unset current dir for safekeeper

.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 = "3"
+dep-format-version = "2"
 
 # Setting workspace.resolver = "2" in the root Cargo.toml is HIGHLY recommended.
 # Hakari works much better with the new feature resolver.

.dockerignore

@@ -15,7 +15,6 @@
 !proxy/
 !safekeeper/
 !storage_broker/
-!trace/
 !vendor/postgres-v14/
 !vendor/postgres-v15/
 !workspace_hack/

.github/PULL_REQUEST_TEMPLATE/release-pr.md

@@ -14,7 +14,7 @@
 - [ ] 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)
 - [ ] Check [recent operation failures](https://console.neon.tech/admin/operations?action=create_timeline%2Cstart_compute%2Cstop_compute%2Csuspend_compute%2Capply_config%2Cdelete_timeline%2Cdelete_tenant%2Ccreate_branch%2Ccheck_availability&sort=updated_at&order=desc&had_retries=some)
-- [ ] Check [cloud SLO dashboard](https://neonprod.grafana.net/d/_oWcBMJ7k/cloud-slos?orgId=1)
-- [ ] Check [compute startup metrics dashboard](https://neonprod.grafana.net/d/5OkYJEmVz/compute-startup-time)
+- [ ] Check [cloud SLO dashboard](https://observer.zenith.tech/d/_oWcBMJ7k/cloud-slos?orgId=1)
+- [ ] Check [compute startup metrics dashboard](https://observer.zenith.tech/d/5OkYJEmVz/compute-startup-time)
 
 <!-- List everything that should be done **after** release, any admin UI configuration / Grafana dashboard / alert changes / setting changes / etc -->

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

@@ -123,8 +123,8 @@ runs:
           exit 1
         fi
         if [[ "${{ inputs.run_in_parallel }}" == "true" ]]; then
-          # -n16 uses sixteen processes to run tests via pytest-xdist
-          EXTRA_PARAMS="-n16 $EXTRA_PARAMS"
+          # -n4 uses four processes to run tests via pytest-xdist
+          EXTRA_PARAMS="-n4 $EXTRA_PARAMS"
 
           # --dist=loadgroup points tests marked with @pytest.mark.xdist_group
           # to the same worker to make @pytest.mark.order work with xdist

.github/ansible/deploy.yaml

@@ -117,8 +117,7 @@
       shell:
         cmd: |
           INSTANCE_ID=$(curl -s http://169.254.169.254/latest/meta-data/instance-id)
-          curl -sfS -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" {{ console_mgmt_base_url }}/management/api/v2/pageservers/$INSTANCE_ID | jq '.version = {{ current_version }}' > /tmp/new_version
-          curl -sfS -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" -X POST -d@/tmp/new_version {{ console_mgmt_base_url }}/management/api/v2/pageservers
+          curl -sfS -d '{"version": {{ current_version }} }' -X PATCH {{ console_mgmt_base_url }}/api/v1/pageservers/$INSTANCE_ID
       tags:
       - pageserver
 
@@ -187,7 +186,6 @@
       shell:
         cmd: |
           INSTANCE_ID=$(curl -s http://169.254.169.254/latest/meta-data/instance-id)
-          curl -sfS -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" {{ console_mgmt_base_url }}/management/api/v2/safekeepers/$INSTANCE_ID | jq '.version = {{ current_version }}' > /tmp/new_version
-          curl -sfS -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" -X POST -d@/tmp/new_version {{ console_mgmt_base_url }}/management/api/v2/safekeepers
+          curl -sfS -d '{"version": {{ current_version }} }' -X PATCH {{ console_mgmt_base_url }}/api/v1/safekeepers/$INSTANCE_ID
       tags:
       - safekeeper

.github/ansible/neon-stress.hosts.yaml

@@ -0,0 +1,32 @@
+storage:
+  vars:
+    bucket_name: neon-storage-ireland
+    bucket_region: eu-west-1
+    console_mgmt_base_url: http://neon-stress-console.local
+    broker_endpoint: http://storage-broker.neon-stress.local:50051
+    safekeeper_enable_s3_offload: 'false'
+    pageserver_config_stub:
+      pg_distrib_dir: /usr/local
+      remote_storage:
+        bucket_name: "{{ bucket_name }}"
+        bucket_region: "{{ bucket_region }}"
+        prefix_in_bucket: "{{ inventory_hostname }}"
+    safekeeper_s3_prefix: neon-stress/wal
+    hostname_suffix: ".local"
+    remote_user: admin
+    sentry_environment: development
+  children:
+    pageservers:
+      hosts:
+        neon-stress-ps-1:
+          console_region_id: aws-eu-west-1
+        neon-stress-ps-2:
+          console_region_id: aws-eu-west-1
+    safekeepers:
+      hosts:
+        neon-stress-sk-1:
+          console_region_id: aws-eu-west-1
+        neon-stress-sk-2:
+          console_region_id: aws-eu-west-1
+        neon-stress-sk-3:
+          console_region_id: aws-eu-west-1

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

@@ -6,8 +6,6 @@ storage:
     broker_endpoint: http://storage-broker-lb.epsilon.ap-southeast-1.internal.aws.neon.tech:50051
     pageserver_config_stub:
       pg_distrib_dir: /usr/local
-      metric_collection_endpoint: http://console-release.local/billing/api/v1/usage_events
-      metric_collection_interval: 10min
       remote_storage:
         bucket_name: "{{ bucket_name }}"
         bucket_region: "{{ bucket_region }}"

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

@@ -6,8 +6,6 @@ storage:
     broker_endpoint: http://storage-broker-lb.gamma.eu-central-1.internal.aws.neon.tech:50051
     pageserver_config_stub:
       pg_distrib_dir: /usr/local
-      metric_collection_endpoint: http://console-release.local/billing/api/v1/usage_events
-      metric_collection_interval: 10min
       remote_storage:
         bucket_name: "{{ bucket_name }}"
         bucket_region: "{{ bucket_region }}"

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

@@ -6,8 +6,6 @@ storage:
     broker_endpoint: http://storage-broker-lb.delta.us-east-2.internal.aws.neon.tech:50051
     pageserver_config_stub:
       pg_distrib_dir: /usr/local
-      metric_collection_endpoint: http://console-release.local/billing/api/v1/usage_events
-      metric_collection_interval: 10min
       remote_storage:
         bucket_name: "{{ bucket_name }}"
         bucket_region: "{{ bucket_region }}"
@@ -36,4 +34,4 @@ storage:
           ansible_host:  i-06d113fb73bfddeb0
         safekeeper-2.us-east-2.aws.neon.tech:
           ansible_host:  i-09f66c8e04afff2e8
-
+          

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

@@ -6,8 +6,6 @@ storage:
     broker_endpoint: http://storage-broker-lb.eta.us-west-2.internal.aws.neon.tech:50051
     pageserver_config_stub:
       pg_distrib_dir: /usr/local
-      metric_collection_endpoint: http://console-release.local/billing/api/v1/usage_events
-      metric_collection_interval: 10min
       remote_storage:
         bucket_name: "{{ bucket_name }}"
         bucket_region: "{{ bucket_region }}"
@@ -27,8 +25,6 @@ storage:
           ansible_host: i-0d9f6dfae0e1c780d 
         pageserver-1.us-west-2.aws.neon.tech:
           ansible_host: i-0c834be1dddba8b3f
-        pageserver-2.us-west-2.aws.neon.tech:
-          ansible_host: i-051642d372c0a4f32
 
     safekeepers:
       hosts:

.github/ansible/production.hosts.yaml

@@ -7,8 +7,6 @@ storage:
     broker_endpoint: http://storage-broker.prod.local:50051
     pageserver_config_stub:
       pg_distrib_dir: /usr/local
-      metric_collection_endpoint: http://console-release.local/billing/api/v1/usage_events
-      metric_collection_interval: 10min
       remote_storage:
         bucket_name: "{{ bucket_name }}"
         bucket_region: "{{ bucket_region }}"
@@ -36,5 +34,5 @@ storage:
           console_region_id: aws-us-west-2
         zenith-1-sk-2:
           console_region_id: aws-us-west-2
-        zenith-1-sk-4:
+        zenith-1-sk-3:
           console_region_id: aws-us-west-2

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

@@ -6,8 +6,6 @@ storage:
     broker_endpoint: http://storage-broker-lb.zeta.eu-west-1.internal.aws.neon.build:50051
     pageserver_config_stub:
       pg_distrib_dir: /usr/local
-      metric_collection_endpoint: http://console-staging.local/billing/api/v1/usage_events
-      metric_collection_interval: 10min
       remote_storage:
         bucket_name: "{{ bucket_name }}"
         bucket_region: "{{ bucket_region }}"
@@ -18,7 +16,7 @@ storage:
     ansible_aws_ssm_region: eu-west-1
     ansible_aws_ssm_bucket_name: neon-dev-storage-eu-west-1
     console_region_id: aws-eu-west-1
-    sentry_environment: staging
+    sentry_environment: development
 
   children:
     pageservers:

.github/ansible/staging.hosts.yaml

@@ -0,0 +1,35 @@
+storage:
+  vars:
+    bucket_name: zenith-staging-storage-us-east-1
+    bucket_region: us-east-1
+    console_mgmt_base_url: http://console-staging.local
+    broker_endpoint: http://storage-broker.staging.local:50051
+    pageserver_config_stub:
+      pg_distrib_dir: /usr/local
+      remote_storage:
+        bucket_name: "{{ bucket_name }}"
+        bucket_region: "{{ bucket_region }}"
+        prefix_in_bucket: "{{ inventory_hostname }}"
+    safekeeper_s3_prefix: us-stage/wal
+    hostname_suffix: ".local"
+    remote_user: admin
+    sentry_environment: development
+
+  children:
+    pageservers:
+      hosts:
+        zenith-us-stage-ps-2:
+          console_region_id: aws-us-east-1
+        zenith-us-stage-ps-3:
+          console_region_id: aws-us-east-1
+        zenith-us-stage-ps-4:
+          console_region_id: aws-us-east-1
+
+    safekeepers:
+      hosts:
+        zenith-us-stage-sk-4:
+          console_region_id: aws-us-east-1
+        zenith-us-stage-sk-5:
+          console_region_id: aws-us-east-1
+        zenith-us-stage-sk-6:
+          console_region_id: aws-us-east-1

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

@@ -6,8 +6,6 @@ storage:
     broker_endpoint: http://storage-broker-lb.beta.us-east-2.internal.aws.neon.build:50051
     pageserver_config_stub:
       pg_distrib_dir: /usr/local
-      metric_collection_endpoint: http://console-staging.local/billing/api/v1/usage_events
-      metric_collection_interval: 10min
       remote_storage:
         bucket_name: "{{ bucket_name }}"
         bucket_region: "{{ bucket_region }}"
@@ -18,7 +16,7 @@ storage:
     ansible_aws_ssm_region: us-east-2
     ansible_aws_ssm_bucket_name: neon-staging-storage-us-east-2
     console_region_id: aws-us-east-2
-    sentry_environment: staging
+    sentry_environment: development
 
   children:
     pageservers:
@@ -27,10 +25,6 @@ storage:
           ansible_host: i-0c3e70929edb5d691
         pageserver-1.us-east-2.aws.neon.build:
           ansible_host: i-0565a8b4008aa3f40
-        pageserver-2.us-east-2.aws.neon.build:
-          ansible_host: i-01e31cdf7e970586a
-        pageserver-3.us-east-2.aws.neon.build:
-          ansible_host: i-0602a0291365ef7cc
 
     safekeepers:
       hosts:

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

@@ -8,10 +8,7 @@ settings:
   authBackend: "console"
   authEndpoint: "http://console-staging.local/management/api/v2"
   domain: "*.eu-west-1.aws.neon.build"
-  sentryEnvironment: "staging"
-  wssPort: 8443
-  metricCollectionEndpoint: "http://console-staging.local/billing/api/v1/usage_events"
-  metricCollectionInterval: "1min"
+  sentryEnvironment: "development"
 
 # -- Additional labels for neon-proxy pods
 podLabels:
@@ -26,7 +23,6 @@ exposedService:
     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: eu-west-1.aws.neon.build
-  httpsPort: 443
 
 #metrics:
 #  enabled: true

.github/helm-values/dev-eu-west-1-zeta.neon-storage-broker.yaml

@@ -49,4 +49,4 @@ extraManifests:
           - "{{ .Release.Namespace }}"
 
 settings:
-  sentryEnvironment: "staging"
+  sentryEnvironment: "development"

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

@@ -8,10 +8,7 @@ settings:
   authBackend: "link"
   authEndpoint: "https://console.stage.neon.tech/authenticate_proxy_request/"
   uri: "https://console.stage.neon.tech/psql_session/"
-  domain: "pg.neon.build"
-  sentryEnvironment: "staging"
-  metricCollectionEndpoint: "http://console-staging.local/billing/api/v1/usage_events"
-  metricCollectionInterval: "1min"
+  sentryEnvironment: "development"
 
 # -- Additional labels for neon-proxy-link pods
 podLabels:

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

@@ -8,10 +8,7 @@ settings:
   authBackend: "console"
   authEndpoint: "http://console-staging.local/management/api/v2"
   domain: "*.cloud.stage.neon.tech"
-  sentryEnvironment: "staging"
-  wssPort: 8443
-  metricCollectionEndpoint: "http://console-staging.local/billing/api/v1/usage_events"
-  metricCollectionInterval: "1min"
+  sentryEnvironment: "development"
 
 # -- Additional labels for neon-proxy pods
 podLabels:
@@ -26,7 +23,6 @@ exposedService:
     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: neon-proxy-scram-legacy.beta.us-east-2.aws.neon.build
-  httpsPort: 443
 
 #metrics:
 #  enabled: true

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

@@ -8,10 +8,7 @@ settings:
   authBackend: "console"
   authEndpoint: "http://console-staging.local/management/api/v2"
   domain: "*.us-east-2.aws.neon.build"
-  sentryEnvironment: "staging"
-  wssPort: 8443
-  metricCollectionEndpoint: "http://console-staging.local/billing/api/v1/usage_events"
-  metricCollectionInterval: "1min"
+  sentryEnvironment: "development"
 
 # -- Additional labels for neon-proxy pods
 podLabels:
@@ -26,7 +23,6 @@ exposedService:
     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-2.aws.neon.build
-  httpsPort: 443
 
 #metrics:
 #  enabled: true

.github/helm-values/dev-us-east-2-beta.neon-storage-broker.yaml

@@ -49,4 +49,4 @@ extraManifests:
           - "{{ .Release.Namespace }}"
 
 settings:
-  sentryEnvironment: "staging"
+  sentryEnvironment: "development"

.github/helm-values/neon-stress.neon-storage-broker.yaml

@@ -0,0 +1,56 @@
+# Helm chart values for neon-storage-broker
+podLabels:
+  neon_env: neon-stress
+  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.neon-stress.local
+  # service.type -- Service type
+  type: LoadBalancer
+  # service.port -- broker listen port
+  port: 50051
+
+ingress:
+  enabled: false
+
+metrics:
+  enabled: true
+  serviceMonitor:
+    enabled: true
+    selector:
+      release: kube-prometheus-stack
+
+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: "development"

.github/helm-values/neon-stress.proxy-scram.yaml

@@ -0,0 +1,52 @@
+fullnameOverride: "neon-stress-proxy-scram"
+
+settings:
+  authBackend: "console"
+  authEndpoint: "http://neon-stress-console.local/management/api/v2"
+  domain: "*.stress.neon.tech"
+  sentryEnvironment: "development"
+
+podLabels:
+  zenith_service: proxy-scram
+  zenith_env: staging
+  zenith_region: eu-west-1
+  zenith_region_slug: ireland
+
+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: '*.stress.neon.tech'
+
+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/neon-stress.proxy.yaml

@@ -0,0 +1,61 @@
+fullnameOverride: "neon-stress-proxy"
+
+settings:
+  authBackend: "link"
+  authEndpoint: "https://console.dev.neon.tech/authenticate_proxy_request/"
+  uri: "https://console.dev.neon.tech/psql_session/"
+  sentryEnvironment: "development"
+
+# -- Additional labels for zenith-proxy pods
+podLabels:
+  zenith_service: proxy
+  zenith_env: staging
+  zenith_region: eu-west-1
+  zenith_region_slug: ireland
+
+service:
+  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: internal
+    external-dns.alpha.kubernetes.io/hostname: neon-stress-proxy.local
+  type: LoadBalancer
+
+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: connect.dev.neon.tech
+
+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

@@ -9,9 +9,6 @@ settings:
   authEndpoint: "http://console-release.local/management/api/v2"
   domain: "*.ap-southeast-1.aws.neon.tech"
   sentryEnvironment: "production"
-  wssPort: 8443
-  metricCollectionEndpoint: "http://console-release.local/billing/api/v1/usage_events"
-  metricCollectionInterval: "10min"
 
 # -- Additional labels for neon-proxy pods
 podLabels:
@@ -26,7 +23,6 @@ exposedService:
     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: ap-southeast-1.aws.neon.tech
-  httpsPort: 443
 
 #metrics:
 #  enabled: true

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

@@ -9,9 +9,6 @@ settings:
   authEndpoint: "http://console-release.local/management/api/v2"
   domain: "*.eu-central-1.aws.neon.tech"
   sentryEnvironment: "production"
-  wssPort: 8443
-  metricCollectionEndpoint: "http://console-release.local/billing/api/v1/usage_events"
-  metricCollectionInterval: "10min"
 
 # -- Additional labels for neon-proxy pods
 podLabels:
@@ -26,7 +23,6 @@ exposedService:
     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: eu-central-1.aws.neon.tech
-  httpsPort: 443
 
 #metrics:
 #  enabled: true

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

@@ -9,9 +9,6 @@ settings:
   authEndpoint: "http://console-release.local/management/api/v2"
   domain: "*.us-east-2.aws.neon.tech"
   sentryEnvironment: "production"
-  wssPort: 8443
-  metricCollectionEndpoint: "http://console-release.local/billing/api/v1/usage_events"
-  metricCollectionInterval: "10min"
 
 # -- Additional labels for neon-proxy pods
 podLabels:
@@ -26,7 +23,6 @@ exposedService:
     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-2.aws.neon.tech
-  httpsPort: 443
 
 #metrics:
 #  enabled: true

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

@@ -9,9 +9,6 @@ settings:
   authEndpoint: "http://console-release.local/management/api/v2"
   domain: "*.us-west-2.aws.neon.tech"
   sentryEnvironment: "production"
-  wssPort: 8443
-  metricCollectionEndpoint: "http://console-release.local/billing/api/v1/usage_events"
-  metricCollectionInterval: "10min"
 
 # -- Additional labels for neon-proxy pods
 podLabels:
@@ -26,7 +23,6 @@ exposedService:
     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-west-2.aws.neon.tech
-  httpsPort: 443
 
 #metrics:
 #  enabled: true

.github/helm-values/production.proxy-scram.yaml

@@ -1,39 +1,28 @@
-# Helm chart values for neon-proxy-scram.
-# This is a YAML-formatted file.
-
-image:
-  repository: neondatabase/neon
-
 settings:
   authBackend: "console"
   authEndpoint: "http://console-release.local/management/api/v2"
   domain: "*.cloud.neon.tech"
   sentryEnvironment: "production"
-  wssPort: 8443
-  metricCollectionEndpoint: "http://console-release.local/billing/api/v1/usage_events"
-  metricCollectionInterval: "10min"
 
-# -- Additional labels for neon-proxy pods
 podLabels:
   zenith_service: proxy-scram
-  zenith_env: prod
+  zenith_env: production
   zenith_region: us-west-2
-  zenith_region_slug: us-west-2
+  zenith_region_slug: oregon
 
 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: neon-proxy-scram-legacy.eta.us-west-2.aws.neon.tech
-  httpsPort: 443
+    external-dns.alpha.kubernetes.io/hostname: '*.cloud.neon.tech'
 
-#metrics:
-#  enabled: true
-#  serviceMonitor:
-#    enabled: true
-#    selector:
-#      release: kube-prometheus-stack
+metrics:
+  enabled: true
+  serviceMonitor:
+    enabled: true
+    selector:
+      release: kube-prometheus-stack
 
 extraManifests:
   - apiVersion: operator.victoriametrics.com/v1beta1

.github/helm-values/production.proxy.yaml

@@ -1,37 +1,37 @@
-# Helm chart values for neon-proxy-link.
-# This is a YAML-formatted file.
-
-image:
-  repository: neondatabase/neon
-
 settings:
   authBackend: "link"
   authEndpoint: "https://console.neon.tech/authenticate_proxy_request/"
   uri: "https://console.neon.tech/psql_session/"
-  domain: "pg.neon.tech"
   sentryEnvironment: "production"
 
 # -- Additional labels for zenith-proxy pods
 podLabels:
   zenith_service: proxy
   zenith_env: production
-  zenith_region: us-east-2
-  zenith_region_slug: us-east-2
+  zenith_region: us-west-2
+  zenith_region_slug: oregon
 
 service:
-  type: LoadBalancer
   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: internal
-    external-dns.alpha.kubernetes.io/hostname: neon-proxy-link-mgmt.delta.us-east-2.aws.neon.tech
+    external-dns.alpha.kubernetes.io/hostname: proxy-release.local
+  type: LoadBalancer
 
 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: neon-proxy-link.delta.us-east-2.aws.neon.tech
+    external-dns.alpha.kubernetes.io/hostname: connect.neon.tech,pg.neon.tech
+
+metrics:
+  enabled: true
+  serviceMonitor:
+    enabled: true
+    selector:
+      release: kube-prometheus-stack
 
 extraManifests:
   - apiVersion: operator.victoriametrics.com/v1beta1

.github/helm-values/staging.neon-storage-broker.yaml

@@ -0,0 +1,56 @@
+# 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.staging.local
+  # service.type -- Service type
+  type: LoadBalancer
+  # service.port -- broker listen port
+  port: 50051
+
+ingress:
+  enabled: false
+
+metrics:
+  enabled: true
+  serviceMonitor:
+    enabled: true
+    selector:
+      release: kube-prometheus-stack
+
+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: "development"

.github/helm-values/staging.proxy-scram.yaml

@@ -0,0 +1,57 @@
+# Helm chart values for zenith-proxy.
+# This is a YAML-formatted file.
+
+image:
+  repository: neondatabase/neon
+
+settings:
+  authBackend: "console"
+  authEndpoint: "http://console-staging.local/management/api/v2"
+  domain: "*.cloud.stage.neon.tech"
+  sentryEnvironment: "development"
+
+# -- Additional labels for zenith-proxy pods
+podLabels:
+  zenith_service: proxy-scram
+  zenith_env: staging
+  zenith_region: us-east-1
+  zenith_region_slug: virginia
+
+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.stage.neon.tech
+
+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/staging.proxy.yaml

@@ -0,0 +1,57 @@
+# Helm chart values for zenith-proxy.
+# This is a YAML-formatted file.
+
+image:
+  repository: neondatabase/neon
+
+settings:
+  authBackend: "link"
+  authEndpoint: "https://console.stage.neon.tech/authenticate_proxy_request/"
+  uri: "https://console.stage.neon.tech/psql_session/"
+  sentryEnvironment: "development"
+
+# -- Additional labels for zenith-proxy pods
+podLabels:
+  zenith_service: proxy
+  zenith_env: staging
+  zenith_region: us-east-1
+  zenith_region_slug: virginia
+
+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: connect.stage.neon.tech
+
+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/pull_request_template.md

@@ -1,10 +0,0 @@
-## Describe your changes
-
-## Issue ticket number and link
-
-## Checklist before requesting a review
-- [ ] I have performed a self-review of my code.
-- [ ] If it is a core feature, I have added thorough tests.
-- [ ] Do we need to implement analytics? if so did you add the relevant metrics to the dashboard?
-- [ ] If this PR requires public announcement, mark it with /release-notes label and add several sentences in this section.
-

.github/workflows/benchmarking.yml

@@ -407,7 +407,7 @@ jobs:
 
     runs-on: [ self-hosted, us-east-2, x64 ]
     container:
-      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
+      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rustlegacy:pinned
       options: --init
 
     timeout-minutes: 360 # 6h
@@ -489,108 +489,3 @@ jobs:
         slack-message: "Periodic TPC-H perf testing ${{ matrix.platform }}: ${{ job.status }}\n${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}"
       env:
         SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
-
-  user-examples-compare:
-    if: success() || failure()
-    needs: [ tpch-compare ]
-
-    strategy:
-      fail-fast: false
-      matrix:
-        # neon-captest-prefetch: We have pre-created projects with prefetch enabled
-        # rds-aurora: Aurora Postgres Serverless v2 with autoscaling from 0.5 to 2 ACUs
-        # rds-postgres: RDS Postgres db.m5.large instance (2 vCPU, 8 GiB) with gp3 EBS storage
-        platform: [ neon-captest-prefetch, rds-postgres, rds-aurora ]
-
-    env:
-      POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
-      DEFAULT_PG_VERSION: 14
-      TEST_OUTPUT: /tmp/test_output
-      BUILD_TYPE: remote
-      SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref == 'refs/heads/main' ) }}
-      PLATFORM: ${{ matrix.platform }}
-
-    runs-on: [ self-hosted, us-east-2, x64 ]
-    container:
-      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
-      options: --init
-
-    timeout-minutes: 360 # 6h
-
-    steps:
-    - uses: actions/checkout@v3
-
-    - name: Download Neon artifact
-      uses: ./.github/actions/download
-      with:
-        name: neon-${{ runner.os }}-release-artifact
-        path: /tmp/neon/
-        prefix: latest
-
-    - name: Add Postgres binaries to PATH
-      run: |
-        ${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/bin/pgbench --version
-        echo "${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/bin" >> $GITHUB_PATH
-
-    - name: Set up Connection String
-      id: set-up-connstr
-      run: |
-        case "${PLATFORM}" in
-          neon-captest-prefetch)
-            CONNSTR=${{ secrets.BENCHMARK_USER_EXAMPLE_CAPTEST_CONNSTR }}
-            ;;
-          rds-aurora)
-            CONNSTR=${{ secrets.BENCHMARK_USER_EXAMPLE_RDS_AURORA_CONNSTR }}
-            ;;
-          rds-postgres)
-            CONNSTR=${{ secrets.BENCHMARK_USER_EXAMPLE_RDS_POSTGRES_CONNSTR }}
-            ;;
-          *)
-            echo 2>&1 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-prefetch', 'rds-aurora', or 'rds-postgres'"
-            exit 1
-            ;;
-        esac
-
-        echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
-
-        psql ${CONNSTR} -c "SELECT version();"
-
-    - name: Set database options
-      if: matrix.platform == 'neon-captest-prefetch'
-      run: |
-        DB_NAME=$(psql ${BENCHMARK_CONNSTR} --no-align --quiet -t -c "SELECT current_database()")
-
-        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET enable_seqscan_prefetch=on"
-        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET effective_io_concurrency=32"
-        psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET maintenance_io_concurrency=32"
-      env:
-        BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
-
-    - name: Run user examples
-      uses: ./.github/actions/run-python-test-set
-      with:
-        build_type: ${{ env.BUILD_TYPE }}
-        test_selection: performance/test_perf_olap.py
-        run_in_parallel: false
-        save_perf_report: ${{ env.SAVE_PERF_REPORT }}
-        extra_params: -m remote_cluster --timeout 21600 -k test_user_examples
-      env:
-        VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
-        PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
-        BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
-
-    - name: Create Allure report
-      if: success() || failure()
-      uses: ./.github/actions/allure-report
-      with:
-        action: generate
-        build_type: ${{ env.BUILD_TYPE }}
-
-    - name: Post to a Slack channel
-      if: ${{ github.event.schedule && failure() }}
-      uses: slackapi/slack-github-action@v1
-      with:
-        channel-id: "C033QLM5P7D" # dev-staging-stream
-        slack-message: "Periodic TPC-H perf testing ${{ matrix.platform }}: ${{ job.status }}\n${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}"
-      env:
-        SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}

.github/workflows/build_and_test.yml

@@ -1,4 +1,4 @@
-name: Build and Test
+name: Test and Deploy
 
 on:
   push:
@@ -19,12 +19,10 @@ concurrency:
 env:
   RUST_BACKTRACE: 1
   COPT: '-Werror'
-  AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_DEV }}
-  AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_KEY_DEV }}
 
 jobs:
   tag:
-    runs-on: [ self-hosted, gen3, small ]
+    runs-on: [ self-hosted, dev, x64 ]
     container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/base:pinned
     outputs:
       build-tag: ${{steps.build-tag.outputs.tag}}
@@ -52,9 +50,9 @@ jobs:
         id: build-tag
 
   check-codestyle-python:
-    runs-on: [ self-hosted, gen3, small ]
+    runs-on: [ self-hosted, dev, x64 ]
     container:
-      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
+      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/cloud:pinned
       options: --init
 
     steps:
@@ -87,7 +85,7 @@ jobs:
         run: poetry run mypy .
 
   check-codestyle-rust:
-    runs-on: [ self-hosted, gen3, large ]
+    runs-on: [ self-hosted, dev, x64 ]
     container:
       image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
       options: --init
@@ -99,21 +97,20 @@ jobs:
           submodules: true
           fetch-depth: 1
 
-#      Disabled for now
-#      - name: Restore cargo deps cache
-#        id: cache_cargo
-#        uses: actions/cache@v3
-#        with:
-#          path: |
-#            !~/.cargo/registry/src
-#            ~/.cargo/git/
-#            target/
-#          key: v1-${{ runner.os }}-cargo-clippy-${{ hashFiles('rust-toolchain.toml') }}-${{ hashFiles('Cargo.lock') }}
+      - name: Restore cargo deps cache
+        id: cache_cargo
+        uses: actions/cache@v3
+        with:
+          path: |
+            ~/.cargo/registry/
+            !~/.cargo/registry/src
+            ~/.cargo/git/
+            target/
+          key: v1-${{ runner.os }}-cargo-clippy-${{ hashFiles('rust-toolchain.toml') }}-${{ hashFiles('Cargo.lock') }}
 
       # Some of our rust modules use FFI and need those to be checked
       - name: Get postgres headers
         run: make postgres-headers -j$(nproc)
-
       - name: Run cargo clippy
         run: ./run_clippy.sh
 
@@ -129,13 +126,8 @@ jobs:
           cargo hakari generate --diff  # workspace-hack Cargo.toml is up-to-date
           cargo hakari manage-deps --dry-run  # all workspace crates depend on workspace-hack
 
-      # https://github.com/EmbarkStudios/cargo-deny
-      - name: Check rust licenses/bans/advisories/sources
-        if: ${{ !cancelled() }}
-        run: cargo deny check
-
   build-neon:
-    runs-on: [ self-hosted, gen3, large ]
+    runs-on: [ self-hosted, dev, x64 ]
     container:
       image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
       options: --init
@@ -143,6 +135,7 @@ jobs:
       fail-fast: false
       matrix:
         build_type: [ debug, release ]
+
     env:
       BUILD_TYPE: ${{ matrix.build_type }}
       GIT_VERSION: ${{ github.sha }}
@@ -184,37 +177,36 @@ jobs:
       # corresponding Cargo.toml files for their descriptions.
       - name: Set env variables
         run: |
-          CARGO_FEATURES="--features testing"
           if [[ $BUILD_TYPE == "debug" ]]; then
             cov_prefix="scripts/coverage --profraw-prefix=$GITHUB_JOB --dir=/tmp/coverage run"
+            CARGO_FEATURES="--features testing"
             CARGO_FLAGS="--locked $CARGO_FEATURES"
           elif [[ $BUILD_TYPE == "release" ]]; then
             cov_prefix=""
+            CARGO_FEATURES="--features testing,profiling"
             CARGO_FLAGS="--locked --release $CARGO_FEATURES"
           fi
           echo "cov_prefix=${cov_prefix}" >> $GITHUB_ENV
           echo "CARGO_FEATURES=${CARGO_FEATURES}" >> $GITHUB_ENV
           echo "CARGO_FLAGS=${CARGO_FLAGS}" >> $GITHUB_ENV
-          echo "CARGO_HOME=${GITHUB_WORKSPACE}/.cargo" >> $GITHUB_ENV
 
-      # Disabled for now
       # Don't include the ~/.cargo/registry/src directory. It contains just
       # uncompressed versions of the crates in ~/.cargo/registry/cache
       # directory, and it's faster to let 'cargo' to rebuild it from the
       # compressed crates.
-#      - name: Cache cargo deps
-#        id: cache_cargo
-#        uses: actions/cache@v3
-#        with:
-#          path: |
-#            ~/.cargo/registry/
-#            !~/.cargo/registry/src
-#            ~/.cargo/git/
-#            target/
-#          # Fall back to older versions of the key, if no cache for current Cargo.lock was found
-#          key: |
-#            v1-${{ runner.os }}-${{ matrix.build_type }}-cargo-${{ hashFiles('rust-toolchain.toml') }}-${{ hashFiles('Cargo.lock') }}
-#            v1-${{ runner.os }}-${{ matrix.build_type }}-cargo-${{ hashFiles('rust-toolchain.toml') }}-
+      - name: Cache cargo deps
+        id: cache_cargo
+        uses: actions/cache@v3
+        with:
+          path: |
+            ~/.cargo/registry/
+            !~/.cargo/registry/src
+            ~/.cargo/git/
+            target/
+          # Fall back to older versions of the key, if no cache for current Cargo.lock was found
+          key: |
+            v1-${{ runner.os }}-${{ matrix.build_type }}-cargo-${{ hashFiles('rust-toolchain.toml') }}-${{ hashFiles('Cargo.lock') }}
+            v1-${{ runner.os }}-${{ matrix.build_type }}-cargo-${{ hashFiles('rust-toolchain.toml') }}-
 
       - name: Cache postgres v14 build
         id: cache_pg_14
@@ -304,7 +296,7 @@ jobs:
         uses: ./.github/actions/save-coverage-data
 
   regress-tests:
-    runs-on: [ self-hosted, gen3, large ]
+    runs-on: [ self-hosted, dev, x64 ]
     container:
       image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
       options: --init
@@ -337,7 +329,7 @@ jobs:
         uses: ./.github/actions/save-coverage-data
 
   benchmarks:
-    runs-on: [ self-hosted, gen3, small ]
+    runs-on: [ self-hosted, dev, x64 ]
     container:
       image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
       options: --init
@@ -368,7 +360,7 @@ jobs:
       # while coverage is currently collected for the debug ones
 
   merge-allure-report:
-    runs-on: [ self-hosted, gen3, small ]
+    runs-on: [ self-hosted, dev, x64 ]
     container:
       image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
       options: --init
@@ -405,7 +397,7 @@ jobs:
           DATABASE_URL="$TEST_RESULT_CONNSTR" poetry run python3 scripts/ingest_regress_test_result.py --revision ${SHA} --reference ${GITHUB_REF} --build-type ${BUILD_TYPE} --ingest suites.json
 
   coverage-report:
-    runs-on: [ self-hosted, gen3, small ]
+    runs-on: [ self-hosted, dev, x64 ]
     container:
       image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
       options: --init
@@ -421,17 +413,16 @@ jobs:
           submodules: true
           fetch-depth: 1
 
-#      Disabled for now
-#      - name: Restore cargo deps cache
-#        id: cache_cargo
-#        uses: actions/cache@v3
-#        with:
-#          path: |
-#            ~/.cargo/registry/
-#            !~/.cargo/registry/src
-#            ~/.cargo/git/
-#            target/
-#          key: v1-${{ runner.os }}-${{ matrix.build_type }}-cargo-${{ hashFiles('rust-toolchain.toml') }}-${{ hashFiles('Cargo.lock') }}
+      - name: Restore cargo deps cache
+        id: cache_cargo
+        uses: actions/cache@v3
+        with:
+          path: |
+            ~/.cargo/registry/
+            !~/.cargo/registry/src
+            ~/.cargo/git/
+            target/
+          key: v1-${{ runner.os }}-${{ matrix.build_type }}-cargo-${{ hashFiles('rust-toolchain.toml') }}-${{ hashFiles('Cargo.lock') }}
 
       - name: Get Neon artifact
         uses: ./.github/actions/download
@@ -481,7 +472,7 @@ jobs:
             }"
 
   trigger-e2e-tests:
-    runs-on: [ self-hosted, gen3, small ]
+    runs-on: [ self-hosted, dev, x64 ]
     container:
       image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/base:pinned
       options: --init
@@ -526,10 +517,9 @@ jobs:
             }"
 
   neon-image:
-    runs-on: [ self-hosted, gen3, large ]
+    runs-on: [ self-hosted, dev, x64 ]
     needs: [ tag ]
-    # https://github.com/GoogleContainerTools/kaniko/issues/2005
-    container: gcr.io/kaniko-project/executor:v1.7.0-debug
+    container: gcr.io/kaniko-project/executor:v1.9.0-debug
     defaults:
       run:
         shell: sh -eu {0}
@@ -545,16 +535,12 @@ jobs:
         run: echo "{\"credsStore\":\"ecr-login\"}" > /kaniko/.docker/config.json
 
       - name: Kaniko build neon
-        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
-        run: rm -rf ~/.ecr
+        run: /kaniko/executor --snapshotMode=redo --cache=true --cache-repo 369495373322.dkr.ecr.eu-central-1.amazonaws.com/cache --snapshotMode=redo --context . --build-arg GIT_VERSION=${{ github.sha }} --destination 369495373322.dkr.ecr.eu-central-1.amazonaws.com/neon:${{needs.tag.outputs.build-tag}}
 
   compute-tools-image:
-    runs-on: [ self-hosted, gen3, large ]
+    runs-on: [ self-hosted, dev, x64 ]
     needs: [ tag ]
-    container: gcr.io/kaniko-project/executor:v1.7.0-debug
+    container: gcr.io/kaniko-project/executor:v1.9.0-debug
     defaults:
       run:
         shell: sh -eu {0}
@@ -567,19 +553,12 @@ jobs:
         run: echo "{\"credsStore\":\"ecr-login\"}" > /kaniko/.docker/config.json
 
       - name: Kaniko build compute tools
-        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}}
+        run: /kaniko/executor --snapshotMode=redo --cache=true --cache-repo 369495373322.dkr.ecr.eu-central-1.amazonaws.com/cache --snapshotMode=redo --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}}
 
-      - name: Cleanup ECR folder
-        run: rm -rf ~/.ecr
-
-  compute-node-image:
-    runs-on: [ self-hosted, gen3, large ]
-    container: gcr.io/kaniko-project/executor:v1.7.0-debug
+  compute-node-image-v14:
+    runs-on: [ self-hosted, dev, x64 ]
+    container: gcr.io/kaniko-project/executor:v1.9.0-debug
     needs: [ tag ]
-    strategy:
-      fail-fast: false
-      matrix:
-        version: [ v14, v15 ]
     defaults:
       run:
         shell: sh -eu {0}
@@ -594,59 +573,33 @@ jobs:
       - name: Configure ECR login
         run: echo "{\"credsStore\":\"ecr-login\"}" > /kaniko/.docker/config.json
 
-      - name: Kaniko build compute node with extensions
-        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}}
+      - name: Kaniko build compute node with extensions v14
+        run: /kaniko/executor --skip-unused-stages  --snapshotMode=redo --cache=true --cache-repo 369495373322.dkr.ecr.eu-central-1.amazonaws.com/cache  --context . --build-arg GIT_VERSION=${{ github.sha }} --dockerfile Dockerfile.compute-node-v14 --destination 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v14:${{needs.tag.outputs.build-tag}}
 
-      - name: Cleanup ECR folder
-        run: rm -rf ~/.ecr
-
-  vm-compute-node-image:
-    runs-on: [ self-hosted, gen3, large ]
-    needs: [ tag, compute-node-image ]
-    strategy:
-      fail-fast: false
-      matrix:
-        version: [ v14, v15 ]
+  compute-node-image-v15:
+    runs-on: [ self-hosted, dev, x64 ]
+    container: gcr.io/kaniko-project/executor:v1.9.0-debug
+    needs: [ tag ]
     defaults:
       run:
         shell: sh -eu {0}
-    env:
-      VM_INFORMANT_VERSION: 0.1.1
 
     steps:
-      - name: Downloading latest vm-builder
-        run: |
-          curl -L https://github.com/neondatabase/neonvm/releases/latest/download/vm-builder -o vm-builder
-          chmod +x vm-builder
+      - name: Checkout
+        uses: actions/checkout@v1 # v3 won't work with kaniko
+        with:
+          submodules: true
+          fetch-depth: 0
 
-      - name: Pulling compute-node image
-        run: |
-          docker pull 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-${{ matrix.version }}:${{needs.tag.outputs.build-tag}}
+      - name: Configure ECR login
+        run: echo "{\"credsStore\":\"ecr-login\"}" > /kaniko/.docker/config.json
 
-      - name: Downloading VM informant version ${{ env.VM_INFORMANT_VERSION }}
-        run: |
-          curl -fL https://github.com/neondatabase/autoscaling/releases/download/${{ env.VM_INFORMANT_VERSION }}/vm-informant -o vm-informant
-          chmod +x vm-informant
-
-      - name: Adding VM informant to compute-node image
-        run: |
-          ID=$(docker create 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-${{ matrix.version }}:${{needs.tag.outputs.build-tag}})
-          docker cp vm-informant $ID:/bin/vm-informant
-          docker commit $ID temp-vm-compute-node
-          docker rm -f $ID
-
-      - name: Build vm image
-        run: |
-          # note: as of 2023-01-12, vm-builder requires a trailing ":latest" for local images
-          ./vm-builder -src=temp-vm-compute-node:latest -dst=369495373322.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-${{ matrix.version }}:${{needs.tag.outputs.build-tag}}
-
-      - name: Pushing vm-compute-node image
-        run: |
-          docker push 369495373322.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-${{ matrix.version }}:${{needs.tag.outputs.build-tag}}
+      - name: Kaniko build compute node with extensions v15
+        run: /kaniko/executor --skip-unused-stages --snapshotMode=redo --cache=true --cache-repo 369495373322.dkr.ecr.eu-central-1.amazonaws.com/cache --context . --build-arg GIT_VERSION=${{ github.sha }} --dockerfile Dockerfile.compute-node-v15 --destination 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v15:${{needs.tag.outputs.build-tag}}
 
   test-images:
-    needs: [ tag, neon-image, compute-node-image, compute-tools-image ]
-    runs-on: [ self-hosted, gen3, small ]
+    needs: [ tag, neon-image, compute-node-image-v14, compute-node-image-v15, compute-tools-image ]
+    runs-on: [ self-hosted, dev, x64 ]
 
     steps:
       - name: Checkout
@@ -688,39 +641,20 @@ jobs:
           docker compose -f ./docker-compose/docker-compose.yml down
 
   promote-images:
-    runs-on: [ self-hosted, gen3, small ]
-    needs: [ tag, test-images, vm-compute-node-image ]
-    container: golang:1.19-bullseye
+    runs-on: [ self-hosted, dev, x64 ]
+    needs: [ tag, test-images ]
     if: github.event_name != 'workflow_dispatch'
+    container: amazon/aws-cli
+    strategy:
+      fail-fast: false
+      matrix:
+        name: [ neon, compute-node-v14, compute-node-v15, compute-tools ]
 
     steps:
-      - name: Install Crane & ECR helper
-        if: |
-          (github.ref_name == 'main' || github.ref_name == 'release') &&
-          github.event_name != 'workflow_dispatch'
+      - name: Promote image to latest
         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
+          export MANIFEST=$(aws ecr batch-get-image --repository-name ${{ matrix.name }} --image-ids imageTag=${{needs.tag.outputs.build-tag}} --query 'images[].imageManifest' --output text)
+          aws ecr put-image --repository-name ${{ matrix.name }} --image-tag latest --image-manifest "$MANIFEST"
 
   push-docker-hub:
     runs-on: [ self-hosted, dev, x64 ]
@@ -747,15 +681,9 @@ jobs:
       - 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
 
@@ -767,9 +695,7 @@ jobs:
           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
           crane copy 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v14:${{needs.tag.outputs.build-tag}} 093970136003.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v14:latest
-          crane copy 369495373322.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-v14:${{needs.tag.outputs.build-tag}} 093970136003.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-v14:latest
           crane copy 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v15:${{needs.tag.outputs.build-tag}} 093970136003.dkr.ecr.eu-central-1.amazonaws.com/compute-node-v15:latest
-          crane copy 369495373322.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-v15:${{needs.tag.outputs.build-tag}} 093970136003.dkr.ecr.eu-central-1.amazonaws.com/vm-compute-node-v15:latest
 
       - name: Configure Docker Hub login
         run: |
@@ -786,15 +712,9 @@ jobs:
       - 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
 
@@ -806,15 +726,115 @@ jobs:
           crane tag neondatabase/neon:${{needs.tag.outputs.build-tag}} latest
           crane tag neondatabase/compute-tools:${{needs.tag.outputs.build-tag}} latest
           crane tag neondatabase/compute-node-v14:${{needs.tag.outputs.build-tag}} latest
-          crane tag neondatabase/vm-compute-node-v14:${{needs.tag.outputs.build-tag}} latest
           crane tag neondatabase/compute-node-v15:${{needs.tag.outputs.build-tag}} latest
-          crane tag neondatabase/vm-compute-node-v15:${{needs.tag.outputs.build-tag}} latest
 
-      - name: Cleanup ECR folder
-        run: rm -rf ~/.ecr
+  calculate-deploy-targets:
+    runs-on: [ self-hosted, dev, x64 ]
+    if: |
+      (github.ref_name == 'main' || github.ref_name == 'release') &&
+      github.event_name != 'workflow_dispatch'
+    outputs:
+      matrix-include: ${{ steps.set-matrix.outputs.include }}
+    steps:
+      - id: set-matrix
+        run: |
+          if [[ "$GITHUB_REF_NAME" == "main" ]]; then
+            STAGING='{"env_name": "staging", "proxy_job": "neon-proxy", "proxy_config": "staging.proxy", "storage_broker_ns": "neon-storage-broker", "storage_broker_config": "staging.neon-storage-broker", "kubeconfig_secret": "STAGING_KUBECONFIG_DATA", "console_api_key_secret": "NEON_STAGING_API_KEY"}'
+            echo "include=[$STAGING]" >> $GITHUB_OUTPUT
+          elif [[ "$GITHUB_REF_NAME" == "release" ]]; then
+            PRODUCTION='{"env_name": "production", "proxy_job": "neon-proxy", "proxy_config": "production.proxy", "storage_broker_ns": "neon-storage-broker", "storage_broker_config": "production.neon-storage-broker", "kubeconfig_secret": "PRODUCTION_KUBECONFIG_DATA", "console_api_key_secret": "NEON_PRODUCTION_API_KEY"}'
+            echo "include=[$PRODUCTION]" >> $GITHUB_OUTPUT
+          else
+            echo "GITHUB_REF_NAME (value '$GITHUB_REF_NAME') is not set to either 'main' or 'release'"
+            exit 1
+          fi
+
+  deploy:
+    runs-on: [ self-hosted, dev, x64 ]
+    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: [ push-docker-hub, calculate-deploy-targets, tag, regress-tests ]
+    if: |
+      (github.ref_name == 'main' || github.ref_name == 'release') &&
+      github.event_name != 'workflow_dispatch'
+    defaults:
+      run:
+        shell: bash
+    strategy:
+      matrix:
+        include: ${{fromJSON(needs.calculate-deploy-targets.outputs.matrix-include)}}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          submodules: true
+          fetch-depth: 0
+
+      - name: Redeploy
+        run: |
+          export DOCKER_TAG=${{needs.tag.outputs.build-tag}}
+          cd "$(pwd)/.github/ansible"
+
+          if [[ "$GITHUB_REF_NAME" == "main" ]]; then
+            ./get_binaries.sh
+          elif [[ "$GITHUB_REF_NAME" == "release" ]]; then
+            RELEASE=true ./get_binaries.sh
+          else
+            echo "GITHUB_REF_NAME (value '$GITHUB_REF_NAME') is not set to either 'main' or 'release'"
+            exit 1
+          fi
+
+          eval $(ssh-agent)
+          echo "${{ secrets.TELEPORT_SSH_KEY }}"  | tr -d '\n'| base64 --decode >ssh-key
+          echo "${{ secrets.TELEPORT_SSH_CERT }}" | tr -d '\n'| base64 --decode >ssh-key-cert.pub
+          chmod 0600 ssh-key
+          ssh-add ssh-key
+          rm -f ssh-key ssh-key-cert.pub
+          ANSIBLE_CONFIG=./ansible.cfg ansible-galaxy collection install sivel.toiletwater
+          ANSIBLE_CONFIG=./ansible.cfg ansible-playbook deploy.yaml -i ${{ matrix.env_name }}.hosts.yaml -e CONSOLE_API_TOKEN=${{ secrets[matrix.console_api_key_secret] }} -e SENTRY_URL_PAGESERVER=${{ secrets.SENTRY_URL_PAGESERVER }} -e SENTRY_URL_SAFEKEEPER=${{ secrets.SENTRY_URL_SAFEKEEPER }}
+          rm -f neon_install.tar.gz .neon_current_version
+
+  deploy-new:
+    runs-on: [ self-hosted, dev, x64 ]
+    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: [ push-docker-hub, calculate-deploy-targets, tag, regress-tests ]
+    if: |
+      (github.ref_name == 'main') &&
+      github.event_name != 'workflow_dispatch'
+    defaults:
+      run:
+        shell: bash
+    strategy:
+      matrix:
+        target_region: [ us-east-2 ]
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          submodules: true
+          fetch-depth: 0
+
+      - name: Redeploy
+        run: |
+          export DOCKER_TAG=${{needs.tag.outputs.build-tag}}
+          cd "$(pwd)/.github/ansible"
+          if [[ "$GITHUB_REF_NAME" == "main" ]]; then
+            ./get_binaries.sh
+          elif [[ "$GITHUB_REF_NAME" == "release" ]]; then
+            RELEASE=true ./get_binaries.sh
+          else
+            echo "GITHUB_REF_NAME (value '$GITHUB_REF_NAME') is not set to either 'main' or 'release'"
+            exit 1
+          fi
+          ansible-galaxy collection install sivel.toiletwater
+          ansible-playbook deploy.yaml -i staging.${{ matrix.target_region }}.hosts.yaml -e @ssm_config -e CONSOLE_API_TOKEN=${{ secrets.NEON_STAGING_API_KEY }} -e SENTRY_URL_PAGESERVER=${{ secrets.SENTRY_URL_PAGESERVER }} -e SENTRY_URL_SAFEKEEPER=${{ secrets.SENTRY_URL_SAFEKEEPER }}
+          rm -f neon_install.tar.gz .neon_current_version
 
   deploy-pr-test-new:
-    runs-on: [ self-hosted, gen3, small ]
+    runs-on: [ self-hosted, dev, x64 ]
     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
@@ -846,40 +866,297 @@ jobs:
           ansible-playbook deploy.yaml -i staging.${{ matrix.target_region }}.hosts.yaml -e @ssm_config -e CONSOLE_API_TOKEN=${{ secrets.NEON_STAGING_API_KEY }} -e SENTRY_URL_PAGESERVER=${{ secrets.SENTRY_URL_PAGESERVER }} -e SENTRY_URL_SAFEKEEPER=${{ secrets.SENTRY_URL_SAFEKEEPER }}
           rm -f neon_install.tar.gz .neon_current_version
 
-      - name: Cleanup ansible folder
-        run: rm -rf ~/.ansible
-
-  deploy:
-    runs-on: [ self-hosted, gen3, small ]
-    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/ansible:latest
+  deploy-prod-new:
+    runs-on: prod
+    container: 093970136003.dkr.ecr.eu-central-1.amazonaws.com/ansible:latest
+    # 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: [ push-docker-hub, tag, regress-tests ]
-    if: ( github.ref_name == 'main' || github.ref_name == 'release' ) && github.event_name != 'workflow_dispatch'
+    if: |
+      (github.ref_name == 'release') &&
+      github.event_name != 'workflow_dispatch'
+    defaults:
+      run:
+        shell: bash
+    strategy:
+      matrix:
+        target_region: [ us-east-2, us-west-2, eu-central-1, ap-southeast-1 ]
     steps:
       - name: Checkout
         uses: actions/checkout@v3
         with:
-          submodules: false
+          submodules: true
           fetch-depth: 0
 
-      - name: Trigger deploy workflow
-        env:
-          GH_TOKEN: ${{ github.token }}
+      - name: Redeploy
         run: |
+          export DOCKER_TAG=${{needs.tag.outputs.build-tag}}
+          cd "$(pwd)/.github/ansible"
+
           if [[ "$GITHUB_REF_NAME" == "main" ]]; then
-            gh workflow run deploy-dev.yml --ref main -f branch=${{ github.sha }} -f dockerTag=${{needs.tag.outputs.build-tag}}
+            ./get_binaries.sh
           elif [[ "$GITHUB_REF_NAME" == "release" ]]; then
-            gh workflow run deploy-prod.yml --ref release -f branch=${{ github.sha }} -f dockerTag=${{needs.tag.outputs.build-tag}} -f disclamerAcknowledged=true
+            RELEASE=true ./get_binaries.sh
           else
             echo "GITHUB_REF_NAME (value '$GITHUB_REF_NAME') is not set to either 'main' or 'release'"
             exit 1
           fi
 
+          ansible-galaxy collection install sivel.toiletwater
+          ansible-playbook deploy.yaml -i prod.${{ matrix.target_region }}.hosts.yaml -e @ssm_config -e CONSOLE_API_TOKEN=${{ secrets.NEON_PRODUCTION_API_KEY }} -e SENTRY_URL_PAGESERVER=${{ secrets.SENTRY_URL_PAGESERVER }} -e SENTRY_URL_SAFEKEEPER=${{ secrets.SENTRY_URL_SAFEKEEPER }}
+          rm -f neon_install.tar.gz .neon_current_version
+
+  deploy-proxy:
+    runs-on: [ self-hosted, dev, x64 ]
+    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/base:pinned
+    # Compute image isn't strictly required for proxy deploy, but let's still wait for it to run all deploy jobs consistently.
+    needs: [ push-docker-hub, calculate-deploy-targets, tag, regress-tests ]
+    if: |
+      (github.ref_name == 'main' || github.ref_name == 'release') &&
+      github.event_name != 'workflow_dispatch'
+    defaults:
+      run:
+        shell: bash
+    strategy:
+      matrix:
+        include: ${{fromJSON(needs.calculate-deploy-targets.outputs.matrix-include)}}
+    env:
+      KUBECONFIG: .kubeconfig
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          submodules: true
+          fetch-depth: 0
+
+      - name: Add curl
+        run: apt update && apt install curl -y
+
+      - name: Store kubeconfig file
+        run: |
+          echo "${{ secrets[matrix.kubeconfig_secret] }}" | base64 --decode > ${KUBECONFIG}
+          chmod 0600 ${KUBECONFIG}
+
+      - name: Setup helm v3
+        run: |
+          curl -s https://raw.githubusercontent.com/helm/helm/main/scripts/get-helm-3 | bash
+          helm repo add neondatabase https://neondatabase.github.io/helm-charts
+
+      - name: Re-deploy proxy
+        run: |
+          DOCKER_TAG=${{needs.tag.outputs.build-tag}}
+          helm upgrade ${{ matrix.proxy_job }}       neondatabase/neon-proxy --namespace neon-proxy --install -f .github/helm-values/${{ matrix.proxy_config }}.yaml       --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
+          helm upgrade ${{ matrix.proxy_job }}-scram neondatabase/neon-proxy --namespace neon-proxy --install -f .github/helm-values/${{ matrix.proxy_config }}-scram.yaml --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
+
+  deploy-storage-broker:
+    name: deploy storage broker on old staging and old prod
+    runs-on: [ self-hosted, dev, x64 ]
+    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/base:pinned
+    # Compute image isn't strictly required for proxy deploy, but let's still wait for it to run all deploy jobs consistently.
+    needs: [ push-docker-hub, calculate-deploy-targets, tag, regress-tests ]
+    if: |
+      (github.ref_name == 'main' || github.ref_name == 'release') &&
+      github.event_name != 'workflow_dispatch'
+    defaults:
+      run:
+        shell: bash
+    strategy:
+      matrix:
+        include: ${{fromJSON(needs.calculate-deploy-targets.outputs.matrix-include)}}
+    env:
+      KUBECONFIG: .kubeconfig
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          submodules: true
+          fetch-depth: 0
+
+      - name: Add curl
+        run: apt update && apt install curl -y
+
+      - name: Store kubeconfig file
+        run: |
+          echo "${{ secrets[matrix.kubeconfig_secret] }}" | base64 --decode > ${KUBECONFIG}
+          chmod 0600 ${KUBECONFIG}
+
+      - name: Setup helm v3
+        run: |
+          curl -s https://raw.githubusercontent.com/helm/helm/main/scripts/get-helm-3 | bash
+          helm repo add neondatabase https://neondatabase.github.io/helm-charts
+
+      - name: Deploy storage-broker
+        run:
+          helm upgrade neon-storage-broker neondatabase/neon-storage-broker --namespace ${{ matrix.storage_broker_ns }} --create-namespace --install --atomic -f .github/helm-values/${{ matrix.storage_broker_config }}.yaml --set image.tag=${{ needs.tag.outputs.build-tag }} --set settings.sentryUrl=${{ secrets.SENTRY_URL_BROKER }} --wait --timeout 5m0s
+
+  deploy-proxy-new:
+    runs-on: [ self-hosted, dev, x64 ]
+    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/ansible:pinned
+    # Compute image isn't strictly required for proxy deploy, but let's still wait for it to run all deploy jobs consistently.
+    needs: [ push-docker-hub, tag, regress-tests ]
+    if: |
+      (github.ref_name == 'main') &&
+      github.event_name != 'workflow_dispatch'
+    defaults:
+      run:
+        shell: bash
+    strategy:
+      matrix:
+        include:
+          - target_region:  us-east-2
+            target_cluster: dev-us-east-2-beta
+            deploy_link_proxy: true
+            deploy_legacy_scram_proxy: true
+          - target_region:  eu-west-1
+            target_cluster: dev-eu-west-1-zeta
+            deploy_link_proxy: false
+            deploy_legacy_scram_proxy: false
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          submodules: true
+          fetch-depth: 0
+
+      - name: Configure environment
+        run: |
+          helm repo add neondatabase https://neondatabase.github.io/helm-charts
+          aws --region ${{ matrix.target_region }} eks update-kubeconfig --name  ${{ matrix.target_cluster }}
+
+      - name: Re-deploy scram proxy
+        run: |
+          DOCKER_TAG=${{needs.tag.outputs.build-tag}}
+          helm upgrade neon-proxy-scram neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install -f .github/helm-values/${{ matrix.target_cluster }}.neon-proxy-scram.yaml --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
+
+      - name: Re-deploy link proxy
+        if: matrix.deploy_link_proxy
+        run: |
+          DOCKER_TAG=${{needs.tag.outputs.build-tag}}
+          helm upgrade neon-proxy-link neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install -f .github/helm-values/${{ matrix.target_cluster }}.neon-proxy-link.yaml --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
+
+      - name: Re-deploy legacy scram proxy
+        if: matrix.deploy_legacy_scram_proxy
+        run: |
+          DOCKER_TAG=${{needs.tag.outputs.build-tag}}
+          helm upgrade neon-proxy-scram-legacy neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install -f .github/helm-values/${{ matrix.target_cluster }}.neon-proxy-scram-legacy.yaml --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
+
+  deploy-storage-broker-dev-new:
+    runs-on: [ self-hosted, dev, x64 ]
+    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/ansible:pinned
+    # Compute image isn't strictly required for proxy deploy, but let's still wait for it to run all deploy jobs consistently.
+    needs: [ push-docker-hub, tag, regress-tests ]
+    if: |
+      (github.ref_name == 'main') &&
+      github.event_name != 'workflow_dispatch'
+    defaults:
+      run:
+        shell: bash
+    strategy:
+      matrix:
+        include:
+          - target_region:  us-east-2
+            target_cluster: dev-us-east-2-beta
+          - target_region:  eu-west-1
+            target_cluster: dev-eu-west-1-zeta
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          submodules: true
+          fetch-depth: 0
+
+      - name: Configure environment
+        run: |
+          helm repo add neondatabase https://neondatabase.github.io/helm-charts
+          aws --region ${{ matrix.target_region }} eks update-kubeconfig --name  ${{ matrix.target_cluster }}
+
+      - name: Deploy storage-broker
+        run:
+          helm upgrade neon-storage-broker-lb neondatabase/neon-storage-broker --namespace neon-storage-broker-lb --create-namespace --install --atomic -f .github/helm-values/${{ matrix.target_cluster }}.neon-storage-broker.yaml --set image.tag=${{ needs.tag.outputs.build-tag }} --set settings.sentryUrl=${{ secrets.SENTRY_URL_BROKER }} --wait --timeout 5m0s
+
+  deploy-proxy-prod-new:
+    runs-on: prod
+    container: 093970136003.dkr.ecr.eu-central-1.amazonaws.com/ansible:latest
+    # Compute image isn't strictly required for proxy deploy, but let's still wait for it to run all deploy jobs consistently.
+    needs: [ push-docker-hub, tag, regress-tests ]
+    if: |
+      (github.ref_name == 'release') &&
+      github.event_name != 'workflow_dispatch'
+    defaults:
+      run:
+        shell: bash
+    strategy:
+      matrix:
+        include:
+          - target_region:  us-east-2
+            target_cluster: prod-us-east-2-delta
+          - target_region:  us-west-2
+            target_cluster: prod-us-west-2-eta
+          - target_region: eu-central-1
+            target_cluster: prod-eu-central-1-gamma
+          - target_region: ap-southeast-1
+            target_cluster: prod-ap-southeast-1-epsilon
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          submodules: true
+          fetch-depth: 0
+
+      - name: Configure environment
+        run: |
+          helm repo add neondatabase https://neondatabase.github.io/helm-charts
+          aws --region ${{ matrix.target_region }} eks update-kubeconfig --name  ${{ matrix.target_cluster }}
+
+      - name: Re-deploy proxy
+        run: |
+          DOCKER_TAG=${{needs.tag.outputs.build-tag}}
+          helm upgrade neon-proxy-scram neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install -f .github/helm-values/${{ matrix.target_cluster }}.neon-proxy-scram.yaml --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
+
+  deploy-storage-broker-prod-new:
+    runs-on: prod
+    container: 093970136003.dkr.ecr.eu-central-1.amazonaws.com/ansible:latest
+    # Compute image isn't strictly required for proxy deploy, but let's still wait for it to run all deploy jobs consistently.
+    needs: [ push-docker-hub, tag, regress-tests ]
+    if: |
+      (github.ref_name == 'release') &&
+      github.event_name != 'workflow_dispatch'
+    defaults:
+      run:
+        shell: bash
+    strategy:
+      matrix:
+        include:
+          - target_region:  us-east-2
+            target_cluster: prod-us-east-2-delta
+          - target_region:  us-west-2
+            target_cluster: prod-us-west-2-eta
+          - target_region: eu-central-1
+            target_cluster: prod-eu-central-1-gamma
+          - target_region: ap-southeast-1
+            target_cluster: prod-ap-southeast-1-epsilon
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          submodules: true
+          fetch-depth: 0
+
+      - name: Configure environment
+        run: |
+          helm repo add neondatabase https://neondatabase.github.io/helm-charts
+          aws --region ${{ matrix.target_region }} eks update-kubeconfig --name  ${{ matrix.target_cluster }}
+
+      - name: Deploy storage-broker
+        run:
+          helm upgrade neon-storage-broker-lb neondatabase/neon-storage-broker --namespace neon-storage-broker-lb --create-namespace --install --atomic -f .github/helm-values/${{ matrix.target_cluster }}.neon-storage-broker.yaml --set image.tag=${{ needs.tag.outputs.build-tag }} --set settings.sentryUrl=${{ secrets.SENTRY_URL_BROKER }} --wait --timeout 5m0s
+
   promote-compatibility-data:
-    runs-on: [ self-hosted, gen3, small ]
+    runs-on: [ self-hosted, dev, x64 ]
     container:
       image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
       options: --init
-    needs: [ push-docker-hub, tag, regress-tests ]
+    needs: [ deploy, deploy-proxy ]
     if: github.ref_name == 'release' && github.event_name != 'workflow_dispatch'
     steps:
       - name: Promote compatibility snapshot for the release

.github/workflows/deploy-dev.yml

@@ -1,179 +0,0 @@
-name: Neon Deploy dev
-
-on:
-  workflow_dispatch:
-    inputs:
-      dockerTag:
-        description: 'Docker tag to deploy'
-        required: true
-        type: string
-      branch:
-        description: 'Branch or commit used for deploy scripts and configs'
-        required: true
-        type: string
-        default: 'main'
-      deployStorage:
-        description: 'Deploy storage'
-        required: true
-        type: boolean
-        default: true
-      deployProxy:
-        description: 'Deploy proxy'
-        required: true
-        type: boolean
-        default: true
-      deployStorageBroker:
-        description: 'Deploy storage-broker'
-        required: true
-        type: boolean
-        default: true
-
-env:
-  AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_DEV }}
-  AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_KEY_DEV }}
-
-concurrency:
-  group: deploy-dev
-  cancel-in-progress: false
-
-jobs:
-  deploy-storage-new:
-    runs-on: [ self-hosted, gen3, small ]
-    container:
-      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/ansible:pinned
-      options: --user root --privileged
-    if: inputs.deployStorage
-    defaults:
-      run:
-        shell: bash
-    strategy:
-      matrix:
-        target_region: [ eu-west-1, us-east-2 ]
-    environment:
-      name: dev-${{ matrix.target_region }}
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          submodules: true
-          fetch-depth: 0
-          ref: ${{ inputs.branch }}
-
-      - name: Redeploy
-        run: |
-          export DOCKER_TAG=${{ inputs.dockerTag }}
-          cd "$(pwd)/.github/ansible"
-
-          ./get_binaries.sh
-
-          ansible-galaxy collection install sivel.toiletwater
-          ansible-playbook deploy.yaml -i staging.${{ matrix.target_region }}.hosts.yaml -e @ssm_config -e CONSOLE_API_TOKEN=${{ secrets.NEON_STAGING_API_KEY }} -e SENTRY_URL_PAGESERVER=${{ secrets.SENTRY_URL_PAGESERVER }} -e SENTRY_URL_SAFEKEEPER=${{ secrets.SENTRY_URL_SAFEKEEPER }}
-          rm -f neon_install.tar.gz .neon_current_version
-
-      - name: Cleanup ansible folder
-        run: rm -rf ~/.ansible
-
-  deploy-proxy-new:
-    runs-on: [ self-hosted, gen3, small ]
-    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/ansible:pinned
-    if: inputs.deployProxy
-    defaults:
-      run:
-        shell: bash
-    strategy:
-      matrix:
-        include:
-          - target_region:  us-east-2
-            target_cluster: dev-us-east-2-beta
-            deploy_link_proxy: true
-            deploy_legacy_scram_proxy: true
-          - target_region:  eu-west-1
-            target_cluster: dev-eu-west-1-zeta
-            deploy_link_proxy: false
-            deploy_legacy_scram_proxy: false
-    environment:
-      name: dev-${{ 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  ${{ matrix.target_cluster }}
-  
-      - name: Re-deploy scram proxy
-        run: |
-          DOCKER_TAG=${{ inputs.dockerTag }}
-          helm upgrade neon-proxy-scram neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install --atomic -f .github/helm-values/${{ matrix.target_cluster }}.neon-proxy-scram.yaml --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
-  
-      - name: Re-deploy link proxy
-        if: matrix.deploy_link_proxy
-        run: |
-          DOCKER_TAG=${{ inputs.dockerTag }}
-          helm upgrade neon-proxy-link neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install --atomic -f .github/helm-values/${{ matrix.target_cluster }}.neon-proxy-link.yaml --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
-  
-      - name: Re-deploy legacy scram proxy
-        if: matrix.deploy_legacy_scram_proxy
-        run: |
-          DOCKER_TAG=${{ inputs.dockerTag }}
-          helm upgrade neon-proxy-scram-legacy neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install --atomic -f .github/helm-values/${{ matrix.target_cluster }}.neon-proxy-scram-legacy.yaml --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
-  
-      - name: Cleanup helm folder
-        run: rm -rf ~/.cache
-  
-  deploy-storage-broker-new:
-    runs-on: [ self-hosted, gen3, small ]
-    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/ansible:pinned
-    if: inputs.deployStorageBroker
-    defaults:
-      run:
-        shell: bash
-    strategy:
-      matrix:
-        include:
-          - target_region:  us-east-2
-            target_cluster: dev-us-east-2-beta
-          - target_region:  eu-west-1
-            target_cluster: dev-eu-west-1-zeta
-    environment:
-      name: dev-${{ 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  ${{ matrix.target_cluster }}
-  
-      - name: Deploy storage-broker
-        run:
-          helm upgrade neon-storage-broker-lb neondatabase/neon-storage-broker --namespace neon-storage-broker-lb --create-namespace --install --atomic -f .github/helm-values/${{ matrix.target_cluster }}.neon-storage-broker.yaml --set image.tag=${{ inputs.dockerTag }} --set settings.sentryUrl=${{ secrets.SENTRY_URL_BROKER }} --wait --timeout 5m0s
-  
-      - name: Cleanup helm folder
-        run: rm -rf ~/.cache

.github/workflows/deploy-prod.yml

@@ -1,240 +0,0 @@
-name: Neon Deploy prod
-
-on:
-  workflow_dispatch:
-    inputs:
-      dockerTag:
-        description: 'Docker tag to deploy'
-        required: true
-        type: string
-      branch:
-        description: 'Branch or commit used for deploy scripts and configs'
-        required: true
-        type: string
-        default: 'release'
-      deployStorage:
-        description: 'Deploy storage'
-        required: true
-        type: boolean
-        default: true
-      deployProxy:
-        description: 'Deploy proxy'
-        required: true
-        type: boolean
-        default: true
-      deployStorageBroker:
-        description: 'Deploy storage-broker'
-        required: true
-        type: boolean
-        default: true
-      disclamerAcknowledged:
-        description: 'I confirm that there is an emergency and I can not use regular release workflow'
-        required: true
-        type: boolean
-        default: false
-
-concurrency:
-  group: deploy-prod
-  cancel-in-progress: false
-
-jobs:
-  deploy-prod-new:
-    runs-on: prod
-    container: 093970136003.dkr.ecr.eu-central-1.amazonaws.com/ansible:latest
-    if: inputs.deployStorage && inputs.disclamerAcknowledged
-    defaults:
-      run:
-        shell: bash
-    strategy:
-      matrix:
-        target_region: [ us-east-2, us-west-2, eu-central-1, ap-southeast-1 ]
-    environment:
-      name: prod-${{ matrix.target_region }}
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          submodules: true
-          fetch-depth: 0
-          ref: ${{ inputs.branch }}
-
-      - name: Redeploy
-        run: |
-          export DOCKER_TAG=${{ inputs.dockerTag }}
-          cd "$(pwd)/.github/ansible"
-
-          ./get_binaries.sh
-
-          ansible-galaxy collection install sivel.toiletwater
-          ansible-playbook deploy.yaml -i prod.${{ matrix.target_region }}.hosts.yaml -e @ssm_config -e CONSOLE_API_TOKEN=${{ secrets.NEON_PRODUCTION_API_KEY }} -e SENTRY_URL_PAGESERVER=${{ secrets.SENTRY_URL_PAGESERVER }} -e SENTRY_URL_SAFEKEEPER=${{ secrets.SENTRY_URL_SAFEKEEPER }}
-          rm -f neon_install.tar.gz .neon_current_version
-
-  deploy-proxy-prod-new:
-    runs-on: prod
-    container: 093970136003.dkr.ecr.eu-central-1.amazonaws.com/ansible:latest
-    if: inputs.deployProxy && inputs.disclamerAcknowledged
-    defaults:
-      run:
-        shell: bash
-    strategy:
-      matrix:
-        include:
-          - target_region:  us-east-2
-            target_cluster: prod-us-east-2-delta
-            deploy_link_proxy: true
-            deploy_legacy_scram_proxy: false
-          - target_region:  us-west-2
-            target_cluster: prod-us-west-2-eta
-            deploy_link_proxy: false
-            deploy_legacy_scram_proxy: true
-          - target_region: eu-central-1
-            target_cluster: prod-eu-central-1-gamma
-            deploy_link_proxy: false
-            deploy_legacy_scram_proxy: false
-          - target_region: ap-southeast-1
-            target_cluster: prod-ap-southeast-1-epsilon
-            deploy_link_proxy: false
-            deploy_legacy_scram_proxy: false
-    environment:
-      name: prod-${{ matrix.target_region }}
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          submodules: true
-          fetch-depth: 0
-          ref: ${{ inputs.branch }}
-
-      - name: Configure environment
-        run: |
-          helm repo add neondatabase https://neondatabase.github.io/helm-charts
-          aws --region ${{ matrix.target_region }} eks update-kubeconfig --name  ${{ matrix.target_cluster }}
-
-      - name: Re-deploy scram proxy
-        run: |
-          DOCKER_TAG=${{ inputs.dockerTag }}
-          helm upgrade neon-proxy-scram neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install --atomic -f .github/helm-values/${{ matrix.target_cluster }}.neon-proxy-scram.yaml --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
-
-      - name: Re-deploy link proxy
-        if: matrix.deploy_link_proxy
-        run: |
-          DOCKER_TAG=${{ inputs.dockerTag }}
-          helm upgrade neon-proxy-link neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install --atomic -f .github/helm-values/${{ matrix.target_cluster }}.neon-proxy-link.yaml --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
-
-      - name: Re-deploy legacy scram proxy
-        if: matrix.deploy_legacy_scram_proxy
-        run: |
-          DOCKER_TAG=${{ inputs.dockerTag }}
-          helm upgrade neon-proxy-scram-legacy neondatabase/neon-proxy --namespace neon-proxy --create-namespace --install --atomic -f .github/helm-values/${{ matrix.target_cluster }}.neon-proxy-scram-legacy.yaml --set image.tag=${DOCKER_TAG} --set settings.sentryUrl=${{ secrets.SENTRY_URL_PROXY }} --wait --timeout 15m0s
-
-  deploy-storage-broker-prod-new:
-    runs-on: prod
-    container: 093970136003.dkr.ecr.eu-central-1.amazonaws.com/ansible:latest
-    if: inputs.deployStorageBroker && inputs.disclamerAcknowledged
-    defaults:
-      run:
-        shell: bash
-    strategy:
-      matrix:
-        include:
-          - target_region:  us-east-2
-            target_cluster: prod-us-east-2-delta
-          - target_region:  us-west-2
-            target_cluster: prod-us-west-2-eta
-          - target_region: eu-central-1
-            target_cluster: prod-eu-central-1-gamma
-          - target_region: ap-southeast-1
-            target_cluster: prod-ap-southeast-1-epsilon
-    environment:
-      name: prod-${{ matrix.target_region }}
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          submodules: true
-          fetch-depth: 0
-          ref: ${{ inputs.branch }}
-
-      - name: Configure environment
-        run: |
-          helm repo add neondatabase https://neondatabase.github.io/helm-charts
-          aws --region ${{ matrix.target_region }} eks update-kubeconfig --name  ${{ matrix.target_cluster }}
-
-      - name: Deploy storage-broker
-        run:
-          helm upgrade neon-storage-broker-lb neondatabase/neon-storage-broker --namespace neon-storage-broker-lb --create-namespace --install --atomic -f .github/helm-values/${{ matrix.target_cluster }}.neon-storage-broker.yaml --set image.tag=${{ inputs.dockerTag }} --set settings.sentryUrl=${{ secrets.SENTRY_URL_BROKER }} --wait --timeout 5m0s
-
-  # Deploy to old account below          
-
-  deploy:
-    runs-on: prod
-    container: 093970136003.dkr.ecr.eu-central-1.amazonaws.com/ansible:latest
-    if: inputs.deployStorage && inputs.disclamerAcknowledged
-    defaults:
-      run:
-        shell: bash
-    environment:
-      name: prod-old
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          submodules: true
-          fetch-depth: 0
-          ref: ${{ inputs.branch }}
-
-      - name: Redeploy
-        run: |
-          export DOCKER_TAG=${{ inputs.dockerTag }}
-          cd "$(pwd)/.github/ansible"
-
-          ./get_binaries.sh
-
-          eval $(ssh-agent)
-          echo "${{ secrets.TELEPORT_SSH_KEY }}"  | tr -d '\n'| base64 --decode >ssh-key
-          echo "${{ secrets.TELEPORT_SSH_CERT }}" | tr -d '\n'| base64 --decode >ssh-key-cert.pub
-          chmod 0600 ssh-key
-          ssh-add ssh-key
-          rm -f ssh-key ssh-key-cert.pub
-          ANSIBLE_CONFIG=./ansible.cfg ansible-galaxy collection install sivel.toiletwater
-          ANSIBLE_CONFIG=./ansible.cfg ansible-playbook deploy.yaml -i production.hosts.yaml -e CONSOLE_API_TOKEN=${{ secrets.NEON_PRODUCTION_API_KEY }} -e SENTRY_URL_PAGESERVER=${{ secrets.SENTRY_URL_PAGESERVER }} -e SENTRY_URL_SAFEKEEPER=${{ secrets.SENTRY_URL_SAFEKEEPER }}
-          rm -f neon_install.tar.gz .neon_current_version
-
-      # Cleanup script fails otherwise - rm: cannot remove '/nvme/actions-runner/_work/_temp/_github_home/.ansible/collections': Permission denied
-      - name: Cleanup ansible folder
-        run: rm -rf ~/.ansible
-
-  deploy-storage-broker:
-    name: deploy storage broker on old staging and old prod
-    runs-on: [ self-hosted, gen3, small ]
-    container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/ansible:pinned
-    if: inputs.deployStorageBroker && inputs.disclamerAcknowledged
-    defaults:
-      run:
-        shell: bash
-    environment:
-      name: prod-old
-    env:
-      KUBECONFIG: .kubeconfig
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          submodules: true
-          fetch-depth: 0
-          ref: ${{ inputs.branch }}
-
-      - name: Store kubeconfig file
-        run: |
-          echo "${{ secrets.PRODUCTION_KUBECONFIG_DATA }}" | base64 --decode > ${KUBECONFIG}
-          chmod 0600 ${KUBECONFIG}
-
-      - name: Add neon helm chart
-        run: helm repo add neondatabase https://neondatabase.github.io/helm-charts
-
-      - name: Deploy storage-broker
-        run:
-          helm upgrade neon-storage-broker neondatabase/neon-storage-broker --namespace neon-storage-broker --create-namespace --install --atomic -f .github/helm-values/production.neon-storage-broker.yaml --set image.tag=${{ inputs.dockerTag }} --set settings.sentryUrl=${{ secrets.SENTRY_URL_BROKER }} --wait --timeout 5m0s
-
-      - name: Cleanup helm folder
-        run: rm -rf ~/.cache

.github/workflows/neon_extra_builds.yml

@@ -4,7 +4,6 @@ on:
   push:
     branches:
     - main
-  pull_request:
 
 defaults:
   run:
@@ -21,7 +20,6 @@ env:
 
 jobs:
   check-macos-build:
-    if: github.ref_name == 'main' || contains(github.event.pull_request.labels.*.name, 'run-extra-build-macos')
     timeout-minutes: 90
     runs-on: macos-latest
 
@@ -95,16 +93,11 @@ jobs:
         run: ./run_clippy.sh
 
   gather-rust-build-stats:
-    if: github.ref_name == 'main' || contains(github.event.pull_request.labels.*.name, 'run-extra-build-stats')
-    runs-on: [ self-hosted, gen3, large ]
-    container:
-      image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
-      options: --init
+    timeout-minutes: 90
+    runs-on: ubuntu-latest
 
     env:
       BUILD_TYPE: release
-      # remove the cachepot wrapper and build without crate caches
-      RUSTC_WRAPPER: ""
       # build with incremental compilation produce partial results
       # so do not attempt to cache this build, also disable the incremental compilation
       CARGO_INCREMENTAL: 0
@@ -116,6 +109,11 @@ jobs:
           submodules: true
           fetch-depth: 1
 
+      - name: Install Ubuntu postgres dependencies
+        run: |
+          sudo apt update
+          sudo apt install build-essential libreadline-dev zlib1g-dev flex bison libseccomp-dev libssl-dev protobuf-compiler
+
       # Some of our rust modules use FFI and need those to be checked
       - name: Get postgres headers
         run: make postgres-headers -j$(nproc)
@@ -124,31 +122,7 @@ jobs:
         run: cargo build --all --release --timings
 
       - name: Upload the build stats
-        id: upload-stats
-        env:
-          BUCKET: neon-github-public-dev
-          SHA: ${{ github.event.pull_request.head.sha || github.sha }}
-          AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_DEV }}
-          AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_KEY_DEV }}
-        run: |
-          REPORT_URL=https://${BUCKET}.s3.amazonaws.com/build-stats/${SHA}/${GITHUB_RUN_ID}/cargo-timing.html
-          aws s3 cp --only-show-errors ./target/cargo-timings/cargo-timing.html "s3://${BUCKET}/build-stats/${SHA}/${GITHUB_RUN_ID}/"
-          echo "report-url=${REPORT_URL}" >> $GITHUB_OUTPUT
-
-      - name: Publish build stats report
-        uses: actions/github-script@v6
-        env:
-          REPORT_URL: ${{ steps.upload-stats.outputs.report-url }}
-          SHA: ${{ github.event.pull_request.head.sha || github.sha }}
+        uses: actions/upload-artifact@v3
         with:
-          script: |
-            const { REPORT_URL, SHA } = process.env
-
-            await github.rest.repos.createCommitStatus({
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              sha: `${SHA}`,
-              state: 'success',
-              target_url: `${REPORT_URL}`,
-              context: `Build stats (release)`,
-            })
+          name: neon-${{ runner.os }}-release-build-stats
+          path: ./target/cargo-timings/

.github/workflows/release.yml

@@ -1,33 +0,0 @@
-name: Create Release Branch
-
-on:
-  schedule:
-    - cron: '0 10 * * 2'
-
-jobs:
-  create_release_branch:
-    runs-on: [ubuntu-latest]
-
-    steps:
-    - name: Check out code
-      uses: actions/checkout@v3
-      with:
-        ref: main
-
-    - name: Get current date
-      id: date
-      run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_OUTPUT
-
-    - name: Create release branch
-      run: git checkout -b releases/${{ steps.date.outputs.date }}
-
-    - name: Push new branch
-      run: git push origin releases/${{ steps.date.outputs.date }}
-
-    - name: Create pull request into release
-      uses: thomaseizinger/create-pull-request@e3972219c86a56550fb70708d96800d8e24ba862 # 1.3.0
-      with:
-        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        head: releases/${{ steps.date.outputs.date }}
-        base: release
-        title: Release ${{ steps.date.outputs.date }}

Cargo.toml

@@ -1,3 +1,14 @@
+# 'named-profiles' feature was stabilized in cargo 1.57. This line makes the
+# build work with older cargo versions.
+#
+# We have this because as of this writing, the latest cargo Debian package
+# that's available is 1.56. (Confusingly, the Debian package version number
+# is 0.57, whereas 'cargo --version' says 1.56.)
+#
+# See https://tracker.debian.org/pkg/cargo for the current status of the
+# package. When that gets updated, we can remove this.
+cargo-features = ["named-profiles"]
+
 [workspace]
 members = [
     "compute_tools",
@@ -7,155 +18,9 @@ members = [
     "safekeeper",
     "storage_broker",
     "workspace_hack",
-    "trace",
     "libs/*",
 ]
 
-[workspace.package]
-edition = "2021"
-license = "Apache-2.0"
-
-## All dependency versions, used in the project
-[workspace.dependencies]
-anyhow = { version = "1.0", features = ["backtrace"] }
-async-stream = "0.3"
-async-trait = "0.1"
-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 = "0.51.0"
-base64 = "0.13.0"
-bincode = "1.3"
-bindgen = "0.61"
-bstr = "1.0"
-byteorder = "1.4"
-bytes = "1.0"
-chrono = { version = "0.4", default-features = false, features = ["clock"] }
-clap = { version = "4.0", features = ["derive"] }
-close_fds = "0.3.2"
-comfy-table = "6.1"
-const_format = "0.2"
-crc32c = "0.6"
-crossbeam-utils = "0.8.5"
-enum-map = "2.4.2"
-enumset = "1.0.12"
-fail = "0.5.0"
-fs2 = "0.4.3"
-futures = "0.3"
-futures-core = "0.3"
-futures-util = "0.3"
-git-version = "0.3"
-hashbrown = "0.13"
-hashlink = "0.8.1"
-hex = "0.4"
-hex-literal = "0.3"
-hmac = "0.12.1"
-hostname = "0.3.1"
-humantime = "2.1"
-humantime-serde = "1.1.1"
-hyper = "0.14"
-hyper-tungstenite = "0.9"
-itertools = "0.10"
-jsonwebtoken = "8"
-libc = "0.2"
-md5 = "0.7.0"
-memoffset = "0.8"
-nix = "0.26"
-notify = "5.0.0"
-num-traits = "0.2.15"
-once_cell = "1.13"
-opentelemetry = "0.18.0"
-opentelemetry-otlp = { version = "0.11.0", default_features=false, features = ["http-proto", "trace", "http", "reqwest-client"] }
-opentelemetry-semantic-conventions = "0.10.0"
-tracing-opentelemetry = "0.18.0"
-parking_lot = "0.12"
-pin-project-lite = "0.2"
-prometheus = {version = "0.13", default_features=false, features = ["process"]} # removes protobuf dependency
-prost = "0.11"
-rand = "0.8"
-regex = "1.4"
-reqwest = { version = "0.11", default-features = false, features = ["rustls-tls"] }
-routerify = "3"
-rpds = "0.12.0"
-rustls = "0.20"
-rustls-pemfile = "1"
-rustls-split = "0.3"
-scopeguard = "1.1"
-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 = "0.4.4"
-strum = "0.24"
-strum_macros = "0.24"
-svg_fmt = "0.4.1"
-tar = "0.4"
-thiserror = "1.0"
-tls-listener = { version = "0.6", features = ["rustls", "hyper-h1"] }
-tokio = { version = "1.17", features = ["macros"] }
-tokio-postgres-rustls = "0.9.0"
-tokio-rustls = "0.23"
-tokio-stream = "0.1"
-tokio-util = { version = "0.7", features = ["io"] }
-toml = "0.5"
-toml_edit = { version = "0.17", features = ["easy"] }
-tonic = {version = "0.8", features = ["tls", "tls-roots"]}
-tracing = "0.1"
-tracing-subscriber = { version = "0.3", features = ["env-filter"] }
-url = "2.2"
-uuid = { version = "1.2", features = ["v4", "serde"] }
-walkdir = "2.3.2"
-webpki-roots = "0.22.5"
-x509-parser = "0.14"
-
-## TODO replace this with tracing
-env_logger = "0.10"
-log = "0.4"
-
-## Libraries from neondatabase/ git forks, ideally with changes to be upstreamed
-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e" }
-postgres-protocol = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e" }
-postgres-types = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e" }
-tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e" }
-tokio-tar = { git = "https://github.com/neondatabase/tokio-tar.git", rev="404df61437de0feef49ba2ccdbdd94eb8ad6e142" }
-
-## Other git libraries
-heapless = { default-features=false, features=[], git = "https://github.com/japaric/heapless.git", rev = "644653bf3b831c6bb4963be2de24804acf5e5001" } # upstream release pending
-
-## Local libraries
-consumption_metrics = { version = "0.1", path = "./libs/consumption_metrics/" }
-metrics = { version = "0.1", path = "./libs/metrics/" }
-pageserver_api = { version = "0.1", path = "./libs/pageserver_api/" }
-postgres_connection = { version = "0.1", path = "./libs/postgres_connection/" }
-postgres_ffi = { version = "0.1", path = "./libs/postgres_ffi/" }
-pq_proto = { version = "0.1", path = "./libs/pq_proto/" }
-remote_storage = { version = "0.1", path = "./libs/remote_storage/" }
-safekeeper_api = { version = "0.1", path = "./libs/safekeeper_api" }
-storage_broker = { version = "0.1", path = "./storage_broker/" } # Note: main broker code is inside the binary crate, so linking with the library shouldn't be heavy.
-tenant_size_model = { version = "0.1", path = "./libs/tenant_size_model/" }
-tracing-utils = { version = "0.1", path = "./libs/tracing-utils/" }
-utils = { version = "0.1", path = "./libs/utils/" }
-
-## Common library dependency
-workspace_hack = { version = "0.1", path = "./workspace_hack/" }
-
-## Build dependencies
-criterion = "0.4"
-rcgen = "0.10"
-rstest = "0.16"
-tempfile = "3.2"
-tonic-build = "0.8"
-
-# This is only needed for proxy's tests.
-# TODO: we should probably fork `tokio-postgres-rustls` instead.
-[patch.crates-io]
-tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e" }
-
-################# Binary contents sections
-
 [profile.release]
 # This is useful for profiling and, to some extent, debug.
 # Besides, debug info should not affect the performance.
@@ -216,3 +81,9 @@ inherits = "release"
 debug = false # true = 2 = all symbols, 1 = line only
 opt-level = "z"
 lto = true
+
+
+# This is only needed for proxy's tests.
+# TODO: we should probably fork `tokio-postgres-rustls` instead.
+[patch.crates-io]
+tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e" }

Dockerfile.compute-node-v14

@@ -1,5 +1,8 @@
-ARG REPOSITORY=369495373322.dkr.ecr.eu-central-1.amazonaws.com
-ARG IMAGE=rust
+#
+# This file is identical to the Dockerfile.compute-node-v15 file
+# except for the version of Postgres that is built.
+#
+
 ARG TAG=pinned
 
 #########################################################################################
@@ -10,8 +13,7 @@ ARG TAG=pinned
 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
+    zlib1g-dev libxml2-dev libcurl4-openssl-dev libossp-uuid-dev wget pkg-config libssl-dev
 
 #########################################################################################
 #
@@ -20,21 +22,14 @@ RUN apt update &&  \
 #
 #########################################################################################
 FROM build-deps AS pg-build
-ARG PG_VERSION
-COPY vendor/postgres-${PG_VERSION} postgres
+COPY vendor/postgres-v14 postgres
 RUN cd postgres && \
-    ./configure CFLAGS='-O2 -g3' --enable-debug --with-openssl --with-uuid=ossp --with-icu && \
+    ./configure CFLAGS='-O2 -g3' --enable-debug --with-openssl --with-uuid=ossp && \
     make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s install && \
     make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s -C contrib/ install && \
     # Install headers
     make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s -C src/include install && \
-    make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s -C src/interfaces/libpq install && \
-    # Enable some of contrib extensions
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/bloom.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/pgrowlocks.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/intagg.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/pgstattuple.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/earthdistance.control
+    make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s -C src/interfaces/libpq install
 
 #########################################################################################
 #
@@ -45,34 +40,22 @@ RUN cd postgres && \
 FROM build-deps AS postgis-build
 COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
 RUN apt update && \
-    apt install -y cmake gdal-bin libboost-dev libboost-thread-dev libboost-filesystem-dev \
-    libboost-system-dev libboost-iostreams-dev libboost-program-options-dev libboost-timer-dev \
-    libcgal-dev libgdal-dev libgmp-dev libmpfr-dev libopenscenegraph-dev libprotobuf-c-dev \
-    protobuf-c-compiler xsltproc
-
-RUN wget https://gitlab.com/Oslandia/SFCGAL/-/archive/v1.3.10/SFCGAL-v1.3.10.tar.gz && \
-    tar zxvf SFCGAL-v1.3.10.tar.gz && \
-    cd SFCGAL-v1.3.10 && cmake . && make -j $(getconf _NPROCESSORS_ONLN) && \
-    DESTDIR=/sfcgal make install -j $(getconf _NPROCESSORS_ONLN) && \
-    make clean && cp -R /sfcgal/* /
+    apt install -y gdal-bin libgdal-dev libprotobuf-c-dev protobuf-c-compiler xsltproc
 
 RUN wget https://download.osgeo.org/postgis/source/postgis-3.3.1.tar.gz && \
     tar xvzf postgis-3.3.1.tar.gz && \
     cd postgis-3.3.1 && \
     ./autogen.sh && \
     export PATH="/usr/local/pgsql/bin:$PATH" && \
-    ./configure --with-sfcgal=/usr/local/bin/sfcgal-config && \
+    ./configure && \
     make -j $(getconf _NPROCESSORS_ONLN) install && \
     cd extensions/postgis && \
     make clean && \
     make -j $(getconf _NPROCESSORS_ONLN) install && \
     echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis.control && \
     echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_raster.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_sfcgal.control && \
     echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_tiger_geocoder.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_topology.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/address_standardizer.control && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/address_standardizer_data_us.control
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_topology.control
 
 #########################################################################################
 #
@@ -144,27 +127,6 @@ RUN wget https://github.com/zachasme/h3-pg/archive/refs/tags/v4.0.1.tar.gz -O h3
     echo 'trusted = true' >> /usr/local/pgsql/share/extension/h3.control && \
     echo 'trusted = true' >> /usr/local/pgsql/share/extension/h3_postgis.control
 
-#########################################################################################
-#
-# Layer "unit-pg-build"
-# compile unit extension
-#
-#########################################################################################
-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 && \
-    tar xvzf 7.7.tar.gz && \
-    cd postgresql-unit-7.7 && \
-    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 && \
-    # unit extension's "create extension" script relies on absolute install path to fill some reference tables.
-    # We move the extension from '/usr/local/pgsql/' to '/usr/local/'  after it is build. So we need to adjust the path.
-    # This one-liner removes pgsql/ part of the path.
-    # NOTE: Other extensions that rely on MODULEDIR variable after building phase will need the same fix.
-    find /usr/local/pgsql/share/extension/ -name "unit*.sql" -print0 | xargs -0 sed -i "s|pgsql/||g" && \
-    echo 'trusted = true' >> /usr/local/pgsql/share/extension/unit.control
-
 #########################################################################################
 #
 # Layer "neon-pg-ext-build"
@@ -173,11 +135,9 @@ RUN wget https://github.com/df7cb/postgresql-unit/archive/refs/tags/7.7.tar.gz &
 #########################################################################################
 FROM build-deps AS neon-pg-ext-build
 COPY --from=postgis-build /usr/local/pgsql/ /usr/local/pgsql/
-COPY --from=postgis-build /sfcgal/* /
 COPY --from=plv8-build /usr/local/pgsql/ /usr/local/pgsql/
 COPY --from=h3-pg-build /usr/local/pgsql/ /usr/local/pgsql/
 COPY --from=h3-pg-build /h3/usr /
-COPY --from=unit-pg-build /usr/local/pgsql/ /usr/local/pgsql/
 COPY pgxn/ pgxn/
 
 RUN make -j $(getconf _NPROCESSORS_ONLN) \
@@ -190,7 +150,7 @@ RUN make -j $(getconf _NPROCESSORS_ONLN) \
 # Compile and run the Neon-specific `compute_ctl` binary
 #
 #########################################################################################
-FROM $REPOSITORY/$IMAGE:$TAG AS compute-tools
+FROM 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:$TAG AS compute-tools
 USER nonroot
 # Copy entire project to get Cargo.* files with proper dependencies for the whole project
 COPY --chown=nonroot . .
@@ -210,6 +170,9 @@ RUN cd /usr/local/pgsql/bin && rm ecpg raster2pgsql shp2pgsql pgtopo_export pgto
 # Remove headers that we won't need anymore - we've completed installation of all extensions
 RUN rm -r /usr/local/pgsql/include
 
+# Remove now-useless PGXS src infrastructure
+RUN rm -r /usr/local/pgsql/lib/pgxs/src
+
 # Remove static postgresql libraries - all compilation is finished, so we
 # can now remove these files - they must be included in other binaries by now
 # if they were to be used by other libraries.
@@ -235,24 +198,17 @@ COPY --from=compute-tools --chown=postgres /home/nonroot/target/release-line-deb
 
 # Install:
 # libreadline8 for psql
-# libicu67, locales for collations (including ICU)
 # libossp-uuid16 for extension ossp-uuid
-# libgeos, libgdal, libsfcgal1, libproj and libprotobuf-c1 for PostGIS
+# libgeos, libgdal, libproj and libprotobuf-c1 for PostGIS
 RUN apt update &&  \
     apt install --no-install-recommends -y \
-        locales \
-        libicu67 \
         libreadline8 \
         libossp-uuid16 \
         libgeos-c1v5 \
         libgdal28 \
         libproj19 \
-        libprotobuf-c1 \
-        libsfcgal1 \
-        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
+        libprotobuf-c1 && \
+    rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
 
-ENV LANG en_US.utf8
 USER postgres
 ENTRYPOINT ["/usr/local/bin/compute_ctl"]

Dockerfile.compute-node-v15

@@ -0,0 +1,214 @@
+#
+# This file is identical to the Dockerfile.compute-node-v14 file
+# except for the version of Postgres that is built.
+#
+
+ARG TAG=pinned
+
+#########################################################################################
+#
+# Layer "build-deps"
+#
+#########################################################################################
+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
+
+#########################################################################################
+#
+# Layer "pg-build"
+# Build Postgres from the neon postgres repository.
+#
+#########################################################################################
+FROM build-deps AS pg-build
+COPY vendor/postgres-v15 postgres
+RUN cd postgres && \
+    ./configure CFLAGS='-O2 -g3' --enable-debug --with-openssl --with-uuid=ossp && \
+    make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s install && \
+    make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s -C contrib/ install && \
+    # Install headers
+    make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s -C src/include install && \
+    make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s -C src/interfaces/libpq install
+
+#########################################################################################
+#
+# Layer "postgis-build"
+# Build PostGIS from the upstream PostGIS mirror.
+#
+#########################################################################################
+FROM build-deps AS postgis-build
+COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
+RUN apt update && \
+    apt install -y gdal-bin libgdal-dev libprotobuf-c-dev protobuf-c-compiler xsltproc
+
+RUN wget https://download.osgeo.org/postgis/source/postgis-3.3.1.tar.gz && \
+    tar xvzf postgis-3.3.1.tar.gz && \
+    cd postgis-3.3.1 && \
+    ./autogen.sh && \
+    export PATH="/usr/local/pgsql/bin:$PATH" && \
+    ./configure && \
+    make -j $(getconf _NPROCESSORS_ONLN) install && \
+    cd extensions/postgis && \
+    make clean && \
+    make -j $(getconf _NPROCESSORS_ONLN) install && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis.control && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_raster.control && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_tiger_geocoder.control && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_topology.control
+
+#########################################################################################
+#
+# Layer "plv8-build"
+# Build plv8
+#
+#########################################################################################
+FROM build-deps AS plv8-build
+COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
+RUN apt update && \
+    apt install -y ninja-build python3-dev libc++-dev libc++abi-dev libncurses5 binutils
+
+# https://github.com/plv8/plv8/issues/475:
+#   v8 uses gold for linking and sets `--thread-count=4` which breaks
+#   gold version <= 1.35 (https://sourceware.org/bugzilla/show_bug.cgi?id=23607)
+# Install newer gold version manually as debian-testing binutils version updates
+# libc version, which in turn breaks other extension built against non-testing libc.
+RUN wget https://ftp.gnu.org/gnu/binutils/binutils-2.38.tar.gz && \
+    tar xvzf binutils-2.38.tar.gz && \
+    cd binutils-2.38 && \
+    cd libiberty && ./configure && make -j $(getconf _NPROCESSORS_ONLN) && \
+    cd ../bfd && ./configure && make bfdver.h && \
+    cd ../gold && ./configure && make -j $(getconf _NPROCESSORS_ONLN) && make install && \
+    cp /usr/local/bin/ld.gold /usr/bin/gold
+
+# Sed is used to patch for https://github.com/plv8/plv8/issues/503
+RUN wget https://github.com/plv8/plv8/archive/refs/tags/v3.1.4.tar.gz && \
+    tar xvzf v3.1.4.tar.gz && \
+    cd plv8-3.1.4 && \
+    export PATH="/usr/local/pgsql/bin:$PATH" && \
+    sed -i 's/MemoryContextAlloc(/MemoryContextAllocZero(/' plv8.cc && \
+    make DOCKER=1 -j $(getconf _NPROCESSORS_ONLN) install && \
+    rm -rf /plv8-* && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/plv8.control
+
+#########################################################################################
+#
+# Layer "h3-pg-build"
+# Build h3_pg
+#
+#########################################################################################
+FROM build-deps AS h3-pg-build
+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 \
+      && 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/v4.0.1.tar.gz -O h3.tgz && \
+    tar xvzf h3.tgz  && \
+    cd h3-4.0.1 && \
+    mkdir build && \
+    cd build && \
+    cmake .. -DCMAKE_BUILD_TYPE=Release && \
+    make -j $(getconf _NPROCESSORS_ONLN) && \
+    DESTDIR=/h3 make install && \
+    cp -R /h3/usr / && \
+    rm -rf build
+
+RUN wget https://github.com/zachasme/h3-pg/archive/refs/tags/v4.0.1.tar.gz -O h3-pg.tgz && \
+    tar xvzf h3-pg.tgz && \
+    cd h3-pg-4.0.1 && \
+    export PATH="/usr/local/pgsql/bin:$PATH" && \
+    make -j $(getconf _NPROCESSORS_ONLN) && \
+    make -j $(getconf _NPROCESSORS_ONLN) install && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/h3.control && \
+    echo 'trusted = true' >> /usr/local/pgsql/share/extension/h3_postgis.control
+
+#########################################################################################
+#
+# Layer "neon-pg-ext-build"
+# compile neon extensions
+#
+#########################################################################################
+FROM build-deps AS neon-pg-ext-build
+COPY --from=postgis-build /usr/local/pgsql/ /usr/local/pgsql/
+COPY --from=plv8-build /usr/local/pgsql/ /usr/local/pgsql/
+COPY --from=h3-pg-build /usr/local/pgsql/ /usr/local/pgsql/
+COPY --from=h3-pg-build /h3/usr /
+COPY pgxn/ pgxn/
+
+RUN make -j $(getconf _NPROCESSORS_ONLN) \
+        PG_CONFIG=/usr/local/pgsql/bin/pg_config \
+        -C pgxn/neon \
+        -s install
+
+#########################################################################################
+#
+# Compile and run the Neon-specific `compute_ctl` binary
+#
+#########################################################################################
+FROM 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:$TAG AS compute-tools
+USER nonroot
+# Copy entire project to get Cargo.* files with proper dependencies for the whole project
+COPY --chown=nonroot . .
+RUN cd compute_tools && cargo build --locked --profile release-line-debug-size-lto
+
+#########################################################################################
+#
+# Clean up postgres folder before inclusion
+#
+#########################################################################################
+FROM neon-pg-ext-build AS postgres-cleanup-layer
+COPY --from=neon-pg-ext-build /usr/local/pgsql /usr/local/pgsql
+
+# Remove binaries from /bin/ that we won't use (or would manually copy & install otherwise)
+RUN cd /usr/local/pgsql/bin && rm ecpg raster2pgsql shp2pgsql pgtopo_export pgtopo_import pgsql2shp
+
+# Remove headers that we won't need anymore - we've completed installation of all extensions
+RUN rm -r /usr/local/pgsql/include
+
+# Remove now-useless PGXS src infrastructure
+RUN rm -r /usr/local/pgsql/lib/pgxs/src
+
+# Remove static postgresql libraries - all compilation is finished, so we
+# can now remove these files - they must be included in other binaries by now
+# if they were to be used by other libraries.
+RUN rm /usr/local/pgsql/lib/lib*.a
+
+#########################################################################################
+#
+# Final layer
+# Put it all together into the final image
+#
+#########################################################################################
+FROM debian:bullseye-slim
+# Add user postgres
+RUN mkdir /var/db && useradd -m -d /var/db/postgres postgres && \
+    echo "postgres:test_console_pass" | chpasswd && \
+    mkdir /var/db/postgres/compute && mkdir /var/db/postgres/specs && \
+    chown -R postgres:postgres /var/db/postgres && \
+    chmod 0750 /var/db/postgres/compute && \
+    echo '/usr/local/lib' >> /etc/ld.so.conf && /sbin/ldconfig
+
+COPY --from=postgres-cleanup-layer --chown=postgres /usr/local/pgsql /usr/local
+COPY --from=compute-tools --chown=postgres /home/nonroot/target/release-line-debug-size-lto/compute_ctl /usr/local/bin/compute_ctl
+
+# Install:
+# libreadline8 for psql
+# libossp-uuid16 for extension ossp-uuid
+# libgeos, libgdal, libproj and libprotobuf-c1 for PostGIS
+RUN apt update &&  \
+    apt install --no-install-recommends -y \
+        libreadline8 \
+        libossp-uuid16 \
+        libgeos-c1v5 \
+        libgdal28 \
+        libproj19 \
+        libprotobuf-c1 && \
+    rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
+
+USER postgres
+ENTRYPOINT ["/usr/local/bin/compute_ctl"]

README.md

@@ -31,8 +31,7 @@ libssl-dev clang pkg-config libpq-dev cmake postgresql-client protobuf-compiler
 * On Fedora, these packages are needed:
 ```bash
 dnf install flex bison readline-devel zlib-devel openssl-devel \
-  libseccomp-devel perl clang cmake postgresql postgresql-contrib protobuf-compiler \
-  protobuf-devel
+  libseccomp-devel perl clang cmake postgresql postgresql-contrib protobuf-compiler
 ```
 
 2. [Install Rust](https://www.rust-lang.org/tools/install)
@@ -108,7 +107,7 @@ make -j`sysctl -n hw.logicalcpu`
 To run the `psql` client, install the `postgresql-client` package or modify `PATH` and `LD_LIBRARY_PATH` to include `pg_install/bin` and `pg_install/lib`, respectively.
 
 To run the integration tests or Python scripts (not required to use the code), install
-Python (3.9 or higher), and install python3 packages using `./scripts/pysync` (requires [poetry>=1.3](https://python-poetry.org/)) in the project directory.
+Python (3.9 or higher), and install python3 packages using `./scripts/pysync` (requires [poetry](https://python-poetry.org/)) in the project directory.
 
 
 #### Running neon database
@@ -118,8 +117,11 @@ Python (3.9 or higher), and install python3 packages using `./scripts/pysync` (r
 # Later that would be responsibility of a package install script
 > ./target/debug/neon_local init
 Starting pageserver at '127.0.0.1:64000' in '.neon'.
+pageserver started, pid: 2545906
+Successfully initialized timeline de200bd42b49cc1814412c7e592dd6e9
+Stopped pageserver 1 process with pid 2545906
 
-# start pageserver, safekeeper, and broker for their intercommunication
+# start pageserver and safekeeper
 > ./target/debug/neon_local start
 Starting neon broker at 127.0.0.1:50051
 storage_broker started, pid: 2918372
@@ -128,12 +130,6 @@ pageserver started, pid: 2918386
 Starting safekeeper at '127.0.0.1:5454' in '.neon/safekeepers/sk1'.
 safekeeper 1 started, pid: 2918437
 
-# create initial tenant and use it as a default for every future neon_local invocation
-> ./target/debug/neon_local tenant create --set-default
-tenant 9ef87a5bf0d92544f6fafeeb3239695c successfully created on the pageserver
-Created an initial timeline 'de200bd42b49cc1814412c7e592dd6e9' at Lsn 0/16B5A50 for tenant: 9ef87a5bf0d92544f6fafeeb3239695c
-Setting tenant 9ef87a5bf0d92544f6fafeeb3239695c as a default one
-
 # start postgres compute node
 > ./target/debug/neon_local pg start main
 Starting new postgres (v14) main on timeline de200bd42b49cc1814412c7e592dd6e9 ...

compute_tools/Cargo.toml

@@ -1,28 +1,23 @@
 [package]
 name = "compute_tools"
 version = "0.1.0"
-edition.workspace = true
-license.workspace = true
+edition = "2021"
 
 [dependencies]
-anyhow.workspace = true
-chrono.workspace = true
-clap.workspace = true
-futures.workspace = true
-hyper = { workspace = true, features = ["full"] }
-notify.workspace = true
-opentelemetry.workspace = true
-postgres.workspace = true
-regex.workspace = true
-serde.workspace = true
-serde_json.workspace = true
-tar.workspace = true
-tokio = { workspace = true, features = ["rt", "rt-multi-thread"] }
-tokio-postgres.workspace = true
-tracing.workspace = true
-tracing-opentelemetry.workspace = true
-tracing-subscriber.workspace = true
-tracing-utils.workspace = true
-url.workspace = true
-
-workspace_hack.workspace = true
+anyhow = "1.0"
+chrono = { version = "0.4", default-features = false, features = ["clock"] }
+clap = "4.0"
+env_logger = "0.9"
+futures = "0.3.13"
+hyper = { version = "0.14", features = ["full"] }
+log = { version = "0.4", features = ["std", "serde"] }
+notify = "5.0.0"
+postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e" }
+regex = "1"
+serde = { version = "1.0", features = ["derive"] }
+serde_json = "1"
+tar = "0.4"
+tokio = { version = "1.17", features = ["macros", "rt", "rt-multi-thread"] }
+tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e" }
+url = "2.2.2"
+workspace_hack = { version = "0.1", path = "../workspace_hack" }

compute_tools/README.md

@@ -19,10 +19,6 @@ Also `compute_ctl` spawns two separate service threads:
 - `http-endpoint` runs a Hyper HTTP API server, which serves readiness and the
   last activity requests.
 
-If the `vm-informant` binary is present at `/bin/vm-informant`, it will also be started. For VM
-compute nodes, `vm-informant` communicates with the VM autoscaling system. It coordinates
-downscaling and (eventually) will request immediate upscaling under resource pressure.
-
 Usage example:
 ```sh
 compute_ctl -D /var/db/postgres/compute \

compute_tools/src/bin/compute_ctl.rs

@@ -18,10 +18,6 @@
 //! - `http-endpoint` runs a Hyper HTTP API server, which serves readiness and the
 //!   last activity requests.
 //!
-//! If the `vm-informant` binary is present at `/bin/vm-informant`, it will also be started. For VM
-//! compute nodes, `vm-informant` communicates with the VM autoscaling system. It coordinates
-//! downscaling and (eventually) will request immediate upscaling under resource pressure.
-//!
 //! Usage example:
 //! ```sh
 //! compute_ctl -D /var/db/postgres/compute \
@@ -40,11 +36,10 @@ use std::{thread, time::Duration};
 use anyhow::{Context, Result};
 use chrono::Utc;
 use clap::Arg;
-use tracing::{error, info};
+use log::{error, info};
 
 use compute_tools::compute::{ComputeMetrics, ComputeNode, ComputeState, ComputeStatus};
 use compute_tools::http::api::launch_http_server;
-use compute_tools::informant::spawn_vm_informant_if_present;
 use compute_tools::logger::*;
 use compute_tools::monitor::launch_monitor;
 use compute_tools::params::*;
@@ -53,7 +48,8 @@ use compute_tools::spec::*;
 use url::Url;
 
 fn main() -> Result<()> {
-    init_tracing_and_logging(DEFAULT_LOG_LEVEL)?;
+    // TODO: re-use `utils::logging` later
+    init_logger(DEFAULT_LOG_LEVEL)?;
 
     let matches = cli().get_matches();
 
@@ -84,29 +80,6 @@ fn main() -> Result<()> {
         }
     };
 
-    // Extract OpenTelemetry context for the startup actions from the spec, and
-    // attach it to the current tracing context.
-    //
-    // This is used to propagate the context for the 'start_compute' operation
-    // from the neon control plane. This allows linking together the wider
-    // 'start_compute' operation that creates the compute container, with the
-    // startup actions here within the container.
-    //
-    // Switch to the startup context here, and exit it once the startup has
-    // completed and Postgres is up and running.
-    //
-    // NOTE: This is supposed to only cover the *startup* actions. Once
-    // postgres is configured and up-and-running, we exit this span. Any other
-    // actions that are performed on incoming HTTP requests, for example, are
-    // performed in separate spans.
-    let startup_context_guard = if let Some(ref carrier) = spec.startup_tracing_context {
-        use opentelemetry::propagation::TextMapPropagator;
-        use opentelemetry::sdk::propagation::TraceContextPropagator;
-        Some(TraceContextPropagator::new().extract(carrier).attach())
-    } else {
-        None
-    };
-
     let pageserver_connstr = spec
         .cluster
         .settings
@@ -132,7 +105,7 @@ fn main() -> Result<()> {
         tenant,
         timeline,
         pageserver_connstr,
-        metrics: ComputeMetrics::default(),
+        metrics: ComputeMetrics::new(),
         state: RwLock::new(ComputeState::new()),
     };
     let compute = Arc::new(compute_state);
@@ -141,55 +114,30 @@ fn main() -> Result<()> {
     // requests, while configuration is still in progress.
     let _http_handle = launch_http_server(&compute).expect("cannot launch http endpoint thread");
     let _monitor_handle = launch_monitor(&compute).expect("cannot launch compute monitor thread");
-    // Also spawn the thread responsible for handling the VM informant -- if it's present
-    let _vm_informant_handle = spawn_vm_informant_if_present().expect("cannot launch VM informant");
 
-    // Start Postgres
-    let mut delay_exit = false;
-    let mut exit_code = None;
-    let pg = match compute.start_compute() {
-        Ok(pg) => Some(pg),
-        Err(err) => {
-            error!("could not start the compute node: {:?}", err);
+    // Run compute (Postgres) and hang waiting on it.
+    match compute.prepare_and_run() {
+        Ok(ec) => {
+            let code = ec.code().unwrap_or(1);
+            info!("Postgres exited with code {}, shutting down", code);
+            exit(code)
+        }
+        Err(error) => {
+            error!("could not start the compute node: {:?}", error);
+
             let mut state = compute.state.write().unwrap();
-            state.error = Some(format!("{:?}", err));
+            state.error = Some(format!("{:?}", error));
             state.status = ComputeStatus::Failed;
             drop(state);
-            delay_exit = true;
-            None
+
+            // Keep serving HTTP requests, so the cloud control plane was able to
+            // get the actual error.
+            info!("giving control plane 30s to collect the error before shutdown");
+            thread::sleep(Duration::from_secs(30));
+            info!("shutting down");
+            Err(error)
         }
-    };
-
-    // Wait for the child Postgres process forever. In this state Ctrl+C will
-    // propagate to Postgres and it will be shut down as well.
-    if let Some(mut pg) = pg {
-        // Startup is finished, exit the startup tracing span
-        drop(startup_context_guard);
-
-        let ecode = pg
-            .wait()
-            .expect("failed to start waiting on Postgres process");
-        info!("Postgres exited with code {}, shutting down", ecode);
-        exit_code = ecode.code()
     }
-
-    if let Err(err) = compute.check_for_core_dumps() {
-        error!("error while checking for core dumps: {err:?}");
-    }
-
-    // If launch failed, keep serving HTTP requests for a while, so the cloud
-    // control plane can get the actual error.
-    if delay_exit {
-        info!("giving control plane 30s to collect the error before shutdown");
-        thread::sleep(Duration::from_secs(30));
-        info!("shutting down");
-    }
-
-    // Shutdown trace pipeline gracefully, so that it has a chance to send any
-    // pending traces before we exit.
-    tracing_utils::shutdown_tracing();
-
-    exit(exit_code.unwrap_or(1))
 }
 
 fn cli() -> clap::Command {

compute_tools/src/checker.rs

@@ -1,12 +1,11 @@
 use anyhow::{anyhow, Result};
+use log::error;
 use postgres::Client;
 use tokio_postgres::NoTls;
-use tracing::{error, instrument};
 
 use crate::compute::ComputeNode;
 
-#[instrument(skip_all)]
-pub fn create_writability_check_data(client: &mut Client) -> Result<()> {
+pub fn create_writablity_check_data(client: &mut Client) -> Result<()> {
     let query = "
     CREATE TABLE IF NOT EXISTS health_check (
         id serial primary key,
@@ -22,7 +21,6 @@ pub fn create_writability_check_data(client: &mut Client) -> Result<()> {
     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() {

compute_tools/src/compute.rs

@@ -17,17 +17,17 @@
 use std::fs;
 use std::os::unix::fs::PermissionsExt;
 use std::path::Path;
-use std::process::{Command, Stdio};
+use std::process::{Command, ExitStatus, Stdio};
 use std::sync::atomic::{AtomicU64, Ordering};
 use std::sync::RwLock;
 
 use anyhow::{Context, Result};
 use chrono::{DateTime, Utc};
+use log::info;
 use postgres::{Client, NoTls};
 use serde::{Serialize, Serializer};
-use tracing::{info, instrument, warn};
 
-use crate::checker::create_writability_check_data;
+use crate::checker::create_writablity_check_data;
 use crate::config;
 use crate::pg_helpers::*;
 use crate::spec::*;
@@ -91,7 +91,7 @@ pub enum ComputeStatus {
     Failed,
 }
 
-#[derive(Default, Serialize)]
+#[derive(Serialize)]
 pub struct ComputeMetrics {
     pub sync_safekeepers_ms: AtomicU64,
     pub basebackup_ms: AtomicU64,
@@ -99,6 +99,23 @@ pub struct ComputeMetrics {
     pub total_startup_ms: AtomicU64,
 }
 
+impl ComputeMetrics {
+    pub fn new() -> Self {
+        Self {
+            sync_safekeepers_ms: AtomicU64::new(0),
+            basebackup_ms: AtomicU64::new(0),
+            config_ms: AtomicU64::new(0),
+            total_startup_ms: AtomicU64::new(0),
+        }
+    }
+}
+
+impl Default for ComputeMetrics {
+    fn default() -> Self {
+        Self::new()
+    }
+}
+
 impl ComputeNode {
     pub fn set_status(&self, status: ComputeStatus) {
         self.state.write().unwrap().status = status;
@@ -121,7 +138,6 @@ impl ComputeNode {
 
     // Get basebackup from the libpq connection to pageserver using `connstr` and
     // unarchive it to `pgdata` directory overriding all its previous content.
-    #[instrument(skip(self))]
     fn get_basebackup(&self, lsn: &str) -> Result<()> {
         let start_time = Utc::now();
 
@@ -155,12 +171,11 @@ impl ComputeNode {
 
     // Run `postgres` in a special mode with `--sync-safekeepers` argument
     // and return the reported LSN back to the caller.
-    #[instrument(skip(self))]
     fn sync_safekeepers(&self) -> Result<String> {
         let start_time = Utc::now();
 
         let sync_handle = Command::new(&self.pgbin)
-            .args(["--sync-safekeepers"])
+            .args(&["--sync-safekeepers"])
             .env("PGDATA", &self.pgdata) // we cannot use -D in this mode
             .stdout(Stdio::piped())
             .spawn()
@@ -198,7 +213,6 @@ impl ComputeNode {
 
     /// Do all the preparations like PGDATA directory creation, configuration,
     /// safekeepers sync, basebackup, etc.
-    #[instrument(skip(self))]
     pub fn prepare_pgdata(&self) -> Result<()> {
         let spec = &self.spec;
         let pgdata_path = Path::new(&self.pgdata);
@@ -232,27 +246,23 @@ impl ComputeNode {
 
     /// Start Postgres as a child process and manage DBs/roles.
     /// After that this will hang waiting on the postmaster process to exit.
-    #[instrument(skip(self))]
-    pub fn start_postgres(&self) -> Result<std::process::Child> {
+    pub fn run(&self) -> Result<ExitStatus> {
+        let start_time = Utc::now();
+
         let pgdata_path = Path::new(&self.pgdata);
 
         // Run postgres as a child process.
         let mut pg = Command::new(&self.pgbin)
-            .args(["-D", &self.pgdata])
+            .args(&["-D", &self.pgdata])
             .spawn()
             .expect("cannot start postgres process");
 
         wait_for_postgres(&mut pg, pgdata_path)?;
 
-        Ok(pg)
-    }
-
-    #[instrument(skip(self))]
-    pub fn apply_config(&self) -> Result<()> {
         // If connection fails,
         // it may be the old node with `zenith_admin` superuser.
         //
-        // In this case we need to connect with old `zenith_admin` name
+        // In this case we need to connect with old `zenith_admin`name
         // and create new user. We cannot simply rename connected user,
         // but we can create a new one and grant it all privileges.
         let mut client = match Client::connect(self.connstr.as_str(), NoTls) {
@@ -278,43 +288,16 @@ impl ComputeNode {
             Ok(client) => client,
         };
 
-        // Proceed with post-startup configuration. Note, that order of operations is important.
         handle_roles(&self.spec, &mut client)?;
         handle_databases(&self.spec, &mut client)?;
         handle_role_deletions(self, &mut client)?;
         handle_grants(self, &mut client)?;
-        create_writability_check_data(&mut client)?;
+        create_writablity_check_data(&mut client)?;
 
         // 'Close' connection
         drop(client);
-
-        info!(
-            "finished configuration of compute for project {}",
-            self.spec.cluster.cluster_id
-        );
-
-        Ok(())
-    }
-
-    #[instrument(skip(self))]
-    pub fn start_compute(&self) -> Result<std::process::Child> {
-        info!(
-            "starting compute for project {}, operation {}, tenant {}, timeline {}",
-            self.spec.cluster.cluster_id,
-            self.spec.operation_uuid.as_ref().unwrap(),
-            self.tenant,
-            self.timeline,
-        );
-
-        self.prepare_pgdata()?;
-
-        let start_time = Utc::now();
-
-        let pg = self.start_postgres()?;
-
-        self.apply_config()?;
-
         let startup_end_time = Utc::now();
+
         self.metrics.config_ms.store(
             startup_end_time
                 .signed_duration_since(start_time)
@@ -334,70 +317,30 @@ impl ComputeNode {
 
         self.set_status(ComputeStatus::Running);
 
-        Ok(pg)
+        info!(
+            "finished configuration of compute for project {}",
+            self.spec.cluster.cluster_id
+        );
+
+        // Wait for child Postgres process basically forever. In this state Ctrl+C
+        // will propagate to Postgres and it will be shut down as well.
+        let ecode = pg
+            .wait()
+            .expect("failed to start waiting on Postgres process");
+
+        Ok(ecode)
     }
 
-    // Look for core dumps and collect backtraces.
-    //
-    // EKS worker nodes have following core dump settings:
-    //   /proc/sys/kernel/core_pattern -> core
-    //   /proc/sys/kernel/core_uses_pid -> 1
-    //   ulimint -c -> unlimited
-    // which results in core dumps being written to postgres data directory as core.<pid>.
-    //
-    // Use that as a default location and pattern, except macos where core dumps are written
-    // to /cores/ directory by default.
-    pub fn check_for_core_dumps(&self) -> Result<()> {
-        let core_dump_dir = match std::env::consts::OS {
-            "macos" => Path::new("/cores/"),
-            _ => Path::new(&self.pgdata),
-        };
+    pub fn prepare_and_run(&self) -> Result<ExitStatus> {
+        info!(
+            "starting compute for project {}, operation {}, tenant {}, timeline {}",
+            self.spec.cluster.cluster_id,
+            self.spec.operation_uuid.as_ref().unwrap(),
+            self.tenant,
+            self.timeline,
+        );
 
-        // Collect core dump paths if any
-        info!("checking for core dumps in {}", core_dump_dir.display());
-        let files = fs::read_dir(core_dump_dir)?;
-        let cores = files.filter_map(|entry| {
-            let entry = entry.ok()?;
-            let _ = entry.file_name().to_str()?.strip_prefix("core.")?;
-            Some(entry.path())
-        });
-
-        // Print backtrace for each core dump
-        for core_path in cores {
-            warn!(
-                "core dump found: {}, collecting backtrace",
-                core_path.display()
-            );
-
-            // Try first with gdb
-            let backtrace = Command::new("gdb")
-                .args(["--batch", "-q", "-ex", "bt", &self.pgbin])
-                .arg(&core_path)
-                .output();
-
-            // Try lldb if no gdb is found -- that is handy for local testing on macOS
-            let backtrace = match backtrace {
-                Err(ref e) if e.kind() == std::io::ErrorKind::NotFound => {
-                    warn!("cannot find gdb, trying lldb");
-                    Command::new("lldb")
-                        .arg("-c")
-                        .arg(&core_path)
-                        .args(["--batch", "-o", "bt all", "-o", "quit"])
-                        .output()
-                }
-                _ => backtrace,
-            }?;
-
-            warn!(
-                "core dump backtrace: {}",
-                String::from_utf8_lossy(&backtrace.stdout)
-            );
-            warn!(
-                "debugger stderr: {}",
-                String::from_utf8_lossy(&backtrace.stderr)
-            );
-        }
-
-        Ok(())
+        self.prepare_pgdata()?;
+        self.run()
     }
 }

compute_tools/src/http/api.rs

@@ -6,20 +6,32 @@ use std::thread;
 use anyhow::Result;
 use hyper::service::{make_service_fn, service_fn};
 use hyper::{Body, Method, Request, Response, Server, StatusCode};
+use log::{error, info};
 use serde_json;
-use tracing::{error, info};
-use tracing_utils::http::OtelName;
 
-use crate::compute::ComputeNode;
+use crate::compute::{ComputeNode, ComputeStatus};
 
 // Service function to handle all available routes.
-async fn routes(req: Request<Body>, compute: &Arc<ComputeNode>) -> Response<Body> {
-    //
-    // NOTE: The URI path is currently included in traces. That's OK because
-    // it doesn't contain any variable parts or sensitive information. But
-    // please keep that in mind if you change the routing here.
-    //
+async fn routes(req: Request<Body>, compute: Arc<ComputeNode>) -> Response<Body> {
     match (req.method(), req.uri().path()) {
+        // Timestamp of the last Postgres activity in the plain text.
+        // DEPRECATED in favour of /status
+        (&Method::GET, "/last_activity") => {
+            info!("serving /last_active GET request");
+            let state = compute.state.read().unwrap();
+
+            // Use RFC3339 format for consistency.
+            Response::new(Body::from(state.last_active.to_rfc3339()))
+        }
+
+        // Has compute setup process finished? -> true/false.
+        // DEPRECATED in favour of /status
+        (&Method::GET, "/ready") => {
+            info!("serving /ready GET request");
+            let status = compute.get_status();
+            Response::new(Body::from(format!("{}", status == ComputeStatus::Running)))
+        }
+
         // Serialized compute state.
         (&Method::GET, "/status") => {
             info!("serving /status GET request");
@@ -34,9 +46,19 @@ async fn routes(req: Request<Body>, compute: &Arc<ComputeNode>) -> Response<Body
             Response::new(Body::from(serde_json::to_string(&compute.metrics).unwrap()))
         }
 
+        // DEPRECATED, use POST instead
+        (&Method::GET, "/check_writability") => {
+            info!("serving /check_writability GET request");
+            let res = crate::checker::check_writability(&compute).await;
+            match res {
+                Ok(_) => Response::new(Body::from("true")),
+                Err(e) => Response::new(Body::from(e.to_string())),
+            }
+        }
+
         (&Method::POST, "/check_writability") => {
             info!("serving /check_writability POST request");
-            let res = crate::checker::check_writability(compute).await;
+            let res = crate::checker::check_writability(&compute).await;
             match res {
                 Ok(_) => Response::new(Body::from("true")),
                 Err(e) => Response::new(Body::from(e.to_string())),
@@ -62,19 +84,7 @@ async fn serve(state: Arc<ComputeNode>) {
         async move {
             Ok::<_, Infallible>(service_fn(move |req: Request<Body>| {
                 let state = state.clone();
-                async move {
-                    Ok::<_, Infallible>(
-                        // NOTE: We include the URI path in the string. It
-                        // doesn't contain any variable parts or sensitive
-                        // information in this API.
-                        tracing_utils::http::tracing_handler(
-                            req,
-                            |req| routes(req, &state),
-                            OtelName::UriPath,
-                        )
-                        .await,
-                    )
-                }
+                async move { Ok::<_, Infallible>(routes(req, state).await) }
             }))
         }
     });

compute_tools/src/http/openapi_spec.yaml

@@ -37,7 +37,58 @@ paths:
               schema:
                 $ref: "#/components/schemas/ComputeMetrics"
 
+  /ready:
+    get:
+      deprecated: true
+      tags:
+      - "info"
+      summary: Check whether compute startup process finished successfully
+      description: ""
+      operationId: computeIsReady
+      responses:
+        "200":
+          description: Compute is ready ('true') or not ('false')
+          content:
+            text/plain:
+              schema:
+                type: string
+                example: "true"
+
+  /last_activity:
+    get:
+      deprecated: true
+      tags:
+      - "info"
+      summary: Get timestamp of the last compute activity
+      description: ""
+      operationId: getLastComputeActivityTS
+      responses:
+        "200":
+          description: Timestamp of the last compute activity
+          content:
+            text/plain:
+              schema:
+                type: string
+                example: "2022-10-12T07:20:50.52Z"
+
   /check_writability:
+    get:
+      deprecated: true
+      tags:
+      - "check"
+      summary: Check that we can write new data on this compute
+      description: ""
+      operationId: checkComputeWritabilityDeprecated
+      responses:
+        "200":
+          description: Check result
+          content:
+            text/plain:
+              schema:
+                type: string
+                description: Error text or 'true' if check passed
+                example: "true"
+
     post:
       tags:
       - "check"

compute_tools/src/informant.rs

@@ -1,50 +0,0 @@
-use std::path::Path;
-use std::process;
-use std::thread;
-use std::time::Duration;
-use tracing::{info, warn};
-
-use anyhow::{Context, Result};
-
-const VM_INFORMANT_PATH: &str = "/bin/vm-informant";
-const RESTART_INFORMANT_AFTER_MILLIS: u64 = 5000;
-
-/// Launch a thread to start the VM informant if it's present (and restart, on failure)
-pub fn spawn_vm_informant_if_present() -> Result<Option<thread::JoinHandle<()>>> {
-    let exists = Path::new(VM_INFORMANT_PATH)
-        .try_exists()
-        .context("could not check if path exists")?;
-
-    if !exists {
-        return Ok(None);
-    }
-
-    Ok(Some(
-        thread::Builder::new()
-            .name("run-vm-informant".into())
-            .spawn(move || run_informant())?,
-    ))
-}
-
-fn run_informant() -> ! {
-    let restart_wait = Duration::from_millis(RESTART_INFORMANT_AFTER_MILLIS);
-
-    info!("starting VM informant");
-
-    loop {
-        let mut cmd = process::Command::new(VM_INFORMANT_PATH);
-        // Block on subprocess:
-        let result = cmd.status();
-
-        match result {
-            Err(e) => warn!("failed to run VM informant at {VM_INFORMANT_PATH:?}: {e}"),
-            Ok(status) if !status.success() => {
-                warn!("{VM_INFORMANT_PATH} exited with code {status:?}, retrying")
-            }
-            Ok(_) => info!("{VM_INFORMANT_PATH} ended gracefully (unexpectedly). Retrying"),
-        }
-
-        // Wait before retrying
-        thread::sleep(restart_wait);
-    }
-}

compute_tools/src/lib.rs

@@ -8,7 +8,6 @@ pub mod http;
 #[macro_use]
 pub mod logger;
 pub mod compute;
-pub mod informant;
 pub mod monitor;
 pub mod params;
 pub mod pg_helpers;

compute_tools/src/logger.rs

@@ -1,37 +1,43 @@
-use tracing_opentelemetry::OpenTelemetryLayer;
-use tracing_subscriber::layer::SubscriberExt;
-use tracing_subscriber::prelude::*;
+use std::io::Write;
 
-/// Initialize logging to stderr, and OpenTelemetry tracing and exporter.
-///
-/// Logging is configured using either `default_log_level` or
+use anyhow::Result;
+use chrono::Utc;
+use env_logger::{Builder, Env};
+
+macro_rules! info_println {
+    ($($tts:tt)*) => {
+        if log_enabled!(Level::Info) {
+            println!($($tts)*);
+        }
+    }
+}
+
+macro_rules! info_print {
+    ($($tts:tt)*) => {
+        if log_enabled!(Level::Info) {
+            print!($($tts)*);
+        }
+    }
+}
+
+/// Initialize `env_logger` using either `default_level` or
 /// `RUST_LOG` environment variable as default log level.
-///
-/// OpenTelemetry is configured with OTLP/HTTP exporter. It picks up
-/// configuration from environment variables. For example, to change the destination,
-/// set `OTEL_EXPORTER_OTLP_ENDPOINT=http://jaeger:4318`. See
-/// `tracing-utils` package description.
-///
-pub fn init_tracing_and_logging(default_log_level: &str) -> anyhow::Result<()> {
-    // Initialize Logging
-    let env_filter = tracing_subscriber::EnvFilter::try_from_default_env()
-        .unwrap_or_else(|_| tracing_subscriber::EnvFilter::new(default_log_level));
+pub fn init_logger(default_level: &str) -> Result<()> {
+    let env = Env::default().filter_or("RUST_LOG", default_level);
 
-    let fmt_layer = tracing_subscriber::fmt::layer()
-        .with_target(false)
-        .with_writer(std::io::stderr);
-
-    // Initialize OpenTelemetry
-    let otlp_layer =
-        tracing_utils::init_tracing_without_runtime("compute_ctl").map(OpenTelemetryLayer::new);
-
-    // Put it all together
-    tracing_subscriber::registry()
-        .with(env_filter)
-        .with(otlp_layer)
-        .with(fmt_layer)
+    Builder::from_env(env)
+        .format(|buf, record| {
+            let thread_handle = std::thread::current();
+            writeln!(
+                buf,
+                "{} [{}] {}: {}",
+                Utc::now().format("%Y-%m-%d %H:%M:%S%.3f %Z"),
+                thread_handle.name().unwrap_or("main"),
+                record.level(),
+                record.args()
+            )
+        })
         .init();
-    tracing::info!("logging and tracing started");
 
     Ok(())
 }

compute_tools/src/monitor.rs

@@ -3,8 +3,8 @@ use std::{thread, time};
 
 use anyhow::Result;
 use chrono::{DateTime, Utc};
+use log::{debug, info};
 use postgres::{Client, NoTls};
-use tracing::{debug, info};
 
 use crate::compute::ComputeNode;
 
@@ -52,16 +52,10 @@ fn watch_compute_activity(compute: &ComputeNode) {
                     let mut idle_backs: Vec<DateTime<Utc>> = vec![];
 
                     for b in backs.into_iter() {
-                        let state: String = match b.try_get("state") {
-                            Ok(state) => state,
-                            Err(_) => continue,
-                        };
+                        let state: String = b.get("state");
+                        let change: String = b.get("state_change");
 
                         if state == "idle" {
-                            let change: String = match b.try_get("state_change") {
-                                Ok(state_change) => state_change,
-                                Err(_) => continue,
-                            };
                             let change = DateTime::parse_from_rfc3339(&change);
                             match change {
                                 Ok(t) => idle_backs.push(t.with_timezone(&Utc)),
@@ -80,8 +74,10 @@ fn watch_compute_activity(compute: &ComputeNode) {
                         }
                     }
 
-                    // Get idle backend `state_change` with the max timestamp.
-                    if let Some(last) = idle_backs.iter().max() {
+                    // Sort idle backend `state_change` timestamps. The last one corresponds
+                    // to the last activity.
+                    idle_backs.sort();
+                    if let Some(last) = idle_backs.last() {
                         last_active = *last;
                     }
                 }

compute_tools/src/params.rs

@@ -1,9 +1,3 @@
 pub const DEFAULT_LOG_LEVEL: &str = "info";
-// From Postgres docs:
-//   To ease transition from the md5 method to the newer SCRAM method, if md5 is specified
-//   as a method in pg_hba.conf but the user's password on the server is encrypted for SCRAM
-//   (see below), then SCRAM-based authentication will automatically be chosen instead.
-//   https://www.postgresql.org/docs/15/auth-password.html
-//
-// So it's safe to set md5 here, as `control-plane` anyway uses SCRAM for all roles.
+pub const DEFAULT_CONNSTRING: &str = "host=localhost user=postgres";
 pub const PG_HBA_ALL_MD5: &str = "host\tall\t\tall\t\t0.0.0.0/0\t\tmd5";

compute_tools/src/pg_helpers.rs

@@ -11,7 +11,6 @@ use anyhow::{bail, Result};
 use notify::{RecursiveMode, Watcher};
 use postgres::{Client, Transaction};
 use serde::Deserialize;
-use tracing::{debug, instrument};
 
 const POSTGRES_WAIT_TIMEOUT: Duration = Duration::from_millis(60 * 1000); // milliseconds
 
@@ -120,9 +119,16 @@ pub trait GenericOptionsSearch {
 impl GenericOptionsSearch for GenericOptions {
     /// Lookup option by name
     fn find(&self, name: &str) -> Option<String> {
-        let ops = self.as_ref()?;
-        let op = ops.iter().find(|s| s.name == name)?;
-        op.value.clone()
+        match &self {
+            Some(ops) => {
+                let op = ops.iter().find(|s| s.name == name);
+                match op {
+                    Some(op) => op.value.clone(),
+                    None => None,
+                }
+            }
+            None => None,
+        }
     }
 }
 
@@ -130,8 +136,8 @@ impl Role {
     /// Serialize a list of role parameters into a Postgres-acceptable
     /// string of arguments.
     pub fn to_pg_options(&self) -> String {
-        // XXX: consider putting LOGIN as a default option somewhere higher, e.g. in control-plane.
-        // For now, we do not use generic `options` for roles. Once used, add
+        // XXX: consider putting LOGIN as a default option somewhere higher, e.g. in Rails.
+        // For now we do not use generic `options` for roles. Once used, add
         // `self.options.as_pg_options()` somewhere here.
         let mut params: String = "LOGIN".to_string();
 
@@ -155,14 +161,6 @@ impl Role {
 }
 
 impl Database {
-    pub fn new(name: PgIdent, owner: PgIdent) -> Self {
-        Self {
-            name,
-            owner,
-            options: None,
-        }
-    }
-
     /// Serialize a list of database parameters into a Postgres-acceptable
     /// string of arguments.
     /// NB: `TEMPLATE` is actually also an identifier, but so far we only need
@@ -221,7 +219,11 @@ pub fn get_existing_dbs(client: &mut Client) -> Result<Vec<Database>> {
             &[],
         )?
         .iter()
-        .map(|row| Database::new(row.get("datname"), row.get("owner")))
+        .map(|row| Database {
+            name: row.get("datname"),
+            owner: row.get("owner"),
+            options: None,
+        })
         .collect();
 
     Ok(postgres_dbs)
@@ -230,7 +232,6 @@ pub fn get_existing_dbs(client: &mut Client) -> Result<Vec<Database>> {
 /// Wait for Postgres to become ready to accept connections. It's ready to
 /// accept connections when the state-field in `pgdata/postmaster.pid` says
 /// 'ready'.
-#[instrument(skip(pg))]
 pub fn wait_for_postgres(pg: &mut Child, pgdata: &Path) -> Result<()> {
     let pid_path = pgdata.join("postmaster.pid");
 
@@ -289,18 +290,18 @@ pub fn wait_for_postgres(pg: &mut Child, pgdata: &Path) -> Result<()> {
         }
 
         let res = rx.recv_timeout(Duration::from_millis(100));
-        debug!("woken up by notify: {res:?}");
+        log::debug!("woken up by notify: {res:?}");
         // If there are multiple events in the channel already, we only need to be
         // check once. Swallow the extra events before we go ahead to check the
         // pid file.
         while let Ok(res) = rx.try_recv() {
-            debug!("swallowing extra event: {res:?}");
+            log::debug!("swallowing extra event: {res:?}");
         }
 
         // Check that we can open pid file first.
         if let Ok(file) = File::open(&pid_path) {
             if !postmaster_pid_seen {
-                debug!("postmaster.pid appeared");
+                log::debug!("postmaster.pid appeared");
                 watcher
                     .unwatch(pgdata)
                     .expect("Failed to remove pgdata dir watch");
@@ -316,7 +317,7 @@ pub fn wait_for_postgres(pg: &mut Child, pgdata: &Path) -> Result<()> {
             // Pid file could be there and we could read it, but it could be empty, for example.
             if let Some(Ok(line)) = last_line {
                 let status = line.trim();
-                debug!("last line of postmaster.pid: {status:?}");
+                log::debug!("last line of postmaster.pid: {status:?}");
 
                 // Now Postgres is ready to accept connections
                 if status == "ready" {
@@ -332,7 +333,7 @@ pub fn wait_for_postgres(pg: &mut Child, pgdata: &Path) -> Result<()> {
         }
     }
 
-    tracing::info!("PostgreSQL is now running, continuing to configure it");
+    log::info!("PostgreSQL is now running, continuing to configure it");
 
     Ok(())
 }

compute_tools/src/spec.rs

@@ -1,12 +1,11 @@
-use std::collections::HashMap;
 use std::path::Path;
 use std::str::FromStr;
 
 use anyhow::Result;
+use log::{info, log_enabled, warn, Level};
 use postgres::config::Config;
 use postgres::{Client, NoTls};
 use serde::Deserialize;
-use tracing::{info, info_span, instrument, span_enabled, warn, Level};
 
 use crate::compute::ComputeNode;
 use crate::config;
@@ -23,8 +22,6 @@ pub struct ComputeSpec {
     /// Expected cluster state at the end of transition process.
     pub cluster: Cluster,
     pub delta_operations: Option<Vec<DeltaOp>>,
-
-    pub startup_tracing_context: Option<HashMap<String, String>>,
 }
 
 /// Cluster state seen from the perspective of the external tools
@@ -82,25 +79,23 @@ pub fn update_pg_hba(pgdata_path: &Path) -> Result<()> {
 
 /// Given a cluster spec json and open transaction it handles roles creation,
 /// deletion and update.
-#[instrument(skip_all)]
 pub fn handle_roles(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
     let mut xact = client.transaction()?;
     let existing_roles: Vec<Role> = get_existing_roles(&mut xact)?;
 
     // Print a list of existing Postgres roles (only in debug mode)
-    if span_enabled!(Level::INFO) {
-        info!("postgres roles:");
-        for r in &existing_roles {
-            info!(
-                "    - {}:{}",
-                r.name,
-                if r.encrypted_password.is_some() {
-                    "[FILTERED]"
-                } else {
-                    "(null)"
-                }
-            );
-        }
+    info!("postgres roles:");
+    for r in &existing_roles {
+        info_println!(
+            "{} - {}:{}",
+            " ".repeat(27 + 5),
+            r.name,
+            if r.encrypted_password.is_some() {
+                "[FILTERED]"
+            } else {
+                "(null)"
+            }
+        );
     }
 
     // Process delta operations first
@@ -141,80 +136,58 @@ pub fn handle_roles(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
     info!("cluster spec roles:");
     for role in &spec.cluster.roles {
         let name = &role.name;
-        // XXX: with a limited number of roles it is fine, but consider making it a HashMap
-        let pg_role = existing_roles.iter().find(|r| r.name == *name);
 
-        enum RoleAction {
-            None,
-            Update,
-            Create,
-        }
-        let action = if let Some(r) = pg_role {
-            if (r.encrypted_password.is_none() && role.encrypted_password.is_some())
-                || (r.encrypted_password.is_some() && role.encrypted_password.is_none())
-            {
-                RoleAction::Update
-            } else if let Some(pg_pwd) = &r.encrypted_password {
-                // Check whether password changed or not (trim 'md5' prefix first if any)
-                //
-                // This is a backward compatibility hack, which comes from the times when we were using
-                // md5 for everyone and hashes were stored in the console db without md5 prefix. So when
-                // role comes from the control-plane (json spec) `Role.encrypted_password` doesn't have md5 prefix,
-                // but when role comes from Postgres (`get_existing_roles` / `existing_roles`) it has this prefix.
-                // Here is the only place so far where we compare hashes, so it seems to be the best candidate
-                // to place this compatibility layer.
-                let pg_pwd = if let Some(stripped) = pg_pwd.strip_prefix("md5") {
-                    stripped
-                } else {
-                    pg_pwd
-                };
-                if pg_pwd != *role.encrypted_password.as_ref().unwrap() {
-                    RoleAction::Update
-                } else {
-                    RoleAction::None
-                }
-            } else {
-                RoleAction::None
-            }
-        } else {
-            RoleAction::Create
-        };
-
-        match action {
-            RoleAction::None => {}
-            RoleAction::Update => {
-                let mut query: String = format!("ALTER ROLE {} ", name.pg_quote());
-                query.push_str(&role.to_pg_options());
-                xact.execute(query.as_str(), &[])?;
-            }
-            RoleAction::Create => {
-                let mut query: String = format!("CREATE ROLE {} ", name.pg_quote());
-                info!("role create query: '{}'", &query);
-                query.push_str(&role.to_pg_options());
-                xact.execute(query.as_str(), &[])?;
-
-                let grant_query = format!(
-                    "GRANT pg_read_all_data, pg_write_all_data TO {}",
-                    name.pg_quote()
-                );
-                xact.execute(grant_query.as_str(), &[])?;
-                info!("role grant query: '{}'", &grant_query);
-            }
-        }
-
-        if span_enabled!(Level::INFO) {
-            let pwd = if role.encrypted_password.is_some() {
+        info_print!(
+            "{} - {}:{}",
+            " ".repeat(27 + 5),
+            name,
+            if role.encrypted_password.is_some() {
                 "[FILTERED]"
             } else {
                 "(null)"
-            };
-            let action_str = match action {
-                RoleAction::None => "",
-                RoleAction::Create => " -> create",
-                RoleAction::Update => " -> update",
-            };
-            info!("   - {}:{}{}", name, pwd, action_str);
+            }
+        );
+
+        // XXX: with a limited number of roles it is fine, but consider making it a HashMap
+        let pg_role = existing_roles.iter().find(|r| r.name == *name);
+
+        if let Some(r) = pg_role {
+            let mut update_role = false;
+
+            if (r.encrypted_password.is_none() && role.encrypted_password.is_some())
+                || (r.encrypted_password.is_some() && role.encrypted_password.is_none())
+            {
+                update_role = true;
+            } else if let Some(pg_pwd) = &r.encrypted_password {
+                // Check whether password changed or not (trim 'md5:' prefix first)
+                update_role = pg_pwd[3..] != *role.encrypted_password.as_ref().unwrap();
+            }
+
+            if update_role {
+                let mut query: String = format!("ALTER ROLE {} ", name.pg_quote());
+                info_print!(" -> update");
+
+                query.push_str(&role.to_pg_options());
+                xact.execute(query.as_str(), &[])?;
+            }
+        } else {
+            info!("role name: '{}'", &name);
+            let mut query: String = format!("CREATE ROLE {} ", name.pg_quote());
+            info!("role create query: '{}'", &query);
+            info_print!(" -> create");
+
+            query.push_str(&role.to_pg_options());
+            xact.execute(query.as_str(), &[])?;
+
+            let grant_query = format!(
+                "GRANT pg_read_all_data, pg_write_all_data TO {}",
+                name.pg_quote()
+            );
+            xact.execute(grant_query.as_str(), &[])?;
+            info!("role grant query: '{}'", &grant_query);
         }
+
+        info_print!("\n");
     }
 
     xact.commit()?;
@@ -223,32 +196,23 @@ pub fn handle_roles(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
 }
 
 /// Reassign all dependent objects and delete requested roles.
-#[instrument(skip_all)]
 pub fn handle_role_deletions(node: &ComputeNode, client: &mut Client) -> Result<()> {
-    if let Some(ops) = &node.spec.delta_operations {
-        // First, reassign all dependent objects to db owners.
+    let spec = &node.spec;
+
+    // First, reassign all dependent objects to db owners.
+    if let Some(ops) = &spec.delta_operations {
         info!("reassigning dependent objects of to-be-deleted roles");
-
-        // Fetch existing roles. We could've exported and used `existing_roles` from
-        // `handle_roles()`, but we only make this list there before creating new roles.
-        // Which is probably fine as we never create to-be-deleted roles, but that'd
-        // just look a bit untidy. Anyway, the entire `pg_roles` should be in shared
-        // buffers already, so this shouldn't be a big deal.
-        let mut xact = client.transaction()?;
-        let existing_roles: Vec<Role> = get_existing_roles(&mut xact)?;
-        xact.commit()?;
-
         for op in ops {
-            // Check that role is still present in Postgres, as this could be a
-            // restart with the same spec after role deletion.
-            if op.action == "delete_role" && existing_roles.iter().any(|r| r.name == op.name) {
+            if op.action == "delete_role" {
                 reassign_owned_objects(node, &op.name)?;
             }
         }
+    }
 
-        // Second, proceed with role deletions.
+    // Second, proceed with role deletions.
+    let mut xact = client.transaction()?;
+    if let Some(ops) = &spec.delta_operations {
         info!("processing role deletions");
-        let mut xact = client.transaction()?;
         for op in ops {
             // We do not check either role exists or not,
             // Postgres will take care of it for us
@@ -259,7 +223,6 @@ pub fn handle_role_deletions(node: &ComputeNode, client: &mut Client) -> Result<
                 xact.execute(query.as_str(), &[])?;
             }
         }
-        xact.commit()?;
     }
 
     Ok(())
@@ -300,16 +263,13 @@ fn reassign_owned_objects(node: &ComputeNode, role_name: &PgIdent) -> Result<()>
 /// like `CREATE DATABASE` and `DROP DATABASE` do not support it. Statement-level
 /// atomicity should be enough here due to the order of operations and various checks,
 /// which together provide us idempotency.
-#[instrument(skip_all)]
 pub fn handle_databases(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
     let existing_dbs: Vec<Database> = get_existing_dbs(client)?;
 
     // Print a list of existing Postgres databases (only in debug mode)
-    if span_enabled!(Level::INFO) {
-        info!("postgres databases:");
-        for r in &existing_dbs {
-            info!("    {}:{}", r.name, r.owner);
-        }
+    info!("postgres databases:");
+    for r in &existing_dbs {
+        info_println!("{} - {}:{}", " ".repeat(27 + 5), r.name, r.owner);
     }
 
     // Process delta operations first
@@ -352,15 +312,12 @@ pub fn handle_databases(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
     for db in &spec.cluster.databases {
         let name = &db.name;
 
+        info_print!("{} - {}:{}", " ".repeat(27 + 5), db.name, db.owner);
+
         // XXX: with a limited number of databases it is fine, but consider making it a HashMap
         let pg_db = existing_dbs.iter().find(|r| r.name == *name);
 
-        enum DatabaseAction {
-            None,
-            Update,
-            Create,
-        }
-        let action = if let Some(r) = pg_db {
+        if let Some(r) = pg_db {
             // XXX: db owner name is returned as quoted string from Postgres,
             // when quoting is needed.
             let new_owner = if r.owner.starts_with('"') {
@@ -370,42 +327,24 @@ pub fn handle_databases(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
             };
 
             if new_owner != r.owner {
-                // Update the owner
-                DatabaseAction::Update
-            } else {
-                DatabaseAction::None
-            }
-        } else {
-            DatabaseAction::Create
-        };
-
-        match action {
-            DatabaseAction::None => {}
-            DatabaseAction::Update => {
                 let query: String = format!(
                     "ALTER DATABASE {} OWNER TO {}",
                     name.pg_quote(),
                     db.owner.pg_quote()
                 );
-                let _guard = info_span!("executing", query).entered();
-                client.execute(query.as_str(), &[])?;
-            }
-            DatabaseAction::Create => {
-                let mut query: String = format!("CREATE DATABASE {} ", name.pg_quote());
-                query.push_str(&db.to_pg_options());
-                let _guard = info_span!("executing", query).entered();
-                client.execute(query.as_str(), &[])?;
-            }
-        };
+                info_print!(" -> update");
 
-        if span_enabled!(Level::INFO) {
-            let action_str = match action {
-                DatabaseAction::None => "",
-                DatabaseAction::Create => " -> create",
-                DatabaseAction::Update => " -> update",
-            };
-            info!("   - {}:{}{}", db.name, db.owner, action_str);
+                client.execute(query.as_str(), &[])?;
+            }
+        } else {
+            let mut query: String = format!("CREATE DATABASE {} ", name.pg_quote());
+            info_print!(" -> create");
+
+            query.push_str(&db.to_pg_options());
+            client.execute(query.as_str(), &[])?;
         }
+
+        info_print!("\n");
     }
 
     Ok(())
@@ -413,7 +352,6 @@ pub fn handle_databases(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
 
 /// Grant CREATE ON DATABASE to the database owner and do some other alters and grants
 /// to allow users creating trusted extensions and re-creating `public` schema, for example.
-#[instrument(skip_all)]
 pub fn handle_grants(node: &ComputeNode, client: &mut Client) -> Result<()> {
     let spec = &node.spec;
 

compute_tools/tests/pg_helpers_tests.rs

@@ -38,33 +38,4 @@ mod pg_helpers_tests {
 
         assert_eq!(ident.pg_quote(), "\"\"\"name\"\";\\n select 1;\"");
     }
-
-    #[test]
-    fn generic_options_search() {
-        let generic_options: GenericOptions = Some(vec![
-            GenericOption {
-                name: "present_value".into(),
-                value: Some("value".into()),
-                vartype: "string".into(),
-            },
-            GenericOption {
-                name: "missed_value".into(),
-                value: None,
-                vartype: "int".into(),
-            },
-        ]);
-        assert_eq!(generic_options.find("present_value"), Some("value".into()));
-        assert_eq!(generic_options.find("missed_value"), None);
-        assert_eq!(generic_options.find("invalid_value"), None);
-
-        let empty_generic_options: GenericOptions = Some(vec![]);
-        assert_eq!(empty_generic_options.find("present_value"), None);
-        assert_eq!(empty_generic_options.find("missed_value"), None);
-        assert_eq!(empty_generic_options.find("invalid_value"), None);
-
-        let none_generic_options: GenericOptions = None;
-        assert_eq!(none_generic_options.find("present_value"), None);
-        assert_eq!(none_generic_options.find("missed_value"), None);
-        assert_eq!(none_generic_options.find("invalid_value"), None);
-    }
 }

control_plane/Cargo.toml

@@ -1,31 +1,31 @@
 [package]
 name = "control_plane"
 version = "0.1.0"
-edition.workspace = true
-license.workspace = true
+edition = "2021"
 
 [dependencies]
-anyhow.workspace = true
-clap.workspace = true
-comfy-table.workspace = true
-git-version.workspace = true
-nix.workspace = true
-once_cell.workspace = true
-postgres.workspace = true
-regex.workspace = true
-reqwest = { workspace = true, features = ["blocking", "json"] }
-serde.workspace = true
-serde_with.workspace = true
-tar.workspace = true
-thiserror.workspace = true
-toml.workspace = true
-url.workspace = true
+anyhow = "1.0"
+clap = "4.0"
+comfy-table = "6.1"
+git-version = "0.3.5"
+nix = "0.25"
+once_cell = "1.13.0"
+postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev = "43e6db254a97fdecbce33d8bc0890accfd74495e" }
+regex = "1"
+reqwest = { version = "0.11", default-features = false, features = ["blocking", "json", "rustls-tls"] }
+serde = { version = "1.0", features = ["derive"] }
+serde_with = "2.0"
+tar = "0.4.38"
+thiserror = "1"
+toml = "0.5"
+url = "2.2.2"
+
 # Note: Do not directly depend on pageserver or safekeeper; use pageserver_api or safekeeper_api
 # instead, so that recompile times are better.
-pageserver_api.workspace = true
-safekeeper_api.workspace = true
-postgres_connection.workspace = true
-storage_broker.workspace = true
-utils.workspace = true
-
-workspace_hack.workspace = true
+pageserver_api = { path = "../libs/pageserver_api" }
+postgres_connection = { path = "../libs/postgres_connection" }
+safekeeper_api = { path = "../libs/safekeeper_api" }
+# Note: main broker code is inside the binary crate, so linking with the library shouldn't be heavy.
+storage_broker = { version = "0.1", path = "../storage_broker" }
+utils = { path = "../libs/utils" }
+workspace_hack = { version = "0.1", path = "../workspace_hack" }

control_plane/src/background_process.rs

@@ -136,6 +136,22 @@ where
     anyhow::bail!("{process_name} did not start in {RETRY_UNTIL_SECS} seconds");
 }
 
+/// Send SIGTERM to child process
+pub fn send_stop_child_process(child: &std::process::Child) -> anyhow::Result<()> {
+    let pid = child.id();
+    match kill(
+        nix::unistd::Pid::from_raw(pid.try_into().unwrap()),
+        Signal::SIGTERM,
+    ) {
+        Ok(()) => Ok(()),
+        Err(Errno::ESRCH) => {
+            println!("child process with pid {pid} does not exist");
+            Ok(())
+        }
+        Err(e) => anyhow::bail!("Failed to send signal to child process with pid {pid}: {e}"),
+    }
+}
+
 /// Stops the process, using the pid file given. Returns Ok also if the process is already not running.
 pub fn stop_process(immediate: bool, process_name: &str, pid_file: &Path) -> anyhow::Result<()> {
     let pid = match pid_file::read(pid_file)

control_plane/src/bin/neon_local.rs

@@ -263,7 +263,7 @@ fn get_tenant_id(sub_match: &ArgMatches, env: &local_env::LocalEnv) -> anyhow::R
     } else if let Some(default_id) = env.default_tenant_id {
         Ok(default_id)
     } else {
-        anyhow::bail!("No tenant id. Use --tenant-id, or set a default tenant");
+        bail!("No tenant id. Use --tenant-id, or set 'default_tenant_id' in the config file");
     }
 }
 
@@ -284,6 +284,8 @@ fn parse_timeline_id(sub_match: &ArgMatches) -> anyhow::Result<Option<TimelineId
 }
 
 fn handle_init(init_match: &ArgMatches) -> anyhow::Result<LocalEnv> {
+    let initial_timeline_id_arg = parse_timeline_id(init_match)?;
+
     // Create config file
     let toml_file: String = if let Some(config_path) = init_match.get_one::<PathBuf>("config") {
         // load and parse the file
@@ -307,16 +309,30 @@ fn handle_init(init_match: &ArgMatches) -> anyhow::Result<LocalEnv> {
         LocalEnv::parse_config(&toml_file).context("Failed to create neon configuration")?;
     env.init(pg_version)
         .context("Failed to initialize neon repository")?;
+    let initial_tenant_id = env
+        .default_tenant_id
+        .expect("default_tenant_id should be generated by the `env.init()` call above");
 
     // Initialize pageserver, create initial tenant and timeline.
     let pageserver = PageServerNode::from_env(&env);
-    pageserver
-        .initialize(&pageserver_config_overrides(init_match))
+    let initial_timeline_id = pageserver
+        .initialize(
+            Some(initial_tenant_id),
+            initial_timeline_id_arg,
+            &pageserver_config_overrides(init_match),
+            pg_version,
+        )
         .unwrap_or_else(|e| {
             eprintln!("pageserver init failed: {e:?}");
             exit(1);
         });
 
+    env.register_branch_mapping(
+        DEFAULT_BRANCH_NAME.to_owned(),
+        initial_tenant_id,
+        initial_timeline_id,
+    )?;
+
     Ok(env)
 }
 
@@ -372,17 +388,6 @@ fn handle_tenant(tenant_match: &ArgMatches, env: &mut local_env::LocalEnv) -> an
             println!(
                 "Created an initial timeline '{new_timeline_id}' at Lsn {last_record_lsn} for tenant: {new_tenant_id}",
             );
-
-            if create_match.get_flag("set-default") {
-                println!("Setting tenant {new_tenant_id} as a default one");
-                env.default_tenant_id = Some(new_tenant_id);
-            }
-        }
-        Some(("set-default", set_default_match)) => {
-            let tenant_id =
-                parse_tenant_id(set_default_match)?.context("No tenant id specified")?;
-            println!("Setting tenant {tenant_id} as a default one");
-            env.default_tenant_id = Some(tenant_id);
         }
         Some(("config", create_match)) => {
             let tenant_id = get_tenant_id(create_match, env)?;
@@ -544,7 +549,7 @@ fn handle_pg(pg_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<()> {
 
             table.load_preset(comfy_table::presets::NOTHING);
 
-            table.set_header([
+            table.set_header(&[
                 "NODE",
                 "ADDRESS",
                 "TIMELINE",
@@ -579,7 +584,7 @@ fn handle_pg(pg_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<()> {
                     .map(|name| name.as_str())
                     .unwrap_or("?");
 
-                table.add_row([
+                table.add_row(&[
                     node_name.as_str(),
                     &node.address.to_string(),
                     &node.timeline_id.to_string(),
@@ -742,7 +747,7 @@ fn get_safekeeper(env: &local_env::LocalEnv, id: NodeId) -> Result<SafekeeperNod
     if let Some(node) = env.safekeepers.iter().find(|node| node.id == id) {
         Ok(SafekeeperNode::from_env(env, node))
     } else {
-        bail!("could not find safekeeper {id}")
+        bail!("could not find safekeeper '{}'", id)
     }
 }
 
@@ -801,22 +806,22 @@ fn handle_safekeeper(sub_match: &ArgMatches, env: &local_env::LocalEnv) -> Resul
 }
 
 fn handle_start_all(sub_match: &ArgMatches, env: &local_env::LocalEnv) -> anyhow::Result<()> {
+    broker::start_broker_process(env)?;
+    let pageserver = PageServerNode::from_env(env);
+
     // Postgres nodes are not started automatically
 
-    broker::start_broker_process(env)?;
-
-    let pageserver = PageServerNode::from_env(env);
     if let Err(e) = pageserver.start(&pageserver_config_overrides(sub_match)) {
-        eprintln!("pageserver {} start failed: {:#}", env.pageserver.id, e);
-        try_stop_all(env, true);
+        eprintln!("pageserver start failed: {e}");
+        try_stop_storage_broker_process(env);
         exit(1);
     }
 
     for node in env.safekeepers.iter() {
         let safekeeper = SafekeeperNode::from_env(env, node);
         if let Err(e) = safekeeper.start() {
-            eprintln!("safekeeper {} start failed: {:#}", safekeeper.id, e);
-            try_stop_all(env, false);
+            eprintln!("safekeeper '{}' start failed: {e}", safekeeper.id);
+            try_stop_storage_broker_process(env);
             exit(1);
         }
     }
@@ -827,41 +832,35 @@ fn handle_stop_all(sub_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<
     let immediate =
         sub_match.get_one::<String>("stop-mode").map(|s| s.as_str()) == Some("immediate");
 
-    try_stop_all(env, immediate);
-
-    Ok(())
-}
-
-fn try_stop_all(env: &local_env::LocalEnv, immediate: bool) {
     let pageserver = PageServerNode::from_env(env);
 
     // Stop all compute nodes
-    match ComputeControlPlane::load(env.clone()) {
-        Ok(cplane) => {
-            for (_k, node) in cplane.nodes {
-                if let Err(e) = node.stop(false) {
-                    eprintln!("postgres stop failed: {e:#}");
-                }
-            }
-        }
-        Err(e) => {
-            eprintln!("postgres stop failed, could not restore control plane data from env: {e:#}")
+    let cplane = ComputeControlPlane::load(env.clone())?;
+    for (_k, node) in cplane.nodes {
+        if let Err(e) = node.stop(false) {
+            eprintln!("postgres stop failed: {}", e);
         }
     }
 
     if let Err(e) = pageserver.stop(immediate) {
-        eprintln!("pageserver {} stop failed: {:#}", env.pageserver.id, e);
+        eprintln!("pageserver stop failed: {}", e);
     }
 
     for node in env.safekeepers.iter() {
         let safekeeper = SafekeeperNode::from_env(env, node);
         if let Err(e) = safekeeper.stop(immediate) {
-            eprintln!("safekeeper {} stop failed: {:#}", safekeeper.id, e);
+            eprintln!("safekeeper '{}' stop failed: {}", safekeeper.id, e);
         }
     }
 
+    try_stop_storage_broker_process(env);
+
+    Ok(())
+}
+
+fn try_stop_storage_broker_process(env: &local_env::LocalEnv) {
     if let Err(e) = broker::stop_broker_process(env) {
-        eprintln!("neon broker stop failed: {e:#}");
+        eprintln!("neon broker stop failed: {e}");
     }
 }
 
@@ -901,7 +900,6 @@ fn cli() -> Command {
     let stop_mode_arg = Arg::new("stop-mode")
         .short('m')
         .value_parser(["fast", "immediate"])
-        .default_value("fast")
         .help("If 'immediate', don't flush repository data at shutdown")
         .required(false)
         .value_name("stop-mode");
@@ -923,8 +921,9 @@ fn cli() -> Command {
         .version(GIT_VERSION)
         .subcommand(
             Command::new("init")
-                .about("Initialize a new Neon repository, preparing configs for services to start with")
+                .about("Initialize a new Neon repository")
                 .arg(pageserver_config_args.clone())
+                .arg(timeline_id_arg.clone().help("Use a specific timeline id when creating a tenant and its initial timeline"))
                 .arg(
                     Arg::new("config")
                         .long("config")
@@ -986,14 +985,11 @@ fn cli() -> Command {
                 .arg(timeline_id_arg.clone().help("Use a specific timeline id when creating a tenant and its initial timeline"))
                 .arg(Arg::new("config").short('c').num_args(1).action(ArgAction::Append).required(false))
                 .arg(pg_version_arg.clone())
-                .arg(Arg::new("set-default").long("set-default").action(ArgAction::SetTrue).required(false)
-                    .help("Use this tenant in future CLI commands where tenant_id is needed, but not specified"))
                 )
-            .subcommand(Command::new("set-default").arg(tenant_id_arg.clone().required(true))
-                .about("Set a particular tenant as default in future CLI commands where tenant_id is needed, but not specified"))
             .subcommand(Command::new("config")
                 .arg(tenant_id_arg.clone())
-                .arg(Arg::new("config").short('c').num_args(1).action(ArgAction::Append).required(false)))
+                .arg(Arg::new("config").short('c').num_args(1).action(ArgAction::Append).required(false))
+                )
         )
         .subcommand(
             Command::new("pageserver")

control_plane/src/broker.rs

@@ -17,7 +17,7 @@ pub fn start_broker_process(env: &local_env::LocalEnv) -> anyhow::Result<()> {
         "storage_broker",
         &env.base_data_dir,
         &env.storage_broker_bin(),
-        args,
+        &args,
         [],
         background_process::InitialPidFile::Create(&storage_broker_pid_file_path(env)),
         || {

control_plane/src/compute.rs

@@ -44,7 +44,7 @@ impl ComputeControlPlane {
         let mut nodes = BTreeMap::default();
         let pgdatadirspath = &env.pg_data_dirs_path();
 
-        for tenant_dir in fs::read_dir(pgdatadirspath)
+        for tenant_dir in fs::read_dir(&pgdatadirspath)
             .with_context(|| format!("failed to list {}", pgdatadirspath.display()))?
         {
             let tenant_dir = tenant_dir?;
@@ -67,8 +67,8 @@ impl ComputeControlPlane {
     fn get_port(&mut self) -> u16 {
         1 + self
             .nodes
-            .values()
-            .map(|node| node.address.port())
+            .iter()
+            .map(|(_name, node)| node.address.port())
             .max()
             .unwrap_or(self.base_port)
     }
@@ -183,7 +183,7 @@ impl PostgresNode {
 
     fn sync_safekeepers(&self, auth_token: &Option<String>, pg_version: u32) -> Result<Lsn> {
         let pg_path = self.env.pg_bin_dir(pg_version)?.join("postgres");
-        let mut cmd = Command::new(pg_path);
+        let mut cmd = Command::new(&pg_path);
 
         cmd.arg("--sync-safekeepers")
             .env_clear()
@@ -201,7 +201,7 @@ impl PostgresNode {
             .stderr(Stdio::piped());
 
         if let Some(token) = auth_token {
-            cmd.env("NEON_AUTH_TOKEN", token);
+            cmd.env("ZENITH_AUTH_TOKEN", token);
         }
 
         let sync_handle = cmd
@@ -261,7 +261,7 @@ impl PostgresNode {
     }
 
     fn create_pgdata(&self) -> Result<()> {
-        fs::create_dir_all(self.pgdata()).with_context(|| {
+        fs::create_dir_all(&self.pgdata()).with_context(|| {
             format!(
                 "could not create data directory {}",
                 self.pgdata().display()
@@ -304,17 +304,17 @@ impl PostgresNode {
 
             // Set up authentication
             //
-            // $NEON_AUTH_TOKEN will be replaced with value from environment
+            // $ZENITH_AUTH_TOKEN will be replaced with value from environment
             // variable during compute pg startup. It is done this way because
             // otherwise user will be able to retrieve the value using SHOW
             // command or pg_settings
             let password = if let AuthType::NeonJWT = auth_type {
-                "$NEON_AUTH_TOKEN"
+                "$ZENITH_AUTH_TOKEN"
             } else {
                 ""
             };
             // NOTE avoiding spaces in connection string, because it is less error prone if we forward it somewhere.
-            // Also note that not all parameters are supported here. Because in compute we substitute $NEON_AUTH_TOKEN
+            // Also note that not all parameters are supported here. Because in compute we substitute $ZENITH_AUTH_TOKEN
             // We parse this string and build it back with token from env var, and for simplicity rebuild
             // uses only needed variables namely host, port, user, password.
             format!("postgresql://no_user:{password}@{host}:{port}")
@@ -323,7 +323,7 @@ impl PostgresNode {
         conf.append_line("");
         conf.append("neon.pageserver_connstring", &pageserver_connstr);
         if let AuthType::NeonJWT = auth_type {
-            conf.append("neon.safekeeper_token_env", "$NEON_AUTH_TOKEN");
+            conf.append("neon.safekeeper_token_env", "$ZENITH_AUTH_TOKEN");
         }
         conf.append("neon.tenant_id", &self.tenant_id.to_string());
         conf.append("neon.timeline_id", &self.timeline_id.to_string());
@@ -448,7 +448,7 @@ impl PostgresNode {
             self.env.pg_lib_dir(self.pg_version)?.to_str().unwrap(),
         );
         if let Some(token) = auth_token {
-            cmd.env("NEON_AUTH_TOKEN", token);
+            cmd.env("ZENITH_AUTH_TOKEN", token);
         }
 
         let pg_ctl = cmd.output().context("pg_ctl failed")?;
@@ -478,7 +478,7 @@ impl PostgresNode {
                 postgresql_conf_path.to_str().unwrap()
             )
         })?;
-        fs::remove_dir_all(self.pgdata())?;
+        fs::remove_dir_all(&self.pgdata())?;
         self.create_pgdata()?;
 
         // 2. Bring back config files
@@ -514,7 +514,7 @@ impl PostgresNode {
                 "Destroying postgres data directory '{}'",
                 self.pgdata().to_str().unwrap()
             );
-            fs::remove_dir_all(self.pgdata())?;
+            fs::remove_dir_all(&self.pgdata())?;
         } else {
             self.pg_ctl(&["stop"], &None)?;
         }

control_plane/src/local_env.rs

@@ -296,6 +296,11 @@ impl LocalEnv {
             env.neon_distrib_dir = env::current_exe()?.parent().unwrap().to_owned();
         }
 
+        // If no initial tenant ID was given, generate it.
+        if env.default_tenant_id.is_none() {
+            env.default_tenant_id = Some(TenantId::generate());
+        }
+
         env.base_data_dir = base_path();
 
         Ok(env)
@@ -399,7 +404,7 @@ impl LocalEnv {
             }
         }
 
-        fs::create_dir(base_path)?;
+        fs::create_dir(&base_path)?;
 
         // generate keys for jwt
         // openssl genrsa -out private_key.pem 2048
@@ -408,7 +413,7 @@ impl LocalEnv {
             private_key_path = base_path.join("auth_private_key.pem");
             let keygen_output = Command::new("openssl")
                 .arg("genrsa")
-                .args(["-out", private_key_path.to_str().unwrap()])
+                .args(&["-out", private_key_path.to_str().unwrap()])
                 .arg("2048")
                 .stdout(Stdio::null())
                 .output()
@@ -425,10 +430,10 @@ impl LocalEnv {
             // openssl rsa -in private_key.pem -pubout -outform PEM -out public_key.pem
             let keygen_output = Command::new("openssl")
                 .arg("rsa")
-                .args(["-in", private_key_path.to_str().unwrap()])
+                .args(&["-in", private_key_path.to_str().unwrap()])
                 .arg("-pubout")
-                .args(["-outform", "PEM"])
-                .args(["-out", public_key_path.to_str().unwrap()])
+                .args(&["-outform", "PEM"])
+                .args(&["-out", public_key_path.to_str().unwrap()])
                 .stdout(Stdio::null())
                 .output()
                 .context("failed to generate auth private key")?;

control_plane/src/pageserver.rs

@@ -7,7 +7,7 @@ use std::path::PathBuf;
 use std::process::{Child, Command};
 use std::{io, result};
 
-use anyhow::{bail, Context};
+use anyhow::{bail, ensure, Context};
 use pageserver_api::models::{
     TenantConfigRequest, TenantCreateRequest, TenantInfo, TimelineCreateRequest, TimelineInfo,
 };
@@ -130,15 +130,83 @@ impl PageServerNode {
         overrides
     }
 
-    /// Initializes a pageserver node by creating its config with the overrides provided.
-    pub fn initialize(&self, config_overrides: &[&str]) -> anyhow::Result<()> {
+    /// Initializes a pageserver node by creating its config with the overrides provided,
+    /// and creating an initial tenant and timeline afterwards.
+    pub fn initialize(
+        &self,
+        create_tenant: Option<TenantId>,
+        initial_timeline_id: Option<TimelineId>,
+        config_overrides: &[&str],
+        pg_version: u32,
+    ) -> anyhow::Result<TimelineId> {
         // First, run `pageserver --init` and wait for it to write a config into FS and exit.
         self.pageserver_init(config_overrides).with_context(|| {
             format!(
                 "Failed to run init for pageserver node {}",
                 self.env.pageserver.id,
             )
-        })
+        })?;
+
+        // Then, briefly start it fully to run HTTP commands on it,
+        // to create initial tenant and timeline.
+        // We disable the remote storage, since we stop pageserver right after the timeline creation,
+        // hence most of the uploads will either aborted or not started: no point to start them at all.
+        let disabled_remote_storage_override = "remote_storage={}";
+        let mut pageserver_process = self
+            .start_node(
+                &[disabled_remote_storage_override],
+                // Previous overrides will be taken from the config created before, don't overwrite them.
+                false,
+            )
+            .with_context(|| {
+                format!(
+                    "Failed to start a process for pageserver node {}",
+                    self.env.pageserver.id,
+                )
+            })?;
+
+        let init_result = self
+            .try_init_timeline(create_tenant, initial_timeline_id, pg_version)
+            .context("Failed to create initial tenant and timeline for pageserver");
+        match &init_result {
+            Ok(initial_timeline_id) => {
+                println!("Successfully initialized timeline {initial_timeline_id}")
+            }
+            Err(e) => eprintln!("{e:#}"),
+        }
+        background_process::send_stop_child_process(&pageserver_process)?;
+
+        let exit_code = pageserver_process.wait()?;
+        ensure!(
+            exit_code.success(),
+            format!(
+                "pageserver init failed with exit code {:?}",
+                exit_code.code()
+            )
+        );
+        println!(
+            "Stopped pageserver {} process with pid {}",
+            self.env.pageserver.id,
+            pageserver_process.id(),
+        );
+        init_result
+    }
+
+    fn try_init_timeline(
+        &self,
+        new_tenant_id: Option<TenantId>,
+        new_timeline_id: Option<TimelineId>,
+        pg_version: u32,
+    ) -> anyhow::Result<TimelineId> {
+        let initial_tenant_id = self.tenant_create(new_tenant_id, HashMap::new())?;
+        let initial_timeline_info = self.timeline_create(
+            initial_tenant_id,
+            new_timeline_id,
+            None,
+            None,
+            Some(pg_version),
+        )?;
+        Ok(initial_timeline_info.timeline_id)
     }
 
     pub fn repo_path(&self) -> PathBuf {
@@ -173,7 +241,7 @@ impl PageServerNode {
         let mut args = self.pageserver_basic_args(config_overrides, datadir_path_str);
         args.push(Cow::Borrowed("--init"));
 
-        let init_output = Command::new(self.env.pageserver_bin())
+        let init_output = Command::new(&self.env.pageserver_bin())
             .args(args.iter().map(Cow::as_ref))
             .envs(self.pageserver_env_variables()?)
             .output()
@@ -252,7 +320,7 @@ impl PageServerNode {
             let token = self
                 .env
                 .generate_auth_token(&Claims::new(None, Scope::SafekeeperData))?;
-            vec![("NEON_AUTH_TOKEN".to_owned(), token)]
+            vec![("ZENITH_AUTH_TOKEN".to_owned(), token)]
         } else {
             Vec::new()
         })

deny.toml

@@ -1,90 +0,0 @@
-# This file was auto-generated using `cargo deny init`.
-# cargo-deny is a cargo plugin that lets you lint your project's
-# dependency graph to ensure all your dependencies conform
-# to your expectations and requirements.
-
-# Root options
-targets = []
-all-features = false
-no-default-features = false
-feature-depth = 1
-
-# This section is considered when running `cargo deny check advisories`
-# More documentation for the advisories section can be found here:
-# https://embarkstudios.github.io/cargo-deny/checks/advisories/cfg.html
-[advisories]
-db-urls = ["https://github.com/rustsec/advisory-db"]
-vulnerability = "deny"
-unmaintained = "warn"
-yanked = "warn"
-notice = "warn"
-ignore = []
-
-# This section is considered when running `cargo deny check licenses`
-# More documentation for the licenses section can be found here:
-# https://embarkstudios.github.io/cargo-deny/checks/licenses/cfg.html
-[licenses]
-unlicensed = "deny"
-allow = [
-    "Apache-2.0",
-    "Artistic-2.0",
-    "BSD-2-Clause",
-    "BSD-3-Clause",
-    "ISC",
-    "MIT",
-    "MPL-2.0",
-    "OpenSSL",
-    "Unicode-DFS-2016",
-]
-deny = []
-copyleft = "warn"
-allow-osi-fsf-free = "neither"
-default = "deny"
-confidence-threshold = 0.8
-exceptions = [
-    # Zlib license has some restrictions if we decide to change sth
-    { allow = ["Zlib"], name = "const_format_proc_macros", version = "*" },
-    { allow = ["Zlib"], name = "const_format", version = "*" },
-]
-
-[[licenses.clarify]]
-name = "ring"
-version = "*"
-expression = "MIT AND ISC AND OpenSSL"
-license-files = [
-    { path = "LICENSE", hash = 0xbd0eed23 }
-]
-
-[licenses.private]
-ignore = true
-registries = []
-
-# This section is considered when running `cargo deny check bans`.
-# More documentation about the 'bans' section can be found here:
-# https://embarkstudios.github.io/cargo-deny/checks/bans/cfg.html
-[bans]
-multiple-versions = "warn"
-wildcards = "allow"
-highlight = "all"
-workspace-default-features = "allow"
-external-default-features = "allow"
-allow = []
-deny = []
-skip = []
-skip-tree = []
-
-# This section is considered when running `cargo deny check sources`.
-# More documentation about the 'sources' section can be found here:
-# https://embarkstudios.github.io/cargo-deny/checks/sources/cfg.html
-[sources]
-unknown-registry = "warn"
-unknown-git = "warn"
-allow-registry = ["https://github.com/rust-lang/crates.io-index"]
-allow-git = []
-
-[sources.allow-org]
-github = [
-    "neondatabase",
-]
-gitlab = []
-bitbucket = []

docs/authentication.md

@@ -65,7 +65,7 @@ There is no administrative API except those provided by PostgreSQL.
 
 #### Outgoing connections
 Compute connects to Pageserver for getting pages.
-The connection string is configured by the `neon.pageserver_connstring` PostgreSQL GUC, e.g. `postgresql://no_user:$NEON_AUTH_TOKEN@localhost:15028`.
+The connection string is configured by the `neon.pageserver_connstring` PostgreSQL GUC, e.g. `postgresql://no_user:$ZENITH_AUTH_TOKEN@localhost:15028`.
 The environment variable inside the connection string is substituted with
 the JWT token.
 
@@ -77,7 +77,7 @@ If the GUC is unset, no token is passed.
 
 Note that both tokens can be (and typically are) the same;
 the scope is the tenant and the token is usually passed through the
-`$NEON_AUTH_TOKEN` environment variable.
+`$ZENITH_AUTH_TOKEN` environment variable.
 
 ### Pageserver
 #### Overview
@@ -114,7 +114,7 @@ either of three values:
 Pageserver makes a connection to a Safekeeper for each active timeline.
 As Pageserver may want to access any timeline it has on the disk,
 it is given a blanket JWT token to access any data on any Safekeeper.
-This token is passed through an environment variable called `NEON_AUTH_TOKEN`
+This token is passed through an environment variable called `ZENITH_AUTH_TOKEN`
 (non-configurable as of writing this text).
 
 A better way _may be_ to store JWT token for each timeline next to it,

docs/consumption_metrics.md

@@ -1,115 +0,0 @@
-### Overview
-Pageserver and proxy periodically collect consumption metrics and push them to a HTTP endpoint.
-
-This doc describes current implementation details.
-For design details see [the RFC](./rfcs/021-metering.md) and [the discussion on Github](https://github.com/neondatabase/neon/pull/2884).
-
-- The metrics are collected in a separate thread, and the collection interval and endpoint are configurable.
-
-- Metrics are cached, so that we don't send unchanged metrics on every iteration.
-
-- Metrics are sent in batches of 1000 (see CHUNK_SIZE const) metrics max with no particular grouping guarantees.
-
-batch format is
-```json
-
-{ "events" : [metric1, metric2, ...]]}
-
-```
-See metric format examples below.
-
-- All metrics values are in bytes, unless otherwise specified.
-
-- Currently no retries are implemented.
-
-### Pageserver metrics
-
-#### Configuration
-The endpoint and the collection interval are specified in the pageserver config file (or can be passed as command line arguments):
-`metric_collection_endpoint` defaults to None, which means that metric collection is disabled by default.
-`metric_collection_interval` defaults to 10min
-
-#### Metrics
-
-Currently, the following metrics are collected:
-
-- `written_size`
-
-Amount of WAL produced , by a timeline, i.e. last_record_lsn
-This is an absolute, per-timeline metric.
-
-- `resident_size`
-
-Size of all the layer files in the tenant's directory on disk on the pageserver.
-This is an absolute, per-tenant metric.
-
-- `remote_storage_size`
-
-Size of the remote storage (S3) directory.
-This is an absolute, per-tenant metric.
-
-- `timeline_logical_size`
-Logical size of the data in the timeline
-This is an absolute, per-timeline metric.
-
-- `synthetic_storage_size`
-Size of all tenant's branches including WAL
-This is the same metric that `tenant/{tenant_id}/size` endpoint returns.
-This is an absolute, per-tenant metric.
-
-Synthetic storage size is calculated in a separate thread, so it might be slightly outdated.
-
-#### Format example
-
-```json
-{
-"metric": "remote_storage_size",
-"type": "absolute",
-"time": "2022-12-28T11:07:19.317310284Z",
-"idempotency_key": "2022-12-28 11:07:19.317310324 UTC-1-4019",
-"value": 12345454,
-"tenant_id": "5d07d9ce9237c4cd845ea7918c0afa7d",
-"timeline_id": "a03ebb4f5922a1c56ff7485cc8854143",
-}
-```
-
-`idempotency_key` is a unique key for each metric, so that we can deduplicate metrics.
-It is a combination of the time, node_id and a random number.
-
-### Proxy consumption metrics
-
-#### Configuration
-The endpoint and the collection interval can be passed as command line arguments for proxy:
-`metric_collection_endpoint` no default, which means that metric collection is disabled by default.
-`metric_collection_interval` no default
-
-#### Metrics
-
-Currently, only one proxy metric is collected:
-
-- `proxy_io_bytes_per_client`
-Outbound traffic per client.
-This is an incremental, per-endpoint metric.
-
-#### Format example
-
-```json
-{
-"metric": "proxy_io_bytes_per_client",
-"type": "incremental",
-"start_time": "2022-12-28T11:07:19.317310284Z",
-"stop_time": "2022-12-28T11:07:19.317310284Z",
-"idempotency_key": "2022-12-28 11:07:19.317310324 UTC-1-4019",
-"value": 12345454,
-"endpoint_id": "5d07d9ce9237c4cd845ea7918c0afa7d",
-}
-```
-
-The metric is incremental, so the value is the difference between the current and the previous value.
-If there is no previous value, the value, the value is the current value and the `start_time` equals `stop_time`.
-
-### TODO
-
-- [ ] Handle errors better: currently if one tenant fails to gather metrics, the whole iteration fails and metrics are not sent for any tenant.
-- [ ] Add retries
-- [ ] Tune the interval

docs/rfcs/021-metering.md

@@ -1,186 +0,0 @@
-# Consumption tracking
-
-
-# Goals
-
-This proposal is made with two mostly but not entirely overlapping goals:
-
-* Collect info that is needed for consumption-based billing
-* Cross-check AWS bills
-
-
-# Metrics
-
-There are six metrics to collect:
-
-* CPU time. Wall clock seconds * the current number of cores. We have a fixed ratio of memory to cores, so the current memory size is the function of the number of cores. Measured per each `endpoint`.
-
-* Traffic. In/out traffic on the proxy. Measured per each `endpoint`.
-
-* Written size. Amount of data we write. That is different from both traffic and storage size, as only during the writing we
-
-  a) occupy some disk bandwidth on safekeepers
-
-  b) necessarily cross AZ boundaries delivering WAL to all safekeepers
-
-  Each timeline/branch has at most one writer, so the data is collected per branch.
-
-* Synthetic storage size. That is what is exposed now with pageserver's `/v1/tenant/{}/size`. Looks like now it is per-tenant. (Side note: can we make it per branch to show as branch physical size in UI?)
-
-* Real storage size. That is the size of the tenant directory on the pageservers disk. Per-tenant.
-
-* S3 storage size. That is the size of the tenant data on S3. Per-tenant.
-
-That info should be enough to build an internal model that predicts AWS price (hence tracking `written data` and `real storage size`). As for the billing model we probably can get away with mentioning only `CPU time`, `synthetic storage size`, and `traffic` consumption.
-
-# Services participating in metrics collection
-
-## Proxy
-
-For actual implementation details check `/docs/consumption_metrics.md`
-
-Proxy is the only place that knows about traffic flow, so it tracks it and reports it with quite a small interval, let's say 1 minute. A small interval is needed here since the proxy is stateless, and any restart will reset accumulated consumption. Also proxy should report deltas since the last report, not an absolute value of the counter. Such kind of events is easier to integrate over a period of time to get the amount of traffic during some time interval.
-
-Example event:
-
-```json
-{
-"metric": "proxy_io_bytes_per_client",
-"type": "incremental",
-"start_time": "2022-12-28T11:07:19.317310284Z",
-"stop_time": "2022-12-28T11:07:19.317310284Z",
-"idempotency_key": "2022-12-28 11:07:19.317310324 UTC-1-4019",
-"value": 12345454,
-"endpoint_id": "5d07d9ce9237c4cd845ea7918c0afa7d",
-}
-```
-
-Since we report deltas over some period of time, it makes sense to include `event_start_time`/`event_stop_time` where `event_start_time` is the time of the previous report. That will allow us to identify metering gaps better (e.g., failed send/delivery).
-
-When there is no active connection proxy can avoid reporting anything. Also, deltas are additive, so several console instances serving the same user and endpoint can report traffic without coordination.
-
-## Console
-
-The console knows about start/stop events, so it knows the amount of CPU time allocated to each endpoint. It also knows about operation successes and failures and can avoid billing clients after unsuccessful 'suspend' events. The console doesn't know the current compute size within the allowed limits on the endpoint. So with CPU time, we do the following:
-
-* While we don't yet have the autoscaling console can report `cpu time` as the number of seconds since the last `start_compute` event.
-
-* When we have autoscaling, `autoscaler-agent` can report `cpu time`*`compute_units_count` in the same increments as the proxy reports traffic.
-
-Example event:
-
-```json
-{
-    "metric": "effective_compute_seconds",
-    "type": "increment",
-    "endpoint_id": "blazing-warrior-34",
-    "event_start_time": ...,
-    "event_stop_time": ...,
-    "value": 12345454,
-}
-```
-
-I'd also suggest reporting one value, `cpu time`*`compute_units_count`, instead of two separate fields as it makes event schema simpler (it is possible to treat it the same way as traffic) and preserves additivity.
-
-## Pageserver
-
-For actual implementation details check `/docs/consumption_metrics.md`
-
-Pageserver knows / has access to / can calculate the rest of the metrics:
-
-* Written size -- that is basically `last_received_lsn`,
-* Synthetic storage size -- there is a way to calculate it, albeit a costly one,
-* Real storage size -- there is a way to calculate it using a layer map or filesystem,
-* S3 storage size -- can calculate it by S3 API calls
-
-Some of those metrics are expensive to calculate, so the reporting period here is driven mainly by implementation details. We can set it to, for example, once per hour. Not a big deal since the pageserver is stateful, and all metrics can be reported as an absolute value, not increments. At the same time, a smaller reporting period improves UX, so it would be good to have something more real-time.
-
-`written size` is primarily a safekeeper-related metric, but since it is available on both pageserver and safekeeper, we can avoid reporting anything from the safekeeper.
-
-Example event:
-
-```json
-{
-"metric": "remote_storage_size",
-"type": "absolute",
-"time": "2022-12-28T11:07:19.317310284Z",
-"idempotency_key": "2022-12-28 11:07:19.317310324 UTC-1-4019",
-"value": 12345454,
-"tenant_id": "5d07d9ce9237c4cd845ea7918c0afa7d",
-"timeline_id": "a03ebb4f5922a1c56ff7485cc8854143",
-}
-```
-
-# Data collection
-
-## Push vs. pull
-
-We already have pull-based Prometheus metrics, so it is tempting to use them here too. However, in our setup, it is hard to tell when some metric changes. For example, garbage collection will constantly free some disk space over a week, even if the project is down for that week. We could also iterate through all existing tenants/branches/endpoints, but that means some amount of code to do that properly and most likely we will end up with some per-metric hacks in the collector to cut out some of the tenants that are surely not changing that metric.
-
-With the push model, it is easier to publish data only about actively changing metrics -- pageserver knows when it performs s3 offloads, garbage collection and starts/stops consuming data from the safekeeper; proxy knows about connected clients; console / autoscaler-agent knows about active cpu time.
-
-Hence, let's go with a push-based model.
-
-## Common bus vs. proxying through the console
-
-We can implement such push systems in a few ways:
-
-a. Each component pushes its metrics to the "common bus", namely segment, Kafka, or something similar. That approach scales well, but it would be harder to test it locally, will introduce new dependencies, we will have to distribute secrets for that connection to all of the components, etc. We would also have to loop back some of the events and their aggregates to the console, as we want to show some that metrics to the user in real-time.
-
-b. Each component can call HTTP `POST` with its events to the console, and the console can forward it to the segment for later integration with metronome / orb / onebill / etc. With that approach, only the console has to speak with segment. Also since that data passes through the console, the console can save the latest metrics values, so there is no need for constant feedback of that events back from the segment.
-
-# Implementation
-
-Each (proxy|pageserver|autoscaler-agent) sends consumption events to the single endpoint in the console:
-
-```json
-POST /usage_events HTTP/1.1
-Content-Type: application/json
-
-[
-{
-"metric": "remote_storage_size",
-"type": "absolute",
-"time": "2022-12-28T11:07:19.317310284Z",
-"idempotency_key": "2022-12-28 11:07:19.317310324 UTC-1-4019",
-"value": 12345454,
-"tenant_id": "5d07d9ce9237c4cd845ea7918c0afa7d",
-"timeline_id": "a03ebb4f5922a1c56ff7485cc8854143",
-},
-...
-]
-```
-
-![data flow](./images/metering.jpg)
-
-Events could be either:
-* `incremental` -- change in consumption since the previous event or service restart. That is `effective_cpu_seconds`, `traffic_in_bytes`, and `traffic_out_bytes`.
-* `absolute` -- that is the current value of a metric. All of the size-related metrics are absolute.
-
-Each service can post events at its own pace and bundle together data from different tenants/endpoints.
-
-The console algorithm upon receive of events could be the following:
-
-1. Create and send a segment event with the same content (possibly enriching it with tenant/timeline data for endpoint-based events).
-2. Update the latest state of per-tenant and per-endpoint metrics in the database.
-3. Check whether any of that metrics is above the allowed threshold and stop the project if necessary.
-
-Since all the data comes in batches, we can do the batch update to reduce the number of queries in the database. Proxy traffic is probably the most frequent metric, so with batching, we will have extra `number_of_proxies` requests to the database each minute. This is most likely fine for now but will generate many dead tuples in the console database. If that is the case, we can change step 2 to the following:
-
-2.1. Check if there $tenant_$metric / $endpoint_$metric key in Redis
-
-2.2. If no stored value is found and the metric is incremental, then fetch the current value from DWH (which keeps aggregated value for all the events) and publish it.
-
-2.3. Publish a new value (absolute metric) or add an increment to the stored value (incremental metric)
-
-## Consumption watchdog
-
-Since all the data goes through the console, we don't have to run any background thread/coroutines to check whether consumption is within the allowed limits. We only change consumption with `POST /usage_events`, so limit checks could be applied in the same handler.
-
-## Extensibility
-
-If we need to add a new metric (e.g. s3 traffic or something else), the console code should, by default, process it and publish segment event, even if the metric name is unknown to the console.
-
-## Naming & schema
-
-Each metric name should end up with units -- now `_seconds` and `_bytes`, and segment event should always have `tenant_id` and `timeline_id`/`endpoint_id` where applicable.

docs/sourcetree.md

@@ -18,6 +18,10 @@ Intended to be used in integration tests and in CLI tools for local installation
 Documentation of the Neon features and concepts.
 Now it is mostly dev documentation.
 
+`/monitoring`:
+
+TODO
+
 `/pageserver`:
 
 Neon storage service.
@@ -94,13 +98,6 @@ cargo hakari manage-deps
 
 If you don't have hakari installed (`error: no such subcommand: hakari`), install it by running `cargo install cargo-hakari`.
 
-### Checking Rust 3rd-parties
-[Cargo deny](https://embarkstudios.github.io/cargo-deny/index.html) is a cargo plugin that lets us lint project's dependency graph to ensure all dependencies conform to requirements. It detects security issues, matches licenses, and ensures crates only come from trusted sources.
-
-```bash
-cargo deny check
-```
-
 ## Using Python
 Note that Debian/Ubuntu Python packages are stale, as it commonly happens,
 so manual installation of dependencies is not recommended.

libs/consumption_metrics/Cargo.toml

@@ -1,16 +0,0 @@
-[package]
-name = "consumption_metrics"
-version = "0.1.0"
-edition = "2021"
-license = "Apache-2.0"
-
-# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
-
-[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/consumption_metrics/src/lib.rs

@@ -1,50 +0,0 @@
-//!
-//! Shared code for consumption metics collection
-//!
-use chrono::{DateTime, Utc};
-use rand::Rng;
-use serde::Serialize;
-
-#[derive(Serialize, Debug, Clone, Eq, PartialEq, Ord, PartialOrd)]
-#[serde(tag = "type")]
-pub enum EventType {
-    #[serde(rename = "absolute")]
-    Absolute { time: DateTime<Utc> },
-    #[serde(rename = "incremental")]
-    Incremental {
-        start_time: DateTime<Utc>,
-        stop_time: DateTime<Utc>,
-    },
-}
-
-#[derive(Serialize, Debug, Clone, Eq, PartialEq, Ord, PartialOrd)]
-pub struct Event<Extra> {
-    #[serde(flatten)]
-    #[serde(rename = "type")]
-    pub kind: EventType,
-
-    pub metric: &'static str,
-    pub idempotency_key: String,
-    pub value: u64,
-
-    #[serde(flatten)]
-    pub extra: Extra,
-}
-
-pub fn idempotency_key(node_id: String) -> String {
-    format!(
-        "{}-{}-{:04}",
-        Utc::now(),
-        node_id,
-        rand::thread_rng().gen_range(0..=9999)
-    )
-}
-
-pub const CHUNK_SIZE: usize = 1000;
-
-// Just a wrapper around a slice of events
-// to serialize it as `{"events" : [ ] }
-#[derive(serde::Serialize)]
-pub struct EventChunk<'a, T> {
-    pub events: &'a [T],
-}

libs/metrics/Cargo.toml

@@ -1,13 +1,10 @@
 [package]
 name = "metrics"
 version = "0.1.0"
-edition.workspace = true
-license.workspace = true
+edition = "2021"
 
 [dependencies]
-prometheus.workspace = true
-libc.workspace = true
-once_cell.workspace = true
-chrono.workspace = true
-
-workspace_hack.workspace = true
+prometheus = {version = "0.13", default_features=false, features = ["process"]} # removes protobuf dependency
+libc = "0.2"
+once_cell = "1.13.0"
+workspace_hack = { version = "0.1", path = "../../workspace_hack" }

libs/metrics/src/launch_timestamp.rs

@@ -1,34 +0,0 @@
-//! A timestamp captured at process startup to identify restarts of the process, e.g., in logs and metrics.
-
-use chrono::Utc;
-
-use super::register_uint_gauge;
-use std::fmt::Display;
-
-pub struct LaunchTimestamp(chrono::DateTime<Utc>);
-
-impl LaunchTimestamp {
-    pub fn generate() -> Self {
-        LaunchTimestamp(Utc::now())
-    }
-}
-
-impl Display for LaunchTimestamp {
-    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
-        write!(f, "{}", self.0)
-    }
-}
-
-pub fn set_launch_timestamp_metric(launch_ts: &'static LaunchTimestamp) {
-    let millis_since_epoch: u64 = launch_ts
-        .0
-        .timestamp_millis()
-        .try_into()
-        .expect("we're after the epoch, this should be positive");
-    let metric = register_uint_gauge!(
-        "libmetrics_launch_timestamp",
-        "Timestamp (millis since epoch) at wich the process launched."
-    )
-    .unwrap();
-    metric.set(millis_since_epoch);
-}

libs/metrics/src/lib.rs

@@ -8,7 +8,6 @@ pub use prometheus::opts;
 pub use prometheus::register;
 pub use prometheus::{core, default_registry, proto};
 pub use prometheus::{exponential_buckets, linear_buckets};
-pub use prometheus::{register_counter_vec, Counter, CounterVec};
 pub use prometheus::{register_gauge, Gauge};
 pub use prometheus::{register_gauge_vec, GaugeVec};
 pub use prometheus::{register_histogram, Histogram};
@@ -20,7 +19,6 @@ pub use prometheus::{register_int_gauge_vec, IntGaugeVec};
 pub use prometheus::{Encoder, TextEncoder};
 use prometheus::{Registry, Result};
 
-pub mod launch_timestamp;
 mod wrappers;
 pub use wrappers::{CountedReader, CountedWriter};
 
@@ -35,14 +33,6 @@ macro_rules! register_uint_gauge_vec {
     }};
 }
 
-#[macro_export]
-macro_rules! register_uint_gauge {
-    ($NAME:expr, $HELP:expr $(,)?) => {{
-        let gauge = $crate::UIntGauge::new($NAME, $HELP).unwrap();
-        $crate::register(Box::new(gauge.clone())).map(|_| gauge)
-    }};
-}
-
 /// Special internal registry, to collect metrics independently from the default registry.
 /// Was introduced to fix deadlock with lazy registration of metrics in the default registry.
 static INTERNAL_REGISTRY: Lazy<Registry> = Lazy::new(Registry::new);

libs/pageserver_api/Cargo.toml

@@ -1,18 +1,16 @@
 [package]
 name = "pageserver_api"
 version = "0.1.0"
-edition.workspace = true
-license.workspace = true
+edition = "2021"
 
 [dependencies]
-serde.workspace = true
-serde_with.workspace = true
-const_format.workspace = true
-anyhow.workspace = true
-bytes.workspace = true
-byteorder.workspace = true
-utils.workspace = true
-postgres_ffi.workspace = true
-enum-map.workspace = true
+serde = { version = "1.0", features = ["derive"] }
+serde_with = "2.0"
+const_format = "0.2.21"
+anyhow = { version = "1.0", features = ["backtrace"] }
+bytes = "1.0.1"
+byteorder = "1.4.3"
 
-workspace_hack.workspace = true
+utils = { path = "../utils" }
+postgres_ffi = { path = "../postgres_ffi" }
+workspace_hack = { version = "0.1", path = "../../workspace_hack" }

libs/pageserver_api/src/models.rs

@@ -1,14 +1,9 @@
-use std::{
-    collections::HashMap,
-    num::{NonZeroU64, NonZeroUsize},
-    time::SystemTime,
-};
+use std::num::NonZeroU64;
 
 use byteorder::{BigEndian, ReadBytesExt};
 use serde::{Deserialize, Serialize};
 use serde_with::{serde_as, DisplayFromStr};
 use utils::{
-    history_buffer::HistoryBufferWithDropCounter,
     id::{NodeId, TenantId, TimelineId},
     lsn::Lsn,
 };
@@ -34,14 +29,6 @@ pub enum TenantState {
     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 {
     pub fn has_in_progress_downloads(&self) -> bool {
         match self {
@@ -52,32 +39,23 @@ impl TenantState {
             Self::Broken => false,
         }
     }
-
-    pub fn as_str(&self) -> &'static str {
-        match self {
-            TenantState::Loading => state::LOADING,
-            TenantState::Attaching => state::ATTACHING,
-            TenantState::Active => state::ACTIVE,
-            TenantState::Stopping => state::STOPPING,
-            TenantState::Broken => state::BROKEN,
-        }
-    }
 }
 
 /// A state of a timeline in pageserver's memory.
 #[derive(Debug, Clone, Copy, PartialEq, Eq, serde::Serialize, serde::Deserialize)]
 pub enum TimelineState {
-    /// The timeline is recognized by the pageserver but is not yet operational.
-    /// In particular, the walreceiver connection loop is not running for this timeline.
-    /// It will eventually transition to state Active or Broken.
-    Loading,
-    /// The timeline is fully operational.
-    /// It can be queried, and the walreceiver connection loop is running.
+    /// Timeline is fully operational. If the containing Tenant is Active, the timeline's
+    /// background jobs are running otherwise they will be launched when the tenant is activated.
     Active,
-    /// The timeline was previously Loading or Active but is shutting down.
-    /// It cannot transition back into any other state.
+    /// A timeline is recognized by pageserver, but not yet ready to operate.
+    /// The status indicates, that the timeline could eventually go back to Active automatically:
+    /// for example, if the owning tenant goes back to Active again.
+    Suspended,
+    /// A timeline is recognized by pageserver, but not yet ready to operate and not allowed to
+    /// automatically become Active after certain events: only a management call can change this status.
     Stopping,
-    /// The timeline is broken and not operational (previous states: Loading or Active).
+    /// A timeline is recognized by the pageserver, but can no longer be used for
+    /// any operations, because it failed to be activated.
     Broken,
 }
 
@@ -142,6 +120,7 @@ pub struct TenantConfigRequest {
     #[serde_as(as = "DisplayFromStr")]
     pub tenant_id: TenantId,
     #[serde(default)]
+    #[serde_as(as = "Option<DisplayFromStr>")]
     pub checkpoint_distance: Option<u64>,
     pub checkpoint_timeout: Option<String>,
     pub compaction_target_size: Option<u64>,
@@ -184,8 +163,6 @@ pub struct TenantInfo {
     #[serde_as(as = "DisplayFromStr")]
     pub id: TenantId,
     pub state: TenantState,
-    /// Sum of the size of all layer files.
-    /// If a layer is present in both local FS and S3, it counts only once.
     pub current_physical_size: Option<u64>, // physical size is only included in `tenant_status` endpoint
     pub has_in_progress_downloads: Option<bool>,
 }
@@ -214,12 +191,9 @@ pub struct TimelineInfo {
     #[serde_as(as = "DisplayFromStr")]
     pub remote_consistent_lsn: Lsn,
     pub current_logical_size: Option<u64>, // is None when timeline is Unloaded
-    /// Sum of the size of all layer files.
-    /// If a layer is present in both local FS and S3, it counts only once.
     pub current_physical_size: Option<u64>, // is None when timeline is Unloaded
     pub current_logical_size_non_incremental: Option<u64>,
-
-    pub timeline_dir_layer_file_size_sum: Option<u64>,
+    pub current_physical_size_non_incremental: Option<u64>,
 
     pub wal_source_connstr: Option<String>,
     #[serde_as(as = "Option<DisplayFromStr>")]
@@ -231,151 +205,6 @@ pub struct TimelineInfo {
     pub state: TimelineState,
 }
 
-#[derive(Debug, Clone, Serialize)]
-pub struct LayerMapInfo {
-    pub in_memory_layers: Vec<InMemoryLayerInfo>,
-    pub historic_layers: Vec<HistoricLayerInfo>,
-}
-
-#[derive(Debug, Hash, PartialEq, Eq, Clone, Copy, Serialize, Deserialize, enum_map::Enum)]
-#[repr(usize)]
-pub enum LayerAccessKind {
-    GetValueReconstructData,
-    Iter,
-    KeyIter,
-    Dump,
-}
-
-#[derive(Debug, Clone, Serialize, Deserialize)]
-pub struct LayerAccessStatFullDetails {
-    pub when_millis_since_epoch: u64,
-    pub task_kind: &'static str,
-    pub access_kind: LayerAccessKind,
-}
-
-/// An event that impacts the layer's residence status.
-#[serde_as]
-#[derive(Debug, Clone, Serialize, Deserialize)]
-pub struct LayerResidenceEvent {
-    /// The time when the event occurred.
-    /// NB: this timestamp is captured while the residence status changes.
-    /// So, it might be behind/ahead of the actual residence change by a short amount of time.
-    ///
-    #[serde(rename = "timestamp_millis_since_epoch")]
-    #[serde_as(as = "serde_with::TimestampMilliSeconds")]
-    timestamp: SystemTime,
-    /// The new residence status of the layer.
-    status: LayerResidenceStatus,
-    /// The reason why we had to record this event.
-    reason: LayerResidenceEventReason,
-}
-
-/// The reason for recording a given [`ResidenceEvent`].
-#[derive(Debug, Clone, Copy, Serialize, Deserialize)]
-pub enum LayerResidenceEventReason {
-    /// The layer map is being populated, e.g. during timeline load or attach.
-    /// This includes [`RemoteLayer`] objects created in [`reconcile_with_remote`].
-    /// We need to record such events because there is no persistent storage for the events.
-    LayerLoad,
-    /// We just created the layer (e.g., freeze_and_flush or compaction).
-    /// Such layers are always [`LayerResidenceStatus::Resident`].
-    LayerCreate,
-    /// We on-demand downloaded or evicted the given layer.
-    ResidenceChange,
-}
-
-/// The residence status of the layer, after the given [`LayerResidenceEvent`].
-#[derive(Debug, Clone, Copy, Serialize, Deserialize)]
-pub enum LayerResidenceStatus {
-    /// Residence status for a layer file that exists locally.
-    /// It may also exist on the remote, we don't care here.
-    Resident,
-    /// Residence status for a layer file that only exists on the remote.
-    Evicted,
-}
-
-impl LayerResidenceEvent {
-    pub fn new(status: LayerResidenceStatus, reason: LayerResidenceEventReason) -> Self {
-        Self {
-            status,
-            reason,
-            timestamp: SystemTime::now(),
-        }
-    }
-}
-
-#[derive(Debug, Clone, Serialize)]
-pub struct LayerAccessStats {
-    pub access_count_by_access_kind: HashMap<LayerAccessKind, u64>,
-    pub task_kind_access_flag: Vec<&'static str>,
-    pub first: Option<LayerAccessStatFullDetails>,
-    pub accesses_history: HistoryBufferWithDropCounter<LayerAccessStatFullDetails, 16>,
-    pub residence_events_history: HistoryBufferWithDropCounter<LayerResidenceEvent, 16>,
-}
-
-#[serde_as]
-#[derive(Debug, Clone, Serialize)]
-#[serde(tag = "kind")]
-pub enum InMemoryLayerInfo {
-    Open {
-        #[serde_as(as = "DisplayFromStr")]
-        lsn_start: Lsn,
-    },
-    Frozen {
-        #[serde_as(as = "DisplayFromStr")]
-        lsn_start: Lsn,
-        #[serde_as(as = "DisplayFromStr")]
-        lsn_end: Lsn,
-    },
-}
-
-#[serde_as]
-#[derive(Debug, Clone, Serialize)]
-#[serde(tag = "kind")]
-pub enum HistoricLayerInfo {
-    Delta {
-        layer_file_name: String,
-        layer_file_size: Option<u64>,
-
-        #[serde_as(as = "DisplayFromStr")]
-        lsn_start: Lsn,
-        #[serde_as(as = "DisplayFromStr")]
-        lsn_end: Lsn,
-        remote: bool,
-        access_stats: LayerAccessStats,
-    },
-    Image {
-        layer_file_name: String,
-        layer_file_size: Option<u64>,
-
-        #[serde_as(as = "DisplayFromStr")]
-        lsn_start: Lsn,
-        remote: bool,
-        access_stats: LayerAccessStats,
-    },
-}
-
-#[derive(Debug, Serialize, Deserialize)]
-pub struct DownloadRemoteLayersTaskSpawnRequest {
-    pub max_concurrent_downloads: NonZeroUsize,
-}
-
-#[derive(Debug, Serialize, Deserialize, Clone)]
-pub struct DownloadRemoteLayersTaskInfo {
-    pub task_id: String,
-    pub state: DownloadRemoteLayersTaskState,
-    pub total_layer_count: u64,         // stable once `completed`
-    pub successful_download_count: u64, // stable once `completed`
-    pub failed_download_count: u64,     // stable once `completed`
-}
-
-#[derive(Debug, Serialize, Deserialize, Clone)]
-pub enum DownloadRemoteLayersTaskState {
-    Running,
-    Completed,
-    ShutDown,
-}
-
 pub type ConfigureFailpointsRequest = Vec<FailpointConfig>;
 
 /// Information for configuring a single fail point
@@ -395,7 +224,7 @@ pub struct TimelineGcRequest {
 }
 
 // Wrapped in libpq CopyData
-#[derive(PartialEq, Eq, Debug)]
+#[derive(PartialEq, Eq)]
 pub enum PagestreamFeMessage {
     Exists(PagestreamExistsRequest),
     Nblocks(PagestreamNblocksRequest),
@@ -473,7 +302,7 @@ impl PagestreamFeMessage {
         match self {
             Self::Exists(req) => {
                 bytes.put_u8(0);
-                bytes.put_u8(u8::from(req.latest));
+                bytes.put_u8(if req.latest { 1 } else { 0 });
                 bytes.put_u64(req.lsn.0);
                 bytes.put_u32(req.rel.spcnode);
                 bytes.put_u32(req.rel.dbnode);
@@ -483,7 +312,7 @@ impl PagestreamFeMessage {
 
             Self::Nblocks(req) => {
                 bytes.put_u8(1);
-                bytes.put_u8(u8::from(req.latest));
+                bytes.put_u8(if req.latest { 1 } else { 0 });
                 bytes.put_u64(req.lsn.0);
                 bytes.put_u32(req.rel.spcnode);
                 bytes.put_u32(req.rel.dbnode);
@@ -493,7 +322,7 @@ impl PagestreamFeMessage {
 
             Self::GetPage(req) => {
                 bytes.put_u8(2);
-                bytes.put_u8(u8::from(req.latest));
+                bytes.put_u8(if req.latest { 1 } else { 0 });
                 bytes.put_u64(req.lsn.0);
                 bytes.put_u32(req.rel.spcnode);
                 bytes.put_u32(req.rel.dbnode);
@@ -504,7 +333,7 @@ impl PagestreamFeMessage {
 
             Self::DbSize(req) => {
                 bytes.put_u8(3);
-                bytes.put_u8(u8::from(req.latest));
+                bytes.put_u8(if req.latest { 1 } else { 0 });
                 bytes.put_u64(req.lsn.0);
                 bytes.put_u32(req.dbnode);
             }

libs/postgres_connection/Cargo.toml

@@ -1,17 +1,17 @@
 [package]
 name = "postgres_connection"
 version = "0.1.0"
-edition.workspace = true
-license.workspace = true
+edition = "2021"
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
-anyhow.workspace = true
-itertools.workspace = true
-postgres.workspace = true
-tokio-postgres.workspace = true
-url.workspace = true
-
-workspace_hack.workspace = true
+anyhow = "1.0"
+itertools = "0.10.3"
+postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev = "43e6db254a97fdecbce33d8bc0890accfd74495e" }
+tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e" }
+url = "2.2.2"
+workspace_hack = { version = "0.1", path = "../../workspace_hack" }
 
 [dev-dependencies]
-once_cell.workspace = true
+once_cell = "1.13.0"

libs/postgres_ffi/Cargo.toml

@@ -1,31 +1,29 @@
 [package]
 name = "postgres_ffi"
 version = "0.1.0"
-edition.workspace = true
-license.workspace = true
+edition = "2021"
 
 [dependencies]
-rand.workspace = true
-regex.workspace = true
-bytes.workspace = true
-byteorder.workspace = true
-anyhow.workspace = true
-crc32c.workspace = true
-hex.workspace = true
-once_cell.workspace = true
-log.workspace = true
-memoffset.workspace = true
-thiserror.workspace = true
-serde.workspace = true
-utils.workspace = true
-
-workspace_hack.workspace = true
+rand = "0.8.3"
+regex = "1.4.5"
+bytes = "1.0.1"
+byteorder = "1.4.3"
+anyhow = "1.0"
+crc32c = "0.6.0"
+hex = "0.4.3"
+once_cell = "1.13.0"
+log = "0.4.14"
+memoffset = "0.7"
+thiserror = "1.0"
+serde = { version = "1.0", features = ["derive"] }
+utils = { path = "../utils" }
+workspace_hack = { version = "0.1", path = "../../workspace_hack" }
 
 [dev-dependencies]
-env_logger.workspace = true
-postgres.workspace = true
+env_logger = "0.9"
+postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e" }
 wal_craft = { path = "wal_craft" }
 
 [build-dependencies]
-anyhow.workspace = true
-bindgen.workspace = true
+anyhow = "1.0"
+bindgen = "0.61"

libs/postgres_ffi/src/nonrelfile_utils.rs

@@ -14,8 +14,8 @@ pub fn transaction_id_set_status(xid: u32, status: u8, page: &mut BytesMut) {
         status
     );
 
-    let byteno: usize =
-        ((xid % pg_constants::CLOG_XACTS_PER_PAGE) / pg_constants::CLOG_XACTS_PER_BYTE) as usize;
+    let byteno: usize = ((xid as u32 % pg_constants::CLOG_XACTS_PER_PAGE as u32)
+        / pg_constants::CLOG_XACTS_PER_BYTE) as usize;
 
     let bshift: u8 =
         ((xid % pg_constants::CLOG_XACTS_PER_BYTE) * pg_constants::CLOG_BITS_PER_XACT as u32) as u8;
@@ -25,13 +25,13 @@ pub fn transaction_id_set_status(xid: u32, status: u8, page: &mut BytesMut) {
 }
 
 pub fn transaction_id_get_status(xid: u32, page: &[u8]) -> u8 {
-    let byteno: usize =
-        ((xid % pg_constants::CLOG_XACTS_PER_PAGE) / pg_constants::CLOG_XACTS_PER_BYTE) as usize;
+    let byteno: usize = ((xid as u32 % pg_constants::CLOG_XACTS_PER_PAGE as u32)
+        / pg_constants::CLOG_XACTS_PER_BYTE) as usize;
 
     let bshift: u8 =
         ((xid % pg_constants::CLOG_XACTS_PER_BYTE) * pg_constants::CLOG_BITS_PER_XACT as u32) as u8;
 
-    (page[byteno] >> bshift) & pg_constants::CLOG_XACT_BITMASK
+    ((page[byteno] >> bshift) & pg_constants::CLOG_XACT_BITMASK) as u8
 }
 
 // See CLOGPagePrecedes in clog.c

libs/postgres_ffi/src/xlog_utils.rs

@@ -333,7 +333,7 @@ impl CheckPoint {
 // We need this segment to start compute node.
 //
 pub fn generate_wal_segment(segno: u64, system_id: u64) -> Result<Bytes, SerializeError> {
-    let mut seg_buf = BytesMut::with_capacity(WAL_SEGMENT_SIZE);
+    let mut seg_buf = BytesMut::with_capacity(WAL_SEGMENT_SIZE as usize);
 
     let pageaddr = XLogSegNoOffsetToRecPtr(segno, 0, WAL_SEGMENT_SIZE);
     let hdr = XLogLongPageHeaderData {
@@ -574,7 +574,7 @@ mod tests {
 
         // Rename file to partial to actually find last valid lsn, then rename it back.
         fs::rename(
-            cfg.wal_dir().join(last_segment),
+            cfg.wal_dir().join(&last_segment),
             cfg.wal_dir().join(format!("{}.partial", last_segment)),
         )
         .unwrap();

libs/postgres_ffi/wal_craft/Cargo.toml

@@ -1,17 +1,17 @@
 [package]
 name = "wal_craft"
 version = "0.1.0"
-edition.workspace = true
-license.workspace = true
+edition = "2021"
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
-anyhow.workspace = true
-clap.workspace = true
-env_logger.workspace = true
-log.workspace = true
-once_cell.workspace = true
-postgres.workspace = true
-postgres_ffi.workspace = true
-tempfile.workspace = true
-
-workspace_hack.workspace = true
+anyhow = "1.0"
+clap = "4.0"
+env_logger = "0.9"
+log = "0.4"
+once_cell = "1.13.0"
+postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e" }
+postgres_ffi = { path = "../" }
+tempfile = "3.2"
+workspace_hack = { version = "0.1", path = "../../../workspace_hack" }

libs/postgres_ffi/wal_craft/src/lib.rs

@@ -81,7 +81,7 @@ impl Conf {
             .new_pg_command("initdb")?
             .arg("-D")
             .arg(self.datadir.as_os_str())
-            .args(["-U", "postgres", "--no-instructions", "--no-sync"])
+            .args(&["-U", "postgres", "--no-instructions", "--no-sync"])
             .output()?;
         debug!("initdb output: {:?}", output);
         ensure!(
@@ -105,12 +105,12 @@ impl Conf {
         let unix_socket_dir_path = unix_socket_dir.path().to_owned();
         let server_process = self
             .new_pg_command("postgres")?
-            .args(["-c", "listen_addresses="])
+            .args(&["-c", "listen_addresses="])
             .arg("-k")
             .arg(unix_socket_dir_path.as_os_str())
             .arg("-D")
             .arg(self.datadir.as_os_str())
-            .args(["-c", "logging_collector=on"]) // stderr will mess up with tests output
+            .args(&["-c", "logging_collector=on"]) // stderr will mess up with tests output
             .args(REQUIRED_POSTGRES_CONFIG.iter().flat_map(|cfg| ["-c", cfg]))
             .stderr(Stdio::from(log_file))
             .spawn()?;
@@ -142,7 +142,7 @@ impl Conf {
         );
         let output = self
             .new_pg_command("pg_waldump")?
-            .args([
+            .args(&[
                 &first_segment_file.as_os_str(),
                 &last_segment_file.as_os_str(),
             ])

libs/pq_proto/Cargo.toml

@@ -1,18 +1,16 @@
 [package]
 name = "pq_proto"
 version = "0.1.0"
-edition.workspace = true
-license.workspace = true
+edition = "2021"
 
 [dependencies]
-anyhow.workspace = true
-bytes.workspace = true
-pin-project-lite.workspace = true
-postgres-protocol.workspace = true
-rand.workspace = true
-serde.workspace = true
-tokio.workspace = true
-tracing.workspace = true
-thiserror.workspace = true
+anyhow = "1.0"
+bytes = "1.0.1"
+pin-project-lite = "0.2.7"
+postgres-protocol = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e" }
+rand = "0.8.3"
+serde = { version = "1.0", features = ["derive"] }
+tokio = { version = "1.17", features = ["macros"] }
+tracing = "0.1"
 
-workspace_hack.workspace = true
+workspace_hack = { version = "0.1", path = "../../workspace_hack" }

libs/pq_proto/src/lib.rs

@@ -5,7 +5,7 @@
 // Tools for calling certain async methods in sync contexts.
 pub mod sync;
 
-use anyhow::{ensure, Context, Result};
+use anyhow::{bail, ensure, Context, Result};
 use bytes::{Buf, BufMut, Bytes, BytesMut};
 use postgres_protocol::PG_EPOCH;
 use serde::{Deserialize, Serialize};
@@ -194,35 +194,6 @@ macro_rules! retry_read {
     };
 }
 
-/// An error occured during connection being open.
-#[derive(thiserror::Error, Debug)]
-pub enum ConnectionError {
-    /// IO error during writing to or reading from the connection socket.
-    #[error("Socket IO error: {0}")]
-    Socket(std::io::Error),
-    /// Invalid packet was received from client
-    #[error("Protocol error: {0}")]
-    Protocol(String),
-    /// Failed to parse a protocol mesage
-    #[error("Message parse error: {0}")]
-    MessageParse(anyhow::Error),
-}
-
-impl From<anyhow::Error> for ConnectionError {
-    fn from(e: anyhow::Error) -> Self {
-        Self::MessageParse(e)
-    }
-}
-
-impl ConnectionError {
-    pub fn into_io_error(self) -> io::Error {
-        match self {
-            ConnectionError::Socket(io) => io,
-            other => io::Error::new(io::ErrorKind::Other, other.to_string()),
-        }
-    }
-}
-
 impl FeMessage {
     /// Read one message from the stream.
     /// This function returns `Ok(None)` in case of EOF.
@@ -245,9 +216,7 @@ impl FeMessage {
     /// }
     /// ```
     #[inline(never)]
-    pub fn read(
-        stream: &mut (impl io::Read + Unpin),
-    ) -> Result<Option<FeMessage>, ConnectionError> {
+    pub fn read(stream: &mut (impl io::Read + Unpin)) -> anyhow::Result<Option<FeMessage>> {
         Self::read_fut(&mut AsyncishRead(stream)).wait()
     }
 
@@ -255,7 +224,7 @@ impl FeMessage {
     /// See documentation for `Self::read`.
     pub fn read_fut<Reader>(
         stream: &mut Reader,
-    ) -> SyncFuture<Reader, impl Future<Output = Result<Option<FeMessage>, ConnectionError>> + '_>
+    ) -> SyncFuture<Reader, impl Future<Output = anyhow::Result<Option<FeMessage>>> + '_>
     where
         Reader: tokio::io::AsyncRead + Unpin,
     {
@@ -269,21 +238,17 @@ impl FeMessage {
             let tag = match retry_read!(stream.read_u8().await) {
                 Ok(b) => b,
                 Err(e) if e.kind() == io::ErrorKind::UnexpectedEof => return Ok(None),
-                Err(e) => return Err(ConnectionError::Socket(e)),
+                Err(e) => return Err(e.into()),
             };
 
             // The message length includes itself, so it better be at least 4.
-            let len = retry_read!(stream.read_u32().await)
-                .map_err(ConnectionError::Socket)?
+            let len = retry_read!(stream.read_u32().await)?
                 .checked_sub(4)
-                .ok_or_else(|| ConnectionError::Protocol("invalid message length".to_string()))?;
+                .context("invalid message length")?;
 
             let body = {
                 let mut buffer = vec![0u8; len as usize];
-                stream
-                    .read_exact(&mut buffer)
-                    .await
-                    .map_err(ConnectionError::Socket)?;
+                stream.read_exact(&mut buffer).await?;
                 Bytes::from(buffer)
             };
 
@@ -300,11 +265,7 @@ impl FeMessage {
                 b'c' => Ok(Some(FeMessage::CopyDone)),
                 b'f' => Ok(Some(FeMessage::CopyFail)),
                 b'p' => Ok(Some(FeMessage::PasswordMessage(body))),
-                tag => {
-                    return Err(ConnectionError::Protocol(format!(
-                        "unknown message tag: {tag},'{body:?}'"
-                    )))
-                }
+                tag => bail!("unknown message tag: {},'{:?}'", tag, body),
             }
         })
     }
@@ -314,9 +275,7 @@ impl FeStartupPacket {
     /// Read startup message from the stream.
     // XXX: It's tempting yet undesirable to accept `stream` by value,
     // since such a change will cause user-supplied &mut references to be consumed
-    pub fn read(
-        stream: &mut (impl io::Read + Unpin),
-    ) -> Result<Option<FeMessage>, ConnectionError> {
+    pub fn read(stream: &mut (impl io::Read + Unpin)) -> anyhow::Result<Option<FeMessage>> {
         Self::read_fut(&mut AsyncishRead(stream)).wait()
     }
 
@@ -325,7 +284,7 @@ impl FeStartupPacket {
     // since such a change will cause user-supplied &mut references to be consumed
     pub fn read_fut<Reader>(
         stream: &mut Reader,
-    ) -> SyncFuture<Reader, impl Future<Output = Result<Option<FeMessage>, ConnectionError>> + '_>
+    ) -> SyncFuture<Reader, impl Future<Output = anyhow::Result<Option<FeMessage>>> + '_>
     where
         Reader: tokio::io::AsyncRead + Unpin,
     {
@@ -343,41 +302,31 @@ impl FeStartupPacket {
             let len = match retry_read!(stream.read_u32().await) {
                 Ok(len) => len as usize,
                 Err(e) if e.kind() == io::ErrorKind::UnexpectedEof => return Ok(None),
-                Err(e) => return Err(ConnectionError::Socket(e)),
+                Err(e) => return Err(e.into()),
             };
 
             #[allow(clippy::manual_range_contains)]
             if len < 4 || len > MAX_STARTUP_PACKET_LENGTH {
-                return Err(ConnectionError::Protocol(format!(
-                    "invalid message length {len}"
-                )));
+                bail!("invalid message length");
             }
 
-            let request_code =
-                retry_read!(stream.read_u32().await).map_err(ConnectionError::Socket)?;
+            let request_code = retry_read!(stream.read_u32().await)?;
 
             // the rest of startup packet are params
             let params_len = len - 8;
             let mut params_bytes = vec![0u8; params_len];
-            stream
-                .read_exact(params_bytes.as_mut())
-                .await
-                .map_err(ConnectionError::Socket)?;
+            stream.read_exact(params_bytes.as_mut()).await?;
 
             // Parse params depending on request code
             let req_hi = request_code >> 16;
             let req_lo = request_code & ((1 << 16) - 1);
             let message = match (req_hi, req_lo) {
                 (RESERVED_INVALID_MAJOR_VERSION, CANCEL_REQUEST_CODE) => {
-                    if params_len != 8 {
-                        return Err(ConnectionError::Protocol(
-                            "expected 8 bytes for CancelRequest params".to_string(),
-                        ));
-                    }
+                    ensure!(params_len == 8, "expected 8 bytes for CancelRequest params");
                     let mut cursor = Cursor::new(params_bytes);
                     FeStartupPacket::CancelRequest(CancelKeyData {
-                        backend_pid: cursor.read_i32().await.map_err(ConnectionError::Socket)?,
-                        cancel_key: cursor.read_i32().await.map_err(ConnectionError::Socket)?,
+                        backend_pid: cursor.read_i32().await?,
+                        cancel_key: cursor.read_i32().await?,
                     })
                 }
                 (RESERVED_INVALID_MAJOR_VERSION, NEGOTIATE_SSL_CODE) => {
@@ -389,9 +338,7 @@ impl FeStartupPacket {
                     FeStartupPacket::GssEncRequest
                 }
                 (RESERVED_INVALID_MAJOR_VERSION, unrecognized_code) => {
-                    return Err(ConnectionError::Protocol(format!(
-                        "Unrecognized request code {unrecognized_code}"
-                    )));
+                    bail!("Unrecognized request code {}", unrecognized_code)
                 }
                 // TODO bail if protocol major_version is not 3?
                 (major_version, minor_version) => {
@@ -399,21 +346,15 @@ impl FeStartupPacket {
                     // See `postgres: ProcessStartupPacket, build_startup_packet`.
                     let mut tokens = str::from_utf8(&params_bytes)
                         .context("StartupMessage params: invalid utf-8")?
-                        .strip_suffix('\0') // drop packet's own null
-                        .ok_or_else(|| {
-                            ConnectionError::Protocol(
-                                "StartupMessage params: missing null terminator".to_string(),
-                            )
-                        })?
+                        .strip_suffix('\0') // drop packet's own null terminator
+                        .context("StartupMessage params: missing null terminator")?
                         .split_terminator('\0');
 
                     let mut params = HashMap::new();
                     while let Some(name) = tokens.next() {
-                        let value = tokens.next().ok_or_else(|| {
-                            ConnectionError::Protocol(
-                                "StartupMessage params: key without value".to_string(),
-                            )
-                        })?;
+                        let value = tokens
+                            .next()
+                            .context("StartupMessage params: key without value")?;
 
                         params.insert(name.to_owned(), value.to_owned());
                     }
@@ -517,7 +458,7 @@ pub enum BeMessage<'a> {
     CloseComplete,
     // None means column is NULL
     DataRow(&'a [Option<&'a [u8]>]),
-    ErrorResponse(&'a str, Option<&'a [u8; 5]>),
+    ErrorResponse(&'a str),
     /// Single byte - used in response to SSLRequest/GSSENCRequest.
     EncryptionResponse(bool),
     NoData,
@@ -665,7 +606,7 @@ fn write_body<R>(buf: &mut BytesMut, f: impl FnOnce(&mut BytesMut) -> R) -> R {
 }
 
 /// Safe write of s into buf as cstring (String in the protocol).
-fn write_cstr(s: impl AsRef<[u8]>, buf: &mut BytesMut) -> io::Result<()> {
+fn write_cstr(s: impl AsRef<[u8]>, buf: &mut BytesMut) -> Result<(), io::Error> {
     let bytes = s.as_ref();
     if bytes.contains(&0) {
         return Err(io::Error::new(
@@ -685,8 +626,6 @@ fn read_cstr(buf: &mut Bytes) -> anyhow::Result<Bytes> {
     Ok(result)
 }
 
-pub const SQLSTATE_INTERNAL_ERROR: &[u8; 5] = b"XX000";
-
 impl<'a> BeMessage<'a> {
     /// Write message to the given buf.
     // Unlike the reading side, we use BytesMut
@@ -826,7 +765,10 @@ impl<'a> BeMessage<'a> {
             // First byte of each field represents type of this field. Set just enough fields
             // to satisfy rust-postgres client: 'S' -- severity, 'C' -- error, 'M' -- error
             // message text.
-            BeMessage::ErrorResponse(error_msg, pg_error_code) => {
+            BeMessage::ErrorResponse(error_msg) => {
+                // For all the errors set Severity to Error and error code to
+                // 'internal error'.
+
                 // 'E' signalizes ErrorResponse messages
                 buf.put_u8(b'E');
                 write_body(buf, |buf| {
@@ -834,9 +776,7 @@ impl<'a> BeMessage<'a> {
                     buf.put_slice(b"ERROR\0");
 
                     buf.put_u8(b'C'); // SQLSTATE error code
-                    buf.put_slice(&terminate_code(
-                        pg_error_code.unwrap_or(SQLSTATE_INTERNAL_ERROR),
-                    ));
+                    buf.put_slice(b"CXX000\0");
 
                     buf.put_u8(b'M'); // the message
                     write_cstr(error_msg, buf)?;
@@ -859,7 +799,7 @@ impl<'a> BeMessage<'a> {
                     buf.put_slice(b"NOTICE\0");
 
                     buf.put_u8(b'C'); // SQLSTATE error code
-                    buf.put_slice(&terminate_code(SQLSTATE_INTERNAL_ERROR));
+                    buf.put_slice(b"CXX000\0");
 
                     buf.put_u8(b'M'); // the message
                     write_cstr(error_msg.as_bytes(), buf)?;
@@ -941,7 +881,7 @@ impl<'a> BeMessage<'a> {
                     buf.put_u8(b'k');
                     buf.put_u64(req.sent_ptr);
                     buf.put_i64(req.timestamp);
-                    buf.put_u8(u8::from(req.request_reply));
+                    buf.put_u8(if req.request_reply { 1 } else { 0 });
                 });
             }
         }
@@ -1147,12 +1087,3 @@ mod tests {
         let _ = FeStartupPacket::read_fut(stream).await;
     }
 }
-
-fn terminate_code(code: &[u8; 5]) -> [u8; 6] {
-    let mut terminated = [0; 6];
-    for (i, &elem) in code.iter().enumerate() {
-        terminated[i] = elem;
-    }
-
-    terminated
-}

libs/remote_storage/Cargo.toml

@@ -1,28 +1,27 @@
 [package]
 name = "remote_storage"
 version = "0.1.0"
-edition.workspace = true
-license.workspace = true
+edition = "2021"
 
 [dependencies]
-anyhow.workspace = true
-async-trait.workspace = true
-once_cell.workspace = true
-aws-smithy-http.workspace = true
-aws-types.workspace = true
-aws-config.workspace = true
-aws-sdk-s3.workspace = true
-hyper = { workspace = true, features = ["stream"] }
-serde.workspace = true
-serde_json.workspace = true
-tokio = { workspace = true, features = ["sync", "fs", "io-util"] }
-tokio-util.workspace = true
-toml_edit.workspace = true
-tracing.workspace = true
-metrics.workspace = true
-utils.workspace = true
+anyhow = { version = "1.0", features = ["backtrace"] }
+async-trait = "0.1"
+metrics = { version = "0.1", path = "../metrics" }
+utils = { version = "0.1", path = "../utils" }
+once_cell = "1.13.0"
+aws-smithy-http = "0.51.0"
+aws-types = "0.51.0"
+aws-config = { version = "0.51.0", default-features = false, features=["rustls"] }
+aws-sdk-s3 = "0.21.0"
+hyper = { version = "0.14", features = ["stream"] }
+serde = { version = "1.0", features = ["derive"] }
+serde_json = "1"
+tokio = { version = "1.17", features = ["sync", "macros", "fs", "io-util"] }
+tokio-util = { version = "0.7", features = ["io"] }
+toml_edit = { version = "0.14", features = ["easy"] }
+tracing = "0.1.27"
 
-workspace_hack.workspace = true
+workspace_hack = { version = "0.1", path = "../../workspace_hack" }
 
 [dev-dependencies]
-tempfile.workspace = true
+tempfile = "3.2"

libs/remote_storage/src/lib.rs

@@ -7,7 +7,6 @@
 //!
 mod local_fs;
 mod s3_bucket;
-mod simulate_failures;
 
 use std::{
     collections::HashMap,
@@ -25,7 +24,7 @@ use tokio::io;
 use toml_edit::Item;
 use tracing::info;
 
-pub use self::{local_fs::LocalFs, s3_bucket::S3Bucket, simulate_failures::UnreliableWrapper};
+pub use self::{local_fs::LocalFs, s3_bucket::S3Bucket};
 
 /// How many different timelines can be processed simultaneously when synchronizing layers with the remote storage.
 /// During regular work, pageserver produces one layer file per timeline checkpoint, with bursts of concurrency
@@ -78,10 +77,7 @@ pub trait RemoteStorage: Send + Sync + 'static {
     /// Note: here we assume that if the prefix is passed it was obtained via remote_object_id
     /// which already takes into account any kind of global prefix (prefix_in_bucket for S3 or storage_root for LocalFS)
     /// so this method doesnt need to.
-    async fn list_prefixes(
-        &self,
-        prefix: Option<&RemotePath>,
-    ) -> Result<Vec<RemotePath>, DownloadError>;
+    async fn list_prefixes(&self, prefix: Option<&RemotePath>) -> anyhow::Result<Vec<RemotePath>>;
 
     /// Streams the local file contents into remote into the remote storage entry.
     async fn upload(
@@ -154,7 +150,6 @@ impl std::error::Error for DownloadError {}
 pub enum GenericRemoteStorage {
     LocalFs(LocalFs),
     AwsS3(Arc<S3Bucket>),
-    Unreliable(Arc<UnreliableWrapper>),
 }
 
 impl Deref for GenericRemoteStorage {
@@ -164,30 +159,27 @@ impl Deref for GenericRemoteStorage {
         match self {
             GenericRemoteStorage::LocalFs(local_fs) => local_fs,
             GenericRemoteStorage::AwsS3(s3_bucket) => s3_bucket.as_ref(),
-            GenericRemoteStorage::Unreliable(s) => s.as_ref(),
         }
     }
 }
 
 impl GenericRemoteStorage {
-    pub fn from_config(storage_config: &RemoteStorageConfig) -> anyhow::Result<Self> {
+    pub fn from_config(
+        storage_config: &RemoteStorageConfig,
+    ) -> anyhow::Result<GenericRemoteStorage> {
         Ok(match &storage_config.storage {
             RemoteStorageKind::LocalFs(root) => {
                 info!("Using fs root '{}' as a remote storage", root.display());
-                Self::LocalFs(LocalFs::new(root.clone())?)
+                GenericRemoteStorage::LocalFs(LocalFs::new(root.clone())?)
             }
             RemoteStorageKind::AwsS3(s3_config) => {
                 info!("Using s3 bucket '{}' in region '{}' as a remote storage, prefix in bucket: '{:?}', bucket endpoint: '{:?}'",
                       s3_config.bucket_name, s3_config.bucket_region, s3_config.prefix_in_bucket, s3_config.endpoint);
-                Self::AwsS3(Arc::new(S3Bucket::new(s3_config)?))
+                GenericRemoteStorage::AwsS3(Arc::new(S3Bucket::new(s3_config)?))
             }
         })
     }
 
-    pub fn unreliable_wrapper(s: Self, fail_first: u64) -> Self {
-        Self::Unreliable(Arc::new(UnreliableWrapper::new(s, fail_first)))
-    }
-
     /// Takes storage object contents and its size and uploads to remote storage,
     /// mapping `from_path` to the corresponding remote object id in the storage.
     ///

libs/remote_storage/src/local_fs.rs

@@ -92,17 +92,13 @@ impl RemoteStorage for LocalFs {
             .collect())
     }
 
-    async fn list_prefixes(
-        &self,
-        prefix: Option<&RemotePath>,
-    ) -> Result<Vec<RemotePath>, DownloadError> {
+    async fn list_prefixes(&self, prefix: Option<&RemotePath>) -> anyhow::Result<Vec<RemotePath>> {
         let path = match prefix {
             Some(prefix) => Cow::Owned(prefix.with_base(&self.storage_root)),
             None => Cow::Borrowed(&self.storage_root),
         };
         Ok(get_all_files(path.as_ref(), false)
-            .await
-            .map_err(DownloadError::Other)?
+            .await?
             .into_iter()
             .map(|path| {
                 path.strip_prefix(&self.storage_root)

libs/remote_storage/src/s3_bucket.rs

@@ -286,10 +286,7 @@ impl RemoteStorage for S3Bucket {
 
     /// See the doc for `RemoteStorage::list_prefixes`
     /// Note: it wont include empty "directories"
-    async fn list_prefixes(
-        &self,
-        prefix: Option<&RemotePath>,
-    ) -> Result<Vec<RemotePath>, DownloadError> {
+    async fn list_prefixes(&self, prefix: Option<&RemotePath>) -> anyhow::Result<Vec<RemotePath>> {
         // get the passed prefix or if it is not set use prefix_in_bucket value
         let list_prefix = prefix
             .map(|p| self.relative_path_to_s3_object(p))
@@ -311,8 +308,7 @@ impl RemoteStorage for S3Bucket {
                 .concurrency_limiter
                 .acquire()
                 .await
-                .context("Concurrency limiter semaphore got closed during S3 list")
-                .map_err(DownloadError::Other)?;
+                .context("Concurrency limiter semaphore got closed during S3 list")?;
 
             metrics::inc_list_objects();
 
@@ -328,9 +324,7 @@ impl RemoteStorage for S3Bucket {
                 .map_err(|e| {
                     metrics::inc_list_objects_fail();
                     e
-                })
-                .context("Failed to list S3 prefixes")
-                .map_err(DownloadError::Other)?;
+                })?;
 
             document_keys.extend(
                 fetch_response

libs/remote_storage/src/simulate_failures.rs

@@ -1,129 +0,0 @@
-//! This module provides a wrapper around a real RemoteStorage implementation that
-//! causes the first N attempts at each upload or download operatio to fail. For
-//! testing purposes.
-use std::collections::hash_map::Entry;
-use std::collections::HashMap;
-use std::sync::Mutex;
-
-use crate::{Download, DownloadError, RemotePath, RemoteStorage, StorageMetadata};
-
-pub struct UnreliableWrapper {
-    inner: crate::GenericRemoteStorage,
-
-    // This many attempts of each operation will fail, then we let it succeed.
-    attempts_to_fail: u64,
-
-    // Tracks how many failed attempts of each operation has been made.
-    attempts: Mutex<HashMap<RemoteOp, u64>>,
-}
-
-/// Used to identify retries of different unique operation.
-#[derive(Debug, Hash, Eq, PartialEq)]
-enum RemoteOp {
-    List,
-    ListPrefixes(Option<RemotePath>),
-    Upload(RemotePath),
-    Download(RemotePath),
-    Delete(RemotePath),
-}
-
-impl UnreliableWrapper {
-    pub fn new(inner: crate::GenericRemoteStorage, attempts_to_fail: u64) -> Self {
-        assert!(attempts_to_fail > 0);
-        UnreliableWrapper {
-            inner,
-            attempts_to_fail,
-            attempts: Mutex::new(HashMap::new()),
-        }
-    }
-
-    ///
-    /// Common functionality for all operations.
-    ///
-    /// On the first attempts of this operation, return an error. After 'attempts_to_fail'
-    /// attempts, let the operation go ahead, and clear the counter.
-    ///
-    fn attempt(&self, op: RemoteOp) -> Result<u64, DownloadError> {
-        let mut attempts = self.attempts.lock().unwrap();
-
-        match attempts.entry(op) {
-            Entry::Occupied(mut e) => {
-                let attempts_before_this = {
-                    let p = e.get_mut();
-                    *p += 1;
-                    *p
-                };
-
-                if attempts_before_this >= self.attempts_to_fail {
-                    // let it succeed
-                    e.remove();
-                    Ok(attempts_before_this)
-                } else {
-                    let error =
-                        anyhow::anyhow!("simulated failure of remote operation {:?}", e.key());
-                    Err(DownloadError::Other(error))
-                }
-            }
-            Entry::Vacant(e) => {
-                let error = anyhow::anyhow!("simulated failure of remote operation {:?}", e.key());
-                e.insert(1);
-                Err(DownloadError::Other(error))
-            }
-        }
-    }
-}
-
-#[async_trait::async_trait]
-impl RemoteStorage for UnreliableWrapper {
-    /// Lists all items the storage has right now.
-    async fn list(&self) -> anyhow::Result<Vec<RemotePath>> {
-        self.attempt(RemoteOp::List)?;
-        self.inner.list().await
-    }
-
-    async fn list_prefixes(
-        &self,
-        prefix: Option<&RemotePath>,
-    ) -> Result<Vec<RemotePath>, DownloadError> {
-        self.attempt(RemoteOp::ListPrefixes(prefix.cloned()))?;
-        self.inner.list_prefixes(prefix).await
-    }
-
-    async fn upload(
-        &self,
-        data: Box<(dyn tokio::io::AsyncRead + Unpin + Send + Sync + 'static)>,
-        // S3 PUT request requires the content length to be specified,
-        // otherwise it starts to fail with the concurrent connection count increasing.
-        data_size_bytes: usize,
-        to: &RemotePath,
-        metadata: Option<StorageMetadata>,
-    ) -> anyhow::Result<()> {
-        self.attempt(RemoteOp::Upload(to.clone()))?;
-        self.inner.upload(data, data_size_bytes, to, metadata).await
-    }
-
-    async fn download(&self, from: &RemotePath) -> Result<Download, DownloadError> {
-        self.attempt(RemoteOp::Download(from.clone()))?;
-        self.inner.download(from).await
-    }
-
-    async fn download_byte_range(
-        &self,
-        from: &RemotePath,
-        start_inclusive: u64,
-        end_exclusive: Option<u64>,
-    ) -> Result<Download, DownloadError> {
-        // Note: We treat any download_byte_range as an "attempt" of the same
-        // operation. We don't pay attention to the ranges. That's good enough
-        // for now.
-        self.attempt(RemoteOp::Download(from.clone()))?;
-        self.inner
-            .download_byte_range(from, start_inclusive, end_exclusive)
-            .await
-    }
-
-    async fn delete(&self, path: &RemotePath) -> anyhow::Result<()> {
-        self.attempt(RemoteOp::Delete(path.clone()))?;
-        self.inner.delete(path).await
-    }
-}

libs/safekeeper_api/Cargo.toml

@@ -1,13 +1,12 @@
 [package]
 name = "safekeeper_api"
 version = "0.1.0"
-edition.workspace = true
-license.workspace = true
+edition = "2021"
 
 [dependencies]
-serde.workspace = true
-serde_with.workspace = true
-const_format.workspace = true
-utils.workspace = true
+serde = { version = "1.0", features = ["derive"] }
+serde_with = "2.0"
+const_format = "0.2.21"
 
-workspace_hack.workspace = true
+utils = { path = "../utils" }
+workspace_hack = { version = "0.1", path = "../../workspace_hack" }

libs/tenant_size_model/Cargo.toml

@@ -1,11 +1,8 @@
 [package]
 name = "tenant_size_model"
 version = "0.1.0"
-edition.workspace = true
+edition = "2021"
 publish = false
-license.workspace = true
 
 [dependencies]
-anyhow.workspace = true
-
-workspace_hack.workspace = true
+workspace_hack = { version = "0.1", path = "../../workspace_hack" }

libs/tenant_size_model/src/lib.rs

@@ -1,8 +1,6 @@
 use std::borrow::Cow;
 use std::collections::HashMap;
 
-use anyhow::Context;
-
 /// Pricing model or history size builder.
 ///
 /// Maintains knowledge of the branches and their modifications. Generic over the branch name key
@@ -134,25 +132,22 @@ impl<K: std::hash::Hash + Eq + 'static> Storage<K> {
         op: Cow<'static, str>,
         lsn: u64,
         size: Option<u64>,
-    ) -> anyhow::Result<()>
-    where
+    ) where
         K: std::borrow::Borrow<Q>,
-        Q: std::hash::Hash + Eq + std::fmt::Debug,
+        Q: std::hash::Hash + Eq,
     {
-        let Some(lastseg_id) = self.branches.get(branch).copied() else { anyhow::bail!("branch not found: {branch:?}") };
+        let lastseg_id = *self.branches.get(branch).unwrap();
         let newseg_id = self.segments.len();
         let lastseg = &mut self.segments[lastseg_id];
 
         assert!(lsn > lastseg.end_lsn);
 
-        let Some(start_size) = lastseg.end_size else { anyhow::bail!("no end_size on latest segment for {branch:?}") };
-
         let newseg = Segment {
             op,
             parent: Some(lastseg_id),
             start_lsn: lastseg.end_lsn,
             end_lsn: lsn,
-            start_size,
+            start_size: lastseg.end_size.unwrap(),
             end_size: size,
             children_after: Vec::new(),
             needed: false,
@@ -161,8 +156,6 @@ impl<K: std::hash::Hash + Eq + 'static> Storage<K> {
 
         self.segments.push(newseg);
         *self.branches.get_mut(branch).expect("read already") = newseg_id;
-
-        Ok(())
     }
 
     /// Advances the branch with the named operation, by the relative LSN and logical size bytes.
@@ -172,24 +165,21 @@ impl<K: std::hash::Hash + Eq + 'static> Storage<K> {
         op: Cow<'static, str>,
         lsn_bytes: u64,
         size_bytes: i64,
-    ) -> anyhow::Result<()>
-    where
+    ) where
         K: std::borrow::Borrow<Q>,
-        Q: std::hash::Hash + Eq + std::fmt::Debug,
+        Q: std::hash::Hash + Eq,
     {
-        let Some(lastseg_id) = self.branches.get(branch).copied() else { anyhow::bail!("branch not found: {branch:?}") };
+        let lastseg_id = *self.branches.get(branch).unwrap();
         let newseg_id = self.segments.len();
         let lastseg = &mut self.segments[lastseg_id];
 
-        let Some(last_end_size) = lastseg.end_size else { anyhow::bail!("no end_size on latest segment for {branch:?}") };
-
         let newseg = Segment {
             op,
             parent: Some(lastseg_id),
             start_lsn: lastseg.end_lsn,
             end_lsn: lastseg.end_lsn + lsn_bytes,
-            start_size: last_end_size,
-            end_size: Some((last_end_size as i64 + size_bytes) as u64),
+            start_size: lastseg.end_size.unwrap(),
+            end_size: Some((lastseg.end_size.unwrap() as i64 + size_bytes) as u64),
             children_after: Vec::new(),
             needed: false,
         };
@@ -197,54 +187,50 @@ impl<K: std::hash::Hash + Eq + 'static> Storage<K> {
 
         self.segments.push(newseg);
         *self.branches.get_mut(branch).expect("read already") = newseg_id;
-        Ok(())
     }
 
-    pub fn insert<Q: ?Sized>(&mut self, branch: &Q, bytes: u64) -> anyhow::Result<()>
+    pub fn insert<Q: ?Sized>(&mut self, branch: &Q, bytes: u64)
     where
         K: std::borrow::Borrow<Q>,
-        Q: std::hash::Hash + Eq + std::fmt::Debug,
+        Q: std::hash::Hash + Eq,
     {
-        self.modify_branch(branch, "insert".into(), bytes, bytes as i64)
+        self.modify_branch(branch, "insert".into(), bytes, bytes as i64);
     }
 
-    pub fn update<Q: ?Sized>(&mut self, branch: &Q, bytes: u64) -> anyhow::Result<()>
+    pub fn update<Q: ?Sized>(&mut self, branch: &Q, bytes: u64)
     where
         K: std::borrow::Borrow<Q>,
-        Q: std::hash::Hash + Eq + std::fmt::Debug,
+        Q: std::hash::Hash + Eq,
     {
-        self.modify_branch(branch, "update".into(), bytes, 0i64)
+        self.modify_branch(branch, "update".into(), bytes, 0i64);
     }
 
-    pub fn delete<Q: ?Sized>(&mut self, branch: &Q, bytes: u64) -> anyhow::Result<()>
+    pub fn delete<Q: ?Sized>(&mut self, branch: &Q, bytes: u64)
     where
         K: std::borrow::Borrow<Q>,
-        Q: std::hash::Hash + Eq + std::fmt::Debug,
+        Q: std::hash::Hash + Eq,
     {
-        self.modify_branch(branch, "delete".into(), bytes, -(bytes as i64))
+        self.modify_branch(branch, "delete".into(), bytes, -(bytes as i64));
     }
 
-    pub fn branch<Q: ?Sized>(&mut self, parent: &Q, name: K) -> anyhow::Result<()>
+    /// Panics if the parent branch cannot be found.
+    pub fn branch<Q: ?Sized>(&mut self, parent: &Q, name: K)
     where
-        K: std::borrow::Borrow<Q> + std::fmt::Debug,
-        Q: std::hash::Hash + Eq + std::fmt::Debug,
+        K: std::borrow::Borrow<Q>,
+        Q: std::hash::Hash + Eq,
     {
         // Find the right segment
-        let branchseg_id = *self.branches.get(parent).with_context(|| {
-            format!(
-                "should had found the parent {:?} by key. in branches {:?}",
-                parent, self.branches
-            )
-        })?;
-
+        let branchseg_id = *self
+            .branches
+            .get(parent)
+            .expect("should had found the parent by key");
         let _branchseg = &mut self.segments[branchseg_id];
 
         // Create branch name for it
         self.branches.insert(name, branchseg_id);
-        Ok(())
     }
 
-    pub fn calculate(&mut self, retention_period: u64) -> anyhow::Result<SegmentSize> {
+    pub fn calculate(&mut self, retention_period: u64) -> SegmentSize {
         // Phase 1: Mark all the segments that need to be retained
         for (_branch, &last_seg_id) in self.branches.iter() {
             let last_seg = &self.segments[last_seg_id];
@@ -269,7 +255,7 @@ impl<K: std::hash::Hash + Eq + 'static> Storage<K> {
         self.size_from_snapshot_later(0)
     }
 
-    fn size_from_wal(&self, seg_id: usize) -> anyhow::Result<SegmentSize> {
+    fn size_from_wal(&self, seg_id: usize) -> SegmentSize {
         let seg = &self.segments[seg_id];
 
         let this_size = seg.end_lsn - seg.start_lsn;
@@ -280,10 +266,10 @@ impl<K: std::hash::Hash + Eq + 'static> Storage<K> {
         for &child_id in seg.children_after.iter() {
             // try each child both ways
             let child = &self.segments[child_id];
-            let p1 = self.size_from_wal(child_id)?;
+            let p1 = self.size_from_wal(child_id);
 
             let p = if !child.needed {
-                let p2 = self.size_from_snapshot_later(child_id)?;
+                let p2 = self.size_from_snapshot_later(child_id);
                 if p1.total() < p2.total() {
                     p1
                 } else {
@@ -294,15 +280,15 @@ impl<K: std::hash::Hash + Eq + 'static> Storage<K> {
             };
             children.push(p);
         }
-        Ok(SegmentSize {
+        SegmentSize {
             seg_id,
             method: if seg.needed { WalNeeded } else { Wal },
             this_size,
             children,
-        })
+        }
     }
 
-    fn size_from_snapshot_later(&self, seg_id: usize) -> anyhow::Result<SegmentSize> {
+    fn size_from_snapshot_later(&self, seg_id: usize) -> SegmentSize {
         // If this is needed, then it's time to do the snapshot and continue
         // with wal method.
         let seg = &self.segments[seg_id];
@@ -313,10 +299,10 @@ impl<K: std::hash::Hash + Eq + 'static> Storage<K> {
             for &child_id in seg.children_after.iter() {
                 // try each child both ways
                 let child = &self.segments[child_id];
-                let p1 = self.size_from_wal(child_id)?;
+                let p1 = self.size_from_wal(child_id);
 
                 let p = if !child.needed {
-                    let p2 = self.size_from_snapshot_later(child_id)?;
+                    let p2 = self.size_from_snapshot_later(child_id);
                     if p1.total() < p2.total() {
                         p1
                     } else {
@@ -327,12 +313,12 @@ impl<K: std::hash::Hash + Eq + 'static> Storage<K> {
                 };
                 children.push(p);
             }
-            Ok(SegmentSize {
+            SegmentSize {
                 seg_id,
                 method: WalNeeded,
                 this_size: seg.start_size,
                 children,
-            })
+            }
         } else {
             // If any of the direct children are "needed", need to be able to reconstruct here
             let mut children_needed = false;
@@ -347,7 +333,7 @@ impl<K: std::hash::Hash + Eq + 'static> Storage<K> {
             let method1 = if !children_needed {
                 let mut children = Vec::new();
                 for child in seg.children_after.iter() {
-                    children.push(self.size_from_snapshot_later(*child)?);
+                    children.push(self.size_from_snapshot_later(*child));
                 }
                 Some(SegmentSize {
                     seg_id,
@@ -363,25 +349,20 @@ impl<K: std::hash::Hash + Eq + 'static> Storage<K> {
             let method2 = if children_needed || seg.children_after.len() >= 2 {
                 let mut children = Vec::new();
                 for child in seg.children_after.iter() {
-                    children.push(self.size_from_wal(*child)?);
+                    children.push(self.size_from_wal(*child));
                 }
-                let Some(this_size) = seg.end_size else { anyhow::bail!("no end_size at junction {seg_id}") };
                 Some(SegmentSize {
                     seg_id,
                     method: SnapshotAfter,
-                    this_size,
+                    this_size: seg.end_size.unwrap(),
                     children,
                 })
             } else {
                 None
             };
 
-            Ok(match (method1, method2) {
-                (None, None) => anyhow::bail!(
-                    "neither method was applicable: children_after={}, children_needed={}",
-                    seg.children_after.len(),
-                    children_needed
-                ),
+            match (method1, method2) {
+                (None, None) => panic!(),
                 (Some(method), None) => method,
                 (None, Some(method)) => method,
                 (Some(method1), Some(method2)) => {
@@ -391,7 +372,7 @@ impl<K: std::hash::Hash + Eq + 'static> Storage<K> {
                         method2
                     }
                 }
-            })
+            }
         }
     }
 

libs/tenant_size_model/src/main.rs

@@ -7,118 +7,118 @@
 use tenant_size_model::{Segment, SegmentSize, Storage};
 
 // Main branch only. Some updates on it.
-fn scenario_1() -> anyhow::Result<(Vec<Segment>, SegmentSize)> {
+fn scenario_1() -> (Vec<Segment>, SegmentSize) {
     // Create main branch
     let mut storage = Storage::new("main");
 
     // Bulk load 5 GB of data to it
-    storage.insert("main", 5_000)?;
+    storage.insert("main", 5_000);
 
     // Stream of updates
     for _ in 0..5 {
-        storage.update("main", 1_000)?;
+        storage.update("main", 1_000);
     }
 
-    let size = storage.calculate(1000)?;
+    let size = storage.calculate(1000);
 
-    Ok((storage.into_segments(), size))
+    (storage.into_segments(), size)
 }
 
 // Main branch only. Some updates on it.
-fn scenario_2() -> anyhow::Result<(Vec<Segment>, SegmentSize)> {
+fn scenario_2() -> (Vec<Segment>, SegmentSize) {
     // Create main branch
     let mut storage = Storage::new("main");
 
     // Bulk load 5 GB of data to it
-    storage.insert("main", 5_000)?;
+    storage.insert("main", 5_000);
 
     // Stream of updates
     for _ in 0..5 {
-        storage.update("main", 1_000)?;
+        storage.update("main", 1_000);
     }
 
     // Branch
-    storage.branch("main", "child")?;
-    storage.update("child", 1_000)?;
+    storage.branch("main", "child");
+    storage.update("child", 1_000);
 
     // More updates on parent
-    storage.update("main", 1_000)?;
+    storage.update("main", 1_000);
 
-    let size = storage.calculate(1000)?;
+    let size = storage.calculate(1000);
 
-    Ok((storage.into_segments(), size))
+    (storage.into_segments(), size)
 }
 
 // Like 2, but more updates on main
-fn scenario_3() -> anyhow::Result<(Vec<Segment>, SegmentSize)> {
+fn scenario_3() -> (Vec<Segment>, SegmentSize) {
     // Create main branch
     let mut storage = Storage::new("main");
 
     // Bulk load 5 GB of data to it
-    storage.insert("main", 5_000)?;
+    storage.insert("main", 5_000);
 
     // Stream of updates
     for _ in 0..5 {
-        storage.update("main", 1_000)?;
+        storage.update("main", 1_000);
     }
 
     // Branch
-    storage.branch("main", "child")?;
-    storage.update("child", 1_000)?;
+    storage.branch("main", "child");
+    storage.update("child", 1_000);
 
     // More updates on parent
     for _ in 0..5 {
-        storage.update("main", 1_000)?;
+        storage.update("main", 1_000);
     }
 
-    let size = storage.calculate(1000)?;
+    let size = storage.calculate(1000);
 
-    Ok((storage.into_segments(), size))
+    (storage.into_segments(), size)
 }
 
 // Diverged branches
-fn scenario_4() -> anyhow::Result<(Vec<Segment>, SegmentSize)> {
+fn scenario_4() -> (Vec<Segment>, SegmentSize) {
     // Create main branch
     let mut storage = Storage::new("main");
 
     // Bulk load 5 GB of data to it
-    storage.insert("main", 5_000)?;
+    storage.insert("main", 5_000);
 
     // Stream of updates
     for _ in 0..5 {
-        storage.update("main", 1_000)?;
+        storage.update("main", 1_000);
     }
 
     // Branch
-    storage.branch("main", "child")?;
-    storage.update("child", 1_000)?;
+    storage.branch("main", "child");
+    storage.update("child", 1_000);
 
     // More updates on parent
     for _ in 0..8 {
-        storage.update("main", 1_000)?;
+        storage.update("main", 1_000);
     }
 
-    let size = storage.calculate(1000)?;
+    let size = storage.calculate(1000);
 
-    Ok((storage.into_segments(), size))
+    (storage.into_segments(), size)
 }
 
-fn scenario_5() -> anyhow::Result<(Vec<Segment>, SegmentSize)> {
+fn scenario_5() -> (Vec<Segment>, SegmentSize) {
     let mut storage = Storage::new("a");
-    storage.insert("a", 5000)?;
-    storage.branch("a", "b")?;
-    storage.update("b", 4000)?;
-    storage.update("a", 2000)?;
-    storage.branch("a", "c")?;
-    storage.insert("c", 4000)?;
-    storage.insert("a", 2000)?;
+    storage.insert("a", 5000);
+    storage.branch("a", "b");
+    storage.update("b", 4000);
+    storage.update("a", 2000);
+    storage.branch("a", "c");
+    storage.insert("c", 4000);
+    storage.insert("a", 2000);
 
-    let size = storage.calculate(5000)?;
+    let size = storage.calculate(5000);
 
-    Ok((storage.into_segments(), size))
+    (storage.into_segments(), size)
 }
 
-fn scenario_6() -> anyhow::Result<(Vec<Segment>, SegmentSize)> {
+fn scenario_6() -> (Vec<Segment>, SegmentSize) {
     use std::borrow::Cow;
 
     const NO_OP: Cow<'static, str> = Cow::Borrowed("");
@@ -133,18 +133,18 @@ fn scenario_6() -> anyhow::Result<(Vec<Segment>, SegmentSize)> {
 
     let mut storage = Storage::new(None);
 
-    storage.branch(&None, branches[0])?; // at 0
-    storage.modify_branch(&branches[0], NO_OP, 108951064, 43696128)?; // at 108951064
-    storage.branch(&branches[0], branches[1])?; // at 108951064
-    storage.modify_branch(&branches[1], NO_OP, 15560408, -1851392)?; // at 124511472
-    storage.modify_branch(&branches[0], NO_OP, 174464360, -1531904)?; // at 283415424
-    storage.branch(&branches[0], branches[2])?; // at 283415424
-    storage.modify_branch(&branches[2], NO_OP, 15906192, 8192)?; // at 299321616
-    storage.modify_branch(&branches[0], NO_OP, 18909976, 32768)?; // at 302325400
+    storage.branch(&None, branches[0]); // at 0
+    storage.modify_branch(&branches[0], NO_OP, 108951064, 43696128); // at 108951064
+    storage.branch(&branches[0], branches[1]); // at 108951064
+    storage.modify_branch(&branches[1], NO_OP, 15560408, -1851392); // at 124511472
+    storage.modify_branch(&branches[0], NO_OP, 174464360, -1531904); // at 283415424
+    storage.branch(&branches[0], branches[2]); // at 283415424
+    storage.modify_branch(&branches[2], NO_OP, 15906192, 8192); // at 299321616
+    storage.modify_branch(&branches[0], NO_OP, 18909976, 32768); // at 302325400
 
-    let size = storage.calculate(100_000)?;
+    let size = storage.calculate(100_000);
 
-    Ok((storage.into_segments(), size))
+    (storage.into_segments(), size)
 }
 
 fn main() {
@@ -163,8 +163,7 @@ fn main() {
             eprintln!("invalid scenario {}", other);
             std::process::exit(1);
         }
-    }
-    .unwrap();
+    };
 
     graphviz_tree(&segments, &size);
 }
@@ -252,7 +251,7 @@ fn graphviz_tree(segments: &[Segment], tree: &SegmentSize) {
 
 #[test]
 fn scenarios_return_same_size() {
-    type ScenarioFn = fn() -> anyhow::Result<(Vec<Segment>, SegmentSize)>;
+    type ScenarioFn = fn() -> (Vec<Segment>, SegmentSize);
     let truths: &[(u32, ScenarioFn, _)] = &[
         (line!(), scenario_1, 8000),
         (line!(), scenario_2, 9000),
@@ -263,7 +262,7 @@ fn scenarios_return_same_size() {
     ];
 
     for (line, scenario, expected) in truths {
-        let (_, size) = scenario().unwrap();
+        let (_, size) = scenario();
         assert_eq!(*expected, size.total_children(), "scenario on line {line}");
     }
 }

libs/tracing-utils/Cargo.toml

@@ -1,17 +0,0 @@
-[package]
-name = "tracing-utils"
-version = "0.1.0"
-edition.workspace = true
-license.workspace = true
-
-[dependencies]
-hyper.workspace = true
-opentelemetry = { workspace = true, features=["rt-tokio"] }
-opentelemetry-otlp = { workspace = true, default_features=false, features = ["http-proto", "trace", "http", "reqwest-client"] }
-opentelemetry-semantic-conventions.workspace = true
-reqwest = { workspace = true, default-features = false, features = ["rustls-tls"] }
-tokio = { workspace = true, features = ["rt", "rt-multi-thread"] }
-tracing.workspace = true
-tracing-opentelemetry.workspace = true
-tracing-subscriber.workspace = true
-workspace_hack = { version = "0.1", path = "../../workspace_hack" }

libs/tracing-utils/src/http.rs

@@ -1,96 +0,0 @@
-//! Tracing wrapper for Hyper HTTP server
-
-use hyper::HeaderMap;
-use hyper::{Body, Request, Response};
-use std::future::Future;
-use tracing::Instrument;
-use tracing_opentelemetry::OpenTelemetrySpanExt;
-
-/// Configuration option for what to use as the "otel.name" field in the traces.
-pub enum OtelName<'a> {
-    /// Use a constant string
-    Constant(&'a str),
-
-    /// Use the path from the request.
-    ///
-    /// That's very useful information, but is not appropriate if the
-    /// path contains parameters that differ on ever request, or worse,
-    /// sensitive information like usernames or email addresses.
-    ///
-    /// See <https://github.com/open-telemetry/opentelemetry-specification/blob/main/specification/trace/semantic_conventions/http.md#name>
-    UriPath,
-}
-
-/// Handle an incoming HTTP request using the given handler function,
-/// with OpenTelemetry tracing.
-///
-/// This runs 'handler' on the request in a new span, with fields filled in
-/// from the request. Notably, if the request contains tracing information,
-/// it is propagated to the span, so that this request is traced as part of
-/// the same trace.
-///
-/// XXX: Usually, this is handled by existing libraries, or built
-/// directly into HTTP servers. However, I couldn't find one for Hyper,
-/// so I had to write our own. OpenTelemetry website has a registry of
-/// instrumentation libraries at:
-/// https://opentelemetry.io/registry/?language=rust&component=instrumentation
-/// If a Hyper crate appears, consider switching to that.
-pub async fn tracing_handler<F, R>(
-    req: Request<Body>,
-    handler: F,
-    otel_name: OtelName<'_>,
-) -> Response<Body>
-where
-    F: Fn(Request<Body>) -> R,
-    R: Future<Output = Response<Body>>,
-{
-    // Create a tracing span, with context propagated from the incoming
-    // request if any.
-    //
-    // See list of standard fields defined for HTTP requests at
-    // https://github.com/open-telemetry/opentelemetry-specification/blob/main/specification/trace/semantic_conventions/http.md
-    // We only fill in a few of the most useful ones here.
-    let otel_name = match otel_name {
-        OtelName::Constant(s) => s,
-        OtelName::UriPath => req.uri().path(),
-    };
-
-    let span = tracing::info_span!(
-        "http request",
-        otel.name= %otel_name,
-        http.method = %req.method(),
-        http.status_code = tracing::field::Empty,
-    );
-    let parent_ctx = extract_remote_context(req.headers());
-    span.set_parent(parent_ctx);
-
-    // Handle the request within the span
-    let response = handler(req).instrument(span.clone()).await;
-
-    // Fill in the fields from the response code
-    let status = response.status();
-    span.record("http.status_code", status.as_str());
-    span.record(
-        "otel.status_code",
-        if status.is_success() { "OK" } else { "ERROR" },
-    );
-
-    response
-}
-
-// Extract remote tracing context from the HTTP headers
-fn extract_remote_context(headers: &HeaderMap) -> opentelemetry::Context {
-    struct HeaderExtractor<'a>(&'a HeaderMap);
-
-    impl<'a> opentelemetry::propagation::Extractor for HeaderExtractor<'a> {
-        fn get(&self, key: &str) -> Option<&str> {
-            self.0.get(key).and_then(|value| value.to_str().ok())
-        }
-
-        fn keys(&self) -> Vec<&str> {
-            self.0.keys().map(|value| value.as_str()).collect()
-        }
-    }
-    let extractor = HeaderExtractor(headers);
-    opentelemetry::global::get_text_map_propagator(|propagator| propagator.extract(&extractor))
-}

libs/tracing-utils/src/lib.rs

@@ -1,168 +0,0 @@
-//! Helper functions to set up OpenTelemetry tracing.
-//!
-//! This comes in two variants, depending on whether you have a Tokio runtime available.
-//! If you do, call `init_tracing()`. It sets up the trace processor and exporter to use
-//! the current tokio runtime. If you don't have a runtime available, or you don't want
-//! to share the runtime with the tracing tasks, call `init_tracing_without_runtime()`
-//! instead. It sets up a dedicated single-threaded Tokio runtime for the tracing tasks.
-//!
-//! Example:
-//!
-//! ```rust,no_run
-//! use tracing_subscriber::prelude::*;
-//! use tracing_opentelemetry::OpenTelemetryLayer;
-//!
-//! #[tokio::main]
-//! async fn main() {
-//!     // Set up logging to stderr
-//!     let env_filter = tracing_subscriber::EnvFilter::try_from_default_env()
-//!         .unwrap_or_else(|_| tracing_subscriber::EnvFilter::new("info"));
-//!     let fmt_layer = tracing_subscriber::fmt::layer()
-//!         .with_target(false)
-//!         .with_writer(std::io::stderr);
-//!
-//!     // Initialize OpenTelemetry. Exports tracing spans as OpenTelemetry traces
-//!     let otlp_layer = tracing_utils::init_tracing("my_application").await.map(OpenTelemetryLayer::new);
-//!
-//!     // Put it all together
-//!     tracing_subscriber::registry()
-//!         .with(env_filter)
-//!         .with(otlp_layer)
-//!         .with(fmt_layer)
-//!         .init();
-//! }
-//! ```
-
-use opentelemetry::sdk::Resource;
-use opentelemetry::KeyValue;
-use opentelemetry_otlp::WithExportConfig;
-use opentelemetry_otlp::{OTEL_EXPORTER_OTLP_ENDPOINT, OTEL_EXPORTER_OTLP_TRACES_ENDPOINT};
-
-pub use tracing_opentelemetry::OpenTelemetryLayer;
-
-pub mod http;
-
-/// Set up OpenTelemetry exporter, using configuration from environment variables.
-///
-/// `service_name` is set as the OpenTelemetry 'service.name' resource (see
-/// <https://github.com/open-telemetry/opentelemetry-specification/blob/main/specification/resource/semantic_conventions/README.md#service>)
-///
-/// We try to follow the conventions for the environment variables specified in
-/// <https://opentelemetry.io/docs/reference/specification/sdk-environment-variables/>
-///
-/// However, we only support a subset of those options:
-///
-/// - OTEL_SDK_DISABLED is supported. The default is "false", meaning tracing
-///   is enabled by default. Set it to "true" to disable.
-///
-/// - We use the OTLP exporter, with HTTP protocol. Most of the OTEL_EXPORTER_OTLP_*
-///   settings specified in
-///   <https://opentelemetry.io/docs/reference/specification/protocol/exporter/>
-///   are supported, as they are handled by the `opentelemetry-otlp` crate.
-///   Settings related to other exporters have no effect.
-///
-/// - Some other settings are supported by the `opentelemetry` crate.
-///
-/// If you need some other setting, please test if it works first. And perhaps
-/// add a comment in the list above to save the effort of testing for the next
-/// person.
-///
-/// This doesn't block, but is marked as 'async' to hint that this must be called in
-/// asynchronous execution context.
-pub async fn init_tracing(service_name: &str) -> Option<opentelemetry::sdk::trace::Tracer> {
-    if std::env::var("OTEL_SDK_DISABLED") == Ok("true".to_string()) {
-        return None;
-    };
-    Some(init_tracing_internal(service_name.to_string()))
-}
-
-/// Like `init_tracing`, but creates a separate tokio Runtime for the tracing
-/// tasks.
-pub fn init_tracing_without_runtime(
-    service_name: &str,
-) -> Option<opentelemetry::sdk::trace::Tracer> {
-    if std::env::var("OTEL_SDK_DISABLED") == Ok("true".to_string()) {
-        return None;
-    };
-
-    // The opentelemetry batch processor and the OTLP exporter needs a Tokio
-    // runtime. Create a dedicated runtime for them. One thread should be
-    // enough.
-    //
-    // (Alternatively, instead of batching, we could use the "simple
-    // processor", which doesn't need Tokio, and use "reqwest-blocking"
-    // feature for the OTLP exporter, which also doesn't need Tokio.  However,
-    // batching is considered best practice, and also I have the feeling that
-    // the non-Tokio codepaths in the opentelemetry crate are less used and
-    // might be more buggy, so better to stay on the well-beaten path.)
-    //
-    // We leak the runtime so that it keeps running after we exit the
-    // function.
-    let runtime = Box::leak(Box::new(
-        tokio::runtime::Builder::new_multi_thread()
-            .enable_all()
-            .thread_name("otlp runtime thread")
-            .worker_threads(1)
-            .build()
-            .unwrap(),
-    ));
-    let _guard = runtime.enter();
-
-    Some(init_tracing_internal(service_name.to_string()))
-}
-
-fn init_tracing_internal(service_name: String) -> opentelemetry::sdk::trace::Tracer {
-    // Set up exporter from the OTEL_EXPORTER_* environment variables
-    let mut exporter = opentelemetry_otlp::new_exporter().http().with_env();
-
-    // XXX opentelemetry-otlp v0.18.0 has a bug in how it uses the
-    // OTEL_EXPORTER_OTLP_ENDPOINT env variable. According to the
-    // OpenTelemetry spec at
-    // <https://github.com/open-telemetry/opentelemetry-specification/blob/main/specification/protocol/exporter.md#endpoint-urls-for-otlphttp>,
-    // the full exporter URL is formed by appending "/v1/traces" to the value
-    // of OTEL_EXPORTER_OTLP_ENDPOINT. However, opentelemetry-otlp only does
-    // that with the grpc-tonic exporter. Other exporters, like the HTTP
-    // exporter, use the URL from OTEL_EXPORTER_OTLP_ENDPOINT as is, without
-    // appending "/v1/traces".
-    //
-    // See https://github.com/open-telemetry/opentelemetry-rust/pull/950
-    //
-    // Work around that by checking OTEL_EXPORTER_OTLP_ENDPOINT, and setting
-    // the endpoint url with the "/v1/traces" path ourselves. If the bug is
-    // fixed in a later version, we can remove this code. But if we don't
-    // remember to remove this, it won't do any harm either, as the crate will
-    // just ignore the OTEL_EXPORTER_OTLP_ENDPOINT setting when the endpoint
-    // is set directly with `with_endpoint`.
-    if std::env::var(OTEL_EXPORTER_OTLP_TRACES_ENDPOINT).is_err() {
-        if let Ok(mut endpoint) = std::env::var(OTEL_EXPORTER_OTLP_ENDPOINT) {
-            if !endpoint.ends_with('/') {
-                endpoint.push('/');
-            }
-            endpoint.push_str("v1/traces");
-            exporter = exporter.with_endpoint(endpoint);
-        }
-    }
-
-    // Propagate trace information in the standard W3C TraceContext format.
-    opentelemetry::global::set_text_map_propagator(
-        opentelemetry::sdk::propagation::TraceContextPropagator::new(),
-    );
-
-    opentelemetry_otlp::new_pipeline()
-        .tracing()
-        .with_exporter(exporter)
-        .with_trace_config(
-            opentelemetry::sdk::trace::config().with_resource(Resource::new(vec![KeyValue::new(
-                opentelemetry_semantic_conventions::resource::SERVICE_NAME,
-                service_name,
-            )])),
-        )
-        .install_batch(opentelemetry::runtime::Tokio)
-        .expect("could not initialize opentelemetry exporter")
-}
-
-// Shutdown trace pipeline gracefully, so that it has a chance to send any
-// pending traces before we exit.
-pub fn shutdown_tracing() {
-    opentelemetry::global::shutdown_tracer_provider();
-}

libs/utils/Cargo.toml

@@ -1,52 +1,47 @@
 [package]
 name = "utils"
 version = "0.1.0"
-edition.workspace = true
-license.workspace = true
+edition = "2021"
 
 [dependencies]
-atty.workspace = true
-sentry.workspace = true
-async-trait.workspace = true
-anyhow.workspace = true
-bincode.workspace = true
-bytes.workspace = true
-heapless.workspace = true
-hyper = { workspace = true, features = ["full"] }
-routerify.workspace = true
-serde.workspace = true
-serde_json.workspace = true
-thiserror.workspace = true
-tokio.workspace = true
-tokio-rustls.workspace = true
-tracing.workspace = true
-tracing-subscriber = { workspace = true, features = ["json"] }
-nix.workspace = true
-signal-hook.workspace = true
-rand.workspace = true
-jsonwebtoken.workspace = true
-hex = { workspace = true, features = ["serde"] }
-rustls.workspace = true
-rustls-split.workspace = true
-git-version.workspace = true
-serde_with.workspace = true
-once_cell.workspace = true
-strum.workspace = true
-strum_macros.workspace = true
+sentry = "0.29.0"
+async-trait = "0.1"
+anyhow = "1.0"
+bincode = "1.3"
+bytes = "1.0.1"
+hyper = { version = "0.14.7", features = ["full"] }
+routerify = "3"
+serde = { version = "1.0", features = ["derive"] }
+serde_json = "1"
+thiserror = "1.0"
+tokio = { version = "1.17", features = ["macros"]}
+tokio-rustls = "0.23"
+tracing = "0.1"
+tracing-subscriber = { version = "0.3", features = ["env-filter", "json"] }
+nix = "0.25"
+signal-hook = "0.3.10"
+rand = "0.8.3"
+jsonwebtoken = "8"
+hex = { version = "0.4.3", features = ["serde"] }
+rustls = "0.20.2"
+rustls-split = "0.3.0"
+git-version = "0.3.5"
+serde_with = "2.0"
+once_cell = "1.13.0"
+strum = "0.24"
+strum_macros = "0.24"
 
-metrics.workspace = true
-pq_proto.workspace = true
-
-workspace_hack.workspace = true
-url.workspace = true
+metrics = { path = "../metrics" }
+pq_proto = { path = "../pq_proto" }
+workspace_hack = { version = "0.1", path = "../../workspace_hack" }
 
 [dev-dependencies]
-byteorder.workspace = true
-bytes.workspace = true
-hex-literal.workspace = true
-tempfile.workspace = true
-criterion.workspace = true
-rustls-pemfile.workspace = true
+byteorder = "1.4.3"
+bytes = "1.0.1"
+hex-literal = "0.3"
+tempfile = "3.2"
+criterion = "0.4"
+rustls-pemfile = "1"
 
 [[bench]]
 name = "benchmarks"