Merge branch 'main' into problame/batching-benchmark

.github/workflows/benchmarking.yml

@@ -558,12 +558,12 @@ jobs:
         arch=$(uname -m | sed 's/x86_64/amd64/g' | sed 's/aarch64/arm64/g')
 
         cd /home/nonroot
-        wget -q "https://apt.postgresql.org/pub/repos/apt/pool/main/p/postgresql-17/libpq5_17.1-1.pgdg110+1_${arch}.deb"
-        wget -q "https://apt.postgresql.org/pub/repos/apt/pool/main/p/postgresql-16/postgresql-client-16_16.5-1.pgdg110+1_${arch}.deb"
-        wget -q "https://apt.postgresql.org/pub/repos/apt/pool/main/p/postgresql-16/postgresql-16_16.5-1.pgdg110+1_${arch}.deb"
-        dpkg -x libpq5_17.1-1.pgdg110+1_${arch}.deb pg
-        dpkg -x postgresql-16_16.5-1.pgdg110+1_${arch}.deb pg
-        dpkg -x postgresql-client-16_16.5-1.pgdg110+1_${arch}.deb pg
+        wget -q "https://apt.postgresql.org/pub/repos/apt/pool/main/p/postgresql-17/libpq5_17.2-1.pgdg110+1_${arch}.deb"
+        wget -q "https://apt.postgresql.org/pub/repos/apt/pool/main/p/postgresql-16/postgresql-client-16_16.6-1.pgdg110+1_${arch}.deb"
+        wget -q "https://apt.postgresql.org/pub/repos/apt/pool/main/p/postgresql-16/postgresql-16_16.6-1.pgdg110+1_${arch}.deb"
+        dpkg -x libpq5_17.2-1.pgdg110+1_${arch}.deb pg
+        dpkg -x postgresql-16_16.6-1.pgdg110+1_${arch}.deb pg
+        dpkg -x postgresql-client-16_16.6-1.pgdg110+1_${arch}.deb pg
 
         mkdir -p /tmp/neon/pg_install/v16/bin
         ln -s /home/nonroot/pg/usr/lib/postgresql/16/bin/pgbench /tmp/neon/pg_install/v16/bin/pgbench

.github/workflows/report-workflow-stats-batch.yml

@@ -4,10 +4,12 @@ on:
   schedule:
     - cron: '*/15 * * * *'
     - cron: '25 0 * * *'
+    - cron: '25 1 * * 6'
 
 jobs:
-  gh-workflow-stats-batch:
-    name: GitHub Workflow Stats Batch
+  gh-workflow-stats-batch-2h:
+    name: GitHub Workflow Stats Batch 2 hours
+    if: github.event.schedule == '*/15 * * * *'
     runs-on: ubuntu-22.04
     permissions:
       actions: read
@@ -16,14 +18,36 @@ jobs:
       uses: neondatabase/gh-workflow-stats-action@v0.2.1
       with:
         db_uri: ${{ secrets.GH_REPORT_STATS_DB_RW_CONNSTR }}
-        db_table: "gh_workflow_stats_batch_neon"
+        db_table: "gh_workflow_stats_neon"
         gh_token: ${{ secrets.GITHUB_TOKEN }}
         duration: '2h'
-    - name: Export Workflow Run for the past 24 hours
-      if: github.event.schedule == '25 0 * * *'
+
+  gh-workflow-stats-batch-48h:
+    name: GitHub Workflow Stats Batch 48 hours
+    if: github.event.schedule == '25 0 * * *'
+    runs-on: ubuntu-22.04
+    permissions:
+      actions: read
+    steps:
+    - name: Export Workflow Run for the past 48 hours
+      uses: neondatabase/gh-workflow-stats-action@v0.2.1
+      with:
+        db_uri: ${{ secrets.GH_REPORT_STATS_DB_RW_CONNSTR }}
+        db_table: "gh_workflow_stats_neon"
+        gh_token: ${{ secrets.GITHUB_TOKEN }}
+        duration: '48h'
+
+  gh-workflow-stats-batch-30d:
+    name: GitHub Workflow Stats Batch 30 days
+    if: github.event.schedule == '25 1 * * 6'
+    runs-on: ubuntu-22.04
+    permissions:
+      actions: read
+    steps:
+    - name: Export Workflow Run for the past 30 days
       uses: neondatabase/gh-workflow-stats-action@v0.2.1
       with:
         db_uri: ${{ secrets.GH_REPORT_STATS_DB_RW_CONNSTR }}
-        db_table: "gh_workflow_stats_batch_neon"
+        db_table: "gh_workflow_stats_neon"
         gh_token: ${{ secrets.GITHUB_TOKEN }}
-        duration: '24h'
+        duration: '720h'

Cargo.toml

@@ -34,6 +34,7 @@ members = [
     "libs/vm_monitor",
     "libs/walproposer",
     "libs/wal_decoder",
+    "libs/postgres_initdb",
 ]
 
 [workspace.package]
@@ -57,6 +58,7 @@ async-trait = "0.1"
 aws-config = { version = "1.5", default-features = false, features=["rustls", "sso"] }
 aws-sdk-s3 = "1.52"
 aws-sdk-iam = "1.46.0"
+aws-sdk-kms = "1.47.0"
 aws-smithy-async = { version = "1.2.1", default-features = false, features=["rt-tokio"] }
 aws-smithy-types = "1.2"
 aws-credential-types = "1.2.0"
@@ -73,7 +75,7 @@ bytes = "1.0"
 camino = "1.1.6"
 cfg-if = "1.0.0"
 chrono = { version = "0.4", default-features = false, features = ["clock"] }
-clap = { version = "4.0", features = ["derive"] }
+clap = { version = "4.0", features = ["derive", "env"] }
 comfy-table = "7.1"
 const_format = "0.2"
 crc32c = "0.6"
@@ -106,7 +108,7 @@ hyper-util = "0.1"
 tokio-tungstenite = "0.21.0"
 indexmap = "2"
 indoc = "2"
-ipnet = "2.9.0"
+ipnet = "2.10.0"
 itertools = "0.10"
 itoa = "1.0.11"
 jsonwebtoken = "9"
@@ -154,7 +156,7 @@ sentry = { version = "0.32", default-features = false, features = ["backtrace",
 serde = { version = "1.0", features = ["derive"] }
 serde_json = "1"
 serde_path_to_error = "0.1"
-serde_with = "2.0"
+serde_with = { version = "2.0", features = [ "base64" ] }
 serde_assert = "0.5.0"
 sha2 = "0.10.2"
 signal-hook = "0.3"
@@ -213,12 +215,14 @@ tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", br
 compute_api = { version = "0.1", path = "./libs/compute_api/" }
 consumption_metrics = { version = "0.1", path = "./libs/consumption_metrics/" }
 metrics = { version = "0.1", path = "./libs/metrics/" }
+pageserver = { path = "./pageserver" }
 pageserver_api = { version = "0.1", path = "./libs/pageserver_api/" }
 pageserver_client = { path = "./pageserver/client" }
 pageserver_compaction = { version = "0.1", path = "./pageserver/compaction/" }
 postgres_backend = { version = "0.1", path = "./libs/postgres_backend/" }
 postgres_connection = { version = "0.1", path = "./libs/postgres_connection/" }
 postgres_ffi = { version = "0.1", path = "./libs/postgres_ffi/" }
+postgres_initdb = { path = "./libs/postgres_initdb" }
 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" }

compute/compute-node.Dockerfile

@@ -1243,7 +1243,7 @@ RUN make -j $(getconf _NPROCESSORS_ONLN) \
 
 #########################################################################################
 #
-# Compile and run the Neon-specific `compute_ctl` binary
+# Compile and run the Neon-specific `compute_ctl` and `fast_import` binaries
 #
 #########################################################################################
 FROM $REPOSITORY/$IMAGE:$TAG AS compute-tools
@@ -1264,6 +1264,7 @@ RUN cd compute_tools && mold -run cargo build --locked --profile release-line-de
 FROM debian:$DEBIAN_FLAVOR AS compute-tools-image
 
 COPY --from=compute-tools /home/nonroot/target/release-line-debug-size-lto/compute_ctl /usr/local/bin/compute_ctl
+COPY --from=compute-tools /home/nonroot/target/release-line-debug-size-lto/fast_import /usr/local/bin/fast_import
 
 #########################################################################################
 #
@@ -1458,6 +1459,7 @@ RUN mkdir /var/db && useradd -m -d /var/db/postgres postgres && \
 
 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
+COPY --from=compute-tools --chown=postgres /home/nonroot/target/release-line-debug-size-lto/fast_import /usr/local/bin/fast_import
 
 # pgbouncer and its config
 COPY --from=pgbouncer         /usr/local/pgbouncer/bin/pgbouncer /usr/local/bin/pgbouncer
@@ -1533,6 +1535,25 @@ RUN apt update && \
     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
 
+# s5cmd 2.2.2 from https://github.com/peak/s5cmd/releases/tag/v2.2.2
+# used by fast_import
+ARG TARGETARCH
+ADD https://github.com/peak/s5cmd/releases/download/v2.2.2/s5cmd_2.2.2_linux_$TARGETARCH.deb /tmp/s5cmd.deb
+RUN set -ex; \
+    \
+    # Determine the expected checksum based on TARGETARCH
+    if [ "${TARGETARCH}" = "amd64" ]; then \
+        CHECKSUM="392c385320cd5ffa435759a95af77c215553d967e4b1c0fffe52e4f14c29cf85"; \
+    elif [ "${TARGETARCH}" = "arm64" ]; then \
+        CHECKSUM="939bee3cf4b5604ddb00e67f8c157b91d7c7a5b553d1fbb6890fad32894b7b46"; \
+    else \
+        echo "Unsupported architecture: ${TARGETARCH}"; exit 1; \
+    fi; \
+    \
+    # Compute and validate the checksum
+    echo "${CHECKSUM}  /tmp/s5cmd.deb" | sha256sum -c -
+RUN dpkg -i /tmp/s5cmd.deb && rm /tmp/s5cmd.deb
+
 ENV LANG=en_US.utf8
 USER postgres
 ENTRYPOINT ["/usr/local/bin/compute_ctl"]

compute_tools/Cargo.toml

@@ -10,6 +10,10 @@ default = []
 testing = []
 
 [dependencies]
+base64.workspace = true
+aws-config.workspace = true
+aws-sdk-s3.workspace = true
+aws-sdk-kms.workspace = true
 anyhow.workspace = true
 camino.workspace = true
 chrono.workspace = true
@@ -27,6 +31,8 @@ opentelemetry.workspace = true
 opentelemetry_sdk.workspace = true
 postgres.workspace = true
 regex.workspace = true
+serde.workspace = true
+serde_with.workspace = true
 serde_json.workspace = true
 signal-hook.workspace = true
 tar.workspace = true
@@ -43,6 +49,7 @@ thiserror.workspace = true
 url.workspace = true
 prometheus.workspace = true
 
+postgres_initdb.workspace = true
 compute_api.workspace = true
 utils.workspace = true
 workspace_hack.workspace = true