'anysha' }}
+  group: ${{ github.workflow }}-${{ github.ref }}-${{ github.ref == 'refs/heads/main' && github.sha || 'anysha' }}
   cancel-in-progress: true
 
 env:

.github/workflows/pg_clients.yml

@@ -14,7 +14,7 @@ on:
 
 concurrency:
   # Allow only one workflow per any non-`main` branch.
-  group: ${{ github.workflow }}-${{ github.ref_name }}-${{ github.ref_name == 'main' && github.sha || 'anysha' }}
+  group: ${{ github.workflow }}-${{ github.ref }}-${{ github.ref == 'refs/heads/main' && github.sha || 'anysha' }}
   cancel-in-progress: true
 
 jobs:

Cargo.toml

@@ -24,10 +24,10 @@ atty = "0.2.14"
 aws-config = { version = "0.51.0", default-features = false, features=["rustls"] }
 aws-sdk-s3 = "0.21.0"
 aws-smithy-http = "0.51.0"
-aws-types = "0.55"
+aws-types = "0.51.0"
 base64 = "0.13.0"
 bincode = "1.3"
-bindgen = "0.65"
+bindgen = "0.61"
 bstr = "1.0"
 byteorder = "1.4"
 bytes = "1.0"
@@ -50,7 +50,7 @@ git-version = "0.3"
 hashbrown = "0.13"
 hashlink = "0.8.1"
 hex = "0.4"
-hex-literal = "0.4"
+hex-literal = "0.3"
 hmac = "0.12.1"
 hostname = "0.3.1"
 humantime = "2.1"
@@ -80,18 +80,18 @@ reqwest = { version = "0.11", default-features = false, features = ["rustls-tls"
 reqwest-tracing = { version = "0.4.0", features = ["opentelemetry_0_18"] }
 reqwest-middleware = "0.2.0"
 routerify = "3"
-rpds = "0.13"
+rpds = "0.12.0"
 rustls = "0.20"
 rustls-pemfile = "1"
 rustls-split = "0.3"
 scopeguard = "1.1"
-sentry = { version = "0.30", default-features = false, features = ["backtrace", "contexts", "panic", "rustls", "reqwest" ] }
+sentry = { version = "0.29", default-features = false, features = ["backtrace", "contexts", "panic", "rustls", "reqwest" ] }
 serde = { version = "1.0", features = ["derive"] }
 serde_json = "1"
 serde_with = "2.0"
 sha2 = "0.10.2"
 signal-hook = "0.3"
-socket2 = "0.5"
+socket2 = "0.4.4"
 strum = "0.24"
 strum_macros = "0.24"
 svg_fmt = "0.4.1"
@@ -106,17 +106,17 @@ tokio-postgres-rustls = "0.9.0"
 tokio-rustls = "0.23"
 tokio-stream = "0.1"
 tokio-util = { version = "0.7", features = ["io"] }
-toml = "0.7"
-toml_edit = "0.19"
-tonic = {version = "0.9", features = ["tls", "tls-roots"]}
+toml = "0.5"
+toml_edit = { version = "0.17", features = ["easy"] }
+tonic = {version = "0.8", features = ["tls", "tls-roots"]}
 tracing = "0.1"
 tracing-opentelemetry = "0.18.0"
 tracing-subscriber = { version = "0.3", features = ["env-filter"] }
 url = "2.2"
 uuid = { version = "1.2", features = ["v4", "serde"] }
 walkdir = "2.3.2"
-webpki-roots = "0.23"
-x509-parser = "0.15"
+webpki-roots = "0.22.5"
+x509-parser = "0.14"
 
 ## TODO replace this with tracing
 env_logger = "0.10"
@@ -154,9 +154,9 @@ workspace_hack = { version = "0.1", path = "./workspace_hack/" }
 ## Build dependencies
 criterion = "0.4"
 rcgen = "0.10"
-rstest = "0.17"
+rstest = "0.16"
 tempfile = "3.4"
-tonic-build = "0.9"
+tonic-build = "0.8"
 
 # This is only needed for proxy's tests.
 # TODO: we should probably fork `tokio-postgres-rustls` instead.

Dockerfile.compute-node

@@ -12,7 +12,7 @@ FROM debian:bullseye-slim AS build-deps
 RUN apt update &&  \
     apt install -y git autoconf automake libtool build-essential bison flex libreadline-dev \
     zlib1g-dev libxml2-dev libcurl4-openssl-dev libossp-uuid-dev wget pkg-config libssl-dev \
-    libicu-dev libxslt1-dev liblz4-dev libzstd-dev
+    libicu-dev libxslt1-dev
 
 #########################################################################################
 #
@@ -24,13 +24,8 @@ FROM build-deps AS pg-build
 ARG PG_VERSION
 COPY vendor/postgres-${PG_VERSION} postgres
 RUN cd postgres && \
-    export CONFIGURE_CMD="./configure CFLAGS='-O2 -g3' --enable-debug --with-openssl --with-uuid=ossp \
-    --with-icu --with-libxml --with-libxslt --with-lz4" && \
-    if [ "${PG_VERSION}" != "v14" ]; then \
-        # zstd is available only from PG15
-        export CONFIGURE_CMD="${CONFIGURE_CMD} --with-zstd"; \
-    fi && \
-    eval $CONFIGURE_CMD && \
+    ./configure CFLAGS='-O2 -g3' --enable-debug --with-openssl --with-uuid=ossp --with-icu \
+    --with-libxml --with-libxslt && \
     make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s install && \
     make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s -C contrib/ install && \
     # Install headers
@@ -65,7 +60,6 @@ RUN apt update && \
 
 # SFCGAL > 1.3 requires CGAL > 5.2, Bullseye's libcgal-dev is 5.2
 RUN wget https://gitlab.com/Oslandia/SFCGAL/-/archive/v1.3.10/SFCGAL-v1.3.10.tar.gz -O SFCGAL.tar.gz && \
-    echo "4e39b3b2adada6254a7bdba6d297bb28e1a9835a9f879b74f37e2dab70203232 SFCGAL.tar.gz" | sha256sum --check && \
     mkdir sfcgal-src && cd sfcgal-src && tar xvzf ../SFCGAL.tar.gz --strip-components=1 -C . && \
     cmake . && make -j $(getconf _NPROCESSORS_ONLN) && \
     DESTDIR=/sfcgal make install -j $(getconf _NPROCESSORS_ONLN) && \
@@ -74,7 +68,6 @@ RUN wget https://gitlab.com/Oslandia/SFCGAL/-/archive/v1.3.10/SFCGAL-v1.3.10.tar
 ENV PATH "/usr/local/pgsql/bin:$PATH"
 
 RUN wget https://download.osgeo.org/postgis/source/postgis-3.3.2.tar.gz -O postgis.tar.gz && \
-    echo "9a2a219da005a1730a39d1959a1c7cec619b1efb009b65be80ffc25bad299068 postgis.tar.gz" | sha256sum --check && \
     mkdir postgis-src && cd postgis-src && tar xvzf ../postgis.tar.gz --strip-components=1 -C . && \
     ./autogen.sh && \
     ./configure --with-sfcgal=/usr/local/bin/sfcgal-config && \
@@ -91,7 +84,6 @@ RUN wget https://download.osgeo.org/postgis/source/postgis-3.3.2.tar.gz -O postg
     echo 'trusted = true' >> /usr/local/pgsql/share/extension/address_standardizer_data_us.control
 
 RUN wget https://github.com/pgRouting/pgrouting/archive/v3.4.2.tar.gz -O pgrouting.tar.gz && \
-    echo "cac297c07d34460887c4f3b522b35c470138760fe358e351ad1db4edb6ee306e pgrouting.tar.gz" | sha256sum --check && \
     mkdir pgrouting-src && cd pgrouting-src && tar xvzf ../pgrouting.tar.gz --strip-components=1 -C . && \
     mkdir build && \
     cd build && \
@@ -112,7 +104,6 @@ RUN apt update && \
     apt install -y ninja-build python3-dev libncurses5 binutils clang
 
 RUN wget https://github.com/plv8/plv8/archive/refs/tags/v3.1.5.tar.gz -O plv8.tar.gz && \
-    echo "1e108d5df639e4c189e1c5bdfa2432a521c126ca89e7e5a969d46899ca7bf106 plv8.tar.gz" | sha256sum --check && \
     mkdir plv8-src && cd plv8-src && tar xvzf ../plv8.tar.gz --strip-components=1 -C . && \
     export PATH="/usr/local/pgsql/bin:$PATH" && \
     make DOCKER=1 -j $(getconf _NPROCESSORS_ONLN) install && \
@@ -134,13 +125,11 @@ COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
 # packaged cmake is too old
 RUN wget https://github.com/Kitware/CMake/releases/download/v3.24.2/cmake-3.24.2-linux-x86_64.sh \
       -q -O /tmp/cmake-install.sh \
-      && echo "739d372726cb23129d57a539ce1432453448816e345e1545f6127296926b6754 /tmp/cmake-install.sh" | sha256sum --check \
       && chmod u+x /tmp/cmake-install.sh \
       && /tmp/cmake-install.sh --skip-license --prefix=/usr/local/ \
       && rm /tmp/cmake-install.sh
 
 RUN wget https://github.com/uber/h3/archive/refs/tags/v4.1.0.tar.gz -O h3.tar.gz && \
-    echo "ec99f1f5974846bde64f4513cf8d2ea1b8d172d2218ab41803bf6a63532272bc h3.tar.gz" | sha256sum --check && \
     mkdir h3-src && cd h3-src && tar xvzf ../h3.tar.gz --strip-components=1 -C . && \
     mkdir build && cd build && \
     cmake .. -DCMAKE_BUILD_TYPE=Release && \
@@ -150,7 +139,6 @@ RUN wget https://github.com/uber/h3/archive/refs/tags/v4.1.0.tar.gz -O h3.tar.gz
     rm -rf build
 
 RUN wget https://github.com/zachasme/h3-pg/archive/refs/tags/v4.1.2.tar.gz -O h3-pg.tar.gz && \
-    echo "c135aa45999b2ad1326d2537c1cadef96d52660838e4ca371706c08fdea1a956 h3-pg.tar.gz" | sha256sum --check && \
     mkdir h3-pg-src && cd h3-pg-src && tar xvzf ../h3-pg.tar.gz --strip-components=1 -C . && \
     export PATH="/usr/local/pgsql/bin:$PATH" && \
     make -j $(getconf _NPROCESSORS_ONLN) && \
@@ -168,7 +156,6 @@ FROM build-deps AS unit-pg-build
 COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
 
 RUN wget https://github.com/df7cb/postgresql-unit/archive/refs/tags/7.7.tar.gz -O postgresql-unit.tar.gz && \
-    echo "411d05beeb97e5a4abf17572bfcfbb5a68d98d1018918feff995f6ee3bb03e79 postgresql-unit.tar.gz" | sha256sum --check && \
     mkdir postgresql-unit-src && cd postgresql-unit-src && tar xvzf ../postgresql-unit.tar.gz --strip-components=1 -C . && \
     make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
     make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
@@ -189,7 +176,6 @@ FROM build-deps AS vector-pg-build
 COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
 
 RUN wget https://github.com/pgvector/pgvector/archive/refs/tags/v0.4.0.tar.gz -O pgvector.tar.gz && \
-    echo "b76cf84ddad452cc880a6c8c661d137ddd8679c000a16332f4f03ecf6e10bcc8 pgvector.tar.gz" | sha256sum --check && \
     mkdir pgvector-src && cd pgvector-src && tar xvzf ../pgvector.tar.gz --strip-components=1 -C . && \
     make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
     make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
@@ -206,7 +192,6 @@ COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
 
 # 9742dab1b2f297ad3811120db7b21451bca2d3c9 made on 13/11/2021
 RUN wget https://github.com/michelp/pgjwt/archive/9742dab1b2f297ad3811120db7b21451bca2d3c9.tar.gz -O pgjwt.tar.gz && \
-    echo "cfdefb15007286f67d3d45510f04a6a7a495004be5b3aecb12cda667e774203f pgjwt.tar.gz" | sha256sum --check && \
     mkdir pgjwt-src && cd pgjwt-src && tar xvzf ../pgjwt.tar.gz --strip-components=1 -C . && \
     make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
     echo 'trusted = true' >> /usr/local/pgsql/share/extension/pgjwt.control
@@ -221,7 +206,6 @@ FROM build-deps AS hypopg-pg-build
 COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
 
 RUN wget https://github.com/HypoPG/hypopg/archive/refs/tags/1.3.1.tar.gz -O hypopg.tar.gz && \
-    echo "e7f01ee0259dc1713f318a108f987663d60f3041948c2ada57a94b469565ca8e hypopg.tar.gz" | sha256sum --check && \
     mkdir hypopg-src && cd hypopg-src && tar xvzf ../hypopg.tar.gz --strip-components=1 -C . && \
     make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
     make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
@@ -237,7 +221,6 @@ FROM build-deps AS pg-hashids-pg-build
 COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
 
 RUN wget https://github.com/iCyberon/pg_hashids/archive/refs/tags/v1.2.1.tar.gz -O pg_hashids.tar.gz && \
-    echo "74576b992d9277c92196dd8d816baa2cc2d8046fe102f3dcd7f3c3febed6822a pg_hashids.tar.gz" | sha256sum --check && \
     mkdir pg_hashids-src && cd pg_hashids-src && tar xvzf ../pg_hashids.tar.gz --strip-components=1 -C . && \
     make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config USE_PGXS=1 && \
     make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config USE_PGXS=1 && \
@@ -253,7 +236,6 @@ FROM build-deps AS rum-pg-build
 COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
 
 RUN wget https://github.com/postgrespro/rum/archive/refs/tags/1.3.13.tar.gz -O rum.tar.gz && \
-    echo "6ab370532c965568df6210bd844ac6ba649f53055e48243525b0b7e5c4d69a7d rum.tar.gz" | sha256sum --check && \
     mkdir rum-src && cd rum-src && tar xvzf ../rum.tar.gz --strip-components=1 -C . && \
     make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config USE_PGXS=1 && \
     make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config USE_PGXS=1 && \
@@ -269,28 +251,11 @@ FROM build-deps AS pgtap-pg-build
 COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
 
 RUN wget https://github.com/theory/pgtap/archive/refs/tags/v1.2.0.tar.gz -O pgtap.tar.gz && \
-    echo "9c7c3de67ea41638e14f06da5da57bac6f5bd03fea05c165a0ec862205a5c052 pgtap.tar.gz" | sha256sum --check && \
     mkdir pgtap-src && cd pgtap-src && tar xvzf ../pgtap.tar.gz --strip-components=1 -C . && \
     make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
     make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
     echo 'trusted = true' >> /usr/local/pgsql/share/extension/pgtap.control
 
-#########################################################################################
-#
-# Layer "ip4r-pg-build"
-# compile ip4r extension
-#
-#########################################################################################
-FROM build-deps AS ip4r-pg-build
-COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
-
-RUN wget https://github.com/RhodiumToad/ip4r/archive/refs/tags/2.4.1.tar.gz -O ip4r.tar.gz && \
-    echo "78b9f0c1ae45c22182768fe892a32d533c82281035e10914111400bf6301c726 ip4r.tar.gz" | sha256sum --check && \
-    mkdir ip4r-src && cd ip4r-src && tar xvzf ../ip4r.tar.gz --strip-components=1 -C . && \
-    make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
-    make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/ip4r.control
-
 #########################################################################################
 #
 # Layer "prefix-pg-build"
@@ -301,7 +266,6 @@ FROM build-deps AS prefix-pg-build
 COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
 
 RUN wget https://github.com/dimitri/prefix/archive/refs/tags/v1.2.9.tar.gz -O prefix.tar.gz && \
-    echo "38d30a08d0241a8bbb8e1eb8f0152b385051665a8e621c8899e7c5068f8b511e prefix.tar.gz" | sha256sum --check && \
     mkdir prefix-src && cd prefix-src && tar xvzf ../prefix.tar.gz --strip-components=1 -C . && \
     make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
     make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
@@ -317,7 +281,6 @@ FROM build-deps AS hll-pg-build
 COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
 
 RUN wget https://github.com/citusdata/postgresql-hll/archive/refs/tags/v2.17.tar.gz -O hll.tar.gz && \
-    echo "9a18288e884f197196b0d29b9f178ba595b0dfc21fbf7a8699380e77fa04c1e9 hll.tar.gz" | sha256sum --check && \
     mkdir hll-src && cd hll-src && tar xvzf ../hll.tar.gz --strip-components=1 -C . && \
     make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
     make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
@@ -333,7 +296,6 @@ FROM build-deps AS plpgsql-check-pg-build
 COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
 
 RUN wget https://github.com/okbob/plpgsql_check/archive/refs/tags/v2.3.2.tar.gz -O plpgsql_check.tar.gz && \
-    echo "9d81167c4bbeb74eebf7d60147b21961506161addc2aee537f95ad8efeae427b plpgsql_check.tar.gz" | sha256sum --check && \
     mkdir plpgsql_check-src && cd plpgsql_check-src && tar xvzf ../plpgsql_check.tar.gz --strip-components=1 -C . && \
     make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config USE_PGXS=1 && \
     make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config USE_PGXS=1 && \
@@ -353,7 +315,6 @@ ENV PATH "/usr/local/pgsql/bin:$PATH"
 RUN apt-get update && \
     apt-get install -y cmake && \
     wget https://github.com/timescale/timescaledb/archive/refs/tags/2.10.1.tar.gz -O timescaledb.tar.gz && \
-    echo "6fca72a6ed0f6d32d2b3523951ede73dc5f9b0077b38450a029a5f411fdb8c73 timescaledb.tar.gz" | sha256sum --check && \
     mkdir timescaledb-src && cd timescaledb-src && tar xvzf ../timescaledb.tar.gz --strip-components=1 -C . && \
     ./bootstrap -DSEND_TELEMETRY_DEFAULT:BOOL=OFF -DUSE_TELEMETRY:BOOL=OFF -DAPACHE_ONLY:BOOL=ON && \
     cd build && \
@@ -362,39 +323,7 @@ RUN apt-get update && \
     echo "trusted = true" >> /usr/local/pgsql/share/extension/timescaledb.control
 
 #########################################################################################
-#
-# Layer "pg-hint-plan-pg-build"
-# compile pg_hint_plan extension
-#
-#########################################################################################
-FROM build-deps AS pg-hint-plan-pg-build
-COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
-
-ARG PG_VERSION
-ENV PATH "/usr/local/pgsql/bin:$PATH"
-
-RUN case "${PG_VERSION}" in \
-      "v14") \
-        export PG_HINT_PLAN_VERSION=14_1_4_1 \
-        export PG_HINT_PLAN_CHECKSUM=c3501becf70ead27f70626bce80ea401ceac6a77e2083ee5f3ff1f1444ec1ad1 \
-        ;; \
-      "v15") \
-        export PG_HINT_PLAN_VERSION=15_1_5_0 \
-        export PG_HINT_PLAN_CHECKSUM=564cbbf4820973ffece63fbf76e3c0af62c4ab23543142c7caaa682bc48918be \
-        ;; \
-      *) \
-        echo "Export the valid PG_HINT_PLAN_VERSION variable" && exit 1 \
-        ;; \
-    esac && \
-    wget https://github.com/ossc-db/pg_hint_plan/archive/refs/tags/REL${PG_HINT_PLAN_VERSION}.tar.gz -O pg_hint_plan.tar.gz && \
-    echo "${PG_HINT_PLAN_CHECKSUM} pg_hint_plan.tar.gz" | sha256sum --check && \
-    mkdir pg_hint_plan-src && cd pg_hint_plan-src && tar xvzf ../pg_hint_plan.tar.gz --strip-components=1 -C . && \
-    make -j $(getconf _NPROCESSORS_ONLN) && \
-    make install -j $(getconf _NPROCESSORS_ONLN) && \
-    echo "trusted = true" >> /usr/local/pgsql/share/extension/pg_hint_plan.control
-
-#########################################################################################
-#
+# 
 # Layer "rust extensions"
 # This layer is used to build `pgx` deps
 #
@@ -422,7 +351,7 @@ RUN curl -sSO https://static.rust-lang.org/rustup/dist/$(uname -m)-unknown-linux
 USER root
 
 #########################################################################################
-#
+# 
 # Layer "pg-jsonschema-pg-build"
 # Compile "pg_jsonschema" extension
 #
@@ -430,17 +359,15 @@ USER root
 
 FROM rust-extensions-build AS pg-jsonschema-pg-build
 
-# caeab60d70b2fd3ae421ec66466a3abbb37b7ee6 made on 06/03/2023
-# there is no release tag yet, but we need it due to the superuser fix in the control file, switch to git tag after release >= 0.1.5
+# there is no release tag yet, but we need it due to the superuser fix in the control file
 RUN wget https://github.com/supabase/pg_jsonschema/archive/caeab60d70b2fd3ae421ec66466a3abbb37b7ee6.tar.gz -O pg_jsonschema.tar.gz && \
-    echo "54129ce2e7ee7a585648dbb4cef6d73f795d94fe72f248ac01119992518469a4 pg_jsonschema.tar.gz" | sha256sum --check && \
     mkdir pg_jsonschema-src && cd pg_jsonschema-src && tar xvzf ../pg_jsonschema.tar.gz --strip-components=1 -C . && \
     sed -i 's/pgx = "0.7.1"/pgx = { version = "0.7.3", features = [ "unsafe-postgres" ] }/g' Cargo.toml && \
     cargo pgx install --release && \
     echo "trusted = true" >> /usr/local/pgsql/share/extension/pg_jsonschema.control
 
 #########################################################################################
-#
+# 
 # Layer "pg-graphql-pg-build"
 # Compile "pg_graphql" extension
 #
@@ -448,13 +375,11 @@ RUN wget https://github.com/supabase/pg_jsonschema/archive/caeab60d70b2fd3ae421e
 
 FROM rust-extensions-build AS pg-graphql-pg-build
 
-# b4988843647450a153439be367168ed09971af85 made on 22/02/2023 (from remove-pgx-contrib-spiext branch)
 # Currently pgx version bump to >= 0.7.2  causes "call to unsafe function" compliation errors in
 # pgx-contrib-spiext. There is a branch that removes that dependency, so use it. It is on the
 # same 1.1 version we've used before.
-RUN wget https://github.com/yrashk/pg_graphql/archive/b4988843647450a153439be367168ed09971af85.tar.gz -O pg_graphql.tar.gz && \
-    echo "0c7b0e746441b2ec24187d0e03555faf935c2159e2839bddd14df6dafbc8c9bd pg_graphql.tar.gz" | sha256sum --check && \
-    mkdir pg_graphql-src && cd pg_graphql-src && tar xvzf ../pg_graphql.tar.gz --strip-components=1 -C . && \
+RUN git clone -b remove-pgx-contrib-spiext --single-branch https://github.com/yrashk/pg_graphql && \
+    cd pg_graphql && \
     sed -i 's/pgx = "~0.7.1"/pgx = { version = "0.7.3", features = [ "unsafe-postgres" ] }/g' Cargo.toml && \
     sed -i 's/pgx-tests = "~0.7.1"/pgx-tests = "0.7.3"/g' Cargo.toml && \
     cargo pgx install --release && \
@@ -471,10 +396,8 @@ RUN wget https://github.com/yrashk/pg_graphql/archive/b4988843647450a153439be367
 
 FROM rust-extensions-build AS pg-tiktoken-pg-build
 
-# 801f84f08c6881c8aa30f405fafbf00eec386a72 made on 10/03/2023
-RUN wget https://github.com/kelvich/pg_tiktoken/archive/801f84f08c6881c8aa30f405fafbf00eec386a72.tar.gz -O pg_tiktoken.tar.gz && \
-    echo "52f60ac800993a49aa8c609961842b611b6b1949717b69ce2ec9117117e16e4a pg_tiktoken.tar.gz" | sha256sum --check && \
-    mkdir pg_tiktoken-src && cd pg_tiktoken-src && tar xvzf ../pg_tiktoken.tar.gz --strip-components=1 -C . && \
+RUN git clone --depth=1 --single-branch https://github.com/kelvich/pg_tiktoken && \
+    cd pg_tiktoken && \
     cargo pgx install --release && \
     echo "trusted = true" >> /usr/local/pgsql/share/extension/pg_tiktoken.control
 
@@ -500,12 +423,10 @@ COPY --from=hypopg-pg-build /usr/local/pgsql/ /usr/local/pgsql/
 COPY --from=pg-hashids-pg-build /usr/local/pgsql/ /usr/local/pgsql/
 COPY --from=rum-pg-build /usr/local/pgsql/ /usr/local/pgsql/
 COPY --from=pgtap-pg-build /usr/local/pgsql/ /usr/local/pgsql/
-COPY --from=ip4r-pg-build /usr/local/pgsql/ /usr/local/pgsql/
 COPY --from=prefix-pg-build /usr/local/pgsql/ /usr/local/pgsql/
 COPY --from=hll-pg-build /usr/local/pgsql/ /usr/local/pgsql/
 COPY --from=plpgsql-check-pg-build /usr/local/pgsql/ /usr/local/pgsql/
 COPY --from=timescaledb-pg-build /usr/local/pgsql/ /usr/local/pgsql/
-COPY --from=pg-hint-plan-pg-build /usr/local/pgsql/ /usr/local/pgsql/
 COPY pgxn/ pgxn/
 
 RUN make -j $(getconf _NPROCESSORS_ONLN) \
@@ -570,17 +491,13 @@ COPY --from=compute-tools --chown=postgres /home/nonroot/target/release-line-deb
 # Install:
 # libreadline8 for psql
 # libicu67, locales for collations (including ICU and plpgsql_check)
-# liblz4-1 for lz4
 # libossp-uuid16 for extension ossp-uuid
 # libgeos, libgdal, libsfcgal1, libproj and libprotobuf-c1 for PostGIS
 # libxml2, libxslt1.1 for xml2
-# libzstd1 for zstd
 RUN apt update &&  \
     apt install --no-install-recommends -y \
-        gdb \
         locales \
         libicu67 \
-        liblz4-1 \
         libreadline8 \
         libossp-uuid16 \
         libgeos-c1v5 \
@@ -590,8 +507,7 @@ RUN apt update &&  \
         libsfcgal1 \
         libxml2 \
         libxslt1.1 \
-        libzstd1 \
-        procps && \
+        gdb && \
     rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* && \
     localedef -i en_US -c -f UTF-8 -A /usr/share/locale/locale.alias en_US.UTF-8
 

Dockerfile.vm-compute-node

@@ -54,7 +54,7 @@ RUN set -e \
 
 RUN set -e \
 	&& echo "::sysinit:cgconfigparser -l /etc/cgconfig.conf -s 1664" >> /etc/inittab \
-	&& CONNSTR="dbname=postgres user=cloud_admin sslmode=disable" \
+	&& CONNSTR="dbname=neondb user=cloud_admin sslmode=disable" \
 	&& ARGS="--auto-restart --cgroup=neon-postgres --pgconnstr=\"$CONNSTR\"" \
 	&& echo "::respawn:su vm-informant -c '/usr/local/bin/vm-informant $ARGS'" >> /etc/inittab
 

README.md

@@ -147,15 +147,15 @@ Created an initial timeline 'de200bd42b49cc1814412c7e592dd6e9' at Lsn 0/16B5A50
 Setting tenant 9ef87a5bf0d92544f6fafeeb3239695c as a default one
 
 # start postgres compute node
-> ./target/debug/neon_local endpoint start main
-Starting new endpoint main (PostgreSQL v14) on timeline de200bd42b49cc1814412c7e592dd6e9 ...
+> ./target/debug/neon_local pg start main
+Starting new postgres (v14) main on timeline de200bd42b49cc1814412c7e592dd6e9 ...
 Extracting base backup to create postgres instance: path=.neon/pgdatadirs/tenants/9ef87a5bf0d92544f6fafeeb3239695c/main port=55432
-Starting postgres at 'host=127.0.0.1 port=55432 user=cloud_admin dbname=postgres'
+Starting postgres node at 'host=127.0.0.1 port=55432 user=cloud_admin dbname=postgres'
 
 # check list of running postgres instances
-> ./target/debug/neon_local endpoint list
- ENDPOINT  ADDRESS          TIMELINE                          BRANCH NAME  LSN        STATUS
- main      127.0.0.1:55432  de200bd42b49cc1814412c7e592dd6e9  main         0/16B5BA8  running
+> ./target/debug/neon_local pg list
+ NODE  ADDRESS          TIMELINE                          BRANCH NAME  LSN        STATUS
+ main  127.0.0.1:55432  de200bd42b49cc1814412c7e592dd6e9  main         0/16B5BA8  running
 ```
 
 2. Now, it is possible to connect to postgres and run some queries:
@@ -184,14 +184,14 @@ Created timeline 'b3b863fa45fa9e57e615f9f2d944e601' at Lsn 0/16F9A00 for tenant:
 (L) ┗━ @0/16F9A00: migration_check [b3b863fa45fa9e57e615f9f2d944e601]
 
 # start postgres on that branch
-> ./target/debug/neon_local endpoint start migration_check --branch-name migration_check
-Starting new endpoint migration_check (PostgreSQL v14) on timeline b3b863fa45fa9e57e615f9f2d944e601 ...
+> ./target/debug/neon_local pg start migration_check --branch-name migration_check
+Starting new postgres migration_check on timeline b3b863fa45fa9e57e615f9f2d944e601 ...
 Extracting base backup to create postgres instance: path=.neon/pgdatadirs/tenants/9ef87a5bf0d92544f6fafeeb3239695c/migration_check port=55433
-Starting postgres at 'host=127.0.0.1 port=55433 user=cloud_admin dbname=postgres'
+Starting postgres node at 'host=127.0.0.1 port=55433 user=cloud_admin dbname=postgres'
 
 # check the new list of running postgres instances
-> ./target/debug/neon_local endpoint list
- ENDPOINT         ADDRESS          TIMELINE                          BRANCH NAME      LSN        STATUS
+> ./target/debug/neon_local pg list
+ NODE             ADDRESS          TIMELINE                          BRANCH NAME      LSN        STATUS
  main             127.0.0.1:55432  de200bd42b49cc1814412c7e592dd6e9  main             0/16F9A38  running
  migration_check  127.0.0.1:55433  b3b863fa45fa9e57e615f9f2d944e601  migration_check  0/16F9A70  running
 

compute_tools/src/bin/compute_ctl.rs

@@ -46,7 +46,6 @@ use url::Url;
 use compute_api::responses::ComputeStatus;
 
 use compute_tools::compute::{ComputeNode, ComputeState, ParsedSpec};
-use compute_tools::configurator::launch_configurator;
 use compute_tools::http::api::launch_http_server;
 use compute_tools::logger::*;
 use compute_tools::monitor::launch_monitor;
@@ -73,7 +72,7 @@ fn main() -> Result<()> {
     // Try to use just 'postgres' if no path is provided
     let pgbin = matches.get_one::<String>("pgbin").unwrap();
 
-    let spec;
+    let mut spec = None;
     let mut live_config_allowed = false;
     match spec_json {
         // First, try to get cluster spec from the cli argument
@@ -89,13 +88,9 @@ fn main() -> Result<()> {
             } else if let Some(id) = compute_id {
                 if let Some(cp_base) = control_plane_uri {
                     live_config_allowed = true;
-                    spec = match get_spec_from_control_plane(cp_base, id) {
-                        Ok(s) => s,
-                        Err(e) => {
-                            error!("cannot get response from control plane: {}", e);
-                            panic!("neither spec nor confirmation that compute is in the Empty state was received");
-                        }
-                    };
+                    if let Ok(s) = get_spec_from_control_plane(cp_base, id) {
+                        spec = Some(s);
+                    }
                 } else {
                     panic!("must specify both --control-plane-uri and --compute-id or none");
                 }
@@ -118,6 +113,7 @@ fn main() -> Result<()> {
         spec_set = false;
     }
     let compute_node = ComputeNode {
+        start_time: Utc::now(),
         connstr: Url::parse(connstr).context("cannot parse connstr as a URL")?,
         pgdata: pgdata.to_string(),
         pgbin: pgbin.to_string(),
@@ -150,17 +146,6 @@ fn main() -> Result<()> {
     let mut state = compute.state.lock().unwrap();
     let pspec = state.pspec.as_ref().expect("spec must be set");
     let startup_tracing_context = pspec.spec.startup_tracing_context.clone();
-
-    // Record for how long we slept waiting for the spec.
-    state.metrics.wait_for_spec_ms = Utc::now()
-        .signed_duration_since(state.start_time)
-        .to_std()
-        .unwrap()
-        .as_millis() as u64;
-    // Reset start time to the actual start of the configuration, so that
-    // total startup time was properly measured at the end.
-    state.start_time = Utc::now();
-
     state.status = ComputeStatus::Init;
     compute.state_changed.notify_all();
     drop(state);
@@ -190,8 +175,6 @@ fn main() -> Result<()> {
 
     // Launch remaining service threads
     let _monitor_handle = launch_monitor(&compute).expect("cannot launch compute monitor thread");
-    let _configurator_handle =
-        launch_configurator(&compute).expect("cannot launch configurator thread");
 
     // Start Postgres
     let mut delay_exit = false;

compute_tools/src/checker.rs

@@ -1,28 +1,12 @@
 use anyhow::{anyhow, Result};
+use postgres::Client;
 use tokio_postgres::NoTls;
 use tracing::{error, instrument};
 
 use crate::compute::ComputeNode;
 
-/// Update timestamp in a row in a special service table to check
-/// that we can actually write some data in this particular timeline.
-/// Create table if it's missing.
 #[instrument(skip_all)]
-pub async fn check_writability(compute: &ComputeNode) -> Result<()> {
-    // Connect to the database.
-    let (client, connection) = tokio_postgres::connect(compute.connstr.as_str(), NoTls).await?;
-    if client.is_closed() {
-        return Err(anyhow!("connection to postgres closed"));
-    }
-
-    // The connection object performs the actual communication with the database,
-    // so spawn it off to run on its own.
-    tokio::spawn(async move {
-        if let Err(e) = connection.await {
-            error!("connection error: {}", e);
-        }
-    });
-
+pub fn create_writability_check_data(client: &mut Client) -> Result<()> {
     let query = "
     CREATE TABLE IF NOT EXISTS health_check (
         id serial primary key,
@@ -31,15 +15,31 @@ pub async fn check_writability(compute: &ComputeNode) -> Result<()> {
     INSERT INTO health_check VALUES (1, now())
         ON CONFLICT (id) DO UPDATE
          SET updated_at = now();";
-
-    let result = client.simple_query(query).await?;
-
-    if result.len() != 2 {
-        return Err(anyhow::format_err!(
-            "expected 2 query results, but got {}",
-            result.len()
-        ));
+    let result = client.simple_query(query)?;
+    if result.len() < 2 {
+        return Err(anyhow::format_err!("executed  {} queries", result.len()));
+    }
+    Ok(())
+}
+
+#[instrument(skip_all)]
+pub async fn check_writability(compute: &ComputeNode) -> Result<()> {
+    let (client, connection) = tokio_postgres::connect(compute.connstr.as_str(), NoTls).await?;
+    if client.is_closed() {
+        return Err(anyhow!("connection to postgres closed"));
+    }
+    tokio::spawn(async move {
+        if let Err(e) = connection.await {
+            error!("connection error: {}", e);
+        }
+    });
+
+    let result = client
+        .simple_query("UPDATE health_check SET updated_at = now() WHERE id = 1;")
+        .await?;
+
+    if result.len() != 1 {
+        return Err(anyhow!("statement can't be executed"));
     }
-
     Ok(())
 }

compute_tools/src/compute.rs

@@ -32,12 +32,14 @@ use utils::lsn::Lsn;
 use compute_api::responses::{ComputeMetrics, ComputeStatus};
 use compute_api::spec::ComputeSpec;
 
+use crate::checker::create_writability_check_data;
 use crate::config;
 use crate::pg_helpers::*;
 use crate::spec::*;
 
 /// Compute node info shared across several `compute_ctl` threads.
 pub struct ComputeNode {
+    pub start_time: DateTime<Utc>,
     // Url type maintains proper escaping
     pub connstr: url::Url,
     pub pgdata: String,
@@ -65,7 +67,6 @@ pub struct ComputeNode {
 
 #[derive(Clone, Debug)]
 pub struct ComputeState {
-    pub start_time: DateTime<Utc>,
     pub status: ComputeStatus,
     /// Timestamp of the last Postgres activity
     pub last_active: DateTime<Utc>,
@@ -77,7 +78,6 @@ pub struct ComputeState {
 impl ComputeState {
     pub fn new() -> Self {
         Self {
-            start_time: Utc::now(),
             status: ComputeStatus::Empty,
             last_active: Utc::now(),
             error: None,
@@ -342,6 +342,7 @@ impl ComputeNode {
         handle_databases(spec, &mut client)?;
         handle_role_deletions(spec, self.connstr.as_str(), &mut client)?;
         handle_grants(spec, self.connstr.as_str(), &mut client)?;
+        create_writability_check_data(&mut client)?;
         handle_extensions(spec, &mut client)?;
 
         // 'Close' connection
@@ -355,48 +356,6 @@ impl ComputeNode {
         Ok(())
     }
 
-    // We could've wrapped this around `pg_ctl reload`, but right now we don't use
-    // `pg_ctl` for start / stop, so this just seems much easier to do as we already
-    // have opened connection to Postgres and superuser access.
-    #[instrument(skip(self, client))]
-    fn pg_reload_conf(&self, client: &mut Client) -> Result<()> {
-        client.simple_query("SELECT pg_reload_conf()")?;
-        Ok(())
-    }
-
-    /// Similar to `apply_config()`, but does a bit different sequence of operations,
-    /// as it's used to reconfigure a previously started and configured Postgres node.
-    #[instrument(skip(self))]
-    pub fn reconfigure(&self) -> Result<()> {
-        let spec = self.state.lock().unwrap().pspec.clone().unwrap().spec;
-
-        // Write new config
-        let pgdata_path = Path::new(&self.pgdata);
-        config::write_postgres_conf(&pgdata_path.join("postgresql.conf"), &spec)?;
-
-        let mut client = Client::connect(self.connstr.as_str(), NoTls)?;
-        self.pg_reload_conf(&mut client)?;
-
-        // Proceed with post-startup configuration. Note, that order of operations is important.
-        handle_roles(&spec, &mut client)?;
-        handle_databases(&spec, &mut client)?;
-        handle_role_deletions(&spec, self.connstr.as_str(), &mut client)?;
-        handle_grants(&spec, self.connstr.as_str(), &mut client)?;
-        handle_extensions(&spec, &mut client)?;
-
-        // 'Close' connection
-        drop(client);
-
-        let unknown_op = "unknown".to_string();
-        let op_id = spec.operation_uuid.as_ref().unwrap_or(&unknown_op);
-        info!(
-            "finished reconfiguration of compute node for operation {}",
-            op_id
-        );
-
-        Ok(())
-    }
-
     #[instrument(skip(self))]
     pub fn start_compute(&self) -> Result<std::process::Child> {
         let compute_state = self.state.lock().unwrap().clone();
@@ -426,7 +385,7 @@ impl ComputeNode {
                 .unwrap()
                 .as_millis() as u64;
             state.metrics.total_startup_ms = startup_end_time
-                .signed_duration_since(compute_state.start_time)
+                .signed_duration_since(self.start_time)
                 .to_std()
                 .unwrap()
                 .as_millis() as u64;

compute_tools/src/configurator.rs

@@ -1,54 +0,0 @@
-use std::sync::Arc;
-use std::thread;
-
-use anyhow::Result;
-use tracing::{error, info, instrument};
-
-use compute_api::responses::ComputeStatus;
-
-use crate::compute::ComputeNode;
-
-#[instrument(skip(compute))]
-fn configurator_main_loop(compute: &Arc<ComputeNode>) {
-    info!("waiting for reconfiguration requests");
-    loop {
-        let state = compute.state.lock().unwrap();
-        let mut state = compute.state_changed.wait(state).unwrap();
-
-        if state.status == ComputeStatus::ConfigurationPending {
-            info!("got configuration request");
-            state.status = ComputeStatus::Configuration;
-            compute.state_changed.notify_all();
-            drop(state);
-
-            let mut new_status = ComputeStatus::Failed;
-            if let Err(e) = compute.reconfigure() {
-                error!("could not configure compute node: {}", e);
-            } else {
-                new_status = ComputeStatus::Running;
-                info!("compute node configured");
-            }
-
-            // XXX: used to test that API is blocking
-            // std::thread::sleep(std::time::Duration::from_millis(10000));
-
-            compute.set_status(new_status);
-        } else if state.status == ComputeStatus::Failed {
-            info!("compute node is now in Failed state, exiting");
-            break;
-        } else {
-            info!("woken up for compute status: {:?}, sleeping", state.status);
-        }
-    }
-}
-
-pub fn launch_configurator(compute: &Arc<ComputeNode>) -> Result<thread::JoinHandle<()>> {
-    let compute = Arc::clone(compute);
-
-    Ok(thread::Builder::new()
-        .name("compute-configurator".into())
-        .spawn(move || {
-            configurator_main_loop(&compute);
-            info!("configurator thread is exited");
-        })?)
-}

compute_tools/src/http/api.rs

@@ -18,7 +18,6 @@ use tracing_utils::http::OtelName;
 
 fn status_response_from_state(state: &ComputeState) -> ComputeStatusResponse {
     ComputeStatusResponse {
-        start_time: state.start_time,
         tenant: state
             .pspec
             .as_ref()
@@ -86,10 +85,7 @@ async fn routes(req: Request<Body>, compute: &Arc<ComputeNode>) -> Response<Body
             let res = crate::checker::check_writability(compute).await;
             match res {
                 Ok(_) => Response::new(Body::from("true")),
-                Err(e) => {
-                    error!("check_writability failed: {}", e);
-                    Response::new(Body::from(e.to_string()))
-                }
+                Err(e) => Response::new(Body::from(e.to_string())),
             }
         }
 
@@ -159,7 +155,7 @@ async fn handle_configure_request(
         // ```
         {
             let mut state = compute.state.lock().unwrap();
-            if state.status != ComputeStatus::Empty && state.status != ComputeStatus::Running {
+            if state.status != ComputeStatus::Empty {
                 let msg = format!(
                     "invalid compute status for configuration request: {:?}",
                     state.status.clone()

compute_tools/src/http/openapi_spec.yaml

@@ -152,14 +152,11 @@ components:
       type: object
       description: Compute startup metrics.
       required:
-        - wait_for_spec_ms
         - sync_safekeepers_ms
         - basebackup_ms
         - config_ms
         - total_startup_ms
       properties:
-        wait_for_spec_ms:
-          type: integer
         sync_safekeepers_ms:
           type: integer
         basebackup_ms:
@@ -184,13 +181,6 @@ components:
         - status
         - last_active
       properties:
-        start_time:
-          type: string
-          description: |
-            Time when compute was started. If initially compute was started in the `empty`
-            state and then provided with valid spec, `start_time` will be reset to the
-            moment, when spec was received.
-          example: "2022-10-12T07:20:50.52Z"
         status:
           $ref: '#/components/schemas/ComputeStatus'
         last_active:

compute_tools/src/lib.rs

@@ -4,7 +4,6 @@
 //!
 pub mod checker;
 pub mod config;
-pub mod configurator;
 pub mod http;
 #[macro_use]
 pub mod logger;

compute_tools/src/spec.rs

@@ -1,120 +1,38 @@
 use std::path::Path;
 use std::str::FromStr;
 
-use anyhow::{anyhow, bail, Result};
+use anyhow::Result;
 use postgres::config::Config;
 use postgres::{Client, NoTls};
-use reqwest::StatusCode;
-use tracing::{error, info, info_span, instrument, span_enabled, warn, Level};
+use tracing::{info, info_span, instrument, span_enabled, warn, Level};
 
 use crate::config;
 use crate::params::PG_HBA_ALL_MD5;
 use crate::pg_helpers::*;
 
-use compute_api::responses::{ControlPlaneComputeStatus, ControlPlaneSpecResponse};
 use compute_api::spec::{ComputeSpec, Database, PgIdent, Role};
 
-// Do control plane request and return response if any. In case of error it
-// returns a bool flag indicating whether it makes sense to retry the request
-// and a string with error message.
-fn do_control_plane_request(
-    uri: &str,
-    jwt: &str,
-) -> Result<ControlPlaneSpecResponse, (bool, String)> {
-    let resp = reqwest::blocking::Client::new()
-        .get(uri)
-        .header("Authorization", jwt)
-        .send()
-        .map_err(|e| {
-            (
-                true,
-                format!("could not perform spec request to control plane: {}", e),
-            )
-        })?;
-
-    match resp.status() {
-        StatusCode::OK => match resp.json::<ControlPlaneSpecResponse>() {
-            Ok(spec_resp) => Ok(spec_resp),
-            Err(e) => Err((
-                true,
-                format!("could not deserialize control plane response: {}", e),
-            )),
-        },
-        StatusCode::SERVICE_UNAVAILABLE => {
-            Err((true, "control plane is temporarily unavailable".to_string()))
-        }
-        StatusCode::BAD_GATEWAY => {
-            // We have a problem with intermittent 502 errors now
-            // https://github.com/neondatabase/cloud/issues/2353
-            // It's fine to retry GET request in this case.
-            Err((true, "control plane request failed with 502".to_string()))
-        }
-        // Another code, likely 500 or 404, means that compute is unknown to the control plane
-        // or some internal failure happened. Doesn't make much sense to retry in this case.
-        _ => Err((
-            false,
-            format!(
-                "unexpected control plane response status code: {}",
-                resp.status()
-            ),
-        )),
-    }
-}
-
 /// Request spec from the control-plane by compute_id. If `NEON_CONSOLE_JWT`
 /// env variable is set, it will be used for authorization.
-pub fn get_spec_from_control_plane(
-    base_uri: &str,
-    compute_id: &str,
-) -> Result<Option<ComputeSpec>> {
+pub fn get_spec_from_control_plane(base_uri: &str, compute_id: &str) -> Result<ComputeSpec> {
     let cp_uri = format!("{base_uri}/management/api/v2/computes/{compute_id}/spec");
-    let jwt: String = match std::env::var("NEON_CONTROL_PLANE_TOKEN") {
+    let jwt: String = match std::env::var("NEON_CONSOLE_JWT") {
         Ok(v) => v,
         Err(_) => "".to_string(),
     };
-    let mut attempt = 1;
-    let mut spec: Result<Option<ComputeSpec>> = Ok(None);
-
     info!("getting spec from control plane: {}", cp_uri);
 
-    // Do 3 attempts to get spec from the control plane using the following logic:
-    // - network error -> then retry
-    // - compute id is unknown or any other error -> bail out
-    // - no spec for compute yet (Empty state) -> return Ok(None)
-    // - got spec -> return Ok(Some(spec))
-    while attempt < 4 {
-        spec = match do_control_plane_request(&cp_uri, &jwt) {
-            Ok(spec_resp) => match spec_resp.status {
-                ControlPlaneComputeStatus::Empty => Ok(None),
-                ControlPlaneComputeStatus::Attached => {
-                    if let Some(spec) = spec_resp.spec {
-                        Ok(Some(spec))
-                    } else {
-                        bail!("compute is attached, but spec is empty")
-                    }
-                }
-            },
-            Err((retry, msg)) => {
-                if retry {
-                    Err(anyhow!(msg))
-                } else {
-                    bail!(msg);
-                }
-            }
-        };
+    // TODO: check the response. We should distinguish cases when it's
+    // - network error, then retry
+    // - no spec for compute yet, then wait
+    // - compute id is unknown or any other error, then bail out
+    let spec = reqwest::blocking::Client::new()
+        .get(cp_uri)
+        .header("Authorization", jwt)
+        .send()?
+        .json()?;
 
-        if let Err(e) = &spec {
-            error!("attempt {} to get spec failed with: {}", attempt, e);
-        } else {
-            return spec;
-        }
-
-        attempt += 1;
-        std::thread::sleep(std::time::Duration::from_millis(100));
-    }
-
-    // All attempts failed, return error.
-    spec
+    Ok(spec)
 }
 
 /// It takes cluster specification and does the following:

control_plane/src/bin/neon_local.rs

@@ -7,7 +7,7 @@
 //!
 use anyhow::{anyhow, bail, Context, Result};
 use clap::{value_parser, Arg, ArgAction, ArgMatches, Command};
-use control_plane::endpoint::ComputeControlPlane;
+use control_plane::compute::ComputeControlPlane;
 use control_plane::local_env::LocalEnv;
 use control_plane::pageserver::PageServerNode;
 use control_plane::safekeeper::SafekeeperNode;
@@ -106,9 +106,8 @@ fn main() -> Result<()> {
             "start" => handle_start_all(sub_args, &env),
             "stop" => handle_stop_all(sub_args, &env),
             "pageserver" => handle_pageserver(sub_args, &env),
+            "pg" => handle_pg(sub_args, &env),
             "safekeeper" => handle_safekeeper(sub_args, &env),
-            "endpoint" => handle_endpoint(sub_args, &env),
-            "pg" => bail!("'pg' subcommand has been renamed to 'endpoint'"),
             _ => bail!("unexpected subcommand {sub_name}"),
         };
 
@@ -471,10 +470,10 @@ fn handle_timeline(timeline_match: &ArgMatches, env: &mut local_env::LocalEnv) -
             let mut cplane = ComputeControlPlane::load(env.clone())?;
             println!("Importing timeline into pageserver ...");
             pageserver.timeline_import(tenant_id, timeline_id, base, pg_wal, pg_version)?;
+            println!("Creating node for imported timeline ...");
             env.register_branch_mapping(name.to_string(), tenant_id, timeline_id)?;
 
-            println!("Creating endpoint for imported timeline ...");
-            cplane.new_endpoint(tenant_id, name, timeline_id, None, None, pg_version)?;
+            cplane.new_node(tenant_id, name, timeline_id, None, None, pg_version)?;
             println!("Done");
         }
         Some(("branch", branch_match)) => {
@@ -522,10 +521,10 @@ fn handle_timeline(timeline_match: &ArgMatches, env: &mut local_env::LocalEnv) -
     Ok(())
 }
 
-fn handle_endpoint(ep_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<()> {
-    let (sub_name, sub_args) = match ep_match.subcommand() {
-        Some(ep_subcommand_data) => ep_subcommand_data,
-        None => bail!("no endpoint subcommand provided"),
+fn handle_pg(pg_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<()> {
+    let (sub_name, sub_args) = match pg_match.subcommand() {
+        Some(pg_subcommand_data) => pg_subcommand_data,
+        None => bail!("no pg subcommand provided"),
     };
 
     let mut cplane = ComputeControlPlane::load(env.clone())?;
@@ -547,7 +546,7 @@ fn handle_endpoint(ep_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<(
             table.load_preset(comfy_table::presets::NOTHING);
 
             table.set_header([
-                "ENDPOINT",
+                "NODE",
                 "ADDRESS",
                 "TIMELINE",
                 "BRANCH NAME",
@@ -555,39 +554,39 @@ fn handle_endpoint(ep_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<(
                 "STATUS",
             ]);
 
-            for (endpoint_id, endpoint) in cplane
-                .endpoints
+            for ((_, node_name), node) in cplane
+                .nodes
                 .iter()
-                .filter(|(_, endpoint)| endpoint.tenant_id == tenant_id)
+                .filter(|((node_tenant_id, _), _)| node_tenant_id == &tenant_id)
             {
-                let lsn_str = match endpoint.lsn {
+                let lsn_str = match node.lsn {
                     None => {
-                        // -> primary endpoint
+                        // -> primary node
                         // Use the LSN at the end of the timeline.
                         timeline_infos
-                            .get(&endpoint.timeline_id)
+                            .get(&node.timeline_id)
                             .map(|bi| bi.last_record_lsn.to_string())
                             .unwrap_or_else(|| "?".to_string())
                     }
                     Some(lsn) => {
-                        // -> read-only endpoint
-                        // Use the endpoint's LSN.
+                        // -> read-only node
+                        // Use the node's LSN.
                         lsn.to_string()
                     }
                 };
 
                 let branch_name = timeline_name_mappings
-                    .get(&TenantTimelineId::new(tenant_id, endpoint.timeline_id))
+                    .get(&TenantTimelineId::new(tenant_id, node.timeline_id))
                     .map(|name| name.as_str())
                     .unwrap_or("?");
 
                 table.add_row([
-                    endpoint_id.as_str(),
-                    &endpoint.address.to_string(),
-                    &endpoint.timeline_id.to_string(),
+                    node_name.as_str(),
+                    &node.address.to_string(),
+                    &node.timeline_id.to_string(),
                     branch_name,
                     lsn_str.as_str(),
-                    endpoint.status(),
+                    node.status(),
                 ]);
             }
 
@@ -598,10 +597,10 @@ fn handle_endpoint(ep_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<(
                 .get_one::<String>("branch-name")
                 .map(|s| s.as_str())
                 .unwrap_or(DEFAULT_BRANCH_NAME);
-            let endpoint_id = sub_args
-                .get_one::<String>("endpoint_id")
-                .map(String::to_string)
-                .unwrap_or_else(|| format!("ep-{branch_name}"));
+            let node_name = sub_args
+                .get_one::<String>("node")
+                .map(|node_name| node_name.to_string())
+                .unwrap_or_else(|| format!("{branch_name}_node"));
 
             let lsn = sub_args
                 .get_one::<String>("lsn")
@@ -619,15 +618,15 @@ fn handle_endpoint(ep_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<(
                 .copied()
                 .context("Failed to parse postgres version from the argument string")?;
 
-            cplane.new_endpoint(tenant_id, &endpoint_id, timeline_id, lsn, port, pg_version)?;
+            cplane.new_node(tenant_id, &node_name, timeline_id, lsn, port, pg_version)?;
         }
         "start" => {
             let port: Option<u16> = sub_args.get_one::<u16>("port").copied();
-            let endpoint_id = sub_args
-                .get_one::<String>("endpoint_id")
-                .ok_or_else(|| anyhow!("No endpoint ID was provided to start"))?;
+            let node_name = sub_args
+                .get_one::<String>("node")
+                .ok_or_else(|| anyhow!("No node name was provided to start"))?;
 
-            let endpoint = cplane.endpoints.get(endpoint_id.as_str());
+            let node = cplane.nodes.get(&(tenant_id, node_name.to_string()));
 
             let auth_token = if matches!(env.pageserver.pg_auth_type, AuthType::NeonJWT) {
                 let claims = Claims::new(Some(tenant_id), Scope::Tenant);
@@ -637,9 +636,9 @@ fn handle_endpoint(ep_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<(
                 None
             };
 
-            if let Some(endpoint) = endpoint {
-                println!("Starting existing endpoint {endpoint_id}...");
-                endpoint.start(&auth_token)?;
+            if let Some(node) = node {
+                println!("Starting existing postgres {node_name}...");
+                node.start(&auth_token)?;
             } else {
                 let branch_name = sub_args
                     .get_one::<String>("branch-name")
@@ -664,33 +663,27 @@ fn handle_endpoint(ep_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<(
                 // start --port X
                 // stop
                 // start <-- will also use port X even without explicit port argument
-                println!("Starting new endpoint {endpoint_id} (PostgreSQL v{pg_version}) on timeline {timeline_id} ...");
+                println!("Starting new postgres (v{pg_version}) {node_name} on timeline {timeline_id} ...");
 
-                let ep = cplane.new_endpoint(
-                    tenant_id,
-                    endpoint_id,
-                    timeline_id,
-                    lsn,
-                    port,
-                    pg_version,
-                )?;
-                ep.start(&auth_token)?;
+                let node =
+                    cplane.new_node(tenant_id, node_name, timeline_id, lsn, port, pg_version)?;
+                node.start(&auth_token)?;
             }
         }
         "stop" => {
-            let endpoint_id = sub_args
-                .get_one::<String>("endpoint_id")
-                .ok_or_else(|| anyhow!("No endpoint ID was provided to stop"))?;
+            let node_name = sub_args
+                .get_one::<String>("node")
+                .ok_or_else(|| anyhow!("No node name was provided to stop"))?;
             let destroy = sub_args.get_flag("destroy");
 
-            let endpoint = cplane
-                .endpoints
-                .get(endpoint_id.as_str())
-                .with_context(|| format!("postgres endpoint {endpoint_id} is not found"))?;
-            endpoint.stop(destroy)?;
+            let node = cplane
+                .nodes
+                .get(&(tenant_id, node_name.to_string()))
+                .with_context(|| format!("postgres {node_name} is not found"))?;
+            node.stop(destroy)?;
         }
 
-        _ => bail!("Unexpected endpoint subcommand '{sub_name}'"),
+        _ => bail!("Unexpected pg subcommand '{sub_name}'"),
     }
 
     Ok(())
@@ -809,7 +802,7 @@ fn handle_safekeeper(sub_match: &ArgMatches, env: &local_env::LocalEnv) -> Resul
 }
 
 fn handle_start_all(sub_match: &ArgMatches, env: &local_env::LocalEnv) -> anyhow::Result<()> {
-    // Endpoints are not started automatically
+    // Postgres nodes are not started automatically
 
     broker::start_broker_process(env)?;
 
@@ -843,10 +836,10 @@ fn handle_stop_all(sub_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<
 fn try_stop_all(env: &local_env::LocalEnv, immediate: bool) {
     let pageserver = PageServerNode::from_env(env);
 
-    // Stop all endpoints
+    // Stop all compute nodes
     match ComputeControlPlane::load(env.clone()) {
         Ok(cplane) => {
-            for (_k, node) in cplane.endpoints {
+            for (_k, node) in cplane.nodes {
                 if let Err(e) = node.stop(false) {
                     eprintln!("postgres stop failed: {e:#}");
                 }
@@ -879,9 +872,7 @@ fn cli() -> Command {
         .help("Name of the branch to be created or used as an alias for other services")
         .required(false);
 
-    let endpoint_id_arg = Arg::new("endpoint_id")
-        .help("Postgres endpoint id")
-        .required(false);
+    let pg_node_arg = Arg::new("node").help("Postgres node name").required(false);
 
     let safekeeper_id_arg = Arg::new("id").help("safekeeper id").required(false);
 
@@ -1035,27 +1026,27 @@ fn cli() -> Command {
                 )
         )
         .subcommand(
-            Command::new("endpoint")
+            Command::new("pg")
                 .arg_required_else_help(true)
                 .about("Manage postgres instances")
                 .subcommand(Command::new("list").arg(tenant_id_arg.clone()))
                 .subcommand(Command::new("create")
-                    .about("Create a compute endpoint")
-                    .arg(endpoint_id_arg.clone())
+                    .about("Create a postgres compute node")
+                    .arg(pg_node_arg.clone())
                     .arg(branch_name_arg.clone())
                     .arg(tenant_id_arg.clone())
                     .arg(lsn_arg.clone())
                     .arg(port_arg.clone())
                     .arg(
                         Arg::new("config-only")
-                            .help("Don't do basebackup, create endpoint directory with only config files")
+                            .help("Don't do basebackup, create compute node with only config files")
                             .long("config-only")
                             .required(false))
                     .arg(pg_version_arg.clone())
                 )
                 .subcommand(Command::new("start")
-                    .about("Start postgres.\n If the endpoint doesn't exist yet, it is created.")
-                    .arg(endpoint_id_arg.clone())
+                    .about("Start a postgres compute node.\n This command actually creates new node from scratch, but preserves existing config files")
+                    .arg(pg_node_arg.clone())
                     .arg(tenant_id_arg.clone())
                     .arg(branch_name_arg)
                     .arg(timeline_id_arg)
@@ -1065,7 +1056,7 @@ fn cli() -> Command {
                 )
                 .subcommand(
                     Command::new("stop")
-                    .arg(endpoint_id_arg)
+                    .arg(pg_node_arg)
                     .arg(tenant_id_arg)
                     .arg(
                         Arg::new("destroy")
@@ -1077,13 +1068,6 @@ fn cli() -> Command {
                 )
 
         )
-        // Obsolete old name for 'endpoint'. We now just print an error if it's used.
-        .subcommand(
-            Command::new("pg")
-                .hide(true)
-                .arg(Arg::new("ignore-rest").allow_hyphen_values(true).num_args(0..).required(false))
-                .trailing_var_arg(true)
-        )
         .subcommand(
             Command::new("start")
                 .about("Start page server and safekeepers")

control_plane/src/compute.rs

@@ -25,45 +25,54 @@ use crate::postgresql_conf::PostgresConf;
 //
 pub struct ComputeControlPlane {
     base_port: u16,
-
-    // endpoint ID is the key
-    pub endpoints: BTreeMap<String, Arc<Endpoint>>,
-
-    env: LocalEnv,
     pageserver: Arc<PageServerNode>,
+    pub nodes: BTreeMap<(TenantId, String), Arc<PostgresNode>>,
+    env: LocalEnv,
 }
 
 impl ComputeControlPlane {
-    // Load current endpoints from the endpoints/ subdirectories
+    // Load current nodes with ports from data directories on disk
+    // Directory structure has the following layout:
+    // pgdatadirs
+    // |- tenants
+    // |  |- <tenant_id>
+    // |  |   |- <node name>
     pub fn load(env: LocalEnv) -> Result<ComputeControlPlane> {
         let pageserver = Arc::new(PageServerNode::from_env(&env));
 
-        let mut endpoints = BTreeMap::default();
-        for endpoint_dir in fs::read_dir(env.endpoints_path())
-            .with_context(|| format!("failed to list {}", env.endpoints_path().display()))?
+        let mut nodes = BTreeMap::default();
+        let pgdatadirspath = &env.pg_data_dirs_path();
+
+        for tenant_dir in fs::read_dir(pgdatadirspath)
+            .with_context(|| format!("failed to list {}", pgdatadirspath.display()))?
         {
-            let ep = Endpoint::from_dir_entry(endpoint_dir?, &env, &pageserver)?;
-            endpoints.insert(ep.name.clone(), Arc::new(ep));
+            let tenant_dir = tenant_dir?;
+            for timeline_dir in fs::read_dir(tenant_dir.path())
+                .with_context(|| format!("failed to list {}", tenant_dir.path().display()))?
+            {
+                let node = PostgresNode::from_dir_entry(timeline_dir?, &env, &pageserver)?;
+                nodes.insert((node.tenant_id, node.name.clone()), Arc::new(node));
+            }
         }
 
         Ok(ComputeControlPlane {
             base_port: 55431,
-            endpoints,
-            env,
             pageserver,
+            nodes,
+            env,
         })
     }
 
     fn get_port(&mut self) -> u16 {
         1 + self
-            .endpoints
+            .nodes
             .values()
-            .map(|ep| ep.address.port())
+            .map(|node| node.address.port())
             .max()
             .unwrap_or(self.base_port)
     }
 
-    pub fn new_endpoint(
+    pub fn new_node(
         &mut self,
         tenant_id: TenantId,
         name: &str,
@@ -71,9 +80,9 @@ impl ComputeControlPlane {
         lsn: Option<Lsn>,
         port: Option<u16>,
         pg_version: u32,
-    ) -> Result<Arc<Endpoint>> {
+    ) -> Result<Arc<PostgresNode>> {
         let port = port.unwrap_or_else(|| self.get_port());
-        let ep = Arc::new(Endpoint {
+        let node = Arc::new(PostgresNode {
             name: name.to_owned(),
             address: SocketAddr::new("127.0.0.1".parse().unwrap(), port),
             env: self.env.clone(),
@@ -84,45 +93,39 @@ impl ComputeControlPlane {
             pg_version,
         });
 
-        ep.create_pgdata()?;
-        ep.setup_pg_conf()?;
+        node.create_pgdata()?;
+        node.setup_pg_conf()?;
 
-        self.endpoints.insert(ep.name.clone(), Arc::clone(&ep));
+        self.nodes
+            .insert((tenant_id, node.name.clone()), Arc::clone(&node));
 
-        Ok(ep)
+        Ok(node)
     }
 }
 
 ///////////////////////////////////////////////////////////////////////////////
 
 #[derive(Debug)]
-pub struct Endpoint {
-    /// used as the directory name
-    name: String,
-    pub tenant_id: TenantId,
-    pub timeline_id: TimelineId,
-    // Some(lsn) if this is a read-only endpoint anchored at 'lsn'. None for the primary.
-    pub lsn: Option<Lsn>,
-
-    // port and address of the Postgres server
+pub struct PostgresNode {
     pub address: SocketAddr,
-    pg_version: u32,
-
-    // These are not part of the endpoint as such, but the environment
-    // the endpoint runs in.
+    name: String,
     pub env: LocalEnv,
     pageserver: Arc<PageServerNode>,
+    pub timeline_id: TimelineId,
+    pub lsn: Option<Lsn>, // if it's a read-only node. None for primary
+    pub tenant_id: TenantId,
+    pg_version: u32,
 }
 
-impl Endpoint {
+impl PostgresNode {
     fn from_dir_entry(
         entry: std::fs::DirEntry,
         env: &LocalEnv,
         pageserver: &Arc<PageServerNode>,
-    ) -> Result<Endpoint> {
+    ) -> Result<PostgresNode> {
         if !entry.file_type()?.is_dir() {
             anyhow::bail!(
-                "Endpoint::from_dir_entry failed: '{}' is not a directory",
+                "PostgresNode::from_dir_entry failed: '{}' is not a directory",
                 entry.path().display()
             );
         }
@@ -132,7 +135,7 @@ impl Endpoint {
         let name = fname.to_str().unwrap().to_string();
 
         // Read config file into memory
-        let cfg_path = entry.path().join("pgdata").join("postgresql.conf");
+        let cfg_path = entry.path().join("postgresql.conf");
         let cfg_path_str = cfg_path.to_string_lossy();
         let mut conf_file = File::open(&cfg_path)
             .with_context(|| format!("failed to open config file in {}", cfg_path_str))?;
@@ -158,7 +161,7 @@ impl Endpoint {
             conf.parse_field_optional("recovery_target_lsn", &context)?;
 
         // ok now
-        Ok(Endpoint {
+        Ok(PostgresNode {
             address: SocketAddr::new("127.0.0.1".parse().unwrap(), port),
             name,
             env: env.clone(),
@@ -266,7 +269,7 @@ impl Endpoint {
     }
 
     // Write postgresql.conf with default configuration
-    // and PG_VERSION file to the data directory of a new endpoint.
+    // and PG_VERSION file to the data directory of a new node.
     fn setup_pg_conf(&self) -> Result<()> {
         let mut conf = PostgresConf::new();
         conf.append("max_wal_senders", "10");
@@ -286,7 +289,7 @@ impl Endpoint {
         // walproposer panics when basebackup is invalid, it is pointless to restart in this case.
         conf.append("restart_after_crash", "off");
 
-        // Configure the Neon Postgres extension to fetch pages from pageserver
+        // Configure the node to fetch pages from pageserver
         let pageserver_connstr = {
             let config = &self.pageserver.pg_connection_config;
             let (host, port) = (config.host(), config.port());
@@ -322,7 +325,7 @@ impl Endpoint {
         conf.append("max_replication_flush_lag", "10GB");
 
         if !self.env.safekeepers.is_empty() {
-            // Configure Postgres to connect to the safekeepers
+            // Configure the node to connect to the safekeepers
             conf.append("synchronous_standby_names", "walproposer");
 
             let safekeepers = self
@@ -377,12 +380,8 @@ impl Endpoint {
         Ok(())
     }
 
-    pub fn endpoint_path(&self) -> PathBuf {
-        self.env.endpoints_path().join(&self.name)
-    }
-
     pub fn pgdata(&self) -> PathBuf {
-        self.endpoint_path().join("pgdata")
+        self.env.pg_data_dir(&self.tenant_id, &self.name)
     }
 
     pub fn status(&self) -> &str {
@@ -444,11 +443,12 @@ impl Endpoint {
     }
 
     pub fn start(&self, auth_token: &Option<String>) -> Result<()> {
+        // Bail if the node already running.
         if self.status() == "running" {
-            anyhow::bail!("The endpoint is already running");
+            anyhow::bail!("The node is already running");
         }
 
-        // 1. We always start Postgres from scratch, so
+        // 1. We always start compute node from scratch, so
         // if old dir exists, preserve 'postgresql.conf' and drop the directory
         let postgresql_conf_path = self.pgdata().join("postgresql.conf");
         let postgresql_conf = fs::read(&postgresql_conf_path).with_context(|| {
@@ -470,8 +470,8 @@ impl Endpoint {
             File::create(self.pgdata().join("standby.signal"))?;
         }
 
-        // 4. Finally start postgres
-        println!("Starting postgres at '{}'", self.connstr());
+        // 4. Finally start the compute node postgres
+        println!("Starting postgres node at '{}'", self.connstr());
         self.pg_ctl(&["start"], auth_token)
     }
 
@@ -480,7 +480,7 @@ impl Endpoint {
         // use immediate shutdown mode, otherwise,
         // shutdown gracefully to leave the data directory sane.
         //
-        // Postgres is always started from scratch, so stop
+        // Compute node always starts from scratch, so stop
         // without destroy only used for testing and debugging.
         //
         if destroy {
@@ -489,7 +489,7 @@ impl Endpoint {
                 "Destroying postgres data directory '{}'",
                 self.pgdata().to_str().unwrap()
             );
-            fs::remove_dir_all(self.endpoint_path())?;
+            fs::remove_dir_all(self.pgdata())?;
         } else {
             self.pg_ctl(&["stop"], &None)?;
         }

control_plane/src/lib.rs

@@ -9,7 +9,7 @@
 
 mod background_process;
 pub mod broker;
-pub mod endpoint;
+pub mod compute;
 pub mod local_env;
 pub mod pageserver;
 pub mod postgresql_conf;

control_plane/src/local_env.rs

@@ -200,8 +200,14 @@ impl LocalEnv {
         self.neon_distrib_dir.join("storage_broker")
     }
 
-    pub fn endpoints_path(&self) -> PathBuf {
-        self.base_data_dir.join("endpoints")
+    pub fn pg_data_dirs_path(&self) -> PathBuf {
+        self.base_data_dir.join("pgdatadirs").join("tenants")
+    }
+
+    pub fn pg_data_dir(&self, tenant_id: &TenantId, branch_name: &str) -> PathBuf {
+        self.pg_data_dirs_path()
+            .join(tenant_id.to_string())
+            .join(branch_name)
     }
 
     // TODO: move pageserver files into ./pageserver
@@ -421,7 +427,7 @@ impl LocalEnv {
             }
         }
 
-        fs::create_dir_all(self.endpoints_path())?;
+        fs::create_dir_all(self.pg_data_dirs_path())?;
 
         for safekeeper in &self.safekeepers {
             fs::create_dir_all(SafekeeperNode::datadir_path_by_id(self, safekeeper.id))?;

control_plane/src/pageserver.rs

@@ -359,8 +359,8 @@ impl PageServerNode {
                 .transpose()
                 .context("Failed to parse 'trace_read_requests' as bool")?,
             eviction_policy: settings
-                .remove("eviction_policy")
-                .map(serde_json::from_str)
+                .get("eviction_policy")
+                .map(|x| serde_json::from_str(x))
                 .transpose()
                 .context("Failed to parse 'eviction_policy' json")?,
             min_resident_size_override: settings
@@ -368,9 +368,6 @@ impl PageServerNode {
                 .map(|x| x.parse::<u64>())
                 .transpose()
                 .context("Failed to parse 'min_resident_size_override' as integer")?,
-            evictions_low_residence_duration_metric_threshold: settings
-                .remove("evictions_low_residence_duration_metric_threshold")
-                .map(|x| x.to_string()),
         };
         if !settings.is_empty() {
             bail!("Unrecognized tenant settings: {settings:?}")
@@ -448,9 +445,6 @@ impl PageServerNode {
                     .map(|x| x.parse::<u64>())
                     .transpose()
                     .context("Failed to parse 'min_resident_size_override' as an integer")?,
-                evictions_low_residence_duration_metric_threshold: settings
-                    .get("evictions_low_residence_duration_metric_threshold")
-                    .map(|x| x.to_string()),
             })
             .send()?
             .error_from_body()?;

libs/compute_api/src/responses.rs

@@ -1,9 +1,7 @@
 //! Structs representing the JSON formats used in the compute_ctl's HTTP API.
 
 use chrono::{DateTime, Utc};
-use serde::{Deserialize, Serialize, Serializer};
-
-use crate::spec::ComputeSpec;
+use serde::{Serialize, Serializer};
 
 #[derive(Serialize, Debug)]
 pub struct GenericAPIError {
@@ -14,7 +12,6 @@ pub struct GenericAPIError {
 #[derive(Serialize, Debug)]
 #[serde(rename_all = "snake_case")]
 pub struct ComputeStatusResponse {
-    pub start_time: DateTime<Utc>,
     pub tenant: Option<String>,
     pub timeline: Option<String>,
     pub status: ComputeStatus,
@@ -46,8 +43,6 @@ pub enum ComputeStatus {
     Init,
     // Compute is configured and running.
     Running,
-    // New spec is being applied.
-    Configuration,
     // Either startup or configuration failed,
     // compute will exit soon or is waiting for
     // control-plane to terminate it.
@@ -64,29 +59,8 @@ where
 /// Response of the /metrics.json API
 #[derive(Clone, Debug, Default, Serialize)]
 pub struct ComputeMetrics {
-    pub wait_for_spec_ms: u64,
     pub sync_safekeepers_ms: u64,
     pub basebackup_ms: u64,
     pub config_ms: u64,
     pub total_startup_ms: u64,
 }
-
-/// Response of the `/computes/{compute_id}/spec` control-plane API.
-/// This is not actually a compute API response, so consider moving
-/// to a different place.
-#[derive(Deserialize, Debug)]
-pub struct ControlPlaneSpecResponse {
-    pub spec: Option<ComputeSpec>,
-    pub status: ControlPlaneComputeStatus,
-}
-
-#[derive(Deserialize, Clone, Copy, Debug, PartialEq, Eq)]
-#[serde(rename_all = "snake_case")]
-pub enum ControlPlaneComputeStatus {
-    // Compute is known to control-plane, but it's not
-    // yet attached to any timeline / endpoint.
-    Empty,
-    // Compute is attached to some timeline / endpoint and
-    // should be able to start with provided spec.
-    Attached,
-}

libs/consumption_metrics/Cargo.toml

@@ -4,12 +4,13 @@ version = "0.1.0"
 edition = "2021"
 license = "Apache-2.0"
 
-[dependencies]
-anyhow.workspace = true
-chrono.workspace = true
-rand.workspace = true
-serde.workspace = true
-serde_with.workspace = true
-utils.workspace = true
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
-workspace_hack.workspace = true
+[dependencies]
+anyhow = "1.0.68"
+chrono = { version = "0.4", default-features = false, features = ["clock", "serde"] }
+rand = "0.8.3"
+serde = "1.0.152"
+serde_with = "2.1.0"
+utils = { version = "0.1.0", path = "../utils" }
+workspace_hack = { version = "0.1.0", path = "../../workspace_hack" }

libs/pageserver_api/Cargo.toml

@@ -7,7 +7,6 @@ license.workspace = true
 [dependencies]
 serde.workspace = true
 serde_with.workspace = true
-serde_json.workspace = true
 const_format.workspace = true
 anyhow.workspace = true
 bytes.workspace = true
@@ -15,7 +14,6 @@ byteorder.workspace = true
 utils.workspace = true
 postgres_ffi.workspace = true
 enum-map.workspace = true
-strum.workspace = true
-strum_macros.workspace = true
+serde_json.workspace = true
 
 workspace_hack.workspace = true

libs/pageserver_api/src/models.rs

@@ -7,7 +7,6 @@ use std::{
 use byteorder::{BigEndian, ReadBytesExt};
 use serde::{Deserialize, Serialize};
 use serde_with::{serde_as, DisplayFromStr};
-use strum_macros;
 use utils::{
     history_buffer::HistoryBufferWithDropCounter,
     id::{NodeId, TenantId, TimelineId},
@@ -19,23 +18,11 @@ use anyhow::bail;
 use bytes::{BufMut, Bytes, BytesMut};
 
 /// A state of a tenant in pageserver's memory.
-#[derive(
-    Clone,
-    PartialEq,
-    Eq,
-    serde::Serialize,
-    serde::Deserialize,
-    strum_macros::Display,
-    strum_macros::EnumString,
-    strum_macros::EnumVariantNames,
-    strum_macros::AsRefStr,
-    strum_macros::IntoStaticStr,
-)]
-#[serde(tag = "slug", content = "data")]
+#[derive(Debug, Clone, Copy, PartialEq, Eq, serde::Serialize, serde::Deserialize)]
 pub enum TenantState {
-    /// This tenant is being loaded from local disk
+    // This tenant is being loaded from local disk
     Loading,
-    /// This tenant is being downloaded from cloud storage.
+    // This tenant is being downloaded from cloud storage.
     Attaching,
     /// Tenant is fully operational
     Active,
@@ -44,7 +31,15 @@ pub enum TenantState {
     Stopping,
     /// A tenant is recognized by the pageserver, but can no longer be used for
     /// any operations, because it failed to be activated.
-    Broken { reason: String, backtrace: String },
+    Broken,
+}
+
+pub mod state {
+    pub const LOADING: &str = "loading";
+    pub const ATTACHING: &str = "attaching";
+    pub const ACTIVE: &str = "active";
+    pub const STOPPING: &str = "stopping";
+    pub const BROKEN: &str = "broken";
 }
 
 impl TenantState {
@@ -54,26 +49,17 @@ impl TenantState {
             Self::Attaching => true,
             Self::Active => false,
             Self::Stopping => false,
-            Self::Broken { .. } => false,
+            Self::Broken => false,
         }
     }
 
-    pub fn broken_from_reason(reason: String) -> Self {
-        let backtrace_str: String = format!("{}", std::backtrace::Backtrace::force_capture());
-        Self::Broken {
-            reason,
-            backtrace: backtrace_str,
-        }
-    }
-}
-
-impl std::fmt::Debug for TenantState {
-    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+    pub fn as_str(&self) -> &'static str {
         match self {
-            Self::Broken { reason, backtrace } if !reason.is_empty() => {
-                write!(f, "Broken due to: {reason}. Backtrace:\n{backtrace}")
-            }
-            _ => write!(f, "{self}"),
+            TenantState::Loading => state::LOADING,
+            TenantState::Attaching => state::ATTACHING,
+            TenantState::Active => state::ACTIVE,
+            TenantState::Stopping => state::STOPPING,
+            TenantState::Broken => state::BROKEN,
         }
     }
 }
@@ -135,7 +121,6 @@ pub struct TenantCreateRequest {
     // For now, this field is not even documented in the openapi_spec.yml.
     pub eviction_policy: Option<serde_json::Value>,
     pub min_resident_size_override: Option<u64>,
-    pub evictions_low_residence_duration_metric_threshold: Option<String>,
 }
 
 #[serde_as]
@@ -182,7 +167,6 @@ pub struct TenantConfigRequest {
     // For now, this field is not even documented in the openapi_spec.yml.
     pub eviction_policy: Option<serde_json::Value>,
     pub min_resident_size_override: Option<u64>,
-    pub evictions_low_residence_duration_metric_threshold: Option<String>,
 }
 
 impl TenantConfigRequest {
@@ -204,7 +188,6 @@ impl TenantConfigRequest {
             trace_read_requests: None,
             eviction_policy: None,
             min_resident_size_override: None,
-            evictions_low_residence_duration_metric_threshold: None,
         }
     }
 }
@@ -632,7 +615,6 @@ impl PagestreamBeMessage {
 #[cfg(test)]
 mod tests {
     use bytes::Buf;
-    use serde_json::json;
 
     use super::*;
 
@@ -683,57 +665,4 @@ mod tests {
             assert!(msg == reconstructed);
         }
     }
-
-    #[test]
-    fn test_tenantinfo_serde() {
-        // Test serialization/deserialization of TenantInfo
-        let original_active = TenantInfo {
-            id: TenantId::generate(),
-            state: TenantState::Active,
-            current_physical_size: Some(42),
-            has_in_progress_downloads: Some(false),
-        };
-        let expected_active = json!({
-            "id": original_active.id.to_string(),
-            "state": {
-                "slug": "Active",
-            },
-            "current_physical_size": 42,
-            "has_in_progress_downloads": false,
-        });
-
-        let original_broken = TenantInfo {
-            id: TenantId::generate(),
-            state: TenantState::Broken {
-                reason: "reason".into(),
-                backtrace: "backtrace info".into(),
-            },
-            current_physical_size: Some(42),
-            has_in_progress_downloads: Some(false),
-        };
-        let expected_broken = json!({
-            "id": original_broken.id.to_string(),
-            "state": {
-                "slug": "Broken",
-                "data": {
-                    "backtrace": "backtrace info",
-                    "reason": "reason",
-                }
-            },
-            "current_physical_size": 42,
-            "has_in_progress_downloads": false,
-        });
-
-        assert_eq!(
-            serde_json::to_value(&original_active).unwrap(),
-            expected_active
-        );
-
-        assert_eq!(
-            serde_json::to_value(&original_broken).unwrap(),
-            expected_broken
-        );
-        assert!(format!("{:?}", &original_broken.state).contains("reason"));
-        assert!(format!("{:?}", &original_broken.state).contains("backtrace info"));
-    }
 }

libs/postgres_ffi/build.rs

@@ -5,7 +5,7 @@ use std::path::PathBuf;
 use std::process::Command;
 
 use anyhow::{anyhow, Context};
-use bindgen::callbacks::{DeriveInfo, ParseCallbacks};
+use bindgen::callbacks::ParseCallbacks;
 
 #[derive(Debug)]
 struct PostgresFfiCallbacks;
@@ -20,7 +20,7 @@ impl ParseCallbacks for PostgresFfiCallbacks {
 
     // Add any custom #[derive] attributes to the data structures that bindgen
     // creates.
-    fn add_derives(&self, derive_info: &DeriveInfo) -> Vec<String> {
+    fn add_derives(&self, name: &str) -> Vec<String> {
         // This is the list of data structures that we want to serialize/deserialize.
         let serde_list = [
             "XLogRecord",
@@ -31,7 +31,7 @@ impl ParseCallbacks for PostgresFfiCallbacks {
             "ControlFileData",
         ];
 
-        if serde_list.contains(&derive_info.name) {
+        if serde_list.contains(&name) {
             vec![
                 "Default".into(), // Default allows us to easily fill the padding fields with 0.
                 "Serialize".into(),

libs/remote_storage/tests/pagination_tests.rs

@@ -204,7 +204,12 @@ async fn upload_s3_data(
             let data = format!("remote blob data {i}").into_bytes();
             let data_len = data.len();
             task_client
-                .upload(std::io::Cursor::new(data), data_len, &blob_path, None)
+                .upload(
+                    Box::new(std::io::Cursor::new(data)),
+                    data_len,
+                    &blob_path,
+                    None,
+                )
                 .await?;
 
             Ok::<_, anyhow::Error>((blob_prefix, blob_path))

libs/tracing-utils/Cargo.toml

@@ -14,5 +14,4 @@ tokio = { workspace = true, features = ["rt", "rt-multi-thread"] }
 tracing.workspace = true
 tracing-opentelemetry.workspace = true
 tracing-subscriber.workspace = true
-
-workspace_hack.workspace = true
+workspace_hack = { version = "0.1", path = "../../workspace_hack" }

libs/utils/Cargo.toml

@@ -33,7 +33,7 @@ serde_with.workspace = true
 strum.workspace = true
 strum_macros.workspace = true
 url.workspace = true
-uuid.workspace = true
+uuid = { version = "1.2", features = ["v4", "serde"] }
 
 metrics.workspace = true
 workspace_hack.workspace = true

libs/utils/src/http/endpoint.rs

@@ -76,7 +76,6 @@ where
 
         let log_quietly = method == Method::GET;
         async move {
-            let cancellation_guard = RequestCancelled::warn_when_dropped_without_responding();
             if log_quietly {
                 debug!("Handling request");
             } else {
@@ -88,11 +87,7 @@ where
             // Usage of the error handler also means that we expect only the `ApiError` errors to be raised in this call.
             //
             // Panics are not handled separately, there's a `tracing_panic_hook` from another module to do that globally.
-            let res = (self.0)(request).await;
-
-            cancellation_guard.disarm();
-
-            match res {
+            match (self.0)(request).await {
                 Ok(response) => {
                     let response_status = response.status();
                     if log_quietly && response_status.is_success() {
@@ -110,38 +105,6 @@ where
     }
 }
 
-/// Drop guard to WARN in case the request was dropped before completion.
-struct RequestCancelled {
-    warn: Option<tracing::Span>,
-}
-
-impl RequestCancelled {
-    /// Create the drop guard using the [`tracing::Span::current`] as the span.
-    fn warn_when_dropped_without_responding() -> Self {
-        RequestCancelled {
-            warn: Some(tracing::Span::current()),
-        }
-    }
-
-    /// Consume the drop guard without logging anything.
-    fn disarm(mut self) {
-        self.warn = None;
-    }
-}
-
-impl Drop for RequestCancelled {
-    fn drop(&mut self) {
-        if let Some(span) = self.warn.take() {
-            // the span has all of the info already, but the outer `.instrument(span)` has already
-            // been dropped, so we need to manually re-enter it for this message.
-            //
-            // this is what the instrument would do before polling so it is fine.
-            let _g = span.entered();
-            warn!("request was dropped before completing");
-        }
-    }
-}
-
 async fn prometheus_metrics_handler(_req: Request<Body>) -> Result<Response<Body>, ApiError> {
     SERVE_METRICS_COUNT.inc();
 

libs/utils/src/logging.rs

@@ -1,7 +1,6 @@
 use std::str::FromStr;
 
 use anyhow::Context;
-use once_cell::sync::Lazy;
 use strum_macros::{EnumString, EnumVariantNames};
 
 #[derive(EnumString, EnumVariantNames, Eq, PartialEq, Debug, Clone, Copy)]
@@ -24,64 +23,25 @@ impl LogFormat {
     }
 }
 
-static TRACING_EVENT_COUNT: Lazy<metrics::IntCounterVec> = Lazy::new(|| {
-    metrics::register_int_counter_vec!(
-        "libmetrics_tracing_event_count",
-        "Number of tracing events, by level",
-        &["level"]
-    )
-    .expect("failed to define metric")
-});
-
-struct TracingEventCountLayer(&'static metrics::IntCounterVec);
-
-impl<S> tracing_subscriber::layer::Layer<S> for TracingEventCountLayer
-where
-    S: tracing::Subscriber,
-{
-    fn on_event(
-        &self,
-        event: &tracing::Event<'_>,
-        _ctx: tracing_subscriber::layer::Context<'_, S>,
-    ) {
-        let level = event.metadata().level();
-        let level = match *level {
-            tracing::Level::ERROR => "error",
-            tracing::Level::WARN => "warn",
-            tracing::Level::INFO => "info",
-            tracing::Level::DEBUG => "debug",
-            tracing::Level::TRACE => "trace",
-        };
-        self.0.with_label_values(&[level]).inc();
-    }
-}
-
 pub fn init(log_format: LogFormat) -> anyhow::Result<()> {
+    let default_filter_str = "info";
+
     // We fall back to printing all spans at info-level or above if
     // the RUST_LOG environment variable is not set.
-    let rust_log_env_filter = || {
-        tracing_subscriber::EnvFilter::try_from_default_env()
-            .unwrap_or_else(|_| tracing_subscriber::EnvFilter::new("info"))
-    };
+    let env_filter = tracing_subscriber::EnvFilter::try_from_default_env()
+        .unwrap_or_else(|_| tracing_subscriber::EnvFilter::new(default_filter_str));
 
-    // NB: the order of the with() calls does not matter.
-    // See https://docs.rs/tracing-subscriber/0.3.16/tracing_subscriber/layer/index.html#per-layer-filtering
-    use tracing_subscriber::prelude::*;
-    tracing_subscriber::registry()
-        .with({
-            let log_layer = tracing_subscriber::fmt::layer()
-                .with_target(false)
-                .with_ansi(atty::is(atty::Stream::Stdout))
-                .with_writer(std::io::stdout);
-            let log_layer = match log_format {
-                LogFormat::Json => log_layer.json().boxed(),
-                LogFormat::Plain => log_layer.boxed(),
-                LogFormat::Test => log_layer.with_test_writer().boxed(),
-            };
-            log_layer.with_filter(rust_log_env_filter())
-        })
-        .with(TracingEventCountLayer(&TRACING_EVENT_COUNT).with_filter(rust_log_env_filter()))
-        .init();
+    let base_logger = tracing_subscriber::fmt()
+        .with_env_filter(env_filter)
+        .with_target(false)
+        .with_ansi(atty::is(atty::Stream::Stdout))
+        .with_writer(std::io::stdout);
+
+    match log_format {
+        LogFormat::Json => base_logger.json().init(),
+        LogFormat::Plain => base_logger.init(),
+        LogFormat::Test => base_logger.with_test_writer().init(),
+    }
 
     Ok(())
 }
@@ -197,33 +157,3 @@ impl std::fmt::Debug for PrettyLocation<'_, '_> {
         <Self as std::fmt::Display>::fmt(self, f)
     }
 }
-
-#[cfg(test)]
-mod tests {
-    use metrics::{core::Opts, IntCounterVec};
-
-    use super::TracingEventCountLayer;
-
-    #[test]
-    fn tracing_event_count_metric() {
-        let counter_vec =
-            IntCounterVec::new(Opts::new("testmetric", "testhelp"), &["level"]).unwrap();
-        let counter_vec = Box::leak(Box::new(counter_vec)); // make it 'static
-        let layer = TracingEventCountLayer(counter_vec);
-        use tracing_subscriber::prelude::*;
-
-        tracing::subscriber::with_default(tracing_subscriber::registry().with(layer), || {
-            tracing::trace!("foo");
-            tracing::debug!("foo");
-            tracing::info!("foo");
-            tracing::warn!("foo");
-            tracing::error!("foo");
-        });
-
-        assert_eq!(counter_vec.with_label_values(&["trace"]).get(), 1);
-        assert_eq!(counter_vec.with_label_values(&["debug"]).get(), 1);
-        assert_eq!(counter_vec.with_label_values(&["info"]).get(), 1);
-        assert_eq!(counter_vec.with_label_values(&["warn"]).get(), 1);
-        assert_eq!(counter_vec.with_label_values(&["error"]).get(), 1);
-    }
-}

pageserver/benches/bench_layer_map.rs

@@ -13,7 +13,7 @@ use std::time::Instant;
 
 use utils::lsn::Lsn;
 
-use criterion::{black_box, criterion_group, criterion_main, Criterion};
+use criterion::{criterion_group, criterion_main, Criterion};
 
 fn build_layer_map(filename_dump: PathBuf) -> LayerMap<LayerDescriptor> {
     let mut layer_map = LayerMap::<LayerDescriptor>::default();
@@ -33,7 +33,7 @@ fn build_layer_map(filename_dump: PathBuf) -> LayerMap<LayerDescriptor> {
         min_lsn = min(min_lsn, lsn_range.start);
         max_lsn = max(max_lsn, Lsn(lsn_range.end.0 - 1));
 
-        updates.insert_historic(Arc::new(layer)).unwrap();
+        updates.insert_historic(Arc::new(layer));
     }
 
     println!("min: {min_lsn}, max: {max_lsn}");
@@ -114,7 +114,7 @@ fn bench_from_captest_env(c: &mut Criterion) {
     c.bench_function("captest_uniform_queries", |b| {
         b.iter(|| {
             for q in queries.clone().into_iter() {
-                black_box(layer_map.search(q.0, q.1));
+                layer_map.search(q.0, q.1);
             }
         });
     });
@@ -122,11 +122,11 @@ fn bench_from_captest_env(c: &mut Criterion) {
     // test with a key that corresponds to the RelDir entry. See pgdatadir_mapping.rs.
     c.bench_function("captest_rel_dir_query", |b| {
         b.iter(|| {
-            let result = black_box(layer_map.search(
+            let result = layer_map.search(
                 Key::from_hex("000000067F00008000000000000000000001").unwrap(),
                 // This LSN is higher than any of the LSNs in the tree
                 Lsn::from_str("D0/80208AE1").unwrap(),
-            ));
+            );
             result.unwrap();
         });
     });
@@ -183,7 +183,7 @@ fn bench_from_real_project(c: &mut Criterion) {
     group.bench_function("uniform_queries", |b| {
         b.iter(|| {
             for q in queries.clone().into_iter() {
-                black_box(layer_map.search(q.0, q.1));
+                layer_map.search(q.0, q.1);
             }
         });
     });
@@ -215,7 +215,7 @@ fn bench_sequential(c: &mut Criterion) {
             is_incremental: false,
             short_id: format!("Layer {}", i),
         };
-        updates.insert_historic(Arc::new(layer)).unwrap();
+        updates.insert_historic(Arc::new(layer));
     }
     updates.flush();
     println!("Finished layer map init in {:?}", now.elapsed());
@@ -232,7 +232,7 @@ fn bench_sequential(c: &mut Criterion) {
     group.bench_function("uniform_queries", |b| {
         b.iter(|| {
             for q in queries.clone().into_iter() {
-                black_box(layer_map.search(q.0, q.1));
+                layer_map.search(q.0, q.1);
             }
         });
     });

pageserver/src/config.rs

@@ -6,7 +6,6 @@
 
 use anyhow::{anyhow, bail, ensure, Context, Result};
 use remote_storage::{RemotePath, RemoteStorageConfig};
-use serde::de::IntoDeserializer;
 use std::env;
 use storage_broker::Uri;
 use utils::crashsafe::path_with_suffix_extension;
@@ -63,6 +62,7 @@ pub mod defaults {
     pub const DEFAULT_CACHED_METRIC_COLLECTION_INTERVAL: &str = "1 hour";
     pub const DEFAULT_METRIC_COLLECTION_ENDPOINT: Option<reqwest::Url> = None;
     pub const DEFAULT_SYNTHETIC_SIZE_CALCULATION_INTERVAL: &str = "10 min";
+    pub const DEFAULT_EVICTIONS_LOW_RESIDENCE_DURATION_METRIC_THRESHOLD: &str = "24 hour";
 
     ///
     /// Default built-in configuration file.
@@ -91,6 +91,7 @@ pub mod defaults {
 #cached_metric_collection_interval = '{DEFAULT_CACHED_METRIC_COLLECTION_INTERVAL}'
 #synthetic_size_calculation_interval = '{DEFAULT_SYNTHETIC_SIZE_CALCULATION_INTERVAL}'
 
+#evictions_low_residence_duration_metric_threshold = '{DEFAULT_EVICTIONS_LOW_RESIDENCE_DURATION_METRIC_THRESHOLD}'
 
 #disk_usage_based_eviction = {{ max_usage_pct = .., min_avail_bytes = .., period = "10s"}}
 
@@ -107,7 +108,6 @@ pub mod defaults {
 #pitr_interval = '{DEFAULT_PITR_INTERVAL}'
 
 #min_resident_size_override = .. # in bytes
-#evictions_low_residence_duration_metric_threshold = '{DEFAULT_EVICTIONS_LOW_RESIDENCE_DURATION_METRIC_THRESHOLD}'
 
 # [remote_storage]
 
@@ -182,6 +182,9 @@ pub struct PageServerConf {
     pub metric_collection_endpoint: Option<Url>,
     pub synthetic_size_calculation_interval: Duration,
 
+    // See the corresponding metric's help string.
+    pub evictions_low_residence_duration_metric_threshold: Duration,
+
     pub disk_usage_based_eviction: Option<DiskUsageEvictionTaskConfig>,
 
     pub test_remote_failures: u64,
@@ -254,6 +257,8 @@ struct PageServerConfigBuilder {
     metric_collection_endpoint: BuilderValue<Option<Url>>,
     synthetic_size_calculation_interval: BuilderValue<Duration>,
 
+    evictions_low_residence_duration_metric_threshold: BuilderValue<Duration>,
+
     disk_usage_based_eviction: BuilderValue<Option<DiskUsageEvictionTaskConfig>>,
 
     test_remote_failures: BuilderValue<u64>,
@@ -311,6 +316,11 @@ impl Default for PageServerConfigBuilder {
             .expect("cannot parse default synthetic size calculation interval")),
             metric_collection_endpoint: Set(DEFAULT_METRIC_COLLECTION_ENDPOINT),
 
+            evictions_low_residence_duration_metric_threshold: Set(humantime::parse_duration(
+                DEFAULT_EVICTIONS_LOW_RESIDENCE_DURATION_METRIC_THRESHOLD,
+            )
+            .expect("cannot parse DEFAULT_EVICTIONS_LOW_RESIDENCE_DURATION_METRIC_THRESHOLD")),
+
             disk_usage_based_eviction: Set(None),
 
             test_remote_failures: Set(0),
@@ -428,6 +438,10 @@ impl PageServerConfigBuilder {
         self.test_remote_failures = BuilderValue::Set(fail_first);
     }
 
+    pub fn evictions_low_residence_duration_metric_threshold(&mut self, value: Duration) {
+        self.evictions_low_residence_duration_metric_threshold = BuilderValue::Set(value);
+    }
+
     pub fn disk_usage_based_eviction(&mut self, value: Option<DiskUsageEvictionTaskConfig>) {
         self.disk_usage_based_eviction = BuilderValue::Set(value);
     }
@@ -511,6 +525,11 @@ impl PageServerConfigBuilder {
             synthetic_size_calculation_interval: self
                 .synthetic_size_calculation_interval
                 .ok_or(anyhow!("missing synthetic_size_calculation_interval"))?,
+            evictions_low_residence_duration_metric_threshold: self
+                .evictions_low_residence_duration_metric_threshold
+                .ok_or(anyhow!(
+                    "missing evictions_low_residence_duration_metric_threshold"
+                ))?,
             disk_usage_based_eviction: self
                 .disk_usage_based_eviction
                 .ok_or(anyhow!("missing disk_usage_based_eviction"))?,
@@ -702,12 +721,12 @@ impl PageServerConf {
                 "synthetic_size_calculation_interval" =>
                     builder.synthetic_size_calculation_interval(parse_toml_duration(key, item)?),
                 "test_remote_failures" => builder.test_remote_failures(parse_toml_u64(key, item)?),
+                "evictions_low_residence_duration_metric_threshold" => builder.evictions_low_residence_duration_metric_threshold(parse_toml_duration(key, item)?),
                 "disk_usage_based_eviction" => {
                     tracing::info!("disk_usage_based_eviction: {:#?}", &item);
                     builder.disk_usage_based_eviction(
-                        deserialize_from_item("disk_usage_based_eviction", item)
-                            .context("parse disk_usage_based_eviction")?
-                    )
+                    toml_edit::de::from_item(item.clone())
+                    .context("parse disk_usage_based_eviction")?)
                 },
                 "ondemand_download_behavior_treat_error_as_warn" => builder.ondemand_download_behavior_treat_error_as_warn(parse_toml_bool(key, item)?),
                 _ => bail!("unrecognized pageserver option '{key}'"),
@@ -808,25 +827,18 @@ impl PageServerConf {
 
         if let Some(eviction_policy) = item.get("eviction_policy") {
             t_conf.eviction_policy = Some(
-                deserialize_from_item("eviction_policy", eviction_policy)
+                toml_edit::de::from_item(eviction_policy.clone())
                     .context("parse eviction_policy")?,
             );
         }
 
         if let Some(item) = item.get("min_resident_size_override") {
             t_conf.min_resident_size_override = Some(
-                deserialize_from_item("min_resident_size_override", item)
+                toml_edit::de::from_item(item.clone())
                     .context("parse min_resident_size_override")?,
             );
         }
 
-        if let Some(item) = item.get("evictions_low_residence_duration_metric_threshold") {
-            t_conf.evictions_low_residence_duration_metric_threshold = Some(parse_toml_duration(
-                "evictions_low_residence_duration_metric_threshold",
-                item,
-            )?);
-        }
-
         Ok(t_conf)
     }
 
@@ -865,6 +877,10 @@ impl PageServerConf {
             cached_metric_collection_interval: Duration::from_secs(60 * 60),
             metric_collection_endpoint: defaults::DEFAULT_METRIC_COLLECTION_ENDPOINT,
             synthetic_size_calculation_interval: Duration::from_secs(60),
+            evictions_low_residence_duration_metric_threshold: humantime::parse_duration(
+                defaults::DEFAULT_EVICTIONS_LOW_RESIDENCE_DURATION_METRIC_THRESHOLD,
+            )
+            .unwrap(),
             disk_usage_based_eviction: None,
             test_remote_failures: 0,
             ondemand_download_behavior_treat_error_as_warn: false,
@@ -922,18 +938,6 @@ where
     })
 }
 
-fn deserialize_from_item<T>(name: &str, item: &Item) -> anyhow::Result<T>
-where
-    T: serde::de::DeserializeOwned,
-{
-    // ValueDeserializer::new is not public, so use the ValueDeserializer's documented way
-    let deserializer = match item.clone().into_value() {
-        Ok(value) => value.into_deserializer(),
-        Err(item) => anyhow::bail!("toml_edit::Item '{item}' is not a toml_edit::Value"),
-    };
-    T::deserialize(deserializer).with_context(|| format!("deserializing item for node {name}"))
-}
-
 /// Configurable semaphore permits setting.
 ///
 /// Does not allow semaphore permits to be zero, because at runtime initially zero permits and empty
@@ -1000,10 +1004,9 @@ mod tests {
 
     use remote_storage::{RemoteStorageKind, S3Config};
     use tempfile::{tempdir, TempDir};
-    use utils::serde_percent::Percent;
 
     use super::*;
-    use crate::{tenant::config::EvictionPolicy, DEFAULT_PG_VERSION};
+    use crate::DEFAULT_PG_VERSION;
 
     const ALL_BASE_VALUES_TOML: &str = r#"
 # Initial configuration file created by 'pageserver --init'
@@ -1026,6 +1029,8 @@ cached_metric_collection_interval = '22200 s'
 metric_collection_endpoint = 'http://localhost:80/metrics'
 synthetic_size_calculation_interval = '333 s'
 
+evictions_low_residence_duration_metric_threshold = '444 s'
+
 log_format = 'json'
 
 "#;
@@ -1082,6 +1087,9 @@ log_format = 'json'
                 synthetic_size_calculation_interval: humantime::parse_duration(
                     defaults::DEFAULT_SYNTHETIC_SIZE_CALCULATION_INTERVAL
                 )?,
+                evictions_low_residence_duration_metric_threshold: humantime::parse_duration(
+                    defaults::DEFAULT_EVICTIONS_LOW_RESIDENCE_DURATION_METRIC_THRESHOLD
+                )?,
                 disk_usage_based_eviction: None,
                 test_remote_failures: 0,
                 ondemand_download_behavior_treat_error_as_warn: false,
@@ -1136,6 +1144,7 @@ log_format = 'json'
                 cached_metric_collection_interval: Duration::from_secs(22200),
                 metric_collection_endpoint: Some(Url::parse("http://localhost:80/metrics")?),
                 synthetic_size_calculation_interval: Duration::from_secs(333),
+                evictions_low_residence_duration_metric_threshold: Duration::from_secs(444),
                 disk_usage_based_eviction: None,
                 test_remote_failures: 0,
                 ondemand_download_behavior_treat_error_as_warn: false,
@@ -1301,71 +1310,6 @@ trace_read_requests = {trace_read_requests}"#,
         Ok(())
     }
 
-    #[test]
-    fn eviction_pageserver_config_parse() -> anyhow::Result<()> {
-        let tempdir = tempdir()?;
-        let (workdir, pg_distrib_dir) = prepare_fs(&tempdir)?;
-
-        let pageserver_conf_toml = format!(
-            r#"pg_distrib_dir = "{}"
-metric_collection_endpoint = "http://sample.url"
-metric_collection_interval = "10min"
-id = 222
-
-[disk_usage_based_eviction]
-max_usage_pct = 80
-min_avail_bytes = 0
-period = "10s"
-
-[tenant_config]
-evictions_low_residence_duration_metric_threshold = "20m"
-
-[tenant_config.eviction_policy]
-kind = "LayerAccessThreshold"
-period = "20m"
-threshold = "20m"
-"#,
-            pg_distrib_dir.display(),
-        );
-        let toml: Document = pageserver_conf_toml.parse()?;
-        let conf = PageServerConf::parse_and_validate(&toml, &workdir)?;
-
-        assert_eq!(conf.pg_distrib_dir, pg_distrib_dir);
-        assert_eq!(
-            conf.metric_collection_endpoint,
-            Some("http://sample.url".parse().unwrap())
-        );
-        assert_eq!(
-            conf.metric_collection_interval,
-            Duration::from_secs(10 * 60)
-        );
-        assert_eq!(
-            conf.default_tenant_conf
-                .evictions_low_residence_duration_metric_threshold,
-            Duration::from_secs(20 * 60)
-        );
-        assert_eq!(conf.id, NodeId(222));
-        assert_eq!(
-            conf.disk_usage_based_eviction,
-            Some(DiskUsageEvictionTaskConfig {
-                max_usage_pct: Percent::new(80).unwrap(),
-                min_avail_bytes: 0,
-                period: Duration::from_secs(10),
-                #[cfg(feature = "testing")]
-                mock_statvfs: None,
-            })
-        );
-        match &conf.default_tenant_conf.eviction_policy {
-            EvictionPolicy::NoEviction => panic!("Unexpected eviction opolicy tenant settings"),
-            EvictionPolicy::LayerAccessThreshold(eviction_thresold) => {
-                assert_eq!(eviction_thresold.period, Duration::from_secs(20 * 60));
-                assert_eq!(eviction_thresold.threshold, Duration::from_secs(20 * 60));
-            }
-        }
-
-        Ok(())
-    }
-
     fn prepare_fs(tempdir: &TempDir) -> anyhow::Result<(PathBuf, PathBuf)> {
         let tempdir_path = tempdir.path();
 

pageserver/src/http/openapi_spec.yml

@@ -520,43 +520,6 @@ paths:
               schema:
                 $ref: "#/components/schemas/Error"
 
-  /v1/tenant/{tenant_id}/synthetic_size:
-    parameters:
-      - name: tenant_id
-        in: path
-        required: true
-        schema:
-          type: string
-          format: hex
-    get:
-      description: |
-        Calculate tenant's synthetic size
-      responses:
-        "200":
-          description: Tenant's synthetic size
-          content:
-            application/json:
-              schema:
-                $ref: "#/components/schemas/SyntheticSizeResponse"
-        "401":
-          description: Unauthorized Error
-          content:
-            application/json:
-              schema:
-                $ref: "#/components/schemas/UnauthorizedError"
-        "403":
-          description: Forbidden Error
-          content:
-            application/json:
-              schema:
-                $ref: "#/components/schemas/ForbiddenError"
-        "500":
-          description: Generic operation error
-          content:
-            application/json:
-              schema:
-                $ref: "#/components/schemas/Error"
-
   /v1/tenant/{tenant_id}/size:
     parameters:
       - name: tenant_id
@@ -866,9 +829,12 @@ components:
       type: object
       required:
         - id
+        - state
       properties:
         id:
           type: string
+        state:
+          type: string
         current_physical_size:
           type: integer
         has_in_progress_downloads:
@@ -985,84 +951,6 @@ components:
         latest_gc_cutoff_lsn:
           type: string
           format: hex
-
-    SyntheticSizeResponse:
-      type: object
-      required:
-        - id
-        - size
-        - segment_sizes
-        - inputs
-      properties:
-        id:
-          type: string
-          format: hex
-        size:
-          type: integer
-        segment_sizes:
-          type: array
-          items:
-            $ref: "#/components/schemas/SegmentSize"
-        inputs:
-          type: object
-          properties:
-            segments:
-              type: array
-              items:
-                $ref: "#/components/schemas/SegmentData"
-            timeline_inputs:
-              type: array
-              items:
-                $ref: "#/components/schemas/TimelineInput"
-
-    SegmentSize:
-      type: object
-      required:
-        - method
-        - accum_size
-      properties:
-        method:
-          type: string
-        accum_size:
-          type: integer
-
-    SegmentData:
-      type: object
-      required:
-        - segment
-      properties:
-        segment:
-          type: object
-          required:
-            - lsn
-          properties:
-            parent:
-              type: integer
-            lsn:
-              type: integer
-            size:
-              type: integer
-            needed:
-              type: boolean
-        timeline_id:
-          type: string
-          format: hex
-        kind:
-          type: string
-
-    TimelineInput:
-      type: object
-      required:
-        - timeline_id
-      properties:
-        ancestor_id:
-          type: string
-        ancestor_lsn:
-          type: string
-        timeline_id:
-          type: string
-          format: hex
-
     Error:
       type: object
       required:

pageserver/src/http/routes.rs

@@ -465,7 +465,7 @@ async fn tenant_list_handler(request: Request<Body>) -> Result<Response<Body>, A
         .iter()
         .map(|(id, state)| TenantInfo {
             id: *id,
-            state: state.clone(),
+            state: *state,
             current_physical_size: None,
             has_in_progress_downloads: Some(state.has_in_progress_downloads()),
         })
@@ -490,7 +490,7 @@ async fn tenant_status(request: Request<Body>) -> Result<Response<Body>, ApiErro
         let state = tenant.current_state();
         Ok(TenantInfo {
             id: tenant_id,
-            state: state.clone(),
+            state,
             current_physical_size: Some(current_physical_size),
             has_in_progress_downloads: Some(state.has_in_progress_downloads()),
         })
@@ -781,19 +781,6 @@ async fn tenant_create_handler(mut request: Request<Body>) -> Result<Response<Bo
 
     tenant_conf.min_resident_size_override = request_data.min_resident_size_override;
 
-    if let Some(evictions_low_residence_duration_metric_threshold) =
-        request_data.evictions_low_residence_duration_metric_threshold
-    {
-        tenant_conf.evictions_low_residence_duration_metric_threshold = Some(
-            humantime::parse_duration(&evictions_low_residence_duration_metric_threshold)
-                .with_context(bad_duration(
-                    "evictions_low_residence_duration_metric_threshold",
-                    &evictions_low_residence_duration_metric_threshold,
-                ))
-                .map_err(ApiError::BadRequest)?,
-        );
-    }
-
     let target_tenant_id = request_data
         .new_tenant_id
         .map(TenantId::from)
@@ -927,19 +914,6 @@ async fn update_tenant_config_handler(
 
     tenant_conf.min_resident_size_override = request_data.min_resident_size_override;
 
-    if let Some(evictions_low_residence_duration_metric_threshold) =
-        request_data.evictions_low_residence_duration_metric_threshold
-    {
-        tenant_conf.evictions_low_residence_duration_metric_threshold = Some(
-            humantime::parse_duration(&evictions_low_residence_duration_metric_threshold)
-                .with_context(bad_duration(
-                    "evictions_low_residence_duration_metric_threshold",
-                    &evictions_low_residence_duration_metric_threshold,
-                ))
-                .map_err(ApiError::BadRequest)?,
-        );
-    }
-
     let state = get_state(&request);
     mgr::set_new_tenant_config(state.conf, tenant_conf, tenant_id)
         .instrument(info_span!("tenant_config", tenant = ?tenant_id))
@@ -957,7 +931,7 @@ async fn handle_tenant_break(r: Request<Body>) -> Result<Response<Body>, ApiErro
         .await
         .map_err(|_| ApiError::Conflict(String::from("no active tenant found")))?;
 
-    tenant.set_broken("broken from test".to_owned());
+    tenant.set_broken("broken from test");
 
     json_response(StatusCode::OK, ())
 }
@@ -1201,37 +1175,6 @@ async fn handler_404(_: Request<Body>) -> Result<Response<Body>, ApiError> {
     )
 }
 
-#[cfg(feature = "testing")]
-async fn post_tracing_event_handler(mut r: Request<Body>) -> Result<Response<Body>, ApiError> {
-    #[derive(Debug, serde::Deserialize)]
-    #[serde(rename_all = "lowercase")]
-    enum Level {
-        Error,
-        Warn,
-        Info,
-        Debug,
-        Trace,
-    }
-    #[derive(Debug, serde::Deserialize)]
-    struct Request {
-        level: Level,
-        message: String,
-    }
-    let body: Request = json_request(&mut r)
-        .await
-        .map_err(|_| ApiError::BadRequest(anyhow::anyhow!("invalid JSON body")))?;
-
-    match body.level {
-        Level::Error => tracing::error!(?body.message),
-        Level::Warn => tracing::warn!(?body.message),
-        Level::Info => tracing::info!(?body.message),
-        Level::Debug => tracing::debug!(?body.message),
-        Level::Trace => tracing::trace!(?body.message),
-    }
-
-    json_response(StatusCode::OK, ())
-}
-
 pub fn make_router(
     conf: &'static PageServerConf,
     launch_ts: &'static LaunchTimestamp,
@@ -1372,9 +1315,5 @@ pub fn make_router(
             testing_api!("set tenant state to broken", handle_tenant_break),
         )
         .get("/v1/panic", |r| RequestSpan(always_panic_handler).handle(r))
-        .post(
-            "/v1/tracing/event",
-            testing_api!("emit a tracing event", post_tracing_event_handler),
-        )
         .any(handler_404))
 }

pageserver/src/metrics.rs

@@ -1,13 +1,12 @@
 use metrics::core::{AtomicU64, GenericCounter};
 use metrics::{
     register_counter_vec, register_histogram, register_histogram_vec, register_int_counter,
-    register_int_counter_vec, register_int_gauge_vec, register_uint_gauge_vec, Counter, CounterVec,
-    Histogram, HistogramVec, IntCounter, IntCounterVec, IntGauge, IntGaugeVec, UIntGauge,
-    UIntGaugeVec,
+    register_int_counter_vec, register_int_gauge, register_int_gauge_vec, register_uint_gauge_vec,
+    Counter, CounterVec, Histogram, HistogramVec, IntCounter, IntCounterVec, IntGauge, IntGaugeVec,
+    UIntGauge, UIntGaugeVec,
 };
 use once_cell::sync::Lazy;
-use pageserver_api::models::TenantState;
-use strum::VariantNames;
+use pageserver_api::models::state;
 use utils::id::{TenantId, TimelineId};
 
 /// Prometheus histogram buckets (in seconds) for operations in the critical
@@ -148,6 +147,15 @@ static CURRENT_LOGICAL_SIZE: Lazy<UIntGaugeVec> = Lazy::new(|| {
     .expect("failed to define current logical size metric")
 });
 
+// Metrics collected on tenant states.
+const TENANT_STATE_OPTIONS: &[&str] = &[
+    state::LOADING,
+    state::ATTACHING,
+    state::ACTIVE,
+    state::STOPPING,
+    state::BROKEN,
+];
+
 pub static TENANT_STATE_METRIC: Lazy<UIntGaugeVec> = Lazy::new(|| {
     register_uint_gauge_vec!(
         "pageserver_tenant_states_count",
@@ -257,22 +265,6 @@ impl EvictionsWithLowResidenceDuration {
         }
     }
 
-    pub fn change_threshold(
-        &mut self,
-        tenant_id: &str,
-        timeline_id: &str,
-        new_threshold: Duration,
-    ) {
-        if new_threshold == self.threshold {
-            return;
-        }
-        let mut with_new =
-            EvictionsWithLowResidenceDurationBuilder::new(self.data_source, new_threshold)
-                .build(tenant_id, timeline_id);
-        std::mem::swap(self, &mut with_new);
-        with_new.remove(tenant_id, timeline_id);
-    }
-
     // This could be a `Drop` impl, but, we need the `tenant_id` and `timeline_id`.
     fn remove(&mut self, tenant_id: &str, timeline_id: &str) {
         let Some(_counter) = self.counter.take() else {
@@ -350,6 +342,11 @@ pub static LIVE_CONNECTIONS_COUNT: Lazy<IntGaugeVec> = Lazy::new(|| {
     .expect("failed to define a metric")
 });
 
+pub static NUM_ONDISK_LAYERS: Lazy<IntGauge> = Lazy::new(|| {
+    register_int_gauge!("pageserver_ondisk_layers", "Number of layers on-disk")
+        .expect("failed to define a metric")
+});
+
 // remote storage metrics
 
 /// NB: increment _after_ recording the current value into [`REMOTE_TIMELINE_CLIENT_CALLS_STARTED_HIST`].
@@ -380,26 +377,6 @@ static REMOTE_TIMELINE_CLIENT_CALLS_STARTED_HIST: Lazy<HistogramVec> = Lazy::new
     .expect("failed to define a metric")
 });
 
-static REMOTE_TIMELINE_CLIENT_BYTES_STARTED_COUNTER: Lazy<IntCounterVec> = Lazy::new(|| {
-    register_int_counter_vec!(
-        "pageserver_remote_timeline_client_bytes_started",
-        "Incremented by the number of bytes associated with a remote timeline client operation. \
-         The increment happens when the operation is scheduled.",
-        &["tenant_id", "timeline_id", "file_kind", "op_kind"],
-    )
-    .expect("failed to define a metric")
-});
-
-static REMOTE_TIMELINE_CLIENT_BYTES_FINISHED_COUNTER: Lazy<IntCounterVec> = Lazy::new(|| {
-    register_int_counter_vec!(
-        "pageserver_remote_timeline_client_bytes_finished",
-        "Incremented by the number of bytes associated with a remote timeline client operation. \
-         The increment happens when the operation finishes (regardless of success/failure/shutdown).",
-        &["tenant_id", "timeline_id", "file_kind", "op_kind"],
-    )
-    .expect("failed to define a metric")
-});
-
 #[derive(Debug, Clone, Copy, PartialEq, Eq, Hash)]
 pub enum RemoteOpKind {
     Upload,
@@ -620,7 +597,7 @@ pub struct TimelineMetrics {
     pub num_persistent_files_created: IntCounter,
     pub persistent_bytes_written: IntCounter,
     pub evictions: IntCounter,
-    pub evictions_with_low_residence_duration: std::sync::RwLock<EvictionsWithLowResidenceDuration>,
+    pub evictions_with_low_residence_duration: EvictionsWithLowResidenceDuration,
 }
 
 impl TimelineMetrics {
@@ -687,9 +664,7 @@ impl TimelineMetrics {
             num_persistent_files_created,
             persistent_bytes_written,
             evictions,
-            evictions_with_low_residence_duration: std::sync::RwLock::new(
-                evictions_with_low_residence_duration,
-            ),
+            evictions_with_low_residence_duration,
         }
     }
 }
@@ -708,8 +683,6 @@ impl Drop for TimelineMetrics {
         let _ = PERSISTENT_BYTES_WRITTEN.remove_label_values(&[tenant_id, timeline_id]);
         let _ = EVICTIONS.remove_label_values(&[tenant_id, timeline_id]);
         self.evictions_with_low_residence_duration
-            .write()
-            .unwrap()
             .remove(tenant_id, timeline_id);
         for op in STORAGE_TIME_OPERATIONS {
             let _ =
@@ -734,7 +707,7 @@ impl Drop for TimelineMetrics {
 pub fn remove_tenant_metrics(tenant_id: &TenantId) {
     let tid = tenant_id.to_string();
     let _ = TENANT_SYNTHETIC_SIZE_METRIC.remove_label_values(&[&tid]);
-    for state in TenantState::VARIANTS {
+    for state in TENANT_STATE_OPTIONS {
         let _ = TENANT_STATE_METRIC.remove_label_values(&[&tid, state]);
     }
 }
@@ -754,8 +727,6 @@ pub struct RemoteTimelineClientMetrics {
     remote_operation_time: Mutex<HashMap<(&'static str, &'static str, &'static str), Histogram>>,
     calls_unfinished_gauge: Mutex<HashMap<(&'static str, &'static str), IntGauge>>,
     calls_started_hist: Mutex<HashMap<(&'static str, &'static str), Histogram>>,
-    bytes_started_counter: Mutex<HashMap<(&'static str, &'static str), IntCounter>>,
-    bytes_finished_counter: Mutex<HashMap<(&'static str, &'static str), IntCounter>>,
 }
 
 impl RemoteTimelineClientMetrics {
@@ -766,8 +737,6 @@ impl RemoteTimelineClientMetrics {
             remote_operation_time: Mutex::new(HashMap::default()),
             calls_unfinished_gauge: Mutex::new(HashMap::default()),
             calls_started_hist: Mutex::new(HashMap::default()),
-            bytes_started_counter: Mutex::new(HashMap::default()),
-            bytes_finished_counter: Mutex::new(HashMap::default()),
             remote_physical_size_gauge: Mutex::new(None),
         }
     }
@@ -806,7 +775,6 @@ impl RemoteTimelineClientMetrics {
         });
         metric.clone()
     }
-
     fn calls_unfinished_gauge(
         &self,
         file_kind: &RemoteOpFileKind,
@@ -848,125 +816,32 @@ impl RemoteTimelineClientMetrics {
         });
         metric.clone()
     }
-
-    fn bytes_started_counter(
-        &self,
-        file_kind: &RemoteOpFileKind,
-        op_kind: &RemoteOpKind,
-    ) -> IntCounter {
-        // XXX would be nice to have an upgradable RwLock
-        let mut guard = self.bytes_started_counter.lock().unwrap();
-        let key = (file_kind.as_str(), op_kind.as_str());
-        let metric = guard.entry(key).or_insert_with(move || {
-            REMOTE_TIMELINE_CLIENT_BYTES_STARTED_COUNTER
-                .get_metric_with_label_values(&[
-                    &self.tenant_id.to_string(),
-                    &self.timeline_id.to_string(),
-                    key.0,
-                    key.1,
-                ])
-                .unwrap()
-        });
-        metric.clone()
-    }
-
-    fn bytes_finished_counter(
-        &self,
-        file_kind: &RemoteOpFileKind,
-        op_kind: &RemoteOpKind,
-    ) -> IntCounter {
-        // XXX would be nice to have an upgradable RwLock
-        let mut guard = self.bytes_finished_counter.lock().unwrap();
-        let key = (file_kind.as_str(), op_kind.as_str());
-        let metric = guard.entry(key).or_insert_with(move || {
-            REMOTE_TIMELINE_CLIENT_BYTES_FINISHED_COUNTER
-                .get_metric_with_label_values(&[
-                    &self.tenant_id.to_string(),
-                    &self.timeline_id.to_string(),
-                    key.0,
-                    key.1,
-                ])
-                .unwrap()
-        });
-        metric.clone()
-    }
-}
-
-#[cfg(test)]
-impl RemoteTimelineClientMetrics {
-    pub fn get_bytes_started_counter_value(
-        &self,
-        file_kind: &RemoteOpFileKind,
-        op_kind: &RemoteOpKind,
-    ) -> Option<u64> {
-        let guard = self.bytes_started_counter.lock().unwrap();
-        let key = (file_kind.as_str(), op_kind.as_str());
-        guard.get(&key).map(|counter| counter.get())
-    }
-
-    pub fn get_bytes_finished_counter_value(
-        &self,
-        file_kind: &RemoteOpFileKind,
-        op_kind: &RemoteOpKind,
-    ) -> Option<u64> {
-        let guard = self.bytes_finished_counter.lock().unwrap();
-        let key = (file_kind.as_str(), op_kind.as_str());
-        guard.get(&key).map(|counter| counter.get())
-    }
 }
 
 /// See [`RemoteTimelineClientMetrics::call_begin`].
 #[must_use]
-pub(crate) struct RemoteTimelineClientCallMetricGuard {
-    /// Decremented on drop.
-    calls_unfinished_metric: Option<IntGauge>,
-    /// If Some(), this references the bytes_finished metric, and we increment it by the given `u64` on drop.
-    bytes_finished: Option<(IntCounter, u64)>,
-}
+pub(crate) struct RemoteTimelineClientCallMetricGuard(Option<IntGauge>);
 
 impl RemoteTimelineClientCallMetricGuard {
-    /// Consume this guard object without performing the metric updates it would do on `drop()`.
-    /// The caller vouches to do the metric updates manually.
+    /// Consume this guard object without decrementing the metric.
+    /// The caller vouches to do this manually, so that the prior increment of the gauge will cancel out.
     pub fn will_decrement_manually(mut self) {
-        let RemoteTimelineClientCallMetricGuard {
-            calls_unfinished_metric,
-            bytes_finished,
-        } = &mut self;
-        calls_unfinished_metric.take();
-        bytes_finished.take();
+        self.0 = None; // prevent drop() from decrementing
     }
 }
 
 impl Drop for RemoteTimelineClientCallMetricGuard {
     fn drop(&mut self) {
-        let RemoteTimelineClientCallMetricGuard {
-            calls_unfinished_metric,
-            bytes_finished,
-        } = self;
-        if let Some(guard) = calls_unfinished_metric.take() {
+        if let RemoteTimelineClientCallMetricGuard(Some(guard)) = self {
             guard.dec();
         }
-        if let Some((bytes_finished_metric, value)) = bytes_finished {
-            bytes_finished_metric.inc_by(*value);
-        }
     }
 }
 
-/// The enum variants communicate to the [`RemoteTimelineClientMetrics`] whether to
-/// track the byte size of this call in applicable metric(s).
-pub(crate) enum RemoteTimelineClientMetricsCallTrackSize {
-    /// Do not account for this call's byte size in any metrics.
-    /// The `reason` field is there to make the call sites self-documenting
-    /// about why they don't need the metric.
-    DontTrackSize { reason: &'static str },
-    /// Track the byte size of the call in applicable metric(s).
-    Bytes(u64),
-}
-
 impl RemoteTimelineClientMetrics {
-    /// Update the metrics that change when a call to the remote timeline client instance starts.
+    /// Increment the metrics that track ongoing calls to the remote timeline client instance.
     ///
-    /// Drop the returned guard object once the operation is finished to updates corresponding metrics that track completions.
+    /// Drop the returned guard object once the operation is finished to decrement the values.
     /// Or, use [`RemoteTimelineClientCallMetricGuard::will_decrement_manually`] and [`call_end`] if that
     /// is more suitable.
     /// Never do both.
@@ -974,51 +849,24 @@ impl RemoteTimelineClientMetrics {
         &self,
         file_kind: &RemoteOpFileKind,
         op_kind: &RemoteOpKind,
-        size: RemoteTimelineClientMetricsCallTrackSize,
     ) -> RemoteTimelineClientCallMetricGuard {
-        let calls_unfinished_metric = self.calls_unfinished_gauge(file_kind, op_kind);
+        let unfinished_metric = self.calls_unfinished_gauge(file_kind, op_kind);
         self.calls_started_hist(file_kind, op_kind)
-            .observe(calls_unfinished_metric.get() as f64);
-        calls_unfinished_metric.inc(); // NB: inc after the histogram, see comment on underlying metric
-
-        let bytes_finished = match size {
-            RemoteTimelineClientMetricsCallTrackSize::DontTrackSize { reason: _reason } => {
-                // nothing to do
-                None
-            }
-            RemoteTimelineClientMetricsCallTrackSize::Bytes(size) => {
-                self.bytes_started_counter(file_kind, op_kind).inc_by(size);
-                let finished_counter = self.bytes_finished_counter(file_kind, op_kind);
-                Some((finished_counter, size))
-            }
-        };
-        RemoteTimelineClientCallMetricGuard {
-            calls_unfinished_metric: Some(calls_unfinished_metric),
-            bytes_finished,
-        }
+            .observe(unfinished_metric.get() as f64);
+        unfinished_metric.inc();
+        RemoteTimelineClientCallMetricGuard(Some(unfinished_metric))
     }
 
-    /// Manually udpate the metrics that track completions, instead of using the guard object.
+    /// Manually decrement the metric instead of using the guard object.
     /// Using the guard object is generally preferable.
     /// See [`call_begin`] for more context.
-    pub(crate) fn call_end(
-        &self,
-        file_kind: &RemoteOpFileKind,
-        op_kind: &RemoteOpKind,
-        size: RemoteTimelineClientMetricsCallTrackSize,
-    ) {
-        let calls_unfinished_metric = self.calls_unfinished_gauge(file_kind, op_kind);
+    pub(crate) fn call_end(&self, file_kind: &RemoteOpFileKind, op_kind: &RemoteOpKind) {
+        let unfinished_metric = self.calls_unfinished_gauge(file_kind, op_kind);
         debug_assert!(
-            calls_unfinished_metric.get() > 0,
+            unfinished_metric.get() > 0,
             "begin and end should cancel out"
         );
-        calls_unfinished_metric.dec();
-        match size {
-            RemoteTimelineClientMetricsCallTrackSize::DontTrackSize { reason: _reason } => {}
-            RemoteTimelineClientMetricsCallTrackSize::Bytes(size) => {
-                self.bytes_finished_counter(file_kind, op_kind).inc_by(size);
-            }
-        }
+        unfinished_metric.dec();
     }
 }
 
@@ -1031,8 +879,6 @@ impl Drop for RemoteTimelineClientMetrics {
             remote_operation_time,
             calls_unfinished_gauge,
             calls_started_hist,
-            bytes_started_counter,
-            bytes_finished_counter,
         } = self;
         for ((a, b, c), _) in remote_operation_time.get_mut().unwrap().drain() {
             let _ = REMOTE_OPERATION_TIME.remove_label_values(&[tenant_id, timeline_id, a, b, c]);
@@ -1053,22 +899,6 @@ impl Drop for RemoteTimelineClientMetrics {
                 b,
             ]);
         }
-        for ((a, b), _) in bytes_started_counter.get_mut().unwrap().drain() {
-            let _ = REMOTE_TIMELINE_CLIENT_BYTES_STARTED_COUNTER.remove_label_values(&[
-                tenant_id,
-                timeline_id,
-                a,
-                b,
-            ]);
-        }
-        for ((a, b), _) in bytes_finished_counter.get_mut().unwrap().drain() {
-            let _ = REMOTE_TIMELINE_CLIENT_BYTES_FINISHED_COUNTER.remove_label_values(&[
-                tenant_id,
-                timeline_id,
-                a,
-                b,
-            ]);
-        }
         {
             let _ = remote_physical_size_gauge; // use to avoid 'unused' warning in desctructuring above
             let _ = REMOTE_PHYSICAL_SIZE.remove_label_values(&[tenant_id, timeline_id]);

pageserver/src/page_service.rs

@@ -65,7 +65,7 @@ fn copyin_stream(pgb: &mut PostgresBackendTCP) -> impl Stream<Item = io::Result<
 
                 _ = task_mgr::shutdown_watcher() => {
                     // We were requested to shut down.
-                    let msg = "pageserver is shutting down".to_string();
+                    let msg = format!("pageserver is shutting down");
                     let _ = pgb.write_message_noflush(&BeMessage::ErrorResponse(&msg, None));
                     Err(QueryError::Other(anyhow::anyhow!(msg)))
                 }
@@ -700,8 +700,6 @@ impl PageServerHandler {
         full_backup: bool,
         ctx: RequestContext,
     ) -> anyhow::Result<()> {
-        let started = std::time::Instant::now();
-
         // check that the timeline exists
         let timeline = get_active_tenant_timeline(tenant_id, timeline_id, &ctx).await?;
         let latest_gc_cutoff_lsn = timeline.get_latest_gc_cutoff_lsn();
@@ -714,8 +712,6 @@ impl PageServerHandler {
                 .context("invalid basebackup lsn")?;
         }
 
-        let lsn_awaited_after = started.elapsed();
-
         // switch client to COPYOUT
         pgb.write_message_noflush(&BeMessage::CopyOutResponse)?;
         pgb.flush().await?;
@@ -736,17 +732,7 @@ impl PageServerHandler {
 
         pgb.write_message_noflush(&BeMessage::CopyDone)?;
         pgb.flush().await?;
-
-        let basebackup_after = started
-            .elapsed()
-            .checked_sub(lsn_awaited_after)
-            .unwrap_or(Duration::ZERO);
-
-        info!(
-            lsn_await_millis = lsn_awaited_after.as_millis(),
-            basebackup_millis = basebackup_after.as_millis(),
-            "basebackup complete"
-        );
+        info!("basebackup complete");
 
         Ok(())
     }

pageserver/src/tenant.rs

@@ -118,10 +118,6 @@ pub struct Tenant {
     // Global pageserver config parameters
     pub conf: &'static PageServerConf,
 
-    /// The value creation timestamp, used to measure activation delay, see:
-    /// <https://github.com/neondatabase/neon/issues/4025>
-    loading_started_at: Instant,
-
     state: watch::Sender<TenantState>,
 
     // Overridden tenant-specific config parameters.
@@ -271,10 +267,7 @@ impl UninitializedTimeline<'_> {
             .await
             .context("Failed to flush after basebackup import")?;
 
-        // Initialize without loading the layer map. We started with an empty layer map, and already
-        // updated it for the layers that we created during the import.
-        let mut timelines = self.owning_tenant.timelines.lock().unwrap();
-        self.initialize_with_lock(ctx, &mut timelines, false, true)
+        self.initialize(ctx)
     }
 
     fn raw_timeline(&self) -> anyhow::Result<&Arc<Timeline>> {
@@ -626,7 +619,7 @@ impl Tenant {
                 match tenant_clone.attach(ctx).await {
                     Ok(_) => {}
                     Err(e) => {
-                        tenant_clone.set_broken(e.to_string());
+                        tenant_clone.set_broken(&e.to_string());
                         error!("error attaching tenant: {:?}", e);
                     }
                 }
@@ -834,10 +827,7 @@ impl Tenant {
     pub fn create_broken_tenant(conf: &'static PageServerConf, tenant_id: TenantId) -> Arc<Tenant> {
         let wal_redo_manager = Arc::new(PostgresRedoManager::new(conf, tenant_id));
         Arc::new(Tenant::new(
-            TenantState::Broken {
-                reason: "create_broken_tenant".into(),
-                backtrace: String::new(),
-            },
+            TenantState::Broken,
             conf,
             TenantConfOpt::default(),
             wal_redo_manager,
@@ -898,7 +888,7 @@ impl Tenant {
                 match tenant_clone.load(&ctx).await {
                     Ok(()) => {}
                     Err(err) => {
-                        tenant_clone.set_broken(err.to_string());
+                        tenant_clone.set_broken(&err.to_string());
                         error!("could not load tenant {tenant_id}: {err:?}");
                     }
                 }
@@ -1450,7 +1440,7 @@ impl Tenant {
     }
 
     pub fn current_state(&self) -> TenantState {
-        self.state.borrow().clone()
+        *self.state.borrow()
     }
 
     pub fn is_active(&self) -> bool {
@@ -1461,15 +1451,15 @@ impl Tenant {
     fn activate(&self, ctx: &RequestContext) -> anyhow::Result<()> {
         let mut result = Ok(());
         self.state.send_modify(|current_state| {
-            match &*current_state {
+            match *current_state {
                 TenantState::Active => {
                     // activate() was called on an already Active tenant. Shouldn't happen.
                     result = Err(anyhow::anyhow!("Tenant is already active"));
                 }
-                TenantState::Broken { reason, .. } => {
+                TenantState::Broken => {
                     // This shouldn't happen either
                     result = Err(anyhow::anyhow!(
-                        "Could not activate tenant because it is in broken state due to: {reason}",
+                        "Could not activate tenant because it is in broken state"
                     ));
                 }
                 TenantState::Stopping => {
@@ -1480,7 +1470,7 @@ impl Tenant {
                 TenantState::Loading | TenantState::Attaching => {
                     *current_state = TenantState::Active;
 
-                    debug!(tenant_id = %self.tenant_id, "Activating tenant");
+                    info!("Activating tenant {}", self.tenant_id);
 
                     let timelines_accessor = self.timelines.lock().unwrap();
                     let not_broken_timelines = timelines_accessor
@@ -1491,47 +1481,22 @@ impl Tenant {
                     // down when they notice that the tenant is inactive.
                     tasks::start_background_loops(self.tenant_id);
 
-                    let mut activated_timelines = 0;
-                    let mut timelines_broken_during_activation = 0;
-
                     for timeline in not_broken_timelines {
                         match timeline
                             .activate(ctx)
                             .context("timeline activation for activating tenant")
                         {
-                            Ok(()) => {
-                                activated_timelines += 1;
-                            }
+                            Ok(()) => {}
                             Err(e) => {
                                 error!(
                                     "Failed to activate timeline {}: {:#}",
                                     timeline.timeline_id, e
                                 );
                                 timeline.set_state(TimelineState::Broken);
-                                *current_state = TenantState::broken_from_reason(format!(
-                                    "failed to activate timeline {}: {}",
-                                    timeline.timeline_id, e
-                                ));
-
-                                timelines_broken_during_activation += 1;
+                                *current_state = TenantState::Broken;
                             }
                         }
                     }
-
-                    let elapsed = self.loading_started_at.elapsed();
-                    let total_timelines = timelines_accessor.len();
-
-                    // log a lot of stuff, because some tenants sometimes suffer from user-visible
-                    // times to activate. see https://github.com/neondatabase/neon/issues/4025
-                    info!(
-                        since_creation_millis = elapsed.as_millis(),
-                        tenant_id = %self.tenant_id,
-                        activated_timelines,
-                        timelines_broken_during_activation,
-                        total_timelines,
-                        post_state = <&'static str>::from(&*current_state),
-                        "activation attempt finished"
-                    );
                 }
             }
         });
@@ -1541,7 +1506,7 @@ impl Tenant {
     /// Change tenant status to Stopping, to mark that it is being shut down
     pub fn set_stopping(&self) {
         self.state.send_modify(|current_state| {
-            match current_state {
+            match *current_state {
                 TenantState::Active | TenantState::Loading | TenantState::Attaching => {
                     *current_state = TenantState::Stopping;
 
@@ -1557,8 +1522,8 @@ impl Tenant {
                         timeline.set_state(TimelineState::Stopping);
                     }
                 }
-                TenantState::Broken { reason, .. } => {
-                    info!("Cannot set tenant to Stopping state, it is in Broken state due to: {reason}");
+                TenantState::Broken => {
+                    info!("Cannot set tenant to Stopping state, it is already in Broken state");
                 }
                 TenantState::Stopping => {
                     // The tenant was detached, or system shutdown was requested, while we were
@@ -1569,7 +1534,7 @@ impl Tenant {
         });
     }
 
-    pub fn set_broken(&self, reason: String) {
+    pub fn set_broken(&self, reason: &str) {
         self.state.send_modify(|current_state| {
             match *current_state {
                 TenantState::Active => {
@@ -1577,24 +1542,24 @@ impl Tenant {
                     // while loading or attaching a tenant. A tenant that has already been
                     // activated should never be marked as broken. We cope with it the best
                     // we can, but it shouldn't happen.
+                    *current_state = TenantState::Broken;
                     warn!("Changing Active tenant to Broken state, reason: {}", reason);
-                    *current_state = TenantState::broken_from_reason(reason);
                 }
-                TenantState::Broken { .. } => {
+                TenantState::Broken => {
                     // This shouldn't happen either
                     warn!("Tenant is already in Broken state");
                 }
                 TenantState::Stopping => {
                     // This shouldn't happen either
+                    *current_state = TenantState::Broken;
                     warn!(
                         "Marking Stopping tenant as Broken state, reason: {}",
                         reason
                     );
-                    *current_state = TenantState::broken_from_reason(reason);
                 }
                 TenantState::Loading | TenantState::Attaching => {
                     info!("Setting tenant as Broken state, reason: {}", reason);
-                    *current_state = TenantState::broken_from_reason(reason);
+                    *current_state = TenantState::Broken;
                 }
             }
         });
@@ -1607,7 +1572,7 @@ impl Tenant {
     pub async fn wait_to_become_active(&self) -> anyhow::Result<()> {
         let mut receiver = self.state.subscribe();
         loop {
-            let current_state = receiver.borrow_and_update().clone();
+            let current_state = *receiver.borrow_and_update();
             match current_state {
                 TenantState::Loading | TenantState::Attaching => {
                     // in these states, there's a chance that we can reach ::Active
@@ -1616,12 +1581,12 @@ impl Tenant {
                 TenantState::Active { .. } => {
                     return Ok(());
                 }
-                TenantState::Broken { .. } | TenantState::Stopping => {
+                TenantState::Broken | TenantState::Stopping => {
                     // There's no chance the tenant can transition back into ::Active
                     anyhow::bail!(
                         "Tenant {} will not become active. Current state: {:?}",
                         self.tenant_id,
-                        &current_state,
+                        current_state,
                     );
                 }
             }
@@ -1761,13 +1726,6 @@ impl Tenant {
 
     pub fn set_new_tenant_config(&self, new_tenant_conf: TenantConfOpt) {
         *self.tenant_conf.write().unwrap() = new_tenant_conf;
-        // Don't hold self.timelines.lock() during the notifies.
-        // There's no risk of deadlock right now, but there could be if we consolidate
-        // mutexes in struct Timeline in the future.
-        let timelines = self.list_timelines();
-        for timeline in timelines {
-            timeline.tenant_conf_updated();
-        }
     }
 
     fn create_timeline_data(
@@ -1809,23 +1767,21 @@ impl Tenant {
         let (state, mut rx) = watch::channel(state);
 
         tokio::spawn(async move {
-            let mut current_state: &'static str = From::from(&*rx.borrow_and_update());
+            let current_state = *rx.borrow_and_update();
             let tid = tenant_id.to_string();
             TENANT_STATE_METRIC
-                .with_label_values(&[&tid, current_state])
+                .with_label_values(&[&tid, current_state.as_str()])
                 .inc();
             loop {
                 match rx.changed().await {
                     Ok(()) => {
-                        let new_state: &'static str = From::from(&*rx.borrow_and_update());
+                        let new_state = *rx.borrow();
                         TENANT_STATE_METRIC
-                            .with_label_values(&[&tid, current_state])
+                            .with_label_values(&[&tid, current_state.as_str()])
                             .dec();
                         TENANT_STATE_METRIC
-                            .with_label_values(&[&tid, new_state])
+                            .with_label_values(&[&tid, new_state.as_str()])
                             .inc();
-
-                        current_state = new_state;
                     }
                     Err(_sender_dropped_error) => {
                         info!("Tenant dropped the state updates sender, quitting waiting for tenant state change");
@@ -1838,9 +1794,6 @@ impl Tenant {
         Tenant {
             tenant_id,
             conf,
-            // using now here is good enough approximation to catch tenants with really long
-            // activation times.
-            loading_started_at: Instant::now(),
             tenant_conf: Arc::new(RwLock::new(tenant_conf)),
             timelines: Mutex::new(HashMap::new()),
             gc_cs: tokio::sync::Mutex::new(()),
@@ -1923,7 +1876,7 @@ impl Tenant {
             .to_string();
 
             // Convert the config to a toml file.
-            conf_content += &toml_edit::ser::to_string(&tenant_conf)?;
+            conf_content += &toml_edit::easy::to_string(&tenant_conf)?;
 
             let mut target_config_file = VirtualFile::open_with_options(
                 target_config_path,
@@ -2355,8 +2308,6 @@ impl Tenant {
                 )
             })?;
 
-        // Initialize the timeline without loading the layer map, because we already updated the layer
-        // map above, when we imported the datadir.
         let timeline = {
             let mut timelines = self.timelines.lock().unwrap();
             raw_timeline.initialize_with_lock(ctx, &mut timelines, false, true)?
@@ -2851,9 +2802,6 @@ pub mod harness {
                 trace_read_requests: Some(tenant_conf.trace_read_requests),
                 eviction_policy: Some(tenant_conf.eviction_policy),
                 min_resident_size_override: tenant_conf.min_resident_size_override,
-                evictions_low_residence_duration_metric_threshold: Some(
-                    tenant_conf.evictions_low_residence_duration_metric_threshold,
-                ),
             }
         }
     }

pageserver/src/tenant/config.rs

@@ -39,7 +39,6 @@ pub mod defaults {
     pub const DEFAULT_WALRECEIVER_CONNECT_TIMEOUT: &str = "2 seconds";
     pub const DEFAULT_WALRECEIVER_LAGGING_WAL_TIMEOUT: &str = "3 seconds";
     pub const DEFAULT_MAX_WALRECEIVER_LSN_WAL_LAG: u64 = 10 * 1024 * 1024;
-    pub const DEFAULT_EVICTIONS_LOW_RESIDENCE_DURATION_METRIC_THRESHOLD: &str = "24 hour";
 }
 
 /// Per-tenant configuration options
@@ -94,9 +93,6 @@ pub struct TenantConf {
     pub trace_read_requests: bool,
     pub eviction_policy: EvictionPolicy,
     pub min_resident_size_override: Option<u64>,
-    // See the corresponding metric's help string.
-    #[serde(with = "humantime_serde")]
-    pub evictions_low_residence_duration_metric_threshold: Duration,
 }
 
 /// Same as TenantConf, but this struct preserves the information about
@@ -168,11 +164,6 @@ pub struct TenantConfOpt {
     #[serde(skip_serializing_if = "Option::is_none")]
     #[serde(default)]
     pub min_resident_size_override: Option<u64>,
-
-    #[serde(skip_serializing_if = "Option::is_none")]
-    #[serde(with = "humantime_serde")]
-    #[serde(default)]
-    pub evictions_low_residence_duration_metric_threshold: Option<Duration>,
 }
 
 #[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
@@ -237,9 +228,6 @@ impl TenantConfOpt {
             min_resident_size_override: self
                 .min_resident_size_override
                 .or(global_conf.min_resident_size_override),
-            evictions_low_residence_duration_metric_threshold: self
-                .evictions_low_residence_duration_metric_threshold
-                .unwrap_or(global_conf.evictions_low_residence_duration_metric_threshold),
         }
     }
 }
@@ -272,10 +260,6 @@ impl Default for TenantConf {
             trace_read_requests: false,
             eviction_policy: EvictionPolicy::NoEviction,
             min_resident_size_override: None,
-            evictions_low_residence_duration_metric_threshold: humantime::parse_duration(
-                DEFAULT_EVICTIONS_LOW_RESIDENCE_DURATION_METRIC_THRESHOLD,
-            )
-            .expect("cannot parse default evictions_low_residence_duration_metric_threshold"),
         }
     }
 }
@@ -291,9 +275,9 @@ mod tests {
             ..TenantConfOpt::default()
         };
 
-        let toml_form = toml_edit::ser::to_string(&small_conf).unwrap();
+        let toml_form = toml_edit::easy::to_string(&small_conf).unwrap();
         assert_eq!(toml_form, "gc_horizon = 42\n");
-        assert_eq!(small_conf, toml_edit::de::from_str(&toml_form).unwrap());
+        assert_eq!(small_conf, toml_edit::easy::from_str(&toml_form).unwrap());
 
         let json_form = serde_json::to_string(&small_conf).unwrap();
         assert_eq!(json_form, "{\"gc_horizon\":42}");

pageserver/src/tenant/layer_map.rs

@@ -48,14 +48,14 @@ mod layer_coverage;
 
 use crate::context::RequestContext;
 use crate::keyspace::KeyPartitioning;
+use crate::metrics::NUM_ONDISK_LAYERS;
 use crate::repository::Key;
 use crate::tenant::storage_layer::InMemoryLayer;
 use crate::tenant::storage_layer::Layer;
-use anyhow::{bail, Result};
+use anyhow::Result;
 use std::collections::VecDeque;
 use std::ops::Range;
 use std::sync::Arc;
-use tracing::*;
 use utils::lsn::Lsn;
 
 use historic_layer_coverage::BufferedHistoricLayerCoverage;
@@ -126,7 +126,7 @@ where
     ///
     /// Insert an on-disk layer.
     ///
-    pub fn insert_historic(&mut self, layer: Arc<L>) -> anyhow::Result<()> {
+    pub fn insert_historic(&mut self, layer: Arc<L>) {
         self.layer_map.insert_historic_noflush(layer)
     }
 
@@ -274,27 +274,17 @@ where
     ///
     /// Helper function for BatchedUpdates::insert_historic
     ///
-    pub(self) fn insert_historic_noflush(&mut self, layer: Arc<L>) -> anyhow::Result<()> {
-        let key = historic_layer_coverage::LayerKey::from(&*layer);
-        match self.historic.replace(&key, Arc::clone(&layer), |existing| {
-            !Self::compare_arced_layers(existing, &layer)
-        }) {
-            Replacement::Replaced { .. } => {
-                if Self::is_l0(&layer) {
-                    bail!("Duplicate L0 layer {}", layer.short_id());
-                }
-                warn!("Replace duplicate layer {} in layer map", layer.short_id());
-            }
-            Replacement::Unexpected(_) => bail!("Replace layer with itself is prohibited"),
-            Replacement::NotFound | Replacement::RemovalBuffered => {
-                self.historic.insert(key, Arc::clone(&layer));
+    pub(self) fn insert_historic_noflush(&mut self, layer: Arc<L>) {
+        self.historic.insert(
+            historic_layer_coverage::LayerKey::from(&*layer),
+            Arc::clone(&layer),
+        );
 
-                if Self::is_l0(&layer) {
-                    self.l0_delta_layers.push(layer);
-                }
-            }
+        if Self::is_l0(&layer) {
+            self.l0_delta_layers.push(layer);
         }
-        Ok(())
+
+        NUM_ONDISK_LAYERS.inc();
     }
 
     ///
@@ -319,6 +309,8 @@ where
                 "failed to locate removed historic layer from l0_delta_layers"
             );
         }
+
+        NUM_ONDISK_LAYERS.dec();
     }
 
     pub(self) fn replace_historic_noflush(
@@ -846,7 +838,7 @@ mod tests {
 
             let expected_in_counts = (1, usize::from(expected_l0));
 
-            map.batch_update().insert_historic(remote.clone()).unwrap();
+            map.batch_update().insert_historic(remote.clone());
             assert_eq!(count_layer_in(&map, &remote), expected_in_counts);
 
             let replaced = map

pageserver/src/tenant/mgr.rs

@@ -537,7 +537,7 @@ where
             Some(tenant) => match tenant.current_state() {
                 TenantState::Attaching
                 | TenantState::Loading
-                | TenantState::Broken { .. }
+                | TenantState::Broken
                 | TenantState::Active => tenant.set_stopping(),
                 TenantState::Stopping => return Err(TenantStateError::IsStopping(tenant_id)),
             },
@@ -565,7 +565,7 @@ where
             let tenants_accessor = TENANTS.read().await;
             match tenants_accessor.get(&tenant_id) {
                 Some(tenant) => {
-                    tenant.set_broken(e.to_string());
+                    tenant.set_broken(&e.to_string());
                 }
                 None => {
                     warn!("Tenant {tenant_id} got removed from memory");

pageserver/src/tenant/remote_timeline_client.rs

@@ -219,8 +219,7 @@ use utils::lsn::Lsn;
 
 use crate::metrics::{
     MeasureRemoteOp, RemoteOpFileKind, RemoteOpKind, RemoteTimelineClientMetrics,
-    RemoteTimelineClientMetricsCallTrackSize, REMOTE_ONDEMAND_DOWNLOADED_BYTES,
-    REMOTE_ONDEMAND_DOWNLOADED_LAYERS,
+    REMOTE_ONDEMAND_DOWNLOADED_BYTES, REMOTE_ONDEMAND_DOWNLOADED_LAYERS,
 };
 use crate::tenant::remote_timeline_client::index::LayerFileMetadata;
 use crate::{
@@ -368,13 +367,9 @@ impl RemoteTimelineClient {
 
     /// Download index file
     pub async fn download_index_file(&self) -> Result<IndexPart, DownloadError> {
-        let _unfinished_gauge_guard = self.metrics.call_begin(
-            &RemoteOpFileKind::Index,
-            &RemoteOpKind::Download,
-            crate::metrics::RemoteTimelineClientMetricsCallTrackSize::DontTrackSize {
-                reason: "no need for a downloads gauge",
-            },
-        );
+        let _unfinished_gauge_guard = self
+            .metrics
+            .call_begin(&RemoteOpFileKind::Index, &RemoteOpKind::Download);
 
         download::download_index_part(
             self.conf,
@@ -403,13 +398,9 @@ impl RemoteTimelineClient {
         layer_metadata: &LayerFileMetadata,
     ) -> anyhow::Result<u64> {
         let downloaded_size = {
-            let _unfinished_gauge_guard = self.metrics.call_begin(
-                &RemoteOpFileKind::Layer,
-                &RemoteOpKind::Download,
-                crate::metrics::RemoteTimelineClientMetricsCallTrackSize::DontTrackSize {
-                    reason: "no need for a downloads gauge",
-                },
-            );
+            let _unfinished_gauge_guard = self
+                .metrics
+                .call_begin(&RemoteOpFileKind::Layer, &RemoteOpKind::Download);
             download::download_layer_file(
                 self.conf,
                 &self.storage_impl,
@@ -895,32 +886,11 @@ impl RemoteTimelineClient {
     fn calls_unfinished_metric_impl(
         &self,
         op: &UploadOp,
-    ) -> Option<(
-        RemoteOpFileKind,
-        RemoteOpKind,
-        RemoteTimelineClientMetricsCallTrackSize,
-    )> {
-        use RemoteTimelineClientMetricsCallTrackSize::DontTrackSize;
+    ) -> Option<(RemoteOpFileKind, RemoteOpKind)> {
         let res = match op {
-            UploadOp::UploadLayer(_, m) => (
-                RemoteOpFileKind::Layer,
-                RemoteOpKind::Upload,
-                RemoteTimelineClientMetricsCallTrackSize::Bytes(m.file_size()),
-            ),
-            UploadOp::UploadMetadata(_, _) => (
-                RemoteOpFileKind::Index,
-                RemoteOpKind::Upload,
-                DontTrackSize {
-                    reason: "metadata uploads are tiny",
-                },
-            ),
-            UploadOp::Delete(file_kind, _) => (
-                *file_kind,
-                RemoteOpKind::Delete,
-                DontTrackSize {
-                    reason: "should we track deletes? positive or negative sign?",
-                },
-            ),
+            UploadOp::UploadLayer(_, _) => (RemoteOpFileKind::Layer, RemoteOpKind::Upload),
+            UploadOp::UploadMetadata(_, _) => (RemoteOpFileKind::Index, RemoteOpKind::Upload),
+            UploadOp::Delete(file_kind, _) => (*file_kind, RemoteOpKind::Delete),
             UploadOp::Barrier(_) => {
                 // we do not account these
                 return None;
@@ -930,20 +900,20 @@ impl RemoteTimelineClient {
     }
 
     fn calls_unfinished_metric_begin(&self, op: &UploadOp) {
-        let (file_kind, op_kind, track_bytes) = match self.calls_unfinished_metric_impl(op) {
+        let (file_kind, op_kind) = match self.calls_unfinished_metric_impl(op) {
             Some(x) => x,
             None => return,
         };
-        let guard = self.metrics.call_begin(&file_kind, &op_kind, track_bytes);
+        let guard = self.metrics.call_begin(&file_kind, &op_kind);
         guard.will_decrement_manually(); // in unfinished_ops_metric_end()
     }
 
     fn calls_unfinished_metric_end(&self, op: &UploadOp) {
-        let (file_kind, op_kind, track_bytes) = match self.calls_unfinished_metric_impl(op) {
+        let (file_kind, op_kind) = match self.calls_unfinished_metric_impl(op) {
             Some(x) => x,
             None => return,
         };
-        self.metrics.call_end(&file_kind, &op_kind, track_bytes);
+        self.metrics.call_end(&file_kind, &op_kind);
     }
 
     fn stop(&self) {
@@ -1011,19 +981,11 @@ impl RemoteTimelineClient {
 mod tests {
     use super::*;
     use crate::{
-        context::RequestContext,
-        tenant::{
-            harness::{TenantHarness, TIMELINE_ID},
-            Tenant,
-        },
+        tenant::harness::{TenantHarness, TIMELINE_ID},
         DEFAULT_PG_VERSION,
     };
     use remote_storage::{RemoteStorageConfig, RemoteStorageKind};
-    use std::{
-        collections::HashSet,
-        path::{Path, PathBuf},
-    };
-    use tokio::runtime::EnterGuard;
+    use std::{collections::HashSet, path::Path};
     use utils::lsn::Lsn;
 
     pub(super) fn dummy_contents(name: &str) -> Vec<u8> {
@@ -1072,80 +1034,39 @@ mod tests {
         assert_eq!(found, expected);
     }
 
-    struct TestSetup {
-        runtime: &'static tokio::runtime::Runtime,
-        entered_runtime: EnterGuard<'static>,
-        harness: TenantHarness<'static>,
-        tenant: Arc<Tenant>,
-        tenant_ctx: RequestContext,
-        remote_fs_dir: PathBuf,
-        client: Arc<RemoteTimelineClient>,
-    }
-
-    impl TestSetup {
-        fn new(test_name: &str) -> anyhow::Result<Self> {
-            // Use a current-thread runtime in the test
-            let runtime = Box::leak(Box::new(
-                tokio::runtime::Builder::new_current_thread()
-                    .enable_all()
-                    .build()?,
-            ));
-            let entered_runtime = runtime.enter();
-
-            let test_name = Box::leak(Box::new(format!("remote_timeline_client__{test_name}")));
-            let harness = TenantHarness::create(test_name)?;
-            let (tenant, ctx) = runtime.block_on(harness.load());
-            // create an empty timeline directory
-            let timeline =
-                tenant.create_empty_timeline(TIMELINE_ID, Lsn(0), DEFAULT_PG_VERSION, &ctx)?;
-            let _ = timeline.initialize(&ctx).unwrap();
-
-            let remote_fs_dir = harness.conf.workdir.join("remote_fs");
-            std::fs::create_dir_all(remote_fs_dir)?;
-            let remote_fs_dir = std::fs::canonicalize(harness.conf.workdir.join("remote_fs"))?;
-
-            let storage_config = RemoteStorageConfig {
-                max_concurrent_syncs: std::num::NonZeroUsize::new(
-                    remote_storage::DEFAULT_REMOTE_STORAGE_MAX_CONCURRENT_SYNCS,
-                )
-                .unwrap(),
-                max_sync_errors: std::num::NonZeroU32::new(
-                    remote_storage::DEFAULT_REMOTE_STORAGE_MAX_SYNC_ERRORS,
-                )
-                .unwrap(),
-                storage: RemoteStorageKind::LocalFs(remote_fs_dir.clone()),
-            };
-
-            let storage = GenericRemoteStorage::from_config(&storage_config).unwrap();
-
-            let client = Arc::new(RemoteTimelineClient {
-                conf: harness.conf,
-                runtime,
-                tenant_id: harness.tenant_id,
-                timeline_id: TIMELINE_ID,
-                storage_impl: storage,
-                upload_queue: Mutex::new(UploadQueue::Uninitialized),
-                metrics: Arc::new(RemoteTimelineClientMetrics::new(
-                    &harness.tenant_id,
-                    &TIMELINE_ID,
-                )),
-            });
-
-            Ok(Self {
-                runtime,
-                entered_runtime,
-                harness,
-                tenant,
-                tenant_ctx: ctx,
-                remote_fs_dir,
-                client,
-            })
-        }
-    }
-
     // Test scheduling
     #[test]
     fn upload_scheduling() -> anyhow::Result<()> {
+        // Use a current-thread runtime in the test
+        let runtime = Box::leak(Box::new(
+            tokio::runtime::Builder::new_current_thread()
+                .enable_all()
+                .build()?,
+        ));
+        let _entered = runtime.enter();
+
+        let harness = TenantHarness::create("upload_scheduling")?;
+        let (tenant, ctx) = runtime.block_on(harness.load());
+        let _timeline =
+            tenant.create_empty_timeline(TIMELINE_ID, Lsn(0), DEFAULT_PG_VERSION, &ctx)?;
+        let timeline_path = harness.timeline_path(&TIMELINE_ID);
+
+        let remote_fs_dir = harness.conf.workdir.join("remote_fs");
+        std::fs::create_dir_all(remote_fs_dir)?;
+        let remote_fs_dir = std::fs::canonicalize(harness.conf.workdir.join("remote_fs"))?;
+
+        let storage_config = RemoteStorageConfig {
+            max_concurrent_syncs: std::num::NonZeroUsize::new(
+                remote_storage::DEFAULT_REMOTE_STORAGE_MAX_CONCURRENT_SYNCS,
+            )
+            .unwrap(),
+            max_sync_errors: std::num::NonZeroU32::new(
+                remote_storage::DEFAULT_REMOTE_STORAGE_MAX_SYNC_ERRORS,
+            )
+            .unwrap(),
+            storage: RemoteStorageKind::LocalFs(remote_fs_dir.clone()),
+        };
+
         // Test outline:
         //
         // Schedule upload of a bunch of layers. Check that they are started immediately, not queued
@@ -1160,20 +1081,22 @@ mod tests {
         // Schedule another deletion. Check that it's launched immediately.
         // Schedule index upload. Check that it's queued
 
-        let TestSetup {
-            runtime,
-            entered_runtime: _entered_runtime,
-            harness,
-            tenant: _tenant,
-            tenant_ctx: _tenant_ctx,
-            remote_fs_dir,
-            client,
-        } = TestSetup::new("upload_scheduling").unwrap();
-
-        let timeline_path = harness.timeline_path(&TIMELINE_ID);
-
         println!("workdir: {}", harness.conf.workdir.display());
 
+        let storage_impl = GenericRemoteStorage::from_config(&storage_config)?;
+        let client = Arc::new(RemoteTimelineClient {
+            conf: harness.conf,
+            runtime,
+            tenant_id: harness.tenant_id,
+            timeline_id: TIMELINE_ID,
+            storage_impl,
+            upload_queue: Mutex::new(UploadQueue::Uninitialized),
+            metrics: Arc::new(RemoteTimelineClientMetrics::new(
+                &harness.tenant_id,
+                &TIMELINE_ID,
+            )),
+        });
+
         let remote_timeline_dir =
             remote_fs_dir.join(timeline_path.strip_prefix(&harness.conf.workdir)?);
         println!("remote_timeline_dir: {}", remote_timeline_dir.display());
@@ -1293,90 +1216,4 @@ mod tests {
 
         Ok(())
     }
-
-    #[test]
-    fn bytes_unfinished_gauge_for_layer_file_uploads() -> anyhow::Result<()> {
-        // Setup
-
-        let TestSetup {
-            runtime,
-            harness,
-            client,
-            ..
-        } = TestSetup::new("metrics")?;
-
-        let metadata = dummy_metadata(Lsn(0x10));
-        client.init_upload_queue_for_empty_remote(&metadata)?;
-
-        let timeline_path = harness.timeline_path(&TIMELINE_ID);
-
-        let layer_file_name_1: LayerFileName = "000000000000000000000000000000000000-FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF__00000000016B59D8-00000000016B5A51".parse().unwrap();
-        let content_1 = dummy_contents("foo");
-        std::fs::write(
-            timeline_path.join(layer_file_name_1.file_name()),
-            &content_1,
-        )?;
-
-        #[derive(Debug, PartialEq)]
-        struct BytesStartedFinished {
-            started: Option<usize>,
-            finished: Option<usize>,
-        }
-        let get_bytes_started_stopped = || {
-            let started = client
-                .metrics
-                .get_bytes_started_counter_value(&RemoteOpFileKind::Layer, &RemoteOpKind::Upload)
-                .map(|v| v.try_into().unwrap());
-            let stopped = client
-                .metrics
-                .get_bytes_finished_counter_value(&RemoteOpFileKind::Layer, &RemoteOpKind::Upload)
-                .map(|v| v.try_into().unwrap());
-            BytesStartedFinished {
-                started,
-                finished: stopped,
-            }
-        };
-
-        // Test
-
-        let init = get_bytes_started_stopped();
-
-        client.schedule_layer_file_upload(
-            &layer_file_name_1,
-            &LayerFileMetadata::new(content_1.len() as u64),
-        )?;
-
-        let pre = get_bytes_started_stopped();
-
-        runtime.block_on(client.wait_completion())?;
-
-        let post = get_bytes_started_stopped();
-
-        // Validate
-
-        assert_eq!(
-            init,
-            BytesStartedFinished {
-                started: None,
-                finished: None
-            }
-        );
-        assert_eq!(
-            pre,
-            BytesStartedFinished {
-                started: Some(content_1.len()),
-                // assert that the _finished metric is created eagerly so that subtractions work on first sample
-                finished: Some(0),
-            }
-        );
-        assert_eq!(
-            post,
-            BytesStartedFinished {
-                started: Some(content_1.len()),
-                finished: Some(content_1.len())
-            }
-        );
-
-        Ok(())
-    }
 }

pageserver/src/tenant/remote_timeline_client/upload.rs

@@ -74,7 +74,7 @@ pub(super) async fn upload_timeline_layer<'a>(
     })?;
 
     storage
-        .upload(source_file, fs_size, &storage_path, None)
+        .upload(Box::new(source_file), fs_size, &storage_path, None)
         .await
         .with_context(|| {
             format!(

pageserver/src/tenant/tasks.rs

@@ -209,7 +209,7 @@ async fn wait_for_active_tenant(
         loop {
             match tenant_state_updates.changed().await {
                 Ok(()) => {
-                    let new_state = &*tenant_state_updates.borrow();
+                    let new_state = *tenant_state_updates.borrow();
                     match new_state {
                         TenantState::Active => {
                             debug!("Tenant state changed to active, continuing the task loop");

pageserver/src/tenant/timeline.rs

@@ -77,7 +77,6 @@ pub(super) use self::eviction_task::EvictionTaskTenantState;
 use self::eviction_task::EvictionTaskTimelineState;
 use self::walreceiver::{WalReceiver, WalReceiverConf};
 
-use super::config::TenantConf;
 use super::layer_map::BatchedUpdates;
 use super::remote_timeline_client::index::IndexPart;
 use super::remote_timeline_client::RemoteTimelineClient;
@@ -162,7 +161,7 @@ pub struct Timeline {
     ancestor_timeline: Option<Arc<Timeline>>,
     ancestor_lsn: Lsn,
 
-    pub(super) metrics: TimelineMetrics,
+    metrics: TimelineMetrics,
 
     /// Ensures layers aren't frozen by checkpointer between
     /// [`Timeline::get_layer_for_write`] and layer reads.
@@ -1137,8 +1136,6 @@ impl Timeline {
                 if let Some(delta) = local_layer_residence_duration {
                     self.metrics
                         .evictions_with_low_residence_duration
-                        .read()
-                        .unwrap()
                         .observe(delta);
                     info!(layer=%local_layer.short_id(), residence_millis=delta.as_millis(), "evicted layer after known residence period");
                 } else {
@@ -1212,35 +1209,6 @@ impl Timeline {
             .unwrap_or(self.conf.default_tenant_conf.eviction_policy)
     }
 
-    fn get_evictions_low_residence_duration_metric_threshold(
-        tenant_conf: &TenantConfOpt,
-        default_tenant_conf: &TenantConf,
-    ) -> Duration {
-        tenant_conf
-            .evictions_low_residence_duration_metric_threshold
-            .unwrap_or(default_tenant_conf.evictions_low_residence_duration_metric_threshold)
-    }
-
-    pub(super) fn tenant_conf_updated(&self) {
-        // NB: Most tenant conf options are read by background loops, so,
-        // changes will automatically be picked up.
-
-        // The threshold is embedded in the metric. So, we need to update it.
-        {
-            let new_threshold = Self::get_evictions_low_residence_duration_metric_threshold(
-                &self.tenant_conf.read().unwrap(),
-                &self.conf.default_tenant_conf,
-            );
-            let tenant_id_str = self.tenant_id.to_string();
-            let timeline_id_str = self.timeline_id.to_string();
-            self.metrics
-                .evictions_with_low_residence_duration
-                .write()
-                .unwrap()
-                .change_threshold(&tenant_id_str, &timeline_id_str, new_threshold);
-        }
-    }
-
     /// Open a Timeline handle.
     ///
     /// Loads the metadata for the timeline into memory, but not the layer map.
@@ -1272,11 +1240,6 @@ impl Timeline {
         let max_lsn_wal_lag = tenant_conf_guard
             .max_lsn_wal_lag
             .unwrap_or(conf.default_tenant_conf.max_lsn_wal_lag);
-        let evictions_low_residence_duration_metric_threshold =
-            Self::get_evictions_low_residence_duration_metric_threshold(
-                &tenant_conf_guard,
-                &conf.default_tenant_conf,
-            );
         drop(tenant_conf_guard);
 
         Arc::new_cyclic(|myself| {
@@ -1324,7 +1287,7 @@ impl Timeline {
                     &timeline_id,
                     crate::metrics::EvictionsWithLowResidenceDurationBuilder::new(
                         "mtime",
-                        evictions_low_residence_duration_metric_threshold,
+                        conf.evictions_low_residence_duration_metric_threshold,
                     ),
                 ),
 
@@ -1483,7 +1446,7 @@ impl Timeline {
 
                 trace!("found layer {}", layer.path().display());
                 total_physical_size += file_size;
-                updates.insert_historic(Arc::new(layer))?;
+                updates.insert_historic(Arc::new(layer));
                 num_layers += 1;
             } else if let Some(deltafilename) = DeltaFileName::parse_str(&fname) {
                 // Create a DeltaLayer struct for each delta file.
@@ -1515,7 +1478,7 @@ impl Timeline {
 
                 trace!("found layer {}", layer.path().display());
                 total_physical_size += file_size;
-                updates.insert_historic(Arc::new(layer))?;
+                updates.insert_historic(Arc::new(layer));
                 num_layers += 1;
             } else if fname == METADATA_FILE_NAME || fname.ends_with(".old") {
                 // ignore these
@@ -1589,7 +1552,7 @@ impl Timeline {
             // remote index file?
             // If so, rename_to_backup those files & replace their local layer with
             // a RemoteLayer in the layer map so that we re-download them on-demand.
-            if let Some(local_layer) = &local_layer {
+            if let Some(local_layer) = local_layer {
                 let local_layer_path = local_layer
                     .local_path()
                     .expect("caller must ensure that local_layers only contains local layers");
@@ -1614,6 +1577,7 @@ impl Timeline {
                         anyhow::bail!("could not rename file {local_layer_path:?}: {err:?}");
                     } else {
                         self.metrics.resident_physical_size_gauge.sub(local_size);
+                        updates.remove_historic(local_layer);
                         // fall-through to adding the remote layer
                     }
                 } else {
@@ -1649,11 +1613,7 @@ impl Timeline {
                     );
                     let remote_layer = Arc::new(remote_layer);
 
-                    if let Some(local_layer) = &local_layer {
-                        updates.replace_historic(local_layer, remote_layer)?;
-                    } else {
-                        updates.insert_historic(remote_layer)?;
-                    }
+                    updates.insert_historic(remote_layer);
                 }
                 LayerFileName::Delta(deltafilename) => {
                     // Create a RemoteLayer for the delta file.
@@ -1677,11 +1637,7 @@ impl Timeline {
                         LayerAccessStats::for_loading_layer(LayerResidenceStatus::Evicted),
                     );
                     let remote_layer = Arc::new(remote_layer);
-                    if let Some(local_layer) = &local_layer {
-                        updates.replace_historic(local_layer, remote_layer)?;
-                    } else {
-                        updates.insert_historic(remote_layer)?;
-                    }
+                    updates.insert_historic(remote_layer);
                 }
             }
         }
@@ -2728,7 +2684,7 @@ impl Timeline {
             .write()
             .unwrap()
             .batch_update()
-            .insert_historic(Arc::new(new_delta))?;
+            .insert_historic(Arc::new(new_delta));
 
         // update the timeline's physical size
         let sz = new_delta_path.metadata()?.len();
@@ -2933,7 +2889,7 @@ impl Timeline {
             self.metrics
                 .resident_physical_size_gauge
                 .add(metadata.len());
-            updates.insert_historic(Arc::new(l))?;
+            updates.insert_historic(Arc::new(l));
         }
         updates.flush();
         drop(layers);
@@ -3300,10 +3256,6 @@ impl Timeline {
 
         drop(all_keys_iter); // So that deltas_to_compact is no longer borrowed
 
-        fail_point!("compact-level0-phase1-finish", |_| {
-            Err(anyhow::anyhow!("failpoint compact-level0-phase1-finish").into())
-        });
-
         Ok(CompactLevel0Phase1Result {
             new_layers,
             deltas_to_compact,
@@ -3370,7 +3322,7 @@ impl Timeline {
 
             new_layer_paths.insert(new_delta_path, LayerFileMetadata::new(metadata.len()));
             let x: Arc<dyn PersistentLayer + 'static> = Arc::new(l);
-            updates.insert_historic(x)?;
+            updates.insert_historic(x);
         }
 
         // Now that we have reshuffled the data to set of new delta layers, we can

proxy/Cargo.toml

@@ -64,7 +64,6 @@ webpki-roots.workspace = true
 x509-parser.workspace = true
 
 workspace_hack.workspace = true
-tokio-util.workspace = true
 
 [dev-dependencies]
 rcgen.workspace = true

proxy/src/config.rs

@@ -40,7 +40,7 @@ pub fn configure_tls(
     let mut cert_resolver = CertResolver::new();
 
     // add default certificate
-    cert_resolver.add_cert(key_path, cert_path, true)?;
+    cert_resolver.add_cert(key_path, cert_path)?;
 
     // add extra certificates
     if let Some(certs_dir) = certs_dir {
@@ -52,11 +52,8 @@ pub fn configure_tls(
                 let key_path = path.join("tls.key");
                 let cert_path = path.join("tls.crt");
                 if key_path.exists() && cert_path.exists() {
-                    cert_resolver.add_cert(
-                        &key_path.to_string_lossy(),
-                        &cert_path.to_string_lossy(),
-                        false,
-                    )?;
+                    cert_resolver
+                        .add_cert(&key_path.to_string_lossy(), &cert_path.to_string_lossy())?;
                 }
             }
         }
@@ -81,23 +78,16 @@ pub fn configure_tls(
 
 struct CertResolver {
     certs: HashMap<String, Arc<rustls::sign::CertifiedKey>>,
-    default: Option<Arc<rustls::sign::CertifiedKey>>,
 }
 
 impl CertResolver {
     fn new() -> Self {
         Self {
             certs: HashMap::new(),
-            default: None,
         }
     }
 
-    fn add_cert(
-        &mut self,
-        key_path: &str,
-        cert_path: &str,
-        is_default: bool,
-    ) -> anyhow::Result<()> {
+    fn add_cert(&mut self, key_path: &str, cert_path: &str) -> anyhow::Result<()> {
         let priv_key = {
             let key_bytes = std::fs::read(key_path).context("TLS key file")?;
             let mut keys = rustls_pemfile::pkcs8_private_keys(&mut &key_bytes[..])
@@ -146,13 +136,10 @@ impl CertResolver {
             "Failed to parse common name from certificate at '{cert_path}'."
         ))?;
 
-        let cert = Arc::new(rustls::sign::CertifiedKey::new(cert_chain, key));
-
-        if is_default {
-            self.default = Some(cert.clone());
-        }
-
-        self.certs.insert(common_name, cert);
+        self.certs.insert(
+            common_name,
+            Arc::new(rustls::sign::CertifiedKey::new(cert_chain, key)),
+        );
 
         Ok(())
     }
@@ -185,17 +172,7 @@ impl rustls::server::ResolvesServerCert for CertResolver {
                 }
             }
         } else {
-            // No SNI, use the default certificate, otherwise we can't get to
-            // options parameter which can be used to set endpoint name too.
-            // That means that non-SNI flow will not work for CNAME domains in
-            // verify-full mode.
-            //
-            // If that will be a problem we can:
-            //
-            // a) Instead of multi-cert approach use single cert with extra
-            //    domains listed in Subject Alternative Name (SAN).
-            // b) Deploy separate proxy instances for extra domains.
-            self.default.as_ref().cloned()
+            None
         }
     }
 }

proxy/src/http/websocket.rs

@@ -22,7 +22,6 @@ use tokio::{
     io::{self, AsyncBufRead, AsyncRead, AsyncWrite, ReadBuf},
     net::TcpListener,
 };
-use tokio_util::sync::CancellationToken;
 use tracing::{error, info, info_span, warn, Instrument};
 use utils::http::{error::ApiError, json::json_response};
 
@@ -189,7 +188,6 @@ async fn ws_handler(
 pub async fn task_main(
     config: &'static ProxyConfig,
     ws_listener: TcpListener,
-    cancellation_token: CancellationToken,
 ) -> anyhow::Result<()> {
     scopeguard::defer! {
         info!("websocket server has shut down");
@@ -233,7 +231,6 @@ pub async fn task_main(
 
     hyper::Server::builder(accept::from_stream(tls_listener))
         .serve(make_svc)
-        .with_graceful_shutdown(cancellation_token.cancelled())
         .await?;
 
     Ok(())

proxy/src/main.rs

@@ -28,7 +28,6 @@ use config::ProxyConfig;
 use futures::FutureExt;
 use std::{borrow::Cow, future::Future, net::SocketAddr};
 use tokio::{net::TcpListener, task::JoinError};
-use tokio_util::sync::CancellationToken;
 use tracing::{info, warn};
 use utils::{project_git_version, sentry_init::init_sentry};
 
@@ -67,48 +66,39 @@ async fn main() -> anyhow::Result<()> {
     let proxy_address: SocketAddr = args.get_one::<String>("proxy").unwrap().parse()?;
     info!("Starting proxy on {proxy_address}");
     let proxy_listener = TcpListener::bind(proxy_address).await?;
-    let cancellation_token = CancellationToken::new();
 
-    let mut client_tasks = vec![tokio::spawn(proxy::task_main(
-        config,
-        proxy_listener,
-        cancellation_token.clone(),
-    ))];
+    let mut tasks = vec![
+        tokio::spawn(handle_signals()),
+        tokio::spawn(http::server::task_main(http_listener)),
+        tokio::spawn(proxy::task_main(config, proxy_listener)),
+        tokio::spawn(console::mgmt::task_main(mgmt_listener)),
+    ];
 
     if let Some(wss_address) = args.get_one::<String>("wss") {
         let wss_address: SocketAddr = wss_address.parse()?;
         info!("Starting wss on {wss_address}");
         let wss_listener = TcpListener::bind(wss_address).await?;
 
-        client_tasks.push(tokio::spawn(http::websocket::task_main(
+        tasks.push(tokio::spawn(http::websocket::task_main(
             config,
             wss_listener,
-            cancellation_token.clone(),
         )));
     }
 
-    let mut tasks = vec![
-        tokio::spawn(handle_signals(cancellation_token)),
-        tokio::spawn(http::server::task_main(http_listener)),
-        tokio::spawn(console::mgmt::task_main(mgmt_listener)),
-    ];
-
     if let Some(metrics_config) = &config.metric_collection {
         tasks.push(tokio::spawn(metrics::task_main(metrics_config)));
     }
 
-    let tasks = futures::future::try_join_all(tasks.into_iter().map(flatten_err));
-    let client_tasks = futures::future::try_join_all(client_tasks.into_iter().map(flatten_err));
-    tokio::select! {
-        // We are only expecting an error from these forever tasks
-        res = tasks => { res?; },
-        res = client_tasks => { res?; },
-    }
+    // This combinator will block until either all tasks complete or
+    // one of them finishes with an error (others will be cancelled).
+    let tasks = tasks.into_iter().map(flatten_err);
+    let _: Vec<()> = futures::future::try_join_all(tasks).await?;
+
     Ok(())
 }
 
 /// Handle unix signals appropriately.
-async fn handle_signals(token: CancellationToken) -> anyhow::Result<()> {
+async fn handle_signals() -> anyhow::Result<()> {
     use tokio::signal::unix::{signal, SignalKind};
 
     let mut hangup = signal(SignalKind::hangup())?;
@@ -126,9 +116,11 @@ async fn handle_signals(token: CancellationToken) -> anyhow::Result<()> {
                 warn!("received SIGINT, exiting immediately");
                 bail!("interrupted");
             }
+            // TODO: Don't accept new proxy connections.
+            // TODO: Shut down once all exisiting connections have been closed.
             _ = terminate.recv() => {
-                warn!("received SIGTERM, shutting down once all existing connections have closed");
-                token.cancel();
+                warn!("received SIGTERM, exiting immediately");
+                bail!("terminated");
             }
         }
     }

proxy/src/proxy.rs

@@ -17,7 +17,6 @@ use once_cell::sync::Lazy;
 use pq_proto::{BeMessage as Be, FeStartupPacket, StartupMessageParams};
 use std::sync::Arc;
 use tokio::io::{AsyncRead, AsyncWrite, AsyncWriteExt};
-use tokio_util::sync::CancellationToken;
 use tracing::{error, info, warn};
 use utils::measured_stream::MeasuredStream;
 
@@ -64,7 +63,6 @@ static NUM_BYTES_PROXIED_COUNTER: Lazy<IntCounterVec> = Lazy::new(|| {
 pub async fn task_main(
     config: &'static ProxyConfig,
     listener: tokio::net::TcpListener,
-    cancellation_token: CancellationToken,
 ) -> anyhow::Result<()> {
     scopeguard::defer! {
         info!("proxy has shut down");
@@ -74,48 +72,29 @@ pub async fn task_main(
     // will be inherited by all accepted client sockets.
     socket2::SockRef::from(&listener).set_keepalive(true)?;
 
-    let mut connections = tokio::task::JoinSet::new();
     let cancel_map = Arc::new(CancelMap::default());
-
     loop {
-        tokio::select! {
-            accept_result = listener.accept() => {
-                let (socket, peer_addr) = accept_result?;
-                info!("accepted postgres client connection from {peer_addr}");
+        let (socket, peer_addr) = listener.accept().await?;
+        info!("accepted postgres client connection from {peer_addr}");
 
-                let session_id = uuid::Uuid::new_v4();
-                let cancel_map = Arc::clone(&cancel_map);
-                connections.spawn(
-                    async move {
-                        info!("spawned a task for {peer_addr}");
+        let session_id = uuid::Uuid::new_v4();
+        let cancel_map = Arc::clone(&cancel_map);
+        tokio::spawn(
+            async move {
+                info!("spawned a task for {peer_addr}");
 
-                        socket
-                            .set_nodelay(true)
-                            .context("failed to set socket option")?;
+                socket
+                    .set_nodelay(true)
+                    .context("failed to set socket option")?;
 
-                        handle_client(config, &cancel_map, session_id, socket).await
-                    }
-                    .unwrap_or_else(|e| {
-                        // Acknowledge that the task has finished with an error.
-                        error!("per-client task finished with an error: {e:#}");
-                    }),
-                );
+                handle_client(config, &cancel_map, session_id, socket).await
             }
-            _ = cancellation_token.cancelled() => {
-                drop(listener);
-                break;
-            }
-        }
+            .unwrap_or_else(|e| {
+                // Acknowledge that the task has finished with an error.
+                error!("per-client task finished with an error: {e:#}");
+            }),
+        );
     }
-    // Drain connections
-    while let Some(res) = connections.join_next().await {
-        if let Err(e) = res {
-            if !e.is_panic() && !e.is_cancelled() {
-                warn!("unexpected error from joined connection task: {e:?}");
-            }
-        }
-    }
-    Ok(())
 }
 
 // TODO(tech debt): unite this with its twin below.

safekeeper/src/receive_wal.rs

@@ -27,8 +27,6 @@ use tokio::sync::mpsc::error::TryRecvError;
 use tokio::sync::mpsc::Receiver;
 use tokio::sync::mpsc::Sender;
 use tokio::task::spawn_blocking;
-use tokio::time::Duration;
-use tokio::time::Instant;
 use tracing::*;
 use utils::id::TenantTimelineId;
 use utils::lsn::Lsn;
@@ -208,10 +206,6 @@ async fn network_write<IO: AsyncRead + AsyncWrite + Unpin>(
     }
 }
 
-// Send keepalive messages to walproposer, to make sure it receives updates
-// even when it writes a steady stream of messages.
-const KEEPALIVE_INTERVAL: Duration = Duration::from_secs(1);
-
 /// Takes messages from msg_rx, processes and pushes replies to reply_tx.
 struct WalAcceptor {
     tli: Arc<Timeline>,
@@ -259,25 +253,18 @@ impl WalAcceptor {
             timeline: Arc::clone(&self.tli),
         };
 
-        // After this timestamp we will stop processing AppendRequests and send a response
-        // to the walproposer. walproposer sends at least one AppendRequest per second,
-        // we will send keepalives by replying to these requests once per second.
-        let mut next_keepalive = Instant::now();
+        let mut next_msg: ProposerAcceptorMessage;
 
         loop {
             let opt_msg = self.msg_rx.recv().await;
             if opt_msg.is_none() {
                 return Ok(()); // chan closed, streaming terminated
             }
-            let mut next_msg = opt_msg.unwrap();
+            next_msg = opt_msg.unwrap();
 
-            let reply_msg = if matches!(next_msg, ProposerAcceptorMessage::AppendRequest(_)) {
+            if matches!(next_msg, ProposerAcceptorMessage::AppendRequest(_)) {
                 // loop through AppendRequest's while it's readily available to
                 // write as many WAL as possible without fsyncing
-                //
-                // Note: this will need to be rewritten if we want to read non-AppendRequest messages here.
-                // Otherwise, we might end up in a situation where we read a message, but don't
-                // process it.
                 while let ProposerAcceptorMessage::AppendRequest(append_request) = next_msg {
                     let noflush_msg = ProposerAcceptorMessage::NoFlushAppendRequest(append_request);
 
@@ -287,11 +274,6 @@ impl WalAcceptor {
                         }
                     }
 
-                    // get out of this loop if keepalive time is reached
-                    if Instant::now() >= next_keepalive {
-                        break;
-                    }
-
                     match self.msg_rx.try_recv() {
                         Ok(msg) => next_msg = msg,
                         Err(TryRecvError::Empty) => break,
@@ -300,18 +282,18 @@ impl WalAcceptor {
                 }
 
                 // flush all written WAL to the disk
-                self.tli.process_msg(&ProposerAcceptorMessage::FlushWAL)?
+                if let Some(reply) = self.tli.process_msg(&ProposerAcceptorMessage::FlushWAL)? {
+                    if self.reply_tx.send(reply).await.is_err() {
+                        return Ok(()); // chan closed, streaming terminated
+                    }
+                }
             } else {
                 // process message other than AppendRequest
-                self.tli.process_msg(&next_msg)?
-            };
-
-            if let Some(reply) = reply_msg {
-                if self.reply_tx.send(reply).await.is_err() {
-                    return Ok(()); // chan closed, streaming terminated
+                if let Some(reply) = self.tli.process_msg(&next_msg)? {
+                    if self.reply_tx.send(reply).await.is_err() {
+                        return Ok(()); // chan closed, streaming terminated
+                    }
                 }
-                // reset keepalive time
-                next_keepalive = Instant::now() + KEEPALIVE_INTERVAL;
             }
         }
     }

storage_broker/src/bin/storage_broker.rs

@@ -23,6 +23,7 @@ use std::convert::Infallible;
 use std::net::SocketAddr;
 use std::pin::Pin;
 use std::sync::Arc;
+use std::task::Poll;
 use std::time::Duration;
 use tokio::sync::broadcast;
 use tokio::sync::broadcast::error::RecvError;
@@ -373,7 +374,7 @@ impl BrokerService for Broker {
                     Ok(info) => yield info,
                     Err(RecvError::Lagged(skipped_msg)) => {
                         missed_msgs += skipped_msg;
-                        if (futures::poll!(Box::pin(warn_interval.tick()))).is_ready() {
+                        if let Poll::Ready(_) = futures::poll!(Box::pin(warn_interval.tick())) {
                             warn!("subscription id={}, key={:?} addr={:?} dropped {} messages, channel is full",
                                 subscriber.id, subscriber.key, subscriber.remote_addr, missed_msgs);
                             missed_msgs = 0;

test_runner/fixtures/compare_fixtures.py

@@ -114,7 +114,7 @@ class NeonCompare(PgCompare):
         self.timeline = self.env.neon_cli.create_timeline(branch_name, tenant_id=self.tenant)
 
         # Start pg
-        self._pg = self.env.endpoints.create_start(branch_name, "main", self.tenant)
+        self._pg = self.env.postgres.create_start(branch_name, "main", self.tenant)
 
     @property
     def pg(self) -> PgProtocol:

test_runner/fixtures/metrics.py

@@ -45,8 +45,6 @@ PAGESERVER_PER_TENANT_REMOTE_TIMELINE_CLIENT_METRICS: Tuple[str, ...] = (
     *[f"pageserver_remote_timeline_client_calls_started_{x}" for x in ["bucket", "count", "sum"]],
     *[f"pageserver_remote_operation_seconds_{x}" for x in ["bucket", "count", "sum"]],
     "pageserver_remote_physical_size",
-    "pageserver_remote_timeline_client_bytes_started_total",
-    "pageserver_remote_timeline_client_bytes_finished_total",
 )
 
 PAGESERVER_GLOBAL_METRICS: Tuple[str, ...] = (
@@ -55,7 +53,6 @@ PAGESERVER_GLOBAL_METRICS: Tuple[str, ...] = (
     "pageserver_storage_operations_seconds_global_bucket",
     "libmetrics_launch_timestamp",
     "libmetrics_build_info",
-    "libmetrics_tracing_event_count_total",
 )
 
 PAGESERVER_PER_TENANT_METRICS: Tuple[str, ...] = (

test_runner/fixtures/neon_fixtures.py

@@ -830,7 +830,7 @@ class NeonEnvBuilder:
         # Stop all the nodes.
         if self.env:
             log.info("Cleaning up all storage and compute nodes")
-            self.env.endpoints.stop_all()
+            self.env.postgres.stop_all()
             for sk in self.env.safekeepers:
                 sk.stop(immediate=True)
             self.env.pageserver.stop(immediate=True)
@@ -894,7 +894,7 @@ class NeonEnv:
         self.port_distributor = config.port_distributor
         self.s3_mock_server = config.mock_s3_server
         self.neon_cli = NeonCli(env=self)
-        self.endpoints = EndpointFactory(self)
+        self.postgres = PostgresFactory(self)
         self.safekeepers: List[Safekeeper] = []
         self.broker = config.broker
         self.remote_storage = config.remote_storage
@@ -902,7 +902,6 @@ class NeonEnv:
         self.pg_version = config.pg_version
         self.neon_binpath = config.neon_binpath
         self.pg_distrib_dir = config.pg_distrib_dir
-        self.endpoint_counter = 0
 
         # generate initial tenant ID here instead of letting 'neon init' generate it,
         # so that we don't need to dig it out of the config file afterwards.
@@ -1016,13 +1015,6 @@ class NeonEnv:
         priv = (Path(self.repo_dir) / "auth_private_key.pem").read_text()
         return AuthKeys(pub=pub, priv=priv)
 
-    def generate_endpoint_id(self) -> str:
-        """
-        Generate a unique endpoint ID
-        """
-        self.endpoint_counter += 1
-        return "ep-" + str(self.endpoint_counter)
-
 
 @pytest.fixture(scope=shareable_scope)
 def _shared_simple_env(
@@ -1081,7 +1073,7 @@ def neon_simple_env(_shared_simple_env: NeonEnv) -> Iterator[NeonEnv]:
     """
     yield _shared_simple_env
 
-    _shared_simple_env.endpoints.stop_all()
+    _shared_simple_env.postgres.stop_all()
 
 
 @pytest.fixture(scope="function")
@@ -1105,7 +1097,7 @@ def neon_env_builder(
     neon_env_builder.init_start().
 
     After the initialization, you can launch compute nodes by calling
-    the functions in the 'env.endpoints' factory object, stop/start the
+    the functions in the 'env.postgres' factory object, stop/start the
     nodes, etc.
     """
 
@@ -1446,16 +1438,16 @@ class NeonCli(AbstractNeonCli):
             args.extend(["-m", "immediate"])
         return self.raw_cli(args)
 
-    def endpoint_create(
+    def pg_create(
         self,
         branch_name: str,
-        endpoint_id: Optional[str] = None,
+        node_name: Optional[str] = None,
         tenant_id: Optional[TenantId] = None,
         lsn: Optional[Lsn] = None,
         port: Optional[int] = None,
     ) -> "subprocess.CompletedProcess[str]":
         args = [
-            "endpoint",
+            "pg",
             "create",
             "--tenant-id",
             str(tenant_id or self.env.initial_tenant),
@@ -1468,22 +1460,22 @@ class NeonCli(AbstractNeonCli):
             args.extend(["--lsn", str(lsn)])
         if port is not None:
             args.extend(["--port", str(port)])
-        if endpoint_id is not None:
-            args.append(endpoint_id)
+        if node_name is not None:
+            args.append(node_name)
 
         res = self.raw_cli(args)
         res.check_returncode()
         return res
 
-    def endpoint_start(
+    def pg_start(
         self,
-        endpoint_id: str,
+        node_name: str,
         tenant_id: Optional[TenantId] = None,
         lsn: Optional[Lsn] = None,
         port: Optional[int] = None,
     ) -> "subprocess.CompletedProcess[str]":
         args = [
-            "endpoint",
+            "pg",
             "start",
             "--tenant-id",
             str(tenant_id or self.env.initial_tenant),
@@ -1494,30 +1486,30 @@ class NeonCli(AbstractNeonCli):
             args.append(f"--lsn={lsn}")
         if port is not None:
             args.append(f"--port={port}")
-        if endpoint_id is not None:
-            args.append(endpoint_id)
+        if node_name is not None:
+            args.append(node_name)
 
         res = self.raw_cli(args)
         res.check_returncode()
         return res
 
-    def endpoint_stop(
+    def pg_stop(
         self,
-        endpoint_id: str,
+        node_name: str,
         tenant_id: Optional[TenantId] = None,
         destroy=False,
         check_return_code=True,
     ) -> "subprocess.CompletedProcess[str]":
         args = [
-            "endpoint",
+            "pg",
             "stop",
             "--tenant-id",
             str(tenant_id or self.env.initial_tenant),
         ]
         if destroy:
             args.append("--destroy")
-        if endpoint_id is not None:
-            args.append(endpoint_id)
+        if node_name is not None:
+            args.append(node_name)
 
         return self.raw_cli(args, check_return_code=check_return_code)
 
@@ -1913,26 +1905,15 @@ def remote_pg(
     connstr = os.getenv("BENCHMARK_CONNSTR")
     if connstr is None:
         raise ValueError("no connstr provided, use BENCHMARK_CONNSTR environment variable")
-
-    host = parse_dsn(connstr).get("host", "")
-    is_neon = host.endswith(".neon.build")
-
     start_ms = int(datetime.utcnow().timestamp() * 1000)
     with RemotePostgres(pg_bin, connstr) as remote_pg:
-        if is_neon:
-            timeline_id = TimelineId(remote_pg.safe_psql("SHOW neon.timeline_id")[0][0])
-
         yield remote_pg
 
     end_ms = int(datetime.utcnow().timestamp() * 1000)
-    if is_neon:
+    host = parse_dsn(connstr).get("host", "")
+    if host.endswith(".neon.build"):
         # Add 10s margin to the start and end times
-        allure_add_grafana_links(
-            host,
-            timeline_id,
-            start_ms - 10_000,
-            end_ms + 10_000,
-        )
+        allure_add_grafana_links(host, start_ms - 10_000, end_ms + 10_000)
 
 
 class PSQL:
@@ -2052,17 +2033,6 @@ class NeonProxy(PgProtocol):
         self._wait_until_ready()
         return self
 
-    # Sends SIGTERM to the proxy if it has been started
-    def terminate(self):
-        if self._popen:
-            self._popen.terminate()
-
-    # Waits for proxy to exit if it has been opened with a default timeout of
-    # two seconds. Raises subprocess.TimeoutExpired if the proxy does not exit in time.
-    def wait_for_exit(self, timeout=2):
-        if self._popen:
-            self._popen.wait(timeout=2)
-
     @backoff.on_exception(backoff.expo, requests.exceptions.RequestException, max_time=10)
     def _wait_until_ready(self):
         requests.get(f"http://{self.host}:{self.http_port}/v1/status")
@@ -2197,8 +2167,8 @@ def static_proxy(
         yield proxy
 
 
-class Endpoint(PgProtocol):
-    """An object representing a Postgres compute endpoint managed by the control plane."""
+class Postgres(PgProtocol):
+    """An object representing a running postgres daemon."""
 
     def __init__(
         self, env: NeonEnv, tenant_id: TenantId, port: int, check_stop_result: bool = True
@@ -2206,40 +2176,33 @@ class Endpoint(PgProtocol):
         super().__init__(host="localhost", port=port, user="cloud_admin", dbname="postgres")
         self.env = env
         self.running = False
-        self.endpoint_id: Optional[str] = None  # dubious, see asserts below
+        self.node_name: Optional[str] = None  # dubious, see asserts below
         self.pgdata_dir: Optional[str] = None  # Path to computenode PGDATA
         self.tenant_id = tenant_id
         self.port = port
         self.check_stop_result = check_stop_result
-        # path to conf is <repo_dir>/endpoints/<endpoint_id>/pgdata/postgresql.conf
+        # path to conf is <repo_dir>/pgdatadirs/tenants/<tenant_id>/<node_name>/postgresql.conf
 
     def create(
         self,
         branch_name: str,
-        endpoint_id: Optional[str] = None,
+        node_name: Optional[str] = None,
         lsn: Optional[Lsn] = None,
         config_lines: Optional[List[str]] = None,
-    ) -> "Endpoint":
+    ) -> "Postgres":
         """
-        Create a new Postgres endpoint.
+        Create the pg data directory.
         Returns self.
         """
 
         if not config_lines:
             config_lines = []
 
-        if endpoint_id is None:
-            endpoint_id = self.env.generate_endpoint_id()
-        self.endpoint_id = endpoint_id
-
-        self.env.neon_cli.endpoint_create(
-            branch_name,
-            endpoint_id=self.endpoint_id,
-            tenant_id=self.tenant_id,
-            lsn=lsn,
-            port=self.port,
+        self.node_name = node_name or f"{branch_name}_pg_node"
+        self.env.neon_cli.pg_create(
+            branch_name, node_name=self.node_name, tenant_id=self.tenant_id, lsn=lsn, port=self.port
         )
-        path = Path("endpoints") / self.endpoint_id / "pgdata"
+        path = Path("pgdatadirs") / "tenants" / str(self.tenant_id) / self.node_name
         self.pgdata_dir = os.path.join(self.env.repo_dir, path)
 
         if config_lines is None:
@@ -2252,30 +2215,26 @@ class Endpoint(PgProtocol):
 
         return self
 
-    def start(self) -> "Endpoint":
+    def start(self) -> "Postgres":
         """
         Start the Postgres instance.
         Returns self.
         """
 
-        assert self.endpoint_id is not None
+        assert self.node_name is not None
 
-        log.info(f"Starting postgres endpoint {self.endpoint_id}")
+        log.info(f"Starting postgres node {self.node_name}")
 
-        self.env.neon_cli.endpoint_start(self.endpoint_id, tenant_id=self.tenant_id, port=self.port)
+        self.env.neon_cli.pg_start(self.node_name, tenant_id=self.tenant_id, port=self.port)
         self.running = True
 
         return self
 
-    def endpoint_path(self) -> Path:
-        """Path to endpoint directory"""
-        assert self.endpoint_id
-        path = Path("endpoints") / self.endpoint_id
-        return self.env.repo_dir / path
-
     def pg_data_dir_path(self) -> str:
-        """Path to Postgres data directory"""
-        return os.path.join(self.endpoint_path(), "pgdata")
+        """Path to data directory"""
+        assert self.node_name
+        path = Path("pgdatadirs") / "tenants" / str(self.tenant_id) / self.node_name
+        return os.path.join(self.env.repo_dir, path)
 
     def pg_xact_dir_path(self) -> str:
         """Path to pg_xact dir"""
@@ -2289,7 +2248,7 @@ class Endpoint(PgProtocol):
         """Path to postgresql.conf"""
         return os.path.join(self.pg_data_dir_path(), "postgresql.conf")
 
-    def adjust_for_safekeepers(self, safekeepers: str) -> "Endpoint":
+    def adjust_for_safekeepers(self, safekeepers: str) -> "Postgres":
         """
         Adjust instance config for working with wal acceptors instead of
         pageserver (pre-configured by CLI) directly.
@@ -2313,7 +2272,7 @@ class Endpoint(PgProtocol):
             f.write("neon.safekeepers = '{}'\n".format(safekeepers))
         return self
 
-    def config(self, lines: List[str]) -> "Endpoint":
+    def config(self, lines: List[str]) -> "Postgres":
         """
         Add lines to postgresql.conf.
         Lines should be an array of valid postgresql.conf rows.
@@ -2327,32 +2286,32 @@ class Endpoint(PgProtocol):
 
         return self
 
-    def stop(self) -> "Endpoint":
+    def stop(self) -> "Postgres":
         """
         Stop the Postgres instance if it's running.
         Returns self.
         """
 
         if self.running:
-            assert self.endpoint_id is not None
-            self.env.neon_cli.endpoint_stop(
-                self.endpoint_id, self.tenant_id, check_return_code=self.check_stop_result
+            assert self.node_name is not None
+            self.env.neon_cli.pg_stop(
+                self.node_name, self.tenant_id, check_return_code=self.check_stop_result
             )
             self.running = False
 
         return self
 
-    def stop_and_destroy(self) -> "Endpoint":
+    def stop_and_destroy(self) -> "Postgres":
         """
-        Stop the Postgres instance, then destroy the endpoint.
+        Stop the Postgres instance, then destroy it.
         Returns self.
         """
 
-        assert self.endpoint_id is not None
-        self.env.neon_cli.endpoint_stop(
-            self.endpoint_id, self.tenant_id, True, check_return_code=self.check_stop_result
+        assert self.node_name is not None
+        self.env.neon_cli.pg_stop(
+            self.node_name, self.tenant_id, True, check_return_code=self.check_stop_result
         )
-        self.endpoint_id = None
+        self.node_name = None
         self.running = False
 
         return self
@@ -2360,12 +2319,13 @@ class Endpoint(PgProtocol):
     def create_start(
         self,
         branch_name: str,
-        endpoint_id: Optional[str] = None,
+        node_name: Optional[str] = None,
         lsn: Optional[Lsn] = None,
         config_lines: Optional[List[str]] = None,
-    ) -> "Endpoint":
+    ) -> "Postgres":
         """
-        Create an endpoint, apply config, and start Postgres.
+        Create a Postgres instance, apply config
+        and then start it.
         Returns self.
         """
 
@@ -2373,7 +2333,7 @@ class Endpoint(PgProtocol):
 
         self.create(
             branch_name=branch_name,
-            endpoint_id=endpoint_id,
+            node_name=node_name,
             config_lines=config_lines,
             lsn=lsn,
         ).start()
@@ -2382,7 +2342,7 @@ class Endpoint(PgProtocol):
 
         return self
 
-    def __enter__(self) -> "Endpoint":
+    def __enter__(self) -> "Postgres":
         return self
 
     def __exit__(
@@ -2394,33 +2354,33 @@ class Endpoint(PgProtocol):
         self.stop()
 
 
-class EndpointFactory:
-    """An object representing multiple compute endpoints."""
+class PostgresFactory:
+    """An object representing multiple running postgres daemons."""
 
     def __init__(self, env: NeonEnv):
         self.env = env
         self.num_instances: int = 0
-        self.endpoints: List[Endpoint] = []
+        self.instances: List[Postgres] = []
 
     def create_start(
         self,
         branch_name: str,
-        endpoint_id: Optional[str] = None,
+        node_name: Optional[str] = None,
         tenant_id: Optional[TenantId] = None,
         lsn: Optional[Lsn] = None,
         config_lines: Optional[List[str]] = None,
-    ) -> Endpoint:
-        ep = Endpoint(
+    ) -> Postgres:
+        pg = Postgres(
             self.env,
             tenant_id=tenant_id or self.env.initial_tenant,
             port=self.env.port_distributor.get_port(),
         )
         self.num_instances += 1
-        self.endpoints.append(ep)
+        self.instances.append(pg)
 
-        return ep.create_start(
+        return pg.create_start(
             branch_name=branch_name,
-            endpoint_id=endpoint_id,
+            node_name=node_name,
             config_lines=config_lines,
             lsn=lsn,
         )
@@ -2428,33 +2388,30 @@ class EndpointFactory:
     def create(
         self,
         branch_name: str,
-        endpoint_id: Optional[str] = None,
+        node_name: Optional[str] = None,
         tenant_id: Optional[TenantId] = None,
         lsn: Optional[Lsn] = None,
         config_lines: Optional[List[str]] = None,
-    ) -> Endpoint:
-        ep = Endpoint(
+    ) -> Postgres:
+        pg = Postgres(
             self.env,
             tenant_id=tenant_id or self.env.initial_tenant,
             port=self.env.port_distributor.get_port(),
         )
 
-        if endpoint_id is None:
-            endpoint_id = self.env.generate_endpoint_id()
-
         self.num_instances += 1
-        self.endpoints.append(ep)
+        self.instances.append(pg)
 
-        return ep.create(
+        return pg.create(
             branch_name=branch_name,
-            endpoint_id=endpoint_id,
+            node_name=node_name,
             lsn=lsn,
             config_lines=config_lines,
         )
 
-    def stop_all(self) -> "EndpointFactory":
-        for ep in self.endpoints:
-            ep.stop()
+    def stop_all(self) -> "PostgresFactory":
+        for pg in self.instances:
+            pg.stop()
 
         return self
 
@@ -2829,16 +2786,16 @@ def list_files_to_compare(pgdata_dir: Path) -> List[str]:
 def check_restored_datadir_content(
     test_output_dir: Path,
     env: NeonEnv,
-    endpoint: Endpoint,
+    pg: Postgres,
 ):
     # Get the timeline ID. We need it for the 'basebackup' command
-    timeline = TimelineId(endpoint.safe_psql("SHOW neon.timeline_id")[0][0])
+    timeline = TimelineId(pg.safe_psql("SHOW neon.timeline_id")[0][0])
 
     # stop postgres to ensure that files won't change
-    endpoint.stop()
+    pg.stop()
 
     # Take a basebackup from pageserver
-    restored_dir_path = env.repo_dir / f"{endpoint.endpoint_id}_restored_datadir"
+    restored_dir_path = env.repo_dir / f"{pg.node_name}_restored_datadir"
     restored_dir_path.mkdir(exist_ok=True)
 
     pg_bin = PgBin(test_output_dir, env.pg_distrib_dir, env.pg_version)
@@ -2848,7 +2805,7 @@ def check_restored_datadir_content(
         {psql_path}                                    \
             --no-psqlrc                                \
             postgres://localhost:{env.pageserver.service_port.pg}  \
-            -c 'basebackup {endpoint.tenant_id} {timeline}'  \
+            -c 'basebackup {pg.tenant_id} {timeline}'  \
          | tar -x -C {restored_dir_path}
     """
 
@@ -2865,8 +2822,8 @@ def check_restored_datadir_content(
     assert result.returncode == 0
 
     # list files we're going to compare
-    assert endpoint.pgdata_dir
-    pgdata_files = list_files_to_compare(Path(endpoint.pgdata_dir))
+    assert pg.pgdata_dir
+    pgdata_files = list_files_to_compare(Path(pg.pgdata_dir))
     restored_files = list_files_to_compare(restored_dir_path)
 
     # check that file sets are equal
@@ -2877,12 +2834,12 @@ def check_restored_datadir_content(
     # We've already filtered all mismatching files in list_files_to_compare(),
     # so here expect that the content is identical
     (match, mismatch, error) = filecmp.cmpfiles(
-        endpoint.pgdata_dir, restored_dir_path, pgdata_files, shallow=False
+        pg.pgdata_dir, restored_dir_path, pgdata_files, shallow=False
     )
     log.info(f"filecmp result mismatch and error lists:\n\t mismatch={mismatch}\n\t error={error}")
 
     for f in mismatch:
-        f1 = os.path.join(endpoint.pgdata_dir, f)
+        f1 = os.path.join(pg.pgdata_dir, f)
         f2 = os.path.join(restored_dir_path, f)
         stdout_filename = "{}.filediff".format(f2)
 
@@ -2897,24 +2854,24 @@ def check_restored_datadir_content(
 
 
 def wait_for_last_flush_lsn(
-    env: NeonEnv, endpoint: Endpoint, tenant: TenantId, timeline: TimelineId
+    env: NeonEnv, pg: Postgres, tenant: TenantId, timeline: TimelineId
 ) -> Lsn:
     """Wait for pageserver to catch up the latest flush LSN, returns the last observed lsn."""
-    last_flush_lsn = Lsn(endpoint.safe_psql("SELECT pg_current_wal_flush_lsn()")[0][0])
+    last_flush_lsn = Lsn(pg.safe_psql("SELECT pg_current_wal_flush_lsn()")[0][0])
     return wait_for_last_record_lsn(env.pageserver.http_client(), tenant, timeline, last_flush_lsn)
 
 
 def wait_for_wal_insert_lsn(
-    env: NeonEnv, endpoint: Endpoint, tenant: TenantId, timeline: TimelineId
+    env: NeonEnv, pg: Postgres, tenant: TenantId, timeline: TimelineId
 ) -> Lsn:
     """Wait for pageserver to catch up the latest flush LSN, returns the last observed lsn."""
-    last_flush_lsn = Lsn(endpoint.safe_psql("SELECT pg_current_wal_insert_lsn()")[0][0])
+    last_flush_lsn = Lsn(pg.safe_psql("SELECT pg_current_wal_insert_lsn()")[0][0])
     return wait_for_last_record_lsn(env.pageserver.http_client(), tenant, timeline, last_flush_lsn)
 
 
 def fork_at_current_lsn(
     env: NeonEnv,
-    endpoint: Endpoint,
+    pg: Postgres,
     new_branch_name: str,
     ancestor_branch_name: str,
     tenant_id: Optional[TenantId] = None,
@@ -2924,22 +2881,36 @@ def fork_at_current_lsn(
     The "last LSN" is taken from the given Postgres instance. The pageserver will wait for all the
     the WAL up to that LSN to arrive in the pageserver before creating the branch.
     """
-    current_lsn = endpoint.safe_psql("SELECT pg_current_wal_lsn()")[0][0]
+    current_lsn = pg.safe_psql("SELECT pg_current_wal_lsn()")[0][0]
     return env.neon_cli.create_branch(new_branch_name, ancestor_branch_name, tenant_id, current_lsn)
 
 
-def last_flush_lsn_upload(
-    env: NeonEnv, endpoint: Endpoint, tenant_id: TenantId, timeline_id: TimelineId
-) -> Lsn:
-    """
-    Wait for pageserver to catch to the latest flush LSN of given endpoint,
-    checkpoint pageserver, and wait for it to be uploaded (remote_consistent_lsn
-    reaching flush LSN).
-    """
-    last_flush_lsn = wait_for_last_flush_lsn(env, endpoint, tenant_id, timeline_id)
-    ps_http = env.pageserver.http_client()
-    wait_for_last_record_lsn(ps_http, tenant_id, timeline_id, last_flush_lsn)
+def wait_for_sk_commit_lsn_to_arrive_at_pageserver_last_record_lsn(
+    tenant_id: TenantId,
+    timeline_id: TimelineId,
+    safekeepers: List[Safekeeper],
+    pageserver: NeonPageserver,
+):
+    sk_commit_lsns = [
+        sk.http_client().timeline_status(tenant_id, timeline_id).commit_lsn for sk in safekeepers
+    ]
+    lsn = max(sk_commit_lsns)
+    ps_http = pageserver.http_client()
+    wait_for_last_record_lsn(ps_http, tenant_id, timeline_id, lsn)
+    return lsn
+
+
+def wait_for_sk_commit_lsn_to_reach_remote_storage(
+    tenant_id: TenantId,
+    timeline_id: TimelineId,
+    safekeepers: List[Safekeeper],
+    pageserver: NeonPageserver,
+):
+    lsn = wait_for_sk_commit_lsn_to_arrive_at_pageserver_last_record_lsn(
+        tenant_id, timeline_id, safekeepers, pageserver
+    )
+    ps_http = pageserver.http_client()
     # force a checkpoint to trigger upload
     ps_http.timeline_checkpoint(tenant_id, timeline_id)
-    wait_for_upload(ps_http, tenant_id, timeline_id, last_flush_lsn)
-    return last_flush_lsn
+    wait_for_upload(ps_http, tenant_id, timeline_id, lsn)
+    return lsn

test_runner/fixtures/pageserver/http.py

@@ -519,13 +519,6 @@ class PageserverHttpClient(requests.Session):
 
         assert res.status_code == 200
 
-    def download_all_layers(self, tenant_id: TenantId, timeline_id: TimelineId):
-        info = self.layer_map_info(tenant_id, timeline_id)
-        for layer in info.historic_layers:
-            if not layer.remote:
-                continue
-            self.download_layer(tenant_id, timeline_id, layer.layer_file_name)
-
     def evict_layer(self, tenant_id: TenantId, timeline_id: TimelineId, layer_name: str):
         res = self.delete(
             f"http://localhost:{self.port}/v1/tenant/{tenant_id}/timeline/{timeline_id}/layer/{layer_name}",
@@ -550,13 +543,3 @@ class PageserverHttpClient(requests.Session):
     def tenant_break(self, tenant_id: TenantId):
         res = self.put(f"http://localhost:{self.port}/v1/tenant/{tenant_id}/break")
         self.verbose_error(res)
-
-    def post_tracing_event(self, level: str, message: str):
-        res = self.post(
-            f"http://localhost:{self.port}/v1/tracing/event",
-            json={
-                "level": level,
-                "message": message,
-            },
-        )
-        self.verbose_error(res)

test_runner/fixtures/pageserver/utils.py

@@ -1,20 +1,16 @@
 import time
-from typing import Optional
 
 from fixtures.log_helper import log
 from fixtures.pageserver.http import PageserverHttpClient
 from fixtures.types import Lsn, TenantId, TimelineId
 
 
-def assert_tenant_state(
-    pageserver_http: PageserverHttpClient,
-    tenant: TenantId,
-    expected_state: str,
-    message: Optional[str] = None,
+def assert_tenant_status(
+    pageserver_http: PageserverHttpClient, tenant: TenantId, expected_status: str
 ):
     tenant_status = pageserver_http.tenant_status(tenant)
     log.info(f"tenant_status: {tenant_status}")
-    assert tenant_status["state"]["slug"] == expected_state, message or tenant_status
+    assert tenant_status["state"] == expected_status, tenant_status
 
 
 def tenant_exists(pageserver_http: PageserverHttpClient, tenant_id: TenantId):
@@ -54,9 +50,10 @@ def wait_for_upload(
         if current_lsn >= lsn:
             log.info("wait finished")
             return
-        lr_lsn = last_record_lsn(pageserver_http, tenant, timeline)
         log.info(
-            f"waiting for remote_consistent_lsn to reach {lsn}, now {current_lsn}, last_record_lsn={lr_lsn}, iteration {i + 1}"
+            "waiting for remote_consistent_lsn to reach {}, now {}, iteration {}".format(
+                lsn, current_lsn, i + 1
+            )
         )
         time.sleep(1)
     raise Exception(
@@ -71,7 +68,6 @@ def wait_until_tenant_state(
     tenant_id: TenantId,
     expected_state: str,
     iterations: int,
-    period: float = 1.0,
 ) -> bool:
     """
     Does not use `wait_until` for debugging purposes
@@ -80,28 +76,21 @@ def wait_until_tenant_state(
         try:
             tenant = pageserver_http.tenant_status(tenant_id=tenant_id)
             log.debug(f"Tenant {tenant_id} data: {tenant}")
-            if tenant["state"]["slug"] == expected_state:
+            if tenant["state"] == expected_state:
                 return True
         except Exception as e:
             log.debug(f"Tenant {tenant_id} state retrieval failure: {e}")
 
-        time.sleep(period)
+        time.sleep(1)
 
     raise Exception(f"Tenant {tenant_id} did not become {expected_state} in {iterations} seconds")
 
 
 def wait_until_tenant_active(
-    pageserver_http: PageserverHttpClient,
-    tenant_id: TenantId,
-    iterations: int = 30,
-    period: float = 1.0,
+    pageserver_http: PageserverHttpClient, tenant_id: TenantId, iterations: int = 30
 ):
     wait_until_tenant_state(
-        pageserver_http,
-        tenant_id,
-        expected_state="Active",
-        iterations=iterations,
-        period=period,
+        pageserver_http, tenant_id, expected_state="Active", iterations=iterations
     )
 
 

test_runner/fixtures/utils.py

@@ -13,7 +13,6 @@ import allure
 from psycopg2.extensions import cursor
 
 from fixtures.log_helper import log
-from fixtures.types import TimelineId
 
 Fn = TypeVar("Fn", bound=Callable[..., Any])
 
@@ -187,15 +186,11 @@ def allure_attach_from_dir(dir: Path):
             allure.attach.file(source, name, attachment_type, extension)
 
 
-GRAFANA_URL = "https://neonprod.grafana.net"
-GRAFANA_EXPLORE_URL = f"{GRAFANA_URL}/explore"
-GRAFANA_TIMELINE_INSPECTOR_DASHBOARD_URL = f"{GRAFANA_URL}/d/8G011dlnk/timeline-inspector"
-LOGS_STAGING_DATASOURCE_ID = "xHHYY0dVz"
+DATASOURCE_ID = "xHHYY0dVz"
 
 
-def allure_add_grafana_links(host: str, timeline_id: TimelineId, start_ms: int, end_ms: int):
+def allure_add_grafana_links(host: str, start_ms: int, end_ms: int):
     """Add links to server logs in Grafana to Allure report"""
-    links = {}
     # We expect host to be in format like ep-divine-night-159320.us-east-2.aws.neon.build
     endpoint_id, region_id, _ = host.split(".", 2)
 
@@ -207,12 +202,12 @@ def allure_add_grafana_links(host: str, timeline_id: TimelineId, start_ms: int,
     }
 
     params: Dict[str, Any] = {
-        "datasource": LOGS_STAGING_DATASOURCE_ID,
+        "datasource": DATASOURCE_ID,
         "queries": [
             {
                 "expr": "<PUT AN EXPRESSION HERE>",
                 "refId": "A",
-                "datasource": {"type": "loki", "uid": LOGS_STAGING_DATASOURCE_ID},
+                "datasource": {"type": "loki", "uid": DATASOURCE_ID},
                 "editorMode": "code",
                 "queryType": "range",
             }
@@ -225,23 +220,8 @@ def allure_add_grafana_links(host: str, timeline_id: TimelineId, start_ms: int,
     for name, expr in expressions.items():
         params["queries"][0]["expr"] = expr
         query_string = urlencode({"orgId": 1, "left": json.dumps(params)})
-        links[name] = f"{GRAFANA_EXPLORE_URL}?{query_string}"
+        link = f"https://neonprod.grafana.net/explore?{query_string}"
 
-    timeline_qs = urlencode(
-        {
-            "orgId": 1,
-            "var-environment": "victoria-metrics-aws-dev",
-            "var-timeline_id": timeline_id,
-            "var-endpoint_id": endpoint_id,
-            "var-log_datasource": "grafanacloud-neonstaging-logs",
-            "from": start_ms,
-            "to": end_ms,
-        }
-    )
-    link = f"{GRAFANA_TIMELINE_INSPECTOR_DASHBOARD_URL}?{timeline_qs}"
-    links["Timeline Inspector"] = link
-
-    for name, link in links.items():
         allure.dynamic.link(link, name=name)
         log.info(f"{name}: {link}")
 

test_runner/performance/test_branch_creation.py

@@ -52,13 +52,13 @@ def test_branch_creation_heavy_write(neon_compare: NeonCompare, n_branches: int)
     def run_pgbench(branch: str):
         log.info(f"Start a pgbench workload on branch {branch}")
 
-        endpoint = env.endpoints.create_start(branch, tenant_id=tenant)
-        connstr = endpoint.connstr()
+        pg = env.postgres.create_start(branch, tenant_id=tenant)
+        connstr = pg.connstr()
 
         pg_bin.run_capture(["pgbench", "-i", connstr])
         pg_bin.run_capture(["pgbench", "-c10", "-T10", connstr])
 
-        endpoint.stop()
+        pg.stop()
 
     env.neon_cli.create_branch("b0", tenant_id=tenant)
 
@@ -96,8 +96,8 @@ def test_branch_creation_many(neon_compare: NeonCompare, n_branches: int):
 
     env.neon_cli.create_branch("b0")
 
-    endpoint = env.endpoints.create_start("b0")
-    neon_compare.pg_bin.run_capture(["pgbench", "-i", "-s10", endpoint.connstr()])
+    pg = env.postgres.create_start("b0")
+    neon_compare.pg_bin.run_capture(["pgbench", "-i", "-s10", pg.connstr()])
 
     branch_creation_durations = []
 
@@ -124,15 +124,15 @@ def test_branch_creation_many_relations(neon_compare: NeonCompare):
 
     timeline_id = env.neon_cli.create_branch("root")
 
-    endpoint = env.endpoints.create_start("root")
-    with closing(endpoint.connect()) as conn:
+    pg = env.postgres.create_start("root")
+    with closing(pg.connect()) as conn:
         with conn.cursor() as cur:
             for i in range(10000):
                 cur.execute(f"CREATE TABLE t{i} as SELECT g FROM generate_series(1, 1000) g")
 
     # Wait for the pageserver to finish processing all the pending WALs,
     # as we don't want the LSN wait time to be included during the branch creation
-    flush_lsn = Lsn(endpoint.safe_psql("SELECT pg_current_wal_flush_lsn()")[0][0])
+    flush_lsn = Lsn(pg.safe_psql("SELECT pg_current_wal_flush_lsn()")[0][0])
     wait_for_last_record_lsn(
         env.pageserver.http_client(), env.initial_tenant, timeline_id, flush_lsn
     )
@@ -142,7 +142,7 @@ def test_branch_creation_many_relations(neon_compare: NeonCompare):
 
     # run a concurrent insertion to make the ancestor "busy" during the branch creation
     thread = threading.Thread(
-        target=endpoint.safe_psql, args=("INSERT INTO t0 VALUES (generate_series(1, 100000))",)
+        target=pg.safe_psql, args=("INSERT INTO t0 VALUES (generate_series(1, 100000))",)
     )
     thread.start()
 

test_runner/performance/test_branching.py

@@ -42,41 +42,41 @@ def test_compare_child_and_root_pgbench_perf(neon_compare: NeonCompare):
         neon_compare.zenbenchmark.record_pg_bench_result(branch, res)
 
     env.neon_cli.create_branch("root")
-    endpoint_root = env.endpoints.create_start("root")
-    pg_bin.run_capture(["pgbench", "-i", endpoint_root.connstr(), "-s10"])
+    pg_root = env.postgres.create_start("root")
+    pg_bin.run_capture(["pgbench", "-i", pg_root.connstr(), "-s10"])
 
-    fork_at_current_lsn(env, endpoint_root, "child", "root")
+    fork_at_current_lsn(env, pg_root, "child", "root")
 
-    endpoint_child = env.endpoints.create_start("child")
+    pg_child = env.postgres.create_start("child")
 
-    run_pgbench_on_branch("root", ["pgbench", "-c10", "-T10", endpoint_root.connstr()])
-    run_pgbench_on_branch("child", ["pgbench", "-c10", "-T10", endpoint_child.connstr()])
+    run_pgbench_on_branch("root", ["pgbench", "-c10", "-T10", pg_root.connstr()])
+    run_pgbench_on_branch("child", ["pgbench", "-c10", "-T10", pg_child.connstr()])
 
 
 def test_compare_child_and_root_write_perf(neon_compare: NeonCompare):
     env = neon_compare.env
     env.neon_cli.create_branch("root")
-    endpoint_root = env.endpoints.create_start("root")
+    pg_root = env.postgres.create_start("root")
 
-    endpoint_root.safe_psql(
+    pg_root.safe_psql(
         "CREATE TABLE foo(key serial primary key, t text default 'foooooooooooooooooooooooooooooooooooooooooooooooooooo')",
     )
 
     env.neon_cli.create_branch("child", "root")
-    endpoint_child = env.endpoints.create_start("child")
+    pg_child = env.postgres.create_start("child")
 
     with neon_compare.record_duration("root_run_duration"):
-        endpoint_root.safe_psql("INSERT INTO foo SELECT FROM generate_series(1,1000000)")
+        pg_root.safe_psql("INSERT INTO foo SELECT FROM generate_series(1,1000000)")
     with neon_compare.record_duration("child_run_duration"):
-        endpoint_child.safe_psql("INSERT INTO foo SELECT FROM generate_series(1,1000000)")
+        pg_child.safe_psql("INSERT INTO foo SELECT FROM generate_series(1,1000000)")
 
 
 def test_compare_child_and_root_read_perf(neon_compare: NeonCompare):
     env = neon_compare.env
     env.neon_cli.create_branch("root")
-    endpoint_root = env.endpoints.create_start("root")
+    pg_root = env.postgres.create_start("root")
 
-    endpoint_root.safe_psql_many(
+    pg_root.safe_psql_many(
         [
             "CREATE TABLE foo(key serial primary key, t text default 'foooooooooooooooooooooooooooooooooooooooooooooooooooo')",
             "INSERT INTO foo SELECT FROM generate_series(1,1000000)",
@@ -84,12 +84,12 @@ def test_compare_child_and_root_read_perf(neon_compare: NeonCompare):
     )
 
     env.neon_cli.create_branch("child", "root")
-    endpoint_child = env.endpoints.create_start("child")
+    pg_child = env.postgres.create_start("child")
 
     with neon_compare.record_duration("root_run_duration"):
-        endpoint_root.safe_psql("SELECT count(*) from foo")
+        pg_root.safe_psql("SELECT count(*) from foo")
     with neon_compare.record_duration("child_run_duration"):
-        endpoint_child.safe_psql("SELECT count(*) from foo")
+        pg_child.safe_psql("SELECT count(*) from foo")
 
 
 # -----------------------------------------------------------------------

test_runner/performance/test_bulk_tenant_create.py

@@ -35,14 +35,14 @@ def test_bulk_tenant_create(
         # if use_safekeepers == 'with_sa':
         #    wa_factory.start_n_new(3)
 
-        endpoint_tenant = env.endpoints.create_start(
+        pg_tenant = env.postgres.create_start(
             f"test_bulk_tenant_create_{tenants_count}_{i}", tenant_id=tenant
         )
 
         end = timeit.default_timer()
         time_slices.append(end - start)
 
-        endpoint_tenant.stop()
+        pg_tenant.stop()
 
     zenbenchmark.record(
         "tenant_creation_time",

test_runner/performance/test_bulk_update.py

@@ -18,8 +18,8 @@ def test_bulk_update(neon_env_builder: NeonEnvBuilder, zenbenchmark, fillfactor)
 
     timeline_id = env.neon_cli.create_branch("test_bulk_update")
     tenant_id = env.initial_tenant
-    endpoint = env.endpoints.create_start("test_bulk_update")
-    cur = endpoint.connect().cursor()
+    pg = env.postgres.create_start("test_bulk_update")
+    cur = pg.connect().cursor()
     cur.execute("set statement_timeout=0")
 
     cur.execute(f"create table t(x integer) WITH (fillfactor={fillfactor})")
@@ -28,13 +28,13 @@ def test_bulk_update(neon_env_builder: NeonEnvBuilder, zenbenchmark, fillfactor)
         cur.execute(f"insert into t values (generate_series(1,{n_records}))")
 
     cur.execute("vacuum t")
-    wait_for_last_flush_lsn(env, endpoint, tenant_id, timeline_id)
+    wait_for_last_flush_lsn(env, pg, tenant_id, timeline_id)
 
     with zenbenchmark.record_duration("update-no-prefetch"):
         cur.execute("update t set x=x+1")
 
     cur.execute("vacuum t")
-    wait_for_last_flush_lsn(env, endpoint, tenant_id, timeline_id)
+    wait_for_last_flush_lsn(env, pg, tenant_id, timeline_id)
 
     with zenbenchmark.record_duration("delete-no-prefetch"):
         cur.execute("delete from t")
@@ -50,13 +50,13 @@ def test_bulk_update(neon_env_builder: NeonEnvBuilder, zenbenchmark, fillfactor)
         cur.execute(f"insert into t2 values (generate_series(1,{n_records}))")
 
     cur.execute("vacuum t2")
-    wait_for_last_flush_lsn(env, endpoint, tenant_id, timeline_id)
+    wait_for_last_flush_lsn(env, pg, tenant_id, timeline_id)
 
     with zenbenchmark.record_duration("update-with-prefetch"):
         cur.execute("update t2 set x=x+1")
 
     cur.execute("vacuum t2")
-    wait_for_last_flush_lsn(env, endpoint, tenant_id, timeline_id)
+    wait_for_last_flush_lsn(env, pg, tenant_id, timeline_id)
 
     with zenbenchmark.record_duration("delete-with-prefetch"):
         cur.execute("delete from t2")

test_runner/performance/test_compaction.py

@@ -33,11 +33,11 @@ def test_compaction(neon_compare: NeonCompare):
 
     # Create some tables, and run a bunch of INSERTs and UPDATes on them,
     # to generate WAL and layers
-    endpoint = env.endpoints.create_start(
+    pg = env.postgres.create_start(
         "main", tenant_id=tenant_id, config_lines=["shared_buffers=512MB"]
     )
 
-    with closing(endpoint.connect()) as conn:
+    with closing(pg.connect()) as conn:
         with conn.cursor() as cur:
             for i in range(100):
                 cur.execute(f"create table tbl{i} (i int, j int);")
@@ -45,7 +45,7 @@ def test_compaction(neon_compare: NeonCompare):
                 for j in range(100):
                     cur.execute(f"update tbl{i} set j = {j};")
 
-    wait_for_last_flush_lsn(env, endpoint, tenant_id, timeline_id)
+    wait_for_last_flush_lsn(env, pg, tenant_id, timeline_id)
 
     # First compaction generates L1 layers
     with neon_compare.zenbenchmark.record_duration("compaction"):

test_runner/performance/test_latency.py

@@ -2,13 +2,13 @@ import threading
 
 import pytest
 from fixtures.compare_fixtures import PgCompare
-from fixtures.neon_fixtures import PgProtocol
+from fixtures.neon_fixtures import Postgres
 
 from performance.test_perf_pgbench import get_scales_matrix
 from performance.test_wal_backpressure import record_read_latency
 
 
-def start_write_workload(pg: PgProtocol, scale: int = 10):
+def start_write_workload(pg: Postgres, scale: int = 10):
     with pg.connect().cursor() as cur:
         cur.execute(f"create table big as select generate_series(1,{scale*100_000})")
 

test_runner/performance/test_layer_map.py

@@ -25,8 +25,8 @@ def test_layer_map(neon_env_builder: NeonEnvBuilder, zenbenchmark):
     )
 
     env.neon_cli.create_timeline("test_layer_map", tenant_id=tenant)
-    endpoint = env.endpoints.create_start("test_layer_map", tenant_id=tenant)
-    cur = endpoint.connect().cursor()
+    pg = env.postgres.create_start("test_layer_map", tenant_id=tenant)
+    cur = pg.connect().cursor()
     cur.execute("create table t(x integer)")
     for i in range(n_iters):
         cur.execute(f"insert into t values (generate_series(1,{n_records}))")

test_runner/performance/test_startup.py

@@ -14,19 +14,19 @@ def test_startup(neon_env_builder: NeonEnvBuilder, zenbenchmark: NeonBenchmarker
     # Start
     env.neon_cli.create_branch("test_startup")
     with zenbenchmark.record_duration("startup_time"):
-        endpoint = env.endpoints.create_start("test_startup")
-        endpoint.safe_psql("select 1;")
+        pg = env.postgres.create_start("test_startup")
+        pg.safe_psql("select 1;")
 
     # Restart
-    endpoint.stop_and_destroy()
+    pg.stop_and_destroy()
     with zenbenchmark.record_duration("restart_time"):
-        endpoint.create_start("test_startup")
-        endpoint.safe_psql("select 1;")
+        pg.create_start("test_startup")
+        pg.safe_psql("select 1;")
 
     # Fill up
     num_rows = 1000000  # 30 MB
     num_tables = 100
-    with closing(endpoint.connect()) as conn:
+    with closing(pg.connect()) as conn:
         with conn.cursor() as cur:
             for i in range(num_tables):
                 cur.execute(f"create table t_{i} (i integer);")
@@ -34,18 +34,18 @@ def test_startup(neon_env_builder: NeonEnvBuilder, zenbenchmark: NeonBenchmarker
 
     # Read
     with zenbenchmark.record_duration("read_time"):
-        endpoint.safe_psql("select * from t_0;")
+        pg.safe_psql("select * from t_0;")
 
     # Read again
     with zenbenchmark.record_duration("second_read_time"):
-        endpoint.safe_psql("select * from t_0;")
+        pg.safe_psql("select * from t_0;")
 
     # Restart
-    endpoint.stop_and_destroy()
+    pg.stop_and_destroy()
     with zenbenchmark.record_duration("restart_with_data"):
-        endpoint.create_start("test_startup")
-        endpoint.safe_psql("select 1;")
+        pg.create_start("test_startup")
+        pg.safe_psql("select 1;")
 
     # Read
     with zenbenchmark.record_duration("read_after_restart"):
-        endpoint.safe_psql("select * from t_0;")
+        pg.safe_psql("select * from t_0;")

test_runner/regress/test_ancestor_branch.py

@@ -22,8 +22,8 @@ def test_ancestor_branch(neon_env_builder: NeonEnvBuilder):
 
     pageserver_http.configure_failpoints(("flush-frozen-before-sync", "sleep(10000)"))
 
-    endpoint_branch0 = env.endpoints.create_start("main", tenant_id=tenant)
-    branch0_cur = endpoint_branch0.connect().cursor()
+    pg_branch0 = env.postgres.create_start("main", tenant_id=tenant)
+    branch0_cur = pg_branch0.connect().cursor()
     branch0_timeline = TimelineId(query_scalar(branch0_cur, "SHOW neon.timeline_id"))
     log.info(f"b0 timeline {branch0_timeline}")
 
@@ -44,10 +44,10 @@ def test_ancestor_branch(neon_env_builder: NeonEnvBuilder):
 
     # Create branch1.
     env.neon_cli.create_branch("branch1", "main", tenant_id=tenant, ancestor_start_lsn=lsn_100)
-    endpoint_branch1 = env.endpoints.create_start("branch1", tenant_id=tenant)
+    pg_branch1 = env.postgres.create_start("branch1", tenant_id=tenant)
     log.info("postgres is running on 'branch1' branch")
 
-    branch1_cur = endpoint_branch1.connect().cursor()
+    branch1_cur = pg_branch1.connect().cursor()
     branch1_timeline = TimelineId(query_scalar(branch1_cur, "SHOW neon.timeline_id"))
     log.info(f"b1 timeline {branch1_timeline}")
 
@@ -67,9 +67,9 @@ def test_ancestor_branch(neon_env_builder: NeonEnvBuilder):
 
     # Create branch2.
     env.neon_cli.create_branch("branch2", "branch1", tenant_id=tenant, ancestor_start_lsn=lsn_200)
-    endpoint_branch2 = env.endpoints.create_start("branch2", tenant_id=tenant)
+    pg_branch2 = env.postgres.create_start("branch2", tenant_id=tenant)
     log.info("postgres is running on 'branch2' branch")
-    branch2_cur = endpoint_branch2.connect().cursor()
+    branch2_cur = pg_branch2.connect().cursor()
 
     branch2_timeline = TimelineId(query_scalar(branch2_cur, "SHOW neon.timeline_id"))
     log.info(f"b2 timeline {branch2_timeline}")

test_runner/regress/test_auth.py

@@ -64,9 +64,9 @@ def test_compute_auth_to_pageserver(neon_env_builder: NeonEnvBuilder):
 
     branch = "test_compute_auth_to_pageserver"
     env.neon_cli.create_branch(branch)
-    endpoint = env.endpoints.create_start(branch)
+    pg = env.postgres.create_start(branch)
 
-    with closing(endpoint.connect()) as conn:
+    with closing(pg.connect()) as conn:
         with conn.cursor() as cur:
             # we rely upon autocommit after each statement
             # as waiting for acceptors happens there
@@ -83,7 +83,7 @@ def test_auth_failures(neon_env_builder: NeonEnvBuilder, auth_enabled: bool):
 
     branch = f"test_auth_failures_auth_enabled_{auth_enabled}"
     timeline_id = env.neon_cli.create_branch(branch)
-    env.endpoints.create_start(branch)
+    env.postgres.create_start(branch)
 
     tenant_token = env.auth_keys.generate_tenant_token(env.initial_tenant)
     invalid_tenant_token = env.auth_keys.generate_tenant_token(TenantId.generate())