Compare commits

..

16 Commits

Author SHA1 Message Date
Anastasia Lubennikova
dfe815a032 Fix sfcgal_version for v17 2024-10-08 11:56:36 +01:00
Anastasia Lubennikova
8c6a83659a fix typos 2024-10-07 13:47:55 +01:00
Anastasia Lubennikova
0151deb76a Build PostGIS 3.5.0 only for v17
because of sfcgal dependency issue.
See comments in compute/Dockerfile.compute-node
2024-10-07 13:38:16 +01:00
Anastasia Lubennikova
461a680d64 fix unit and plpgsql_check 2024-10-04 17:01:06 +01:00
Anastasia Lubennikova
3de2add040 enable ip4r and pg_ivm for v17 2024-10-04 16:28:06 +01:00
Anastasia Lubennikova
aa6500a64e fix test tar for plv8 2024-10-04 11:07:25 +01:00
Anastasia Lubennikova
9968aec2c5 Fix build dependency on debian bookworm for plv8 2024-10-03 16:05:54 +01:00
Anastasia Lubennikova
ad9800aa18 Fix plv8 build 2024-10-03 15:40:21 +01:00
Anastasia Lubennikova
29e032d326 Fix plv8 build 2024-10-03 12:53:14 +01:00
Anastasia Lubennikova
d754a70802 Merge branch 'main' into enable_v17_extensions 2024-10-03 11:31:08 +01:00
Anastasia Lubennikova
278fe5e736 fix postgis build 2024-10-03 11:23:44 +01:00
Anastasia Lubennikova
a72919e0ec fix typo in postgis build 2024-10-02 16:37:48 +01:00
Anastasia Lubennikova
5a195605ad Fix rdkit build 2024-10-02 15:45:24 +01:00
Anastasia Lubennikova
8d64d9cca4 Merge branch 'main' into enable_v17_extensions 2024-10-02 14:38:14 +01:00
Anastasia Lubennikova
321014d37a fix cgal version 2024-10-02 14:31:35 +01:00
Anastasia Lubennikova
e410e794d6 Enable support of extensions for v17
except for Rust extensions and
ones that do not have new release yet.

Add comments for each extension.
2024-10-02 13:53:55 +01:00
210 changed files with 2011 additions and 2767 deletions

View File

@@ -112,7 +112,7 @@ jobs:
# This isn't exhaustive, just the paths that are most directly compute-related.
# For example, compute_ctl also depends on libs/utils, but we don't trigger
# an e2e run on that.
vendor/*|pgxn/*|compute_tools/*|compute/Dockerfile.compute-node)
vendor/*|pgxn/*|compute_tools/*|libs/vm_monitor/*|compute/Dockerfile.compute-node)
platforms=$(echo "${platforms}" | jq --compact-output '. += ["k8s-neonvm"] | unique')
;;
*)

View File

@@ -1,10 +1,10 @@
/compute_tools/ @neondatabase/control-plane @neondatabase/compute
/compute_tools/vm_monitor/ @neondatabase/autoscaling
/storage_controller @neondatabase/storage
/libs/pageserver_api/ @neondatabase/storage
/libs/postgres_ffi/ @neondatabase/compute @neondatabase/storage
/libs/remote_storage/ @neondatabase/storage
/libs/safekeeper_api/ @neondatabase/storage
/libs/vm_monitor/ @neondatabase/autoscaling
/pageserver/ @neondatabase/storage
/pgxn/ @neondatabase/compute
/pgxn/neon/ @neondatabase/compute @neondatabase/storage

88
Cargo.lock generated
View File

@@ -668,20 +668,19 @@ dependencies = [
[[package]]
name = "axum"
version = "0.7.5"
version = "0.6.20"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3a6c9af12842a67734c9a2e355436e5d03b22383ed60cf13cd0c18fbfe3dcbcf"
checksum = "3b829e4e32b91e643de6eafe82b1d90675f5874230191a4ffbc1b336dec4d6bf"
dependencies = [
"async-trait",
"axum-core",
"axum-core 0.3.4",
"base64 0.21.1",
"bitflags 1.3.2",
"bytes",
"futures-util",
"http 1.1.0",
"http-body 1.0.0",
"http-body-util",
"hyper 1.4.1",
"hyper-util",
"http 0.2.9",
"http-body 0.4.5",
"hyper 0.14.30",
"itoa",
"matchit 0.7.0",
"memchr",
@@ -694,13 +693,56 @@ dependencies = [
"serde_path_to_error",
"serde_urlencoded",
"sha1",
"sync_wrapper 1.0.1",
"sync_wrapper 0.1.2",
"tokio",
"tokio-tungstenite",
"tower",
"tower-layer",
"tower-service",
"tracing",
]
[[package]]
name = "axum"
version = "0.7.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3a6c9af12842a67734c9a2e355436e5d03b22383ed60cf13cd0c18fbfe3dcbcf"
dependencies = [
"async-trait",
"axum-core 0.4.5",
"bytes",
"futures-util",
"http 1.1.0",
"http-body 1.0.0",
"http-body-util",
"itoa",
"matchit 0.7.0",
"memchr",
"mime",
"percent-encoding",
"pin-project-lite",
"rustversion",
"serde",
"sync_wrapper 1.0.1",
"tower",
"tower-layer",
"tower-service",
]
[[package]]
name = "axum-core"
version = "0.3.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "759fa577a247914fd3f7f76d62972792636412fbfd634cd452f6a385a74d2d2c"
dependencies = [
"async-trait",
"bytes",
"futures-util",
"http 0.2.9",
"http-body 0.4.5",
"mime",
"rustversion",
"tower-layer",
"tower-service",
]
[[package]]
@@ -721,7 +763,6 @@ dependencies = [
"sync_wrapper 1.0.1",
"tower-layer",
"tower-service",
"tracing",
]
[[package]]
@@ -1220,7 +1261,6 @@ version = "0.1.0"
dependencies = [
"anyhow",
"bytes",
"camino",
"cfg-if",
"chrono",
"clap",
@@ -6290,9 +6330,9 @@ dependencies = [
[[package]]
name = "tokio-tungstenite"
version = "0.21.0"
version = "0.20.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c83b561d025642014097b66e6c1bb422783339e0909e4429cde4749d1990bc38"
checksum = "2b2dbec703c26b00d74844519606ef15d09a7d6857860f84ad223dec002ddea2"
dependencies = [
"futures-util",
"log",
@@ -6359,7 +6399,7 @@ checksum = "877c5b330756d856ffcc4553ab34a5684481ade925ecc54bcd1bf02b1d0d4d52"
dependencies = [
"async-stream",
"async-trait",
"axum",
"axum 0.7.5",
"base64 0.22.1",
"bytes",
"h2 0.4.4",
@@ -6566,14 +6606,14 @@ checksum = "e421abadd41a4225275504ea4d6566923418b7f05506fbc9c0fe86ba7396114b"
[[package]]
name = "tungstenite"
version = "0.21.0"
version = "0.20.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9ef1a641ea34f399a848dea702823bbecfb4c486f911735368f1f137cb8257e1"
checksum = "9e3dac10fd62eaf6617d3a904ae222845979aec67c615d1c842b4002c7666fb9"
dependencies = [
"byteorder",
"bytes",
"data-encoding",
"http 1.1.0",
"http 0.2.9",
"httparse",
"log",
"rand 0.8.5",
@@ -6801,7 +6841,7 @@ name = "vm_monitor"
version = "0.1.0"
dependencies = [
"anyhow",
"axum",
"axum 0.6.20",
"cgroups-rs",
"clap",
"futures",
@@ -7260,8 +7300,12 @@ version = "0.1.0"
dependencies = [
"ahash",
"anyhow",
"axum",
"axum-core",
"aws-config",
"aws-runtime",
"aws-sigv4",
"aws-smithy-async",
"aws-smithy-http",
"aws-smithy-types",
"base64 0.21.1",
"base64ct",
"bytes",
@@ -7311,6 +7355,7 @@ dependencies = [
"regex-automata 0.4.3",
"regex-syntax 0.8.2",
"reqwest 0.12.4",
"rustls 0.21.11",
"scopeguard",
"serde",
"serde_json",
@@ -7334,6 +7379,7 @@ dependencies = [
"tracing",
"tracing-core",
"url",
"uuid",
"zeroize",
"zstd",
"zstd-safe",

View File

@@ -2,7 +2,6 @@
resolver = "2"
members = [
"compute_tools",
"compute_tools/vm_monitor",
"control_plane",
"control_plane/storcon_cli",
"pageserver",
@@ -32,6 +31,7 @@ members = [
"libs/remote_storage",
"libs/tracing-utils",
"libs/postgres_ffi/wal_craft",
"libs/vm_monitor",
"libs/walproposer",
]
@@ -53,7 +53,7 @@ azure_storage_blobs = { version = "0.19", default-features = false, features = [
flate2 = "1.0.26"
async-stream = "0.3"
async-trait = "0.1"
aws-config = { version = "1.5", default-features = false, features=["rustls", "sso"] }
aws-config = { version = "1.5", default-features = false, features=["rustls"] }
aws-sdk-s3 = "1.52"
aws-sdk-iam = "1.46.0"
aws-smithy-async = { version = "1.2.1", default-features = false, features=["rt-tokio"] }
@@ -61,7 +61,7 @@ aws-smithy-types = "1.2"
aws-credential-types = "1.2.0"
aws-sigv4 = { version = "1.2", features = ["sign-http"] }
aws-types = "1.3"
axum = { version = "0.7.5", features = ["ws"] }
axum = { version = "0.6.20", features = ["ws"] }
base64 = "0.13.0"
bincode = "1.3"
bindgen = "0.70"
@@ -99,10 +99,10 @@ http-types = { version = "2", default-features = false }
http-body-util = "0.1.2"
humantime = "2.1"
humantime-serde = "1.1.1"
hyper0 = { package = "hyper", version = "0.14" }
hyper = "1.4"
hyper = "0.14"
hyper_1 = { package = "hyper", version = "1.4" }
hyper-util = "0.1"
tokio-tungstenite = "0.21.0"
tokio-tungstenite = "0.20.0"
indexmap = "2"
indoc = "2"
ipnet = "2.9.0"
@@ -235,7 +235,7 @@ storage_controller_client = { path = "./storage_controller/client" }
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/" }
vm_monitor = { version = "0.1", path = "./compute_tools/vm_monitor/" }
vm_monitor = { version = "0.1", path = "./libs/vm_monitor/" }
walproposer = { version = "0.1", path = "./libs/walproposer/" }
## Common library dependency

View File

@@ -168,27 +168,27 @@ postgres-check-%: postgres-%
neon-pg-ext-%: postgres-%
+@echo "Compiling neon $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile install
+@echo "Compiling neon_walredo $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-walredo-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-walredo-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_walredo/Makefile install
+@echo "Compiling neon_rmgr $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-rmgr-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-rmgr-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_rmgr/Makefile install
+@echo "Compiling neon_test_utils $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_test_utils/Makefile install
+@echo "Compiling neon_utils $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-utils-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-utils-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_utils/Makefile install
@@ -220,7 +220,7 @@ neon-pg-clean-ext-%:
walproposer-lib: neon-pg-ext-v17
+@echo "Compiling walproposer-lib"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/walproposer-lib
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v17/bin/pg_config COPT='$(COPT)' \
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v17/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/walproposer-lib \
-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile walproposer-lib
cp $(POSTGRES_INSTALL_DIR)/v17/lib/libpgport.a $(POSTGRES_INSTALL_DIR)/build/walproposer-lib
@@ -333,7 +333,7 @@ postgres-%-pgindent: postgres-%-pg-bsd-indent postgres-%-typedefs.list
# Indent pxgn/neon.
.PHONY: neon-pgindent
neon-pgindent: postgres-v17-pg-bsd-indent neon-pg-ext-v17
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v17/bin/pg_config COPT='$(COPT)' \
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v17/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
FIND_TYPEDEF=$(ROOT_PROJECT_DIR)/vendor/postgres-v17/src/tools/find_typedef \
INDENT=$(POSTGRES_INSTALL_DIR)/build/v17/src/tools/pg_bsd_indent/pg_bsd_indent \
PGINDENT_SCRIPT=$(ROOT_PROJECT_DIR)/vendor/postgres-v17/src/tools/pgindent/pgindent \

View File

@@ -58,7 +58,7 @@ curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
1. Install XCode and dependencies
```
xcode-select --install
brew install protobuf openssl flex bison icu4c pkg-config m4
brew install protobuf openssl flex bison icu4c pkg-config
# add openssl to PATH, required for ed25519 keys generation in neon_local
echo 'export PATH="$(brew --prefix openssl)/bin:$PATH"' >> ~/.zshrc

View File

@@ -17,13 +17,14 @@ RUN case $DEBIAN_FLAVOR in \
# Version-specific installs for Bullseye (PG14-PG16):
# The h3_pg extension needs a cmake 3.20+, but Debian bullseye has 3.18.
# Install newer version (3.25) from backports.
# libstdc++-10-dev is required for plv8
bullseye*) \
echo "deb http://deb.debian.org/debian bullseye-backports main" > /etc/apt/sources.list.d/bullseye-backports.list; \
VERSION_INSTALLS="cmake/bullseye-backports cmake-data/bullseye-backports"; \
VERSION_INSTALLS="cmake/bullseye-backports cmake-data/bullseye-backports libstdc++-10-dev"; \
;; \
# Version-specific installs for Bookworm (PG17):
bookworm*) \
VERSION_INSTALLS="cmake"; \
VERSION_INSTALLS="cmake libstdc++-12-dev"; \
;; \
esac && \
apt update && \
@@ -109,13 +110,30 @@ RUN apt update && \
libcgal-dev libgdal-dev libgmp-dev libmpfr-dev libopenscenegraph-dev libprotobuf-c-dev \
protobuf-c-compiler xsltproc
# Postgis 3.5.0 requires SFCGAL 1.4+
#
# It would be nice to update all versions together, but we must solve the SFCGAL dependency first.
# SFCGAL > 1.3 requires CGAL > 5.2, Bullseye's libcgal-dev is 5.2
RUN case "${PG_VERSION}" in "v17") \
mkdir -p /sfcgal && \
echo "Postgis doensn't yet support PG17 (needs 3.4.3, if not higher)" && exit 0;; \
# and also we must check backward compatibility with older versions of PostGIS.
#
# To move faster, use newer versions only for v17
RUN case "${PG_VERSION}" in \
"v17") \
export SFCGAL_VERSION=1.4.1 \
export SFCGAL_CHECKSUM=1800c8a26241588f11cddcf433049e9b9aea902e923414d2ecef33a3295626c3 \
;; \
"v14" | "v15" | "v16") \
export SFCGAL_VERSION=1.3.10 \
export SFCGAL_CHECKSUM=4e39b3b2adada6254a7bdba6d297bb28e1a9835a9f879b74f37e2dab70203232 \
;; \
*) \
echo "unexpected PostgreSQL version" && exit 1 \
;; \
esac && \
wget https://gitlab.com/Oslandia/SFCGAL/-/archive/v1.3.10/SFCGAL-v1.3.10.tar.gz -O SFCGAL.tar.gz && \
echo "4e39b3b2adada6254a7bdba6d297bb28e1a9835a9f879b74f37e2dab70203232 SFCGAL.tar.gz" | sha256sum --check && \
mkdir -p /sfcgal && \
wget https://gitlab.com/sfcgal/SFCGAL/-/archive/v${SFCGAL_VERSION}/SFCGAL-v${SFCGAL_VERSION}.tar.gz -O SFCGAL.tar.gz && \
echo "${SFCGAL_CHECKSUM} SFCGAL.tar.gz" | sha256sum --check && \
mkdir sfcgal-src && cd sfcgal-src && tar xzf ../SFCGAL.tar.gz --strip-components=1 -C . && \
cmake -DCMAKE_BUILD_TYPE=Release . && make -j $(getconf _NPROCESSORS_ONLN) && \
DESTDIR=/sfcgal make install -j $(getconf _NPROCESSORS_ONLN) && \
@@ -123,18 +141,31 @@ RUN case "${PG_VERSION}" in "v17") \
ENV PATH="/usr/local/pgsql/bin:$PATH"
RUN case "${PG_VERSION}" in "v17") \
echo "Postgis doensn't yet support PG17 (needs 3.4.3, if not higher)" && exit 0;; \
# Postgis 3.5.0 supports v17
RUN case "${PG_VERSION}" in \
"v17") \
export POSTGIS_VERSION=3.5.0 \
export POSTGIS_CHECKSUM=ca698a22cc2b2b3467ac4e063b43a28413f3004ddd505bdccdd74c56a647f510 \
;; \
"v14" | "v15" | "v16") \
export POSTGIS_VERSION=3.3.3 \
export POSTGIS_CHECKSUM=74eb356e3f85f14233791013360881b6748f78081cc688ff9d6f0f673a762d13 \
;; \
*) \
echo "unexpected PostgreSQL version" && exit 1 \
;; \
esac && \
wget https://download.osgeo.org/postgis/source/postgis-3.3.3.tar.gz -O postgis.tar.gz && \
echo "74eb356e3f85f14233791013360881b6748f78081cc688ff9d6f0f673a762d13 postgis.tar.gz" | sha256sum --check && \
wget https://download.osgeo.org/postgis/source/postgis-${POSTGIS_VERSION}.tar.gz -O postgis.tar.gz && \
echo "${POSTGIS_CHECKSUM} postgis.tar.gz" | sha256sum --check && \
mkdir postgis-src && cd postgis-src && tar xzf ../postgis.tar.gz --strip-components=1 -C . && \
find /usr/local/pgsql -type f | sed 's|^/usr/local/pgsql/||' > /before.txt &&\
./autogen.sh && \
./configure --with-sfcgal=/usr/local/bin/sfcgal-config && \
make -j $(getconf _NPROCESSORS_ONLN) && \
make -j $(getconf _NPROCESSORS_ONLN) install && \
cd extensions/postgis && \
make clean && \
make -j $(getconf _NPROCESSORS_ONLN) && \
make -j $(getconf _NPROCESSORS_ONLN) install && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_raster.control && \
@@ -152,11 +183,10 @@ RUN case "${PG_VERSION}" in "v17") \
cp /usr/local/pgsql/share/extension/address_standardizer.control /extensions/postgis && \
cp /usr/local/pgsql/share/extension/address_standardizer_data_us.control /extensions/postgis
RUN case "${PG_VERSION}" in "v17") \
echo "v17 extensions are not supported yet. Quit" && exit 0;; \
esac && \
wget https://github.com/pgRouting/pgrouting/archive/v3.4.2.tar.gz -O pgrouting.tar.gz && \
echo "cac297c07d34460887c4f3b522b35c470138760fe358e351ad1db4edb6ee306e pgrouting.tar.gz" | sha256sum --check && \
# not version-specific
# last release v3.6.2 - Mar 30, 2023
RUN wget https://github.com/pgRouting/pgrouting/archive/v3.6.2.tar.gz -O pgrouting.tar.gz && \
echo "f4a1ed79d6f714e52548eca3bb8e5593c6745f1bde92eb5fb858efd8984dffa2 pgrouting.tar.gz" | sha256sum --check && \
mkdir pgrouting-src && cd pgrouting-src && tar xzf ../pgrouting.tar.gz --strip-components=1 -C . && \
mkdir build && cd build && \
cmake -DCMAKE_BUILD_TYPE=Release .. && \
@@ -178,18 +208,18 @@ FROM build-deps AS plv8-build
ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN case "${PG_VERSION}" in "v17") \
echo "v17 extensions are not supported yet. Quit" && exit 0;; \
esac && \
apt update && \
RUN apt update && \
apt install --no-install-recommends -y ninja-build python3-dev libncurses5 binutils clang
RUN case "${PG_VERSION}" in "v17") \
echo "v17 extensions are not supported yet. Quit" && exit 0;; \
esac && \
wget https://github.com/plv8/plv8/archive/refs/tags/v3.1.10.tar.gz -O plv8.tar.gz && \
echo "7096c3290928561f0d4901b7a52794295dc47f6303102fae3f8e42dd575ad97d plv8.tar.gz" | sha256sum --check && \
mkdir plv8-src && cd plv8-src && tar xzf ../plv8.tar.gz --strip-components=1 -C . && \
# plv8 3.2.3 supports v17
# last release v3.2.3 - Sep 7, 2024
# clone the repo instead of downloading the release tarball because plv8 has submodule dependencies
# and the release tarball doesn't include them
ENV PLV8_TAG=v3.2.3
RUN set -e \
&& git clone --recurse-submodules --depth 1 --branch ${PLV8_TAG} https://github.com/plv8/plv8.git plv8-src && \
tar -czf plv8.tar.gz --exclude .git plv8-src && \
cd plv8-src && \
# generate and copy upgrade scripts
mkdir -p upgrade && ./generate_upgrade.sh 3.1.10 && \
cp upgrade/* /usr/local/pgsql/share/extension/ && \
@@ -199,8 +229,10 @@ RUN case "${PG_VERSION}" in "v17") \
find /usr/local/pgsql/ -name "plv8-*.so" | xargs strip && \
# don't break computes with installed old version of plv8
cd /usr/local/pgsql/lib/ && \
ln -s plv8-3.1.10.so plv8-3.1.5.so && \
ln -s plv8-3.1.10.so plv8-3.1.8.so && \
# TODO test this case !!
ln -s plv8-3.2.3.so plv8-3.1.8.so && \
ln -s plv8-3.2.3.so plv8-3.1.5.so && \
ln -s plv8-3.2.3.so plv8-3.1.10.so && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/plv8.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/plcoffee.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/plls.control
@@ -215,10 +247,9 @@ FROM build-deps AS h3-pg-build
ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN case "${PG_VERSION}" in "v17") \
mkdir -p /h3/usr/ && \
echo "v17 extensions are not supported yet. Quit" && exit 0;; \
esac && \
# not version-specific
# last release v4.1.0 - Jan 18, 2023
RUN mkdir -p /h3/usr/ && \
wget https://github.com/uber/h3/archive/refs/tags/v4.1.0.tar.gz -O h3.tar.gz && \
echo "ec99f1f5974846bde64f4513cf8d2ea1b8d172d2218ab41803bf6a63532272bc h3.tar.gz" | sha256sum --check && \
mkdir h3-src && cd h3-src && tar xzf ../h3.tar.gz --strip-components=1 -C . && \
@@ -229,10 +260,9 @@ RUN case "${PG_VERSION}" in "v17") \
cp -R /h3/usr / && \
rm -rf build
RUN case "${PG_VERSION}" in "v17") \
echo "v17 extensions are not supported yet. Quit" && exit 0;; \
esac && \
wget https://github.com/zachasme/h3-pg/archive/refs/tags/v4.1.3.tar.gz -O h3-pg.tar.gz && \
# not version-specific
# last release v4.1.3 - Jul 26, 2023
RUN wget https://github.com/zachasme/h3-pg/archive/refs/tags/v4.1.3.tar.gz -O h3-pg.tar.gz && \
echo "5c17f09a820859ffe949f847bebf1be98511fb8f1bd86f94932512c00479e324 h3-pg.tar.gz" | sha256sum --check && \
mkdir h3-pg-src && cd h3-pg-src && tar xzf ../h3-pg.tar.gz --strip-components=1 -C . && \
export PATH="/usr/local/pgsql/bin:$PATH" && \
@@ -251,11 +281,10 @@ FROM build-deps AS unit-pg-build
ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN case "${PG_VERSION}" in "v17") \
echo "v17 extensions are not supported yet. Quit" && exit 0;; \
esac && \
wget https://github.com/df7cb/postgresql-unit/archive/refs/tags/7.7.tar.gz -O postgresql-unit.tar.gz && \
echo "411d05beeb97e5a4abf17572bfcfbb5a68d98d1018918feff995f6ee3bb03e79 postgresql-unit.tar.gz" | sha256sum --check && \
# not version-specific
# last release 7.9 - Sep 15, 2024
RUN wget https://github.com/df7cb/postgresql-unit/archive/refs/tags/7.9.tar.gz -O postgresql-unit.tar.gz && \
echo "e46de6245dcc8b2c2ecf29873dbd43b2b346773f31dd5ce4b8315895a052b456 postgresql-unit.tar.gz" | sha256sum --check && \
mkdir postgresql-unit-src && cd postgresql-unit-src && tar xzf ../postgresql-unit.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
@@ -281,6 +310,8 @@ COPY compute/patches/pgvector.patch /pgvector.patch
# By default, pgvector Makefile uses `-march=native`. We don't want that,
# because we build the images on different machines than where we run them.
# Pass OPTFLAGS="" to remove it.
#
# v17 is not supported yet because of upstream issue https://github.com/pgvector/pgvector/issues/669
RUN case "${PG_VERSION}" in "v17") \
echo "v17 extensions are not supported yet. Quit" && exit 0;; \
esac && \
@@ -302,12 +333,10 @@ FROM build-deps AS pgjwt-pg-build
ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
# 9742dab1b2f297ad3811120db7b21451bca2d3c9 made on 13/11/2021
RUN case "${PG_VERSION}" in "v17") \
echo "v17 extensions are not supported yet. Quit" && exit 0;; \
esac && \
wget https://github.com/michelp/pgjwt/archive/9742dab1b2f297ad3811120db7b21451bca2d3c9.tar.gz -O pgjwt.tar.gz && \
echo "cfdefb15007286f67d3d45510f04a6a7a495004be5b3aecb12cda667e774203f pgjwt.tar.gz" | sha256sum --check && \
# not version-specific
# doesn't use releases, last commit f3d82fd - Mar 2, 2023
RUN wget https://github.com/michelp/pgjwt/archive/f3d82fd30151e754e19ce5d6a06c71c20689ce3d.tar.gz -O pgjwt.tar.gz && \
echo "dae8ed99eebb7593b43013f6532d772b12dfecd55548d2673f2dfd0163f6d2b9 pgjwt.tar.gz" | sha256sum --check && \
mkdir pgjwt-src && cd pgjwt-src && tar xzf ../pgjwt.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/pgjwt.control
@@ -322,11 +351,10 @@ FROM build-deps AS hypopg-pg-build
ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN case "${PG_VERSION}" in "v17") \
echo "v17 extensions are not supported yet. Quit" && exit 0;; \
esac && \
wget https://github.com/HypoPG/hypopg/archive/refs/tags/1.4.0.tar.gz -O hypopg.tar.gz && \
echo "0821011743083226fc9b813c1f2ef5897a91901b57b6bea85a78e466187c6819 hypopg.tar.gz" | sha256sum --check && \
# HypoPG 1.4.1 supports v17
# last release 1.4.1 - Apr 28, 2024
RUN wget https://github.com/HypoPG/hypopg/archive/refs/tags/1.4.1.tar.gz -O hypopg.tar.gz && \
echo "9afe6357fd389d8d33fad81703038ce520b09275ec00153c6c89282bcdedd6bc hypopg.tar.gz" | sha256sum --check && \
mkdir hypopg-src && cd hypopg-src && tar xzf ../hypopg.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
@@ -342,10 +370,9 @@ FROM build-deps AS pg-hashids-pg-build
ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN case "${PG_VERSION}" in "v17") \
echo "v17 extensions are not supported yet. Quit" && exit 0;; \
esac && \
wget https://github.com/iCyberon/pg_hashids/archive/refs/tags/v1.2.1.tar.gz -O pg_hashids.tar.gz && \
# not version-specific
# last release v1.2.1 -Jan 12, 2018
RUN wget https://github.com/iCyberon/pg_hashids/archive/refs/tags/v1.2.1.tar.gz -O pg_hashids.tar.gz && \
echo "74576b992d9277c92196dd8d816baa2cc2d8046fe102f3dcd7f3c3febed6822a pg_hashids.tar.gz" | sha256sum --check && \
mkdir pg_hashids-src && cd pg_hashids-src && tar xzf ../pg_hashids.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config USE_PGXS=1 && \
@@ -363,7 +390,8 @@ ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
COPY compute/patches/rum.patch /rum.patch
# maybe version-specific
# last release 1.3.13 - Sep 19, 2022
RUN case "${PG_VERSION}" in "v17") \
echo "v17 extensions are not supported yet. Quit" && exit 0;; \
esac && \
@@ -385,11 +413,10 @@ FROM build-deps AS pgtap-pg-build
ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN case "${PG_VERSION}" in "v17") \
echo "v17 extensions are not supported yet. Quit" && exit 0;; \
esac && \
wget https://github.com/theory/pgtap/archive/refs/tags/v1.2.0.tar.gz -O pgtap.tar.gz && \
echo "9c7c3de67ea41638e14f06da5da57bac6f5bd03fea05c165a0ec862205a5c052 pgtap.tar.gz" | sha256sum --check && \
# pgtap 1.3.3 supports v17
# last release v1.3.3 - Apr 8, 2024
RUN wget https://github.com/theory/pgtap/archive/refs/tags/v1.3.3.tar.gz -O pgtap.tar.gz && \
echo "325ea79d0d2515bce96bce43f6823dcd3effbd6c54cb2a4d6c2384fffa3a14c7 pgtap.tar.gz" | sha256sum --check && \
mkdir pgtap-src && cd pgtap-src && tar xzf ../pgtap.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
@@ -405,10 +432,9 @@ FROM build-deps AS ip4r-pg-build
ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN case "${PG_VERSION}" in "v17") \
echo "v17 extensions are not supported yet. Quit" && exit 0;; \
esac && \
wget https://github.com/RhodiumToad/ip4r/archive/refs/tags/2.4.2.tar.gz -O ip4r.tar.gz && \
# not version-specific
# last release v2.4.2 - Jul 29, 2023
RUN wget https://github.com/RhodiumToad/ip4r/archive/refs/tags/2.4.2.tar.gz -O ip4r.tar.gz && \
echo "0f7b1f159974f49a47842a8ab6751aecca1ed1142b6d5e38d81b064b2ead1b4b ip4r.tar.gz" | sha256sum --check && \
mkdir ip4r-src && cd ip4r-src && tar xzf ../ip4r.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
@@ -425,10 +451,9 @@ FROM build-deps AS prefix-pg-build
ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN case "${PG_VERSION}" in "v17") \
echo "v17 extensions are not supported yet. Quit" && exit 0;; \
esac && \
wget https://github.com/dimitri/prefix/archive/refs/tags/v1.2.10.tar.gz -O prefix.tar.gz && \
# not version-specific
# last release v1.2.10 - Jul 5, 2023
RUN wget https://github.com/dimitri/prefix/archive/refs/tags/v1.2.10.tar.gz -O prefix.tar.gz && \
echo "4342f251432a5f6fb05b8597139d3ccde8dcf87e8ca1498e7ee931ca057a8575 prefix.tar.gz" | sha256sum --check && \
mkdir prefix-src && cd prefix-src && tar xzf ../prefix.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
@@ -445,10 +470,9 @@ FROM build-deps AS hll-pg-build
ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN case "${PG_VERSION}" in "v17") \
echo "v17 extensions are not supported yet. Quit" && exit 0;; \
esac && \
wget https://github.com/citusdata/postgresql-hll/archive/refs/tags/v2.18.tar.gz -O hll.tar.gz && \
# not version-specific
# last release v2.18 - Sep 15, 2023
RUN wget https://github.com/citusdata/postgresql-hll/archive/refs/tags/v2.18.tar.gz -O hll.tar.gz && \
echo "e2f55a6f4c4ab95ee4f1b4a2b73280258c5136b161fe9d059559556079694f0e hll.tar.gz" | sha256sum --check && \
mkdir hll-src && cd hll-src && tar xzf ../hll.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
@@ -465,11 +489,10 @@ FROM build-deps AS plpgsql-check-pg-build
ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN case "${PG_VERSION}" in "v17") \
echo "v17 extensions are not supported yet. Quit" && exit 0;; \
esac && \
wget https://github.com/okbob/plpgsql_check/archive/refs/tags/v2.5.3.tar.gz -O plpgsql_check.tar.gz && \
echo "6631ec3e7fb3769eaaf56e3dfedb829aa761abf163d13dba354b4c218508e1c0 plpgsql_check.tar.gz" | sha256sum --check && \
# plpgsql_check v2.7.11 supports v17
# last release v2.7.11 - Sep 16, 2024
RUN wget https://github.com/okbob/plpgsql_check/archive/refs/tags/v2.7.11.tar.gz -O plpgsql_check.tar.gz && \
echo "208933f8dbe8e0d2628eb3851e9f52e6892b8e280c63700c0f1ce7883625d172 plpgsql_check.tar.gz" | sha256sum --check && \
mkdir plpgsql_check-src && cd plpgsql_check-src && tar xzf ../plpgsql_check.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config USE_PGXS=1 && \
make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config USE_PGXS=1 && \
@@ -487,6 +510,8 @@ COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
ARG PG_VERSION
ENV PATH="/usr/local/pgsql/bin:$PATH"
# v17 is not supported yet. TimescaleDB 2.17.0 will support it
# https://github.com/timescale/timescaledb/issues/6949
RUN case "${PG_VERSION}" in "v17") \
echo "v17 extensions are not supported yet. Quit" && exit 0;; \
esac && \
@@ -521,10 +546,9 @@ COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
ARG PG_VERSION
ENV PATH="/usr/local/pgsql/bin:$PATH"
RUN case "${PG_VERSION}" in "v17") \
echo "v17 extensions are not supported yet. Quit" && exit 0;; \
esac && \
case "${PG_VERSION}" in \
# version-specific, has separate releases for each version
# TODO check minor upgrades for v14-16
RUN case "${PG_VERSION}" in \
"v14") \
export PG_HINT_PLAN_VERSION=14_1_4_1 \
export PG_HINT_PLAN_CHECKSUM=c3501becf70ead27f70626bce80ea401ceac6a77e2083ee5f3ff1f1444ec1ad1 \
@@ -538,7 +562,8 @@ RUN case "${PG_VERSION}" in "v17") \
export PG_HINT_PLAN_CHECKSUM=fc85a9212e7d2819d4ae4ac75817481101833c3cfa9f0fe1f980984e12347d00 \
;; \
"v17") \
echo "TODO: PG17 pg_hint_plan support" && exit 0 \
export PG_HINT_PLAN_VERSION=17_1_7_0 \
export PG_HINT_PLAN_CHECKSUM=06dd306328c67a4248f48403c50444f30959fb61ebe963248dbc2afb396fe600 \
;; \
*) \
echo "Export the valid PG_HINT_PLAN_VERSION variable" && exit 1 \
@@ -562,6 +587,9 @@ FROM build-deps AS pg-cron-pg-build
ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
# 1.6.4 available, supports v17
# FIXME: Why is it here? We don't support pg_cron...
# !Do not remove! We set it in shared_preload_libraries and computes will fail to start if library is not found.
ENV PATH="/usr/local/pgsql/bin/:$PATH"
RUN case "${PG_VERSION}" in "v17") \
echo "v17 extensions are not supported yet. Quit" && exit 0;; \
@@ -583,23 +611,21 @@ FROM build-deps AS rdkit-pg-build
ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN case "${PG_VERSION}" in "v17") \
echo "v17 extensions are not supported yet. Quit" && exit 0;; \
esac && \
apt-get update && \
RUN apt-get update && \
apt-get install --no-install-recommends -y \
libboost-iostreams1.74-dev \
libboost-regex1.74-dev \
libboost-serialization1.74-dev \
libboost-system1.74-dev \
#TODO check what exactly is needed
libboost-all-dev \
libeigen3-dev
# rdkit Release_2024_09_1 supports v17
# last release Release_2024_09_1 - Sep 27, 2024
ENV PATH="/usr/local/pgsql/bin/:/usr/local/pgsql/:$PATH"
RUN case "${PG_VERSION}" in "v17") \
echo "v17 extensions are not supported yet. Quit" && exit 0;; \
esac && \
wget https://github.com/rdkit/rdkit/archive/refs/tags/Release_2023_03_3.tar.gz -O rdkit.tar.gz && \
echo "bdbf9a2e6988526bfeb8c56ce3cdfe2998d60ac289078e2215374288185e8c8d rdkit.tar.gz" | sha256sum --check && \
RUN wget https://github.com/rdkit/rdkit/archive/refs/tags/Release_2024_09_1.tar.gz -O rdkit.tar.gz && \
echo "034c00d6e9de323506834da03400761ed8c3721095114369d06805409747a60f rdkit.tar.gz" | sha256sum --check && \
mkdir rdkit-src && cd rdkit-src && tar xzf ../rdkit.tar.gz --strip-components=1 -C . && \
cmake \
-D RDK_BUILD_CAIRO_SUPPORT=OFF \
@@ -638,12 +664,11 @@ FROM build-deps AS pg-uuidv7-pg-build
ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
# not version-specific
# last release v1.5.0 - Mar 21, 2024
ENV PATH="/usr/local/pgsql/bin/:$PATH"
RUN case "${PG_VERSION}" in "v17") \
echo "v17 extensions are not supported yet. Quit" && exit 0;; \
esac && \
wget https://github.com/fboulnois/pg_uuidv7/archive/refs/tags/v1.0.1.tar.gz -O pg_uuidv7.tar.gz && \
echo "0d0759ab01b7fb23851ecffb0bce27822e1868a4a5819bfd276101c716637a7a pg_uuidv7.tar.gz" | sha256sum --check && \
RUN wget https://github.com/fboulnois/pg_uuidv7/archive/refs/tags/v1.5.0.tar.gz -O pg_uuidv7.tar.gz && \
echo "5f53e5ce0fa4e01c1d489f736478224571d4b2b88eaf63186265e38f0b8d3d78 pg_uuidv7.tar.gz" | sha256sum --check && \
mkdir pg_uuidv7-src && cd pg_uuidv7-src && tar xzf ../pg_uuidv7.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) && \
make -j $(getconf _NPROCESSORS_ONLN) install && \
@@ -659,11 +684,10 @@ FROM build-deps AS pg-roaringbitmap-pg-build
ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
# not version-specific
# last release v0.5.4 - Jun 28, 2022
ENV PATH="/usr/local/pgsql/bin/:$PATH"
RUN case "${PG_VERSION}" in "v17") \
echo "v17 extensions is not supported yet by pg_roaringbitmap. Quit" && exit 0;; \
esac && \
wget https://github.com/ChenHuajun/pg_roaringbitmap/archive/refs/tags/v0.5.4.tar.gz -O pg_roaringbitmap.tar.gz && \
RUN wget https://github.com/ChenHuajun/pg_roaringbitmap/archive/refs/tags/v0.5.4.tar.gz -O pg_roaringbitmap.tar.gz && \
echo "b75201efcb1c2d1b014ec4ae6a22769cc7a224e6e406a587f5784a37b6b5a2aa pg_roaringbitmap.tar.gz" | sha256sum --check && \
mkdir pg_roaringbitmap-src && cd pg_roaringbitmap-src && tar xzf ../pg_roaringbitmap.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) && \
@@ -680,12 +704,11 @@ FROM build-deps AS pg-semver-pg-build
ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
# not version-specific
# last release v0.40.0 - Jul 22, 2024
ENV PATH="/usr/local/pgsql/bin/:$PATH"
RUN case "${PG_VERSION}" in "v17") \
echo "v17 is not supported yet by pg_semver. Quit" && exit 0;; \
esac && \
wget https://github.com/theory/pg-semver/archive/refs/tags/v0.32.1.tar.gz -O pg_semver.tar.gz && \
echo "fbdaf7512026d62eec03fad8687c15ed509b6ba395bff140acd63d2e4fbe25d7 pg_semver.tar.gz" | sha256sum --check && \
RUN wget https://github.com/theory/pg-semver/archive/refs/tags/v0.40.0.tar.gz -O pg_semver.tar.gz && \
echo "3e50bcc29a0e2e481e7b6d2bc937cadc5f5869f55d983b5a1aafeb49f5425cfc pg_semver.tar.gz" | sha256sum --check && \
mkdir pg_semver-src && cd pg_semver-src && tar xzf ../pg_semver.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) && \
make -j $(getconf _NPROCESSORS_ONLN) install && \
@@ -700,6 +723,8 @@ RUN case "${PG_VERSION}" in "v17") \
FROM build-deps AS pg-embedding-pg-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
# This is our extension, support stopped in favor of pgvector
# TODO: deprecate it
ARG PG_VERSION
ENV PATH="/usr/local/pgsql/bin/:$PATH"
RUN case "${PG_VERSION}" in \
@@ -726,6 +751,9 @@ FROM build-deps AS pg-anon-pg-build
ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
# This was experimental extension, that never got to real production.
# TODO deprecate it
# !Do not remove! It can be present in shared_preload_libraries and compute will fail to start if library is not found.
ENV PATH="/usr/local/pgsql/bin/:$PATH"
RUN case "${PG_VERSION}" in "v17") \
echo "postgresql_anonymizer does not yet support PG17" && exit 0;; \
@@ -880,6 +908,9 @@ RUN case "${PG_VERSION}" in "v17") \
mkdir pg_session_jwt-src && cd pg_session_jwt-src && tar xzf ../pg_session_jwt.tar.gz --strip-components=1 -C . && \
sed -i 's/pgrx = "=0.11.3"/pgrx = { version = "=0.11.3", features = [ "unsafe-postgres" ] }/g' Cargo.toml && \
cargo pgrx install --release
# it's needed to enable extension because it uses untrusted C language
# sed -i 's/superuser = false/superuser = true/g' /usr/local/pgsql/share/extension/pg_session_jwt.control && \
# echo "trusted = true" >> /usr/local/pgsql/share/extension/pg_session_jwt.control
#########################################################################################
#
@@ -892,13 +923,12 @@ FROM build-deps AS wal2json-pg-build
ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
# wal2json wal2json_2_6 supports v17
# last release wal2json_2_6 - Apr 25, 2024
ENV PATH="/usr/local/pgsql/bin/:$PATH"
RUN case "${PG_VERSION}" in "v17") \
echo "We'll need to update wal2json to 2.6+ for pg17 support" && exit 0;; \
esac && \
wget https://github.com/eulerto/wal2json/archive/refs/tags/wal2json_2_5.tar.gz && \
echo "b516653575541cf221b99cf3f8be9b6821f6dbcfc125675c85f35090f824f00e wal2json_2_5.tar.gz" | sha256sum --check && \
mkdir wal2json-src && cd wal2json-src && tar xzf ../wal2json_2_5.tar.gz --strip-components=1 -C . && \
RUN wget https://github.com/eulerto/wal2json/archive/refs/tags/wal2json_2_6.tar.gz -O wal2json.tar.gz && \
echo "18b4bdec28c74a8fc98a11c72de38378a760327ef8e5e42e975b0029eb96ba0d wal2json.tar.gz" | sha256sum --check && \
mkdir wal2json-src && cd wal2json-src && tar xzf ../wal2json.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) && \
make -j $(getconf _NPROCESSORS_ONLN) install
@@ -912,12 +942,11 @@ FROM build-deps AS pg-ivm-build
ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
# pg_ivm v1.9 supports v17
# last release v1.9 - Jul 31
ENV PATH="/usr/local/pgsql/bin/:$PATH"
RUN case "${PG_VERSION}" in "v17") \
echo "We'll need to update pg_ivm to 1.9+ for pg17 support" && exit 0;; \
esac && \
wget https://github.com/sraoss/pg_ivm/archive/refs/tags/v1.7.tar.gz -O pg_ivm.tar.gz && \
echo "ebfde04f99203c7be4b0e873f91104090e2e83e5429c32ac242d00f334224d5e pg_ivm.tar.gz" | sha256sum --check && \
RUN wget https://github.com/sraoss/pg_ivm/archive/refs/tags/v1.9.tar.gz -O pg_ivm.tar.gz && \
echo "59e15722939f274650abf637f315dd723c87073496ca77236b044cb205270d8b pg_ivm.tar.gz" | sha256sum --check && \
mkdir pg_ivm-src && cd pg_ivm-src && tar xzf ../pg_ivm.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) && \
make -j $(getconf _NPROCESSORS_ONLN) install && \
@@ -933,12 +962,11 @@ FROM build-deps AS pg-partman-build
ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
# should support v17 https://github.com/pgpartman/pg_partman/discussions/693
# last release 5.1.0 Apr 2, 2024
ENV PATH="/usr/local/pgsql/bin/:$PATH"
RUN case "${PG_VERSION}" in "v17") \
echo "pg_partman doesn't support PG17 yet" && exit 0;; \
esac && \
wget https://github.com/pgpartman/pg_partman/archive/refs/tags/v5.0.1.tar.gz -O pg_partman.tar.gz && \
echo "75b541733a9659a6c90dbd40fccb904a630a32880a6e3044d0c4c5f4c8a65525 pg_partman.tar.gz" | sha256sum --check && \
RUN wget https://github.com/pgpartman/pg_partman/archive/refs/tags/v5.1.0.tar.gz -O pg_partman.tar.gz && \
echo "3e3a27d7ff827295d5c55ef72f07a49062d6204b3cb0b9a048645d6db9f3cb9f pg_partman.tar.gz" | sha256sum --check && \
mkdir pg_partman-src && cd pg_partman-src && tar xzf ../pg_partman.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) && \
make -j $(getconf _NPROCESSORS_ONLN) install && \
@@ -1075,20 +1103,6 @@ RUN set -e \
&& make -j $(nproc) dist_man_MANS= \
&& make install dist_man_MANS=
#########################################################################################
#
# Compile the Neon-specific `local_proxy` binary
#
#########################################################################################
FROM $REPOSITORY/$IMAGE:$TAG AS local_proxy
ARG BUILD_TAG
ENV BUILD_TAG=$BUILD_TAG
USER nonroot
# Copy entire project to get Cargo.* files with proper dependencies for the whole project
COPY --chown=nonroot . .
RUN mold -run cargo build --locked --profile release-line-debug-size-lto --bin local_proxy
#########################################################################################
#
# Layers "postgres-exporter" and "sql-exporter"
@@ -1227,10 +1241,6 @@ COPY --from=compute-tools --chown=postgres /home/nonroot/target/release-line-deb
COPY --from=pgbouncer /usr/local/pgbouncer/bin/pgbouncer /usr/local/bin/pgbouncer
COPY --chmod=0666 --chown=postgres compute/etc/pgbouncer.ini /etc/pgbouncer.ini
# local_proxy and its config
COPY --from=local_proxy --chown=postgres /home/nonroot/target/release-line-debug-size-lto/local_proxy /usr/local/bin/local_proxy
RUN mkdir -p /etc/local_proxy && chown postgres:postgres /etc/local_proxy
# Metrics exporter binaries and configuration files
COPY --from=postgres-exporter /bin/postgres_exporter /bin/postgres_exporter
COPY --from=sql-exporter /bin/sql_exporter /bin/sql_exporter

View File

@@ -19,10 +19,6 @@ commands:
user: postgres
sysvInitAction: respawn
shell: '/usr/local/bin/pgbouncer /etc/pgbouncer.ini'
- name: local_proxy
user: postgres
sysvInitAction: respawn
shell: '/usr/local/bin/local_proxy --config-path /etc/local_proxy/config.json --pid-path /etc/local_proxy/pid --http 0.0.0.0:10432'
- name: postgres-exporter
user: nobody
sysvInitAction: respawn

View File

@@ -11,13 +11,12 @@ testing = []
[dependencies]
anyhow.workspace = true
camino.workspace = true
chrono.workspace = true
cfg-if.workspace = true
clap.workspace = true
flate2.workspace = true
futures.workspace = true
hyper0 = { workspace = true, features = ["full"] }
hyper = { workspace = true, features = ["full"] }
nix.workspace = true
notify.workspace = true
num_cpus.workspace = true
@@ -44,7 +43,7 @@ compute_api.workspace = true
utils.workspace = true
workspace_hack.workspace = true
remote_storage = { version = "0.1", path = "../libs/remote_storage/" }
vm_monitor = { version = "0.1", path = "vm_monitor/" }
vm_monitor = { version = "0.1", path = "../libs/vm_monitor/" }
zstd = "0.13"
bytes = "1.0"
rust-ini = "0.20.0"

View File

@@ -20,7 +20,7 @@ Also `compute_ctl` spawns two separate service threads:
last activity requests.
If `AUTOSCALING` environment variable is set, `compute_ctl` will start the
`vm-monitor` located in [`neon/compute_tools/vm_monitor`]. For VM compute nodes,
`vm-monitor` located in [`neon/libs/vm_monitor`]. For VM compute nodes,
`vm-monitor` communicates with the VM autoscaling system. It coordinates
downscaling and requests immediate upscaling under resource pressure.

View File

@@ -21,7 +21,7 @@
//! last activity requests.
//!
//! If `AUTOSCALING` environment variable is set, `compute_ctl` will start the
//! `vm-monitor` located in [`neon/compute_tools/vm_monitor`]. For VM compute nodes,
//! `vm-monitor` located in [`neon/libs/vm_monitor`]. For VM compute nodes,
//! `vm-monitor` communicates with the VM autoscaling system. It coordinates
//! downscaling and requests immediate upscaling under resource pressure.
//!
@@ -402,7 +402,8 @@ fn start_postgres(
) -> Result<(Option<PostgresHandle>, StartPostgresResult)> {
// We got all we need, update the state.
let mut state = compute.state.lock().unwrap();
state.set_status(ComputeStatus::Init, &compute.state_changed);
state.status = ComputeStatus::Init;
compute.state_changed.notify_all();
info!(
"running compute with features: {:?}",

View File

@@ -34,7 +34,6 @@ use nix::sys::signal::{kill, Signal};
use remote_storage::{DownloadError, RemotePath};
use crate::checker::create_availability_check_data;
use crate::local_proxy;
use crate::logger::inlinify;
use crate::pg_helpers::*;
use crate::spec::*;
@@ -109,18 +108,6 @@ impl ComputeState {
metrics: ComputeMetrics::default(),
}
}
pub fn set_status(&mut self, status: ComputeStatus, state_changed: &Condvar) {
let prev = self.status;
info!("Changing compute status from {} to {}", prev, status);
self.status = status;
state_changed.notify_all();
}
pub fn set_failed_status(&mut self, err: anyhow::Error, state_changed: &Condvar) {
self.error = Some(format!("{err:?}"));
self.set_status(ComputeStatus::Failed, state_changed);
}
}
impl Default for ComputeState {
@@ -315,12 +302,15 @@ impl ComputeNode {
pub fn set_status(&self, status: ComputeStatus) {
let mut state = self.state.lock().unwrap();
state.set_status(status, &self.state_changed);
state.status = status;
self.state_changed.notify_all();
}
pub fn set_failed_status(&self, err: anyhow::Error) {
let mut state = self.state.lock().unwrap();
state.set_failed_status(err, &self.state_changed);
state.error = Some(format!("{err:?}"));
state.status = ComputeStatus::Failed;
self.state_changed.notify_all();
}
pub fn get_status(&self) -> ComputeStatus {
@@ -896,11 +886,6 @@ impl ComputeNode {
// 'Close' connection
drop(client);
if let Some(ref local_proxy) = spec.local_proxy_config {
info!("configuring local_proxy");
local_proxy::configure(local_proxy).context("apply_config local_proxy")?;
}
// Run migrations separately to not hold up cold starts
thread::spawn(move || {
let mut connstr = connstr.clone();
@@ -951,19 +936,6 @@ impl ComputeNode {
});
}
if let Some(ref local_proxy) = spec.local_proxy_config {
info!("configuring local_proxy");
// Spawn a thread to do the configuration,
// so that we don't block the main thread that starts Postgres.
let local_proxy = local_proxy.clone();
let _handle = Some(thread::spawn(move || {
if let Err(err) = local_proxy::configure(&local_proxy) {
error!("error while configuring local_proxy: {err:?}");
}
}));
}
// Write new config
let pgdata_path = Path::new(&self.pgdata);
let postgresql_conf_path = pgdata_path.join("postgresql.conf");
@@ -1051,19 +1023,6 @@ impl ComputeNode {
});
}
if let Some(local_proxy) = &pspec.spec.local_proxy_config {
info!("configuring local_proxy");
// Spawn a thread to do the configuration,
// so that we don't block the main thread that starts Postgres.
let local_proxy = local_proxy.clone();
let _handle = thread::spawn(move || {
if let Err(err) = local_proxy::configure(&local_proxy) {
error!("error while configuring local_proxy: {err:?}");
}
});
}
info!(
"start_compute spec.remote_extensions {:?}",
pspec.spec.remote_extensions

View File

@@ -24,7 +24,8 @@ fn configurator_main_loop(compute: &Arc<ComputeNode>) {
// Re-check the status after waking up
if state.status == ComputeStatus::ConfigurationPending {
info!("got configuration request");
state.set_status(ComputeStatus::Configuration, &compute.state_changed);
state.status = ComputeStatus::Configuration;
compute.state_changed.notify_all();
drop(state);
let mut new_status = ComputeStatus::Failed;

View File

@@ -288,7 +288,8 @@ async fn handle_configure_request(
return Err((msg, StatusCode::PRECONDITION_FAILED));
}
state.pspec = Some(parsed_spec);
state.set_status(ComputeStatus::ConfigurationPending, &compute.state_changed);
state.status = ComputeStatus::ConfigurationPending;
compute.state_changed.notify_all();
drop(state);
info!("set new spec and notified waiters");
}
@@ -361,15 +362,15 @@ async fn handle_terminate_request(compute: &Arc<ComputeNode>) -> Result<(), (Str
}
if state.status != ComputeStatus::Empty && state.status != ComputeStatus::Running {
let msg = format!(
"invalid compute status for termination request: {}",
state.status
"invalid compute status for termination request: {:?}",
state.status.clone()
);
return Err((msg, StatusCode::PRECONDITION_FAILED));
}
state.set_status(ComputeStatus::TerminationPending, &compute.state_changed);
state.status = ComputeStatus::TerminationPending;
compute.state_changed.notify_all();
drop(state);
}
forward_termination_signal();
info!("sent signal and notified waiters");
@@ -383,8 +384,7 @@ async fn handle_terminate_request(compute: &Arc<ComputeNode>) -> Result<(), (Str
while state.status != ComputeStatus::Terminated {
state = c.state_changed.wait(state).unwrap();
info!(
"waiting for compute to become {}, current status: {:?}",
ComputeStatus::Terminated,
"waiting for compute to become Terminated, current status: {:?}",
state.status
);
}

View File

@@ -2,9 +2,6 @@
//! configuration.
#![deny(unsafe_code)]
#![deny(clippy::undocumented_unsafe_blocks)]
extern crate hyper0 as hyper;
pub mod checker;
pub mod config;
pub mod configurator;
@@ -15,7 +12,6 @@ pub mod catalog;
pub mod compute;
pub mod disk_quota;
pub mod extension_server;
pub mod local_proxy;
pub mod lsn_lease;
mod migration;
pub mod monitor;

View File

@@ -1,56 +0,0 @@
//! Local Proxy is a feature of our BaaS Neon Authorize project.
//!
//! Local Proxy validates JWTs and manages the pg_session_jwt extension.
//! It also maintains a connection pool to postgres.
use anyhow::{Context, Result};
use camino::Utf8Path;
use compute_api::spec::LocalProxySpec;
use nix::sys::signal::Signal;
use utils::pid_file::{self, PidFileRead};
pub fn configure(local_proxy: &LocalProxySpec) -> Result<()> {
write_local_proxy_conf("/etc/local_proxy/config.json".as_ref(), local_proxy)?;
notify_local_proxy("/etc/local_proxy/pid".as_ref())?;
Ok(())
}
/// Create or completely rewrite configuration file specified by `path`
fn write_local_proxy_conf(path: &Utf8Path, local_proxy: &LocalProxySpec) -> Result<()> {
let config =
serde_json::to_string_pretty(local_proxy).context("serializing LocalProxySpec to json")?;
std::fs::write(path, config).with_context(|| format!("writing {path}"))?;
Ok(())
}
/// Notify local proxy about a new config file.
fn notify_local_proxy(path: &Utf8Path) -> Result<()> {
match pid_file::read(path)? {
// if the file doesn't exist, or isn't locked, local_proxy isn't running
// and will naturally pick up our config later
PidFileRead::NotExist | PidFileRead::NotHeldByAnyProcess(_) => {}
PidFileRead::LockedByOtherProcess(pid) => {
// From the pid_file docs:
//
// > 1. The other process might exit at any time, turning the given PID stale.
// > 2. There is a small window in which `claim_for_current_process` has already
// > locked the file but not yet updates its contents. [`read`] will return
// > this variant here, but with the old file contents, i.e., a stale PID.
// >
// > The kernel is free to recycle PID once it has been `wait(2)`ed upon by
// > its creator. Thus, acting upon a stale PID, e.g., by issuing a `kill`
// > system call on it, bears the risk of killing an unrelated process.
// > This is an inherent limitation of using pidfiles.
// > The only race-free solution is to have a supervisor-process with a lifetime
// > that exceeds that of all of its child-processes (e.g., `runit`, `supervisord`).
//
// This is an ok risk as we only send a SIGHUP which likely won't actually
// kill the process, only reload config.
nix::sys::signal::kill(pid, Signal::SIGHUP).context("sending signal to local_proxy")?;
}
}
Ok(())
}

View File

@@ -1,4 +1,3 @@
use std::collections::HashSet;
use std::fs::File;
use std::path::Path;
use std::str::FromStr;
@@ -190,15 +189,6 @@ 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)?;
let mut jwks_roles = HashSet::new();
if let Some(local_proxy) = &spec.local_proxy_config {
for jwks_setting in local_proxy.jwks.iter().flatten() {
for role_name in &jwks_setting.role_names {
jwks_roles.insert(role_name.clone());
}
}
}
// Print a list of existing Postgres roles (only in debug mode)
if span_enabled!(Level::INFO) {
let mut vec = Vec::new();
@@ -318,9 +308,6 @@ pub fn handle_roles(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
"CREATE ROLE {} INHERIT CREATEROLE CREATEDB BYPASSRLS REPLICATION IN ROLE neon_superuser",
name.pg_quote()
);
if jwks_roles.contains(name.as_str()) {
query = format!("CREATE ROLE {}", name.pg_quote());
}
info!("running role create query: '{}'", &query);
query.push_str(&role.to_pg_options());
xact.execute(query.as_str(), &[])?;

View File

@@ -14,7 +14,7 @@ humantime.workspace = true
nix.workspace = true
once_cell.workspace = true
humantime-serde.workspace = true
hyper0.workspace = true
hyper.workspace = true
regex.workspace = true
reqwest = { workspace = true, features = ["blocking", "json"] }
scopeguard.workspace = true

View File

@@ -599,7 +599,6 @@ impl Endpoint {
remote_extensions,
pgbouncer_settings: None,
shard_stripe_size: Some(shard_stripe_size),
local_proxy_config: None,
};
let spec_path = self.endpoint_path().join("spec.json");
std::fs::write(spec_path, serde_json::to_string_pretty(&spec)?)?;

View File

@@ -3,7 +3,7 @@ use crate::{
local_env::{LocalEnv, NeonStorageControllerConf},
};
use camino::{Utf8Path, Utf8PathBuf};
use hyper0::Uri;
use hyper::Uri;
use nix::unistd::Pid;
use pageserver_api::{
controller_api::{

View File

@@ -5,7 +5,7 @@
Currently we build two main images:
- [neondatabase/neon](https://hub.docker.com/repository/docker/neondatabase/neon) — image with pre-built `pageserver`, `safekeeper` and `proxy` binaries and all the required runtime dependencies. Built from [/Dockerfile](/Dockerfile).
- [neondatabase/compute-node-v16](https://hub.docker.com/repository/docker/neondatabase/compute-node-v16) — compute node image with pre-built Postgres binaries from [neondatabase/postgres](https://github.com/neondatabase/postgres). Similar images exist for v15 and v14. Built from [/compute-node/Dockerfile](/compute/Dockerfile.compute-node).
- [neondatabase/compute-node-v16](https://hub.docker.com/repository/docker/neondatabase/compute-node-v16) — compute node image with pre-built Postgres binaries from [neondatabase/postgres](https://github.com/neondatabase/postgres). Similar images exist for v15 and v14.
And additional intermediate image:

View File

@@ -1,7 +1,5 @@
//! Structs representing the JSON formats used in the compute_ctl's HTTP API.
use std::fmt::Display;
use chrono::{DateTime, Utc};
use serde::{Deserialize, Serialize, Serializer};
@@ -60,21 +58,6 @@ pub enum ComputeStatus {
Terminated,
}
impl Display for ComputeStatus {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
match self {
ComputeStatus::Empty => f.write_str("empty"),
ComputeStatus::ConfigurationPending => f.write_str("configuration-pending"),
ComputeStatus::Init => f.write_str("init"),
ComputeStatus::Running => f.write_str("running"),
ComputeStatus::Configuration => f.write_str("configuration"),
ComputeStatus::Failed => f.write_str("failed"),
ComputeStatus::TerminationPending => f.write_str("termination-pending"),
ComputeStatus::Terminated => f.write_str("terminated"),
}
}
}
fn rfc3339_serialize<S>(x: &Option<DateTime<Utc>>, s: S) -> Result<S::Ok, S::Error>
where
S: Serializer,

View File

@@ -106,10 +106,6 @@ pub struct ComputeSpec {
// Stripe size for pageserver sharding, in pages
#[serde(default)]
pub shard_stripe_size: Option<usize>,
/// Local Proxy configuration used for JWT authentication
#[serde(default)]
pub local_proxy_config: Option<LocalProxySpec>,
}
/// Feature flag to signal `compute_ctl` to enable certain experimental functionality.
@@ -282,13 +278,11 @@ pub struct GenericOption {
/// declare a `trait` on it.
pub type GenericOptions = Option<Vec<GenericOption>>;
/// Configured the local_proxy application with the relevant JWKS and roles it should
/// Configured the local-proxy application with the relevant JWKS and roles it should
/// use for authorizing connect requests using JWT.
#[derive(Clone, Debug, Deserialize, Serialize)]
pub struct LocalProxySpec {
#[serde(default)]
#[serde(skip_serializing_if = "Option::is_none")]
pub jwks: Option<Vec<JwksSettings>>,
pub jwks: Vec<JwksSettings>,
}
#[derive(Clone, Debug, Deserialize, Serialize)]

View File

@@ -296,14 +296,7 @@ pub mod defaults {
pub const DEFAULT_INGEST_BATCH_SIZE: u64 = 100;
/// Soft limit for the maximum size of a vectored read.
///
/// This is determined by the largest NeonWalRecord that can exist (minus dbdir and reldir keys
/// which are bounded by the blob io limits only). As of this writing, that is a `NeonWalRecord::ClogSetCommitted` record,
/// with 32k xids. That's the max number of XIDS on a single CLOG page. The size of such a record
/// is `sizeof(Transactionid) * 32768 + (some fixed overhead from 'timestamp`, the Vec length and whatever extra serde serialization adds)`.
/// That is, slightly above 128 kB.
pub const DEFAULT_MAX_VECTORED_READ_BYTES: usize = 130 * 1024; // 130 KiB
pub const DEFAULT_MAX_VECTORED_READ_BYTES: usize = 128 * 1024; // 128 KiB
pub const DEFAULT_IMAGE_COMPRESSION: ImageCompressionAlgorithm =
ImageCompressionAlgorithm::Zstd { level: Some(1) };

View File

@@ -748,16 +748,6 @@ impl Key {
self.field1 == 0x00 && self.field4 != 0 && self.field6 != 0xffffffff
}
#[inline(always)]
pub fn is_rel_dir_key(&self) -> bool {
self.field1 == 0x00
&& self.field2 != 0
&& self.field3 != 0
&& self.field4 == 0
&& self.field5 == 0
&& self.field6 == 1
}
/// Guaranteed to return `Ok()` if [`Self::is_rel_block_key`] returns `true` for `key`.
#[inline(always)]
pub fn to_rel_block(self) -> anyhow::Result<(RelTag, BlockNumber)> {

View File

@@ -16,7 +16,7 @@ aws-sdk-s3.workspace = true
bytes.workspace = true
camino = { workspace = true, features = ["serde1"] }
humantime-serde.workspace = true
hyper0 = { workspace = true, features = ["stream"] }
hyper = { workspace = true, features = ["stream"] }
futures.workspace = true
serde.workspace = true
serde_json.workspace = true

View File

@@ -14,7 +14,7 @@ use std::time::SystemTime;
use super::REMOTE_STORAGE_PREFIX_SEPARATOR;
use anyhow::Result;
use azure_core::request_options::{IfMatchCondition, MaxResults, Metadata, Range};
use azure_core::request_options::{MaxResults, Metadata, Range};
use azure_core::{Continuable, RetryOptions};
use azure_identity::DefaultAzureCredential;
use azure_storage::StorageCredentials;
@@ -33,10 +33,10 @@ use tracing::debug;
use utils::backoff;
use crate::metrics::{start_measuring_requests, AttemptOutcome, RequestKind};
use crate::ListingObject;
use crate::{
config::AzureConfig, error::Cancelled, ConcurrencyLimiter, Download, DownloadError,
DownloadOpts, Listing, ListingMode, ListingObject, RemotePath, RemoteStorage, StorageMetadata,
TimeTravelError, TimeoutOrCancel,
config::AzureConfig, error::Cancelled, ConcurrencyLimiter, Download, DownloadError, Listing,
ListingMode, RemotePath, RemoteStorage, StorageMetadata, TimeTravelError, TimeoutOrCancel,
};
pub struct AzureBlobStorage {
@@ -259,7 +259,6 @@ fn to_download_error(error: azure_core::Error) -> DownloadError {
if let Some(http_err) = error.as_http_error() {
match http_err.status() {
StatusCode::NotFound => DownloadError::NotFound,
StatusCode::NotModified => DownloadError::Unmodified,
StatusCode::BadRequest => DownloadError::BadInput(anyhow::Error::new(error)),
_ => DownloadError::Other(anyhow::Error::new(error)),
}
@@ -485,16 +484,11 @@ impl RemoteStorage for AzureBlobStorage {
async fn download(
&self,
from: &RemotePath,
opts: &DownloadOpts,
cancel: &CancellationToken,
) -> Result<Download, DownloadError> {
let blob_client = self.client.blob_client(self.relative_path_to_name(from));
let mut builder = blob_client.get();
if let Some(ref etag) = opts.etag {
builder = builder.if_match(IfMatchCondition::NotMatch(etag.to_string()))
}
let builder = blob_client.get();
self.download_for_builder(builder, cancel).await
}

View File

@@ -5,8 +5,6 @@ pub enum DownloadError {
BadInput(anyhow::Error),
/// The file was not found in the remote storage.
NotFound,
/// The caller provided an ETag, and the file was not modified.
Unmodified,
/// A cancellation token aborted the download, typically during
/// tenant detach or process shutdown.
Cancelled,
@@ -26,7 +24,6 @@ impl std::fmt::Display for DownloadError {
write!(f, "Failed to download a remote file due to user input: {e}")
}
DownloadError::NotFound => write!(f, "No file found for the remote object id given"),
DownloadError::Unmodified => write!(f, "File was not modified"),
DownloadError::Cancelled => write!(f, "Cancelled, shutting down"),
DownloadError::Timeout => write!(f, "timeout"),
DownloadError::Other(e) => write!(f, "Failed to download a remote file: {e:?}"),
@@ -41,7 +38,7 @@ impl DownloadError {
pub fn is_permanent(&self) -> bool {
use DownloadError::*;
match self {
BadInput(_) | NotFound | Unmodified | Cancelled => true,
BadInput(_) | NotFound | Cancelled => true,
Timeout | Other(_) => false,
}
}

View File

@@ -161,14 +161,6 @@ pub struct Listing {
pub keys: Vec<ListingObject>,
}
/// Options for downloads. The default value is a plain GET.
#[derive(Default)]
pub struct DownloadOpts {
/// If given, returns [`DownloadError::Unmodified`] if the object still has
/// the same ETag (using If-None-Match).
pub etag: Option<Etag>,
}
/// Storage (potentially remote) API to manage its state.
/// This storage tries to be unaware of any layered repository context,
/// providing basic CRUD operations for storage files.
@@ -253,7 +245,6 @@ pub trait RemoteStorage: Send + Sync + 'static {
async fn download(
&self,
from: &RemotePath,
opts: &DownloadOpts,
cancel: &CancellationToken,
) -> Result<Download, DownloadError>;
@@ -410,18 +401,16 @@ impl<Other: RemoteStorage> GenericRemoteStorage<Arc<Other>> {
}
}
/// See [`RemoteStorage::download`]
pub async fn download(
&self,
from: &RemotePath,
opts: &DownloadOpts,
cancel: &CancellationToken,
) -> Result<Download, DownloadError> {
match self {
Self::LocalFs(s) => s.download(from, opts, cancel).await,
Self::AwsS3(s) => s.download(from, opts, cancel).await,
Self::AzureBlob(s) => s.download(from, opts, cancel).await,
Self::Unreliable(s) => s.download(from, opts, cancel).await,
Self::LocalFs(s) => s.download(from, cancel).await,
Self::AwsS3(s) => s.download(from, cancel).await,
Self::AzureBlob(s) => s.download(from, cancel).await,
Self::Unreliable(s) => s.download(from, cancel).await,
}
}
@@ -583,7 +572,7 @@ impl GenericRemoteStorage {
) -> Result<Download, DownloadError> {
match byte_range {
Some((start, end)) => self.download_byte_range(from, start, end, cancel).await,
None => self.download(from, &DownloadOpts::default(), cancel).await,
None => self.download(from, cancel).await,
}
}

View File

@@ -23,8 +23,8 @@ use tokio_util::{io::ReaderStream, sync::CancellationToken};
use utils::crashsafe::path_with_suffix_extension;
use crate::{
Download, DownloadError, DownloadOpts, Listing, ListingMode, ListingObject, RemotePath,
TimeTravelError, TimeoutOrCancel, REMOTE_STORAGE_PREFIX_SEPARATOR,
Download, DownloadError, Listing, ListingMode, ListingObject, RemotePath, TimeTravelError,
TimeoutOrCancel, REMOTE_STORAGE_PREFIX_SEPARATOR,
};
use super::{RemoteStorage, StorageMetadata};
@@ -494,17 +494,11 @@ impl RemoteStorage for LocalFs {
async fn download(
&self,
from: &RemotePath,
opts: &DownloadOpts,
cancel: &CancellationToken,
) -> Result<Download, DownloadError> {
let target_path = from.with_base(&self.storage_root);
let file_metadata = file_metadata(&target_path).await?;
let etag = mock_etag(&file_metadata);
if opts.etag.as_ref() == Some(&etag) {
return Err(DownloadError::Unmodified);
}
let source = ReaderStream::new(
fs::OpenOptions::new()
@@ -525,6 +519,7 @@ impl RemoteStorage for LocalFs {
let cancel_or_timeout = crate::support::cancel_or_timeout(self.timeout, cancel.clone());
let source = crate::support::DownloadStream::new(cancel_or_timeout, source);
let etag = mock_etag(&file_metadata);
Ok(Download {
metadata,
last_modified: file_metadata
@@ -697,7 +692,7 @@ mod fs_tests {
) -> anyhow::Result<String> {
let cancel = CancellationToken::new();
let download = storage
.download(remote_storage_path, &DownloadOpts::default(), &cancel)
.download(remote_storage_path, &cancel)
.await
.map_err(|e| anyhow::anyhow!("Download failed: {e}"))?;
ensure!(
@@ -778,8 +773,8 @@ mod fs_tests {
"We should upload and download the same contents"
);
let non_existing_path = RemotePath::new(Utf8Path::new("somewhere/else"))?;
match storage.download(&non_existing_path, &DownloadOpts::default(), &cancel).await {
let non_existing_path = "somewhere/else";
match storage.download(&RemotePath::new(Utf8Path::new(non_existing_path))?, &cancel).await {
Err(DownloadError::NotFound) => {} // Should get NotFound for non existing keys
other => panic!("Should get a NotFound error when downloading non-existing storage files, but got: {other:?}"),
}
@@ -1106,13 +1101,7 @@ mod fs_tests {
storage.upload(body, len, &path, None, &cancel).await?;
}
let read = aggregate(
storage
.download(&path, &DownloadOpts::default(), &cancel)
.await?
.download_stream,
)
.await?;
let read = aggregate(storage.download(&path, &cancel).await?.download_stream).await?;
assert_eq!(body, read);
let shorter = Bytes::from_static(b"shorter body");
@@ -1123,13 +1112,7 @@ mod fs_tests {
storage.upload(body, len, &path, None, &cancel).await?;
}
let read = aggregate(
storage
.download(&path, &DownloadOpts::default(), &cancel)
.await?
.download_stream,
)
.await?;
let read = aggregate(storage.download(&path, &cancel).await?.download_stream).await?;
assert_eq!(shorter, read);
Ok(())
}
@@ -1162,13 +1145,7 @@ mod fs_tests {
storage.upload(body, len, &path, None, &cancel).await?;
}
let read = aggregate(
storage
.download(&path, &DownloadOpts::default(), &cancel)
.await?
.download_stream,
)
.await?;
let read = aggregate(storage.download(&path, &cancel).await?.download_stream).await?;
assert_eq!(body, read);
Ok(())

View File

@@ -28,13 +28,12 @@ use aws_sdk_s3::{
Client,
};
use aws_smithy_async::rt::sleep::TokioSleep;
use http_types::StatusCode;
use aws_smithy_types::{body::SdkBody, DateTime};
use aws_smithy_types::{byte_stream::ByteStream, date_time::ConversionError};
use bytes::Bytes;
use futures::stream::Stream;
use hyper0::Body;
use hyper::Body;
use scopeguard::ScopeGuard;
use tokio_util::sync::CancellationToken;
use utils::backoff;
@@ -45,8 +44,8 @@ use crate::{
error::Cancelled,
metrics::{start_counting_cancelled_wait, start_measuring_requests},
support::PermitCarrying,
ConcurrencyLimiter, Download, DownloadError, DownloadOpts, Listing, ListingMode, ListingObject,
RemotePath, RemoteStorage, TimeTravelError, TimeoutOrCancel, MAX_KEYS_PER_DELETE,
ConcurrencyLimiter, Download, DownloadError, Listing, ListingMode, ListingObject, RemotePath,
RemoteStorage, TimeTravelError, TimeoutOrCancel, MAX_KEYS_PER_DELETE,
REMOTE_STORAGE_PREFIX_SEPARATOR,
};
@@ -68,7 +67,6 @@ pub struct S3Bucket {
struct GetObjectRequest {
bucket: String,
key: String,
etag: Option<String>,
range: Option<String>,
}
impl S3Bucket {
@@ -250,18 +248,13 @@ impl S3Bucket {
let started_at = start_measuring_requests(kind);
let mut builder = self
let get_object = self
.client
.get_object()
.bucket(request.bucket)
.key(request.key)
.set_range(request.range);
if let Some(etag) = request.etag {
builder = builder.if_none_match(etag);
}
let get_object = builder.send();
.set_range(request.range)
.send();
let get_object = tokio::select! {
res = get_object => res,
@@ -284,20 +277,6 @@ impl S3Bucket {
);
return Err(DownloadError::NotFound);
}
Err(SdkError::ServiceError(e))
// aws_smithy_runtime_api::http::response::StatusCode isn't
// re-exported by any aws crates, so just check the numeric
// status against http_types::StatusCode instead of pulling it.
if e.raw().status().as_u16() == StatusCode::NotModified =>
{
// Count an unmodified file as a success.
crate::metrics::BUCKET_METRICS.req_seconds.observe_elapsed(
kind,
AttemptOutcome::Ok,
started_at,
);
return Err(DownloadError::Unmodified);
}
Err(e) => {
crate::metrics::BUCKET_METRICS.req_seconds.observe_elapsed(
kind,
@@ -794,7 +773,6 @@ impl RemoteStorage for S3Bucket {
async fn download(
&self,
from: &RemotePath,
opts: &DownloadOpts,
cancel: &CancellationToken,
) -> Result<Download, DownloadError> {
// if prefix is not none then download file `prefix/from`
@@ -803,7 +781,6 @@ impl RemoteStorage for S3Bucket {
GetObjectRequest {
bucket: self.bucket_name.clone(),
key: self.relative_path_to_s3_object(from),
etag: opts.etag.as_ref().map(|e| e.to_string()),
range: None,
},
cancel,
@@ -830,7 +807,6 @@ impl RemoteStorage for S3Bucket {
GetObjectRequest {
bucket: self.bucket_name.clone(),
key: self.relative_path_to_s3_object(from),
etag: None,
range,
},
cancel,

View File

@@ -12,8 +12,8 @@ use std::{collections::hash_map::Entry, sync::Arc};
use tokio_util::sync::CancellationToken;
use crate::{
Download, DownloadError, DownloadOpts, GenericRemoteStorage, Listing, ListingMode, RemotePath,
RemoteStorage, StorageMetadata, TimeTravelError,
Download, DownloadError, GenericRemoteStorage, Listing, ListingMode, RemotePath, RemoteStorage,
StorageMetadata, TimeTravelError,
};
pub struct UnreliableWrapper {
@@ -167,12 +167,11 @@ impl RemoteStorage for UnreliableWrapper {
async fn download(
&self,
from: &RemotePath,
opts: &DownloadOpts,
cancel: &CancellationToken,
) -> Result<Download, DownloadError> {
self.attempt(RemoteOp::Download(from.clone()))
.map_err(DownloadError::Other)?;
self.inner.download(from, opts, cancel).await
self.inner.download(from, cancel).await
}
async fn download_byte_range(

View File

@@ -1,7 +1,8 @@
use anyhow::Context;
use camino::Utf8Path;
use futures::StreamExt;
use remote_storage::{DownloadError, DownloadOpts, ListingMode, ListingObject, RemotePath};
use remote_storage::ListingMode;
use remote_storage::RemotePath;
use std::sync::Arc;
use std::{collections::HashSet, num::NonZeroU32};
use test_context::test_context;
@@ -283,10 +284,7 @@ async fn upload_download_works(ctx: &mut MaybeEnabledStorage) -> anyhow::Result<
ctx.client.upload(data, len, &path, None, &cancel).await?;
// Normal download request
let dl = ctx
.client
.download(&path, &DownloadOpts::default(), &cancel)
.await?;
let dl = ctx.client.download(&path, &cancel).await?;
let buf = download_to_vec(dl).await?;
assert_eq!(&buf, &orig);
@@ -339,54 +337,6 @@ async fn upload_download_works(ctx: &mut MaybeEnabledStorage) -> anyhow::Result<
Ok(())
}
/// Tests that conditional downloads work properly, by returning
/// DownloadError::Unmodified when the object ETag matches the given ETag.
#[test_context(MaybeEnabledStorage)]
#[tokio::test]
async fn download_conditional(ctx: &mut MaybeEnabledStorage) -> anyhow::Result<()> {
let MaybeEnabledStorage::Enabled(ctx) = ctx else {
return Ok(());
};
let cancel = CancellationToken::new();
// Create a file.
let path = RemotePath::new(Utf8Path::new(format!("{}/file", ctx.base_prefix).as_str()))?;
let data = bytes::Bytes::from_static("foo".as_bytes());
let (stream, len) = wrap_stream(data);
ctx.client.upload(stream, len, &path, None, &cancel).await?;
// Download it to obtain its etag.
let mut opts = DownloadOpts::default();
let download = ctx.client.download(&path, &opts, &cancel).await?;
// Download with the etag yields DownloadError::Unmodified.
opts.etag = Some(download.etag);
let result = ctx.client.download(&path, &opts, &cancel).await;
assert!(
matches!(result, Err(DownloadError::Unmodified)),
"expected DownloadError::Unmodified, got {result:?}"
);
// Replace the file contents.
let data = bytes::Bytes::from_static("bar".as_bytes());
let (stream, len) = wrap_stream(data);
ctx.client.upload(stream, len, &path, None, &cancel).await?;
// A download with the old etag should yield the new file.
let download = ctx.client.download(&path, &opts, &cancel).await?;
assert_ne!(download.etag, opts.etag.unwrap(), "ETag did not change");
// A download with the new etag should yield Unmodified again.
opts.etag = Some(download.etag);
let result = ctx.client.download(&path, &opts, &cancel).await;
assert!(
matches!(result, Err(DownloadError::Unmodified)),
"expected DownloadError::Unmodified, got {result:?}"
);
Ok(())
}
#[test_context(MaybeEnabledStorage)]
#[tokio::test]
async fn copy_works(ctx: &mut MaybeEnabledStorage) -> anyhow::Result<()> {
@@ -414,10 +364,7 @@ async fn copy_works(ctx: &mut MaybeEnabledStorage) -> anyhow::Result<()> {
// Normal download request
ctx.client.copy_object(&path, &path_dest, &cancel).await?;
let dl = ctx
.client
.download(&path_dest, &DownloadOpts::default(), &cancel)
.await?;
let dl = ctx.client.download(&path_dest, &cancel).await?;
let buf = download_to_vec(dl).await?;
assert_eq!(&buf, &orig);
@@ -429,56 +376,3 @@ async fn copy_works(ctx: &mut MaybeEnabledStorage) -> anyhow::Result<()> {
Ok(())
}
/// Tests that head_object works properly.
#[test_context(MaybeEnabledStorage)]
#[tokio::test]
async fn head_object(ctx: &mut MaybeEnabledStorage) -> anyhow::Result<()> {
let MaybeEnabledStorage::Enabled(ctx) = ctx else {
return Ok(());
};
let cancel = CancellationToken::new();
let path = RemotePath::new(Utf8Path::new(format!("{}/file", ctx.base_prefix).as_str()))?;
// Errors on missing file.
let result = ctx.client.head_object(&path, &cancel).await;
assert!(
matches!(result, Err(DownloadError::NotFound)),
"expected NotFound, got {result:?}"
);
// Create the file.
let data = bytes::Bytes::from_static("foo".as_bytes());
let (stream, len) = wrap_stream(data);
ctx.client.upload(stream, len, &path, None, &cancel).await?;
// Fetch the head metadata.
let object = ctx.client.head_object(&path, &cancel).await?;
assert_eq!(
object,
ListingObject {
key: path.clone(),
last_modified: object.last_modified, // ignore
size: 3
}
);
// Wait for a couple of seconds, and then update the file to check the last
// modified timestamp.
tokio::time::sleep(std::time::Duration::from_secs(2)).await;
let data = bytes::Bytes::from_static("bar".as_bytes());
let (stream, len) = wrap_stream(data);
ctx.client.upload(stream, len, &path, None, &cancel).await?;
let new = ctx.client.head_object(&path, &cancel).await?;
assert!(
!new.last_modified
.duration_since(object.last_modified)?
.is_zero(),
"last_modified did not advance"
);
Ok(())
}

View File

@@ -12,8 +12,8 @@ use anyhow::Context;
use camino::Utf8Path;
use futures_util::StreamExt;
use remote_storage::{
DownloadError, DownloadOpts, GenericRemoteStorage, ListingMode, RemotePath,
RemoteStorageConfig, RemoteStorageKind, S3Config,
DownloadError, GenericRemoteStorage, ListingMode, RemotePath, RemoteStorageConfig,
RemoteStorageKind, S3Config,
};
use test_context::test_context;
use test_context::AsyncTestContext;
@@ -121,8 +121,7 @@ async fn s3_time_travel_recovery_works(ctx: &mut MaybeEnabledStorage) -> anyhow:
// A little check to ensure that our clock is not too far off from the S3 clock
{
let opts = DownloadOpts::default();
let dl = retry(|| ctx.client.download(&path2, &opts, &cancel)).await?;
let dl = retry(|| ctx.client.download(&path2, &cancel)).await?;
let last_modified = dl.last_modified;
let half_wt = WAIT_TIME.mul_f32(0.5);
let t0_hwt = t0 + half_wt;
@@ -160,12 +159,7 @@ async fn s3_time_travel_recovery_works(ctx: &mut MaybeEnabledStorage) -> anyhow:
let t2_files_recovered = list_files(&ctx.client, &cancel).await?;
println!("after recovery to t2: {t2_files_recovered:?}");
assert_eq!(t2_files, t2_files_recovered);
let path2_recovered_t2 = download_to_vec(
ctx.client
.download(&path2, &DownloadOpts::default(), &cancel)
.await?,
)
.await?;
let path2_recovered_t2 = download_to_vec(ctx.client.download(&path2, &cancel).await?).await?;
assert_eq!(path2_recovered_t2, new_data.as_bytes());
// after recovery to t1: path1 is back, path2 has the old content
@@ -176,12 +170,7 @@ async fn s3_time_travel_recovery_works(ctx: &mut MaybeEnabledStorage) -> anyhow:
let t1_files_recovered = list_files(&ctx.client, &cancel).await?;
println!("after recovery to t1: {t1_files_recovered:?}");
assert_eq!(t1_files, t1_files_recovered);
let path2_recovered_t1 = download_to_vec(
ctx.client
.download(&path2, &DownloadOpts::default(), &cancel)
.await?,
)
.await?;
let path2_recovered_t1 = download_to_vec(ctx.client.download(&path2, &cancel).await?).await?;
assert_eq!(path2_recovered_t1, old_data.as_bytes());
// after recovery to t0: everything is gone except for path1
@@ -427,7 +416,7 @@ async fn download_is_timeouted(ctx: &mut MaybeEnabledStorage) {
let started_at = std::time::Instant::now();
let mut stream = ctx
.client
.download(&path, &DownloadOpts::default(), &cancel)
.download(&path, &cancel)
.await
.expect("download succeeds")
.download_stream;
@@ -502,7 +491,7 @@ async fn download_is_cancelled(ctx: &mut MaybeEnabledStorage) {
{
let stream = ctx
.client
.download(&path, &DownloadOpts::default(), &cancel)
.download(&path, &cancel)
.await
.expect("download succeeds")
.download_stream;

View File

@@ -5,7 +5,7 @@ edition.workspace = true
license.workspace = true
[dependencies]
hyper0.workspace = true
hyper.workspace = true
opentelemetry = { workspace = true, features = ["trace"] }
opentelemetry_sdk = { workspace = true, features = ["rt-tokio"] }
opentelemetry-otlp = { workspace = true, default-features = false, features = ["http-proto", "trace", "http", "reqwest-client"] }

View File

@@ -1,7 +1,7 @@
//! Tracing wrapper for Hyper HTTP server
use hyper0::HeaderMap;
use hyper0::{Body, Request, Response};
use hyper::HeaderMap;
use hyper::{Body, Request, Response};
use std::future::Future;
use tracing::Instrument;
use tracing_opentelemetry::OpenTelemetrySpanExt;

View File

@@ -22,7 +22,7 @@ chrono.workspace = true
git-version.workspace = true
hex = { workspace = true, features = ["serde"] }
humantime.workspace = true
hyper0 = { workspace = true, features = ["full"] }
hyper = { workspace = true, features = ["full"] }
fail.workspace = true
futures = { workspace = true}
jsonwebtoken.workspace = true

View File

@@ -2,8 +2,6 @@
//! between other crates in this repository.
#![deny(clippy::undocumented_unsafe_blocks)]
extern crate hyper0 as hyper;
pub mod backoff;
/// `Lsn` type implements common tasks on Log Sequence Numbers

View File

@@ -7,13 +7,11 @@ use axum::{
extract::{ws::WebSocket, State, WebSocketUpgrade},
response::Response,
};
use axum::{routing::get, Router};
use axum::{routing::get, Router, Server};
use clap::Parser;
use futures::Future;
use std::net::SocketAddr;
use std::{fmt::Debug, time::Duration};
use sysinfo::{RefreshKind, System, SystemExt};
use tokio::net::TcpListener;
use tokio::{sync::broadcast, task::JoinHandle};
use tokio_util::sync::CancellationToken;
use tracing::{error, info};
@@ -134,14 +132,14 @@ pub async fn start(args: &'static Args, token: CancellationToken) -> anyhow::Res
args,
});
let addr_str = args.addr();
let addr: SocketAddr = addr_str.parse().expect("parsing address should not fail");
let listener = TcpListener::bind(&addr)
.await
let addr = args.addr();
let bound = Server::try_bind(&addr.parse().expect("parsing address should not fail"))
.with_context(|| format!("failed to bind to {addr}"))?;
info!(addr_str, "server bound");
axum::serve(listener, app.into_make_service())
info!(addr, "server bound");
bound
.serve(app.into_make_service())
.await
.context("server exited")?;

View File

@@ -79,7 +79,8 @@ pub struct Config {
/// memory.
///
/// The default value of `0.15` means that we *guarantee* sending upscale requests if the
/// cgroup is using more than 85% of total memory.
/// cgroup is using more than 85% of total memory (even if we're *not* separately reserving
/// memory for the file cache).
cgroup_min_overhead_fraction: f64,
cgroup_downscale_threshold_buffer_bytes: u64,
@@ -96,12 +97,24 @@ impl Default for Config {
}
impl Config {
fn cgroup_threshold(&self, total_mem: u64) -> u64 {
// We want our threshold to be met gracefully instead of letting postgres get OOM-killed
// (or if there's room, spilling to swap).
fn cgroup_threshold(&self, total_mem: u64, file_cache_disk_size: u64) -> u64 {
// If the file cache is in tmpfs, then it will count towards shmem usage of the cgroup,
// and thus be non-reclaimable, so we should allow for additional memory usage.
//
// If the file cache sits on disk, our desired stable system state is for it to be fully
// page cached (its contents should only be paged to/from disk in situations where we can't
// upscale fast enough). Page-cached memory is reclaimable, so we need to lower the
// threshold for non-reclaimable memory so we scale up *before* the kernel starts paging
// out the file cache.
let memory_remaining_for_cgroup = total_mem.saturating_sub(file_cache_disk_size);
// Even if we're not separately making room for the file cache (if it's in tmpfs), we still
// want our threshold to be met gracefully instead of letting postgres get OOM-killed.
// So we guarantee that there's at least `cgroup_min_overhead_fraction` of total memory
// remaining above the threshold.
(total_mem as f64 * (1.0 - self.cgroup_min_overhead_fraction)) as u64
let max_threshold = (total_mem as f64 * (1.0 - self.cgroup_min_overhead_fraction)) as u64;
memory_remaining_for_cgroup.min(max_threshold)
}
}
@@ -136,6 +149,11 @@ impl Runner {
let mem = get_total_system_memory();
let mut file_cache_disk_size = 0;
// We need to process file cache initialization before cgroup initialization, so that the memory
// allocated to the file cache is appropriately taken into account when we decide the cgroup's
// memory limits.
if let Some(connstr) = &args.pgconnstr {
info!("initializing file cache");
let config = FileCacheConfig::default();
@@ -166,6 +184,7 @@ impl Runner {
info!("file cache size actually got set to {actual_size}")
}
file_cache_disk_size = actual_size;
state.filecache = Some(file_cache);
}
@@ -188,7 +207,7 @@ impl Runner {
cgroup.watch(hist_tx).await
});
let threshold = state.config.cgroup_threshold(mem);
let threshold = state.config.cgroup_threshold(mem, file_cache_disk_size);
info!(threshold, "set initial cgroup threshold",);
state.cgroup = Some(CgroupState {
@@ -240,7 +259,9 @@ impl Runner {
return Ok((false, status.to_owned()));
}
let new_threshold = self.config.cgroup_threshold(usable_system_memory);
let new_threshold = self
.config
.cgroup_threshold(usable_system_memory, expected_file_cache_size);
let current = last_history.avg_non_reclaimable;
@@ -261,11 +282,13 @@ impl Runner {
// The downscaling has been approved. Downscale the file cache, then the cgroup.
let mut status = vec![];
let mut file_cache_disk_size = 0;
if let Some(file_cache) = &mut self.filecache {
let actual_usage = file_cache
.set_file_cache_size(expected_file_cache_size)
.await
.context("failed to set file cache size")?;
file_cache_disk_size = actual_usage;
let message = format!(
"set file cache size to {} MiB",
bytes_to_mebibytes(actual_usage),
@@ -275,7 +298,9 @@ impl Runner {
}
if let Some(cgroup) = &mut self.cgroup {
let new_threshold = self.config.cgroup_threshold(usable_system_memory);
let new_threshold = self
.config
.cgroup_threshold(usable_system_memory, file_cache_disk_size);
let message = format!(
"set cgroup memory threshold from {} MiB to {} MiB, of new total {} MiB",
@@ -304,6 +329,7 @@ impl Runner {
let new_mem = resources.mem;
let usable_system_memory = new_mem.saturating_sub(self.config.sys_buffer_bytes);
let mut file_cache_disk_size = 0;
if let Some(file_cache) = &mut self.filecache {
let expected_usage = file_cache.config.calculate_cache_size(usable_system_memory);
info!(
@@ -316,6 +342,7 @@ impl Runner {
.set_file_cache_size(expected_usage)
.await
.context("failed to set file cache size")?;
file_cache_disk_size = actual_usage;
if actual_usage != expected_usage {
warn!(
@@ -327,7 +354,9 @@ impl Runner {
}
if let Some(cgroup) = &mut self.cgroup {
let new_threshold = self.config.cgroup_threshold(usable_system_memory);
let new_threshold = self
.config
.cgroup_threshold(usable_system_memory, file_cache_disk_size);
info!(
"set cgroup memory threshold from {} MiB to {} MiB of new total {} MiB",

View File

@@ -30,7 +30,7 @@ futures.workspace = true
hex.workspace = true
humantime.workspace = true
humantime-serde.workspace = true
hyper0.workspace = true
hyper.workspace = true
itertools.workspace = true
md5.workspace = true
nix.workspace = true

View File

@@ -575,7 +575,7 @@ fn start_pageserver(
.build()
.map_err(|err| anyhow!(err))?;
let service = utils::http::RouterService::new(router).unwrap();
let server = hyper0::Server::from_tcp(http_listener)?
let server = hyper::Server::from_tcp(http_listener)?
.serve(service)
.with_graceful_shutdown({
let cancel = cancel.clone();

View File

@@ -13,8 +13,6 @@ pub mod http;
pub mod import_datadir;
pub mod l0_flush;
extern crate hyper0 as hyper;
use futures::{stream::FuturesUnordered, StreamExt};
pub use pageserver_api::keyspace;
use tokio_util::sync::CancellationToken;

View File

@@ -27,7 +27,7 @@ use crate::tenant::Generation;
use crate::virtual_file::owned_buffers_io::io_buf_ext::IoBufExt;
use crate::virtual_file::{on_fatal_io_error, MaybeFatalIo, VirtualFile};
use crate::TEMP_FILE_SUFFIX;
use remote_storage::{DownloadError, DownloadOpts, GenericRemoteStorage, ListingMode, RemotePath};
use remote_storage::{DownloadError, GenericRemoteStorage, ListingMode, RemotePath};
use utils::crashsafe::path_with_suffix_extension;
use utils::id::{TenantId, TimelineId};
use utils::pausable_failpoint;
@@ -153,9 +153,7 @@ async fn download_object<'a>(
.with_context(|| format!("create a destination file for layer '{dst_path}'"))
.map_err(DownloadError::Other)?;
let download = storage
.download(src_path, &DownloadOpts::default(), cancel)
.await?;
let download = storage.download(src_path, cancel).await?;
pausable_failpoint!("before-downloading-layer-stream-pausable");
@@ -206,9 +204,7 @@ async fn download_object<'a>(
.with_context(|| format!("create a destination file for layer '{dst_path}'"))
.map_err(DownloadError::Other)?;
let mut download = storage
.download(src_path, &DownloadOpts::default(), cancel)
.await?;
let mut download = storage.download(src_path, cancel).await?;
pausable_failpoint!("before-downloading-layer-stream-pausable");
@@ -348,9 +344,7 @@ async fn do_download_index_part(
let index_part_bytes = download_retry_forever(
|| async {
let download = storage
.download(&remote_path, &DownloadOpts::default(), cancel)
.await?;
let download = storage.download(&remote_path, cancel).await?;
let mut bytes = Vec::new();
@@ -532,15 +526,10 @@ pub(crate) async fn download_initdb_tar_zst(
.with_context(|| format!("tempfile creation {temp_path}"))
.map_err(DownloadError::Other)?;
let download = match storage
.download(&remote_path, &DownloadOpts::default(), cancel)
.await
{
let download = match storage.download(&remote_path, cancel).await {
Ok(dl) => dl,
Err(DownloadError::NotFound) => {
storage
.download(&remote_preserved_path, &DownloadOpts::default(), cancel)
.await?
storage.download(&remote_preserved_path, cancel).await?
}
Err(other) => Err(other)?,
};

View File

@@ -49,7 +49,7 @@ use futures::Future;
use metrics::UIntGauge;
use pageserver_api::models::SecondaryProgress;
use pageserver_api::shard::TenantShardId;
use remote_storage::{DownloadError, DownloadOpts, Etag, GenericRemoteStorage};
use remote_storage::{DownloadError, Etag, GenericRemoteStorage};
use tokio_util::sync::CancellationToken;
use tracing::{info_span, instrument, warn, Instrument};
@@ -944,34 +944,36 @@ impl<'a> TenantDownloader<'a> {
) -> Result<HeatMapDownload, UpdateError> {
debug_assert_current_span_has_tenant_id();
let tenant_shard_id = self.secondary_state.get_tenant_shard_id();
// TODO: pull up etag check into the request, to do a conditional GET rather than
// issuing a GET and then maybe ignoring the response body
// (https://github.com/neondatabase/neon/issues/6199)
tracing::debug!("Downloading heatmap for secondary tenant",);
let heatmap_path = remote_heatmap_path(tenant_shard_id);
let cancel = &self.secondary_state.cancel;
let opts = DownloadOpts {
etag: prev_etag.cloned(),
};
backoff::retry(
|| async {
let download = match self
let download = self
.remote_storage
.download(&heatmap_path, &opts, cancel)
.download(&heatmap_path, cancel)
.await
{
Ok(download) => download,
Err(DownloadError::Unmodified) => return Ok(HeatMapDownload::Unmodified),
Err(err) => return Err(err.into()),
};
.map_err(UpdateError::from)?;
let mut heatmap_bytes = Vec::new();
let mut body = tokio_util::io::StreamReader::new(download.download_stream);
let _size = tokio::io::copy_buf(&mut body, &mut heatmap_bytes).await?;
Ok(HeatMapDownload::Modified(HeatMapModified {
etag: download.etag,
last_modified: download.last_modified,
bytes: heatmap_bytes,
}))
SECONDARY_MODE.download_heatmap.inc();
if Some(&download.etag) == prev_etag {
Ok(HeatMapDownload::Unmodified)
} else {
let mut heatmap_bytes = Vec::new();
let mut body = tokio_util::io::StreamReader::new(download.download_stream);
let _size = tokio::io::copy_buf(&mut body, &mut heatmap_bytes).await?;
Ok(HeatMapDownload::Modified(HeatMapModified {
etag: download.etag,
last_modified: download.last_modified,
bytes: heatmap_bytes,
}))
}
},
|e| matches!(e, UpdateError::NoData | UpdateError::Cancelled),
FAILED_DOWNLOAD_WARN_THRESHOLD,
@@ -982,7 +984,6 @@ impl<'a> TenantDownloader<'a> {
.await
.ok_or_else(|| UpdateError::Cancelled)
.and_then(|x| x)
.inspect(|_| SECONDARY_MODE.download_heatmap.inc())
}
/// Download heatmap layers that are not present on local disk, or update their

View File

@@ -53,7 +53,6 @@ use camino::{Utf8Path, Utf8PathBuf};
use futures::StreamExt;
use itertools::Itertools;
use pageserver_api::config::MaxVectoredReadBytes;
use pageserver_api::key::DBDIR_KEY;
use pageserver_api::keyspace::KeySpace;
use pageserver_api::models::ImageCompressionAlgorithm;
use pageserver_api::shard::TenantShardId;
@@ -964,25 +963,14 @@ impl DeltaLayerInner {
.blobs_at
.as_slice()
.iter()
.filter_map(|(_, blob_meta)| {
if blob_meta.key.is_rel_dir_key() || blob_meta.key == DBDIR_KEY {
// The size of values for these keys is unbounded and can
// grow very large in pathological cases.
None
} else {
Some(format!("{}@{}", blob_meta.key, blob_meta.lsn))
}
})
.map(|(_, blob_meta)| format!("{}@{}", blob_meta.key, blob_meta.lsn))
.join(", ");
if !offenders.is_empty() {
tracing::warn!(
"Oversized vectored read ({} > {}) for keys {}",
largest_read_size,
read_size_soft_max,
offenders
);
}
tracing::warn!(
"Oversized vectored read ({} > {}) for keys {}",
largest_read_size,
read_size_soft_max,
offenders
);
}
largest_read_size

View File

@@ -49,7 +49,6 @@ use camino::{Utf8Path, Utf8PathBuf};
use hex;
use itertools::Itertools;
use pageserver_api::config::MaxVectoredReadBytes;
use pageserver_api::key::DBDIR_KEY;
use pageserver_api::keyspace::KeySpace;
use pageserver_api::shard::{ShardIdentity, TenantShardId};
use rand::{distributions::Alphanumeric, Rng};
@@ -588,25 +587,14 @@ impl ImageLayerInner {
.blobs_at
.as_slice()
.iter()
.filter_map(|(_, blob_meta)| {
if blob_meta.key.is_rel_dir_key() || blob_meta.key == DBDIR_KEY {
// The size of values for these keys is unbounded and can
// grow very large in pathological cases.
None
} else {
Some(format!("{}@{}", blob_meta.key, blob_meta.lsn))
}
})
.map(|(_, blob_meta)| format!("{}@{}", blob_meta.key, blob_meta.lsn))
.join(", ");
if !offenders.is_empty() {
tracing::warn!(
"Oversized vectored read ({} > {}) for keys {}",
buf_size,
max_vectored_read_bytes,
offenders
);
}
tracing::warn!(
"Oversized vectored read ({} > {}) for keys {}",
buf_size,
max_vectored_read_bytes,
offenders
);
}
let buf = BytesMut::with_capacity(buf_size);

View File

@@ -146,8 +146,6 @@ ConstructDeltaMessage()
if (RootTable.role_table)
{
JsonbValue roles;
HASH_SEQ_STATUS status;
RoleEntry *entry;
roles.type = jbvString;
roles.val.string.val = "roles";
@@ -155,6 +153,9 @@ ConstructDeltaMessage()
pushJsonbValue(&state, WJB_KEY, &roles);
pushJsonbValue(&state, WJB_BEGIN_ARRAY, NULL);
HASH_SEQ_STATUS status;
RoleEntry *entry;
hash_seq_init(&status, RootTable.role_table);
while ((entry = hash_seq_search(&status)) != NULL)
{
@@ -189,12 +190,10 @@ ConstructDeltaMessage()
}
pushJsonbValue(&state, WJB_END_ARRAY, NULL);
}
{
JsonbValue *result = pushJsonbValue(&state, WJB_END_OBJECT, NULL);
Jsonb *jsonb = JsonbValueToJsonb(result);
JsonbValue *result = pushJsonbValue(&state, WJB_END_OBJECT, NULL);
Jsonb *jsonb = JsonbValueToJsonb(result);
return JsonbToCString(NULL, &jsonb->root, 0 /* estimated_len */ );
}
return JsonbToCString(NULL, &jsonb->root, 0 /* estimated_len */ );
}
#define ERROR_SIZE 1024
@@ -273,28 +272,32 @@ SendDeltasToControlPlane()
curl_easy_setopt(handle, CURLOPT_WRITEFUNCTION, ErrorWriteCallback);
}
char *message = ConstructDeltaMessage();
ErrorString str;
str.size = 0;
curl_easy_setopt(handle, CURLOPT_POSTFIELDS, message);
curl_easy_setopt(handle, CURLOPT_WRITEDATA, &str);
const int num_retries = 5;
CURLcode curl_status;
for (int i = 0; i < num_retries; i++)
{
if ((curl_status = curl_easy_perform(handle)) == 0)
break;
elog(LOG, "Curl request failed on attempt %d: %s", i, CurlErrorBuf);
pg_usleep(1000 * 1000);
}
if (curl_status != CURLE_OK)
{
elog(ERROR, "Failed to perform curl request: %s", CurlErrorBuf);
}
else
{
char *message = ConstructDeltaMessage();
ErrorString str;
const int num_retries = 5;
CURLcode curl_status;
long response_code;
str.size = 0;
curl_easy_setopt(handle, CURLOPT_POSTFIELDS, message);
curl_easy_setopt(handle, CURLOPT_WRITEDATA, &str);
for (int i = 0; i < num_retries; i++)
{
if ((curl_status = curl_easy_perform(handle)) == 0)
break;
elog(LOG, "Curl request failed on attempt %d: %s", i, CurlErrorBuf);
pg_usleep(1000 * 1000);
}
if (curl_status != CURLE_OK)
elog(ERROR, "Failed to perform curl request: %s", CurlErrorBuf);
if (curl_easy_getinfo(handle, CURLINFO_RESPONSE_CODE, &response_code) != CURLE_UNKNOWN_OPTION)
{
if (response_code != 200)
@@ -373,11 +376,10 @@ MergeTable()
if (old_table->db_table)
{
InitDbTableIfNeeded();
DbEntry *entry;
HASH_SEQ_STATUS status;
InitDbTableIfNeeded();
hash_seq_init(&status, old_table->db_table);
while ((entry = hash_seq_search(&status)) != NULL)
{
@@ -419,11 +421,10 @@ MergeTable()
if (old_table->role_table)
{
InitRoleTableIfNeeded();
RoleEntry *entry;
HASH_SEQ_STATUS status;
InitRoleTableIfNeeded();
hash_seq_init(&status, old_table->role_table);
while ((entry = hash_seq_search(&status)) != NULL)
{
@@ -514,12 +515,9 @@ RoleIsNeonSuperuser(const char *role_name)
static void
HandleCreateDb(CreatedbStmt *stmt)
{
InitDbTableIfNeeded();
DefElem *downer = NULL;
ListCell *option;
bool found = false;
DbEntry *entry;
InitDbTableIfNeeded();
foreach(option, stmt->options)
{
@@ -528,11 +526,13 @@ HandleCreateDb(CreatedbStmt *stmt)
if (strcmp(defel->defname, "owner") == 0)
downer = defel;
}
bool found = false;
DbEntry *entry = hash_search(
CurrentDdlTable->db_table,
stmt->dbname,
HASH_ENTER,
&found);
entry = hash_search(CurrentDdlTable->db_table,
stmt->dbname,
HASH_ENTER,
&found);
if (!found)
memset(entry->old_name, 0, sizeof(entry->old_name));
@@ -554,24 +554,21 @@ HandleCreateDb(CreatedbStmt *stmt)
static void
HandleAlterOwner(AlterOwnerStmt *stmt)
{
const char *name;
bool found = false;
DbEntry *entry;
const char *new_owner;
if (stmt->objectType != OBJECT_DATABASE)
return;
InitDbTableIfNeeded();
const char *name = strVal(stmt->object);
bool found = false;
DbEntry *entry = hash_search(
CurrentDdlTable->db_table,
name,
HASH_ENTER,
&found);
name = strVal(stmt->object);
entry = hash_search(CurrentDdlTable->db_table,
name,
HASH_ENTER,
&found);
if (!found)
memset(entry->old_name, 0, sizeof(entry->old_name));
const char *new_owner = get_rolespec_name(stmt->newowner);
new_owner = get_rolespec_name(stmt->newowner);
if (RoleIsNeonSuperuser(new_owner))
elog(ERROR, "can't alter owner to neon_superuser");
entry->owner = get_role_oid(new_owner, false);
@@ -581,23 +578,21 @@ HandleAlterOwner(AlterOwnerStmt *stmt)
static void
HandleDbRename(RenameStmt *stmt)
{
bool found = false;
DbEntry *entry;
DbEntry *entry_for_new_name;
Assert(stmt->renameType == OBJECT_DATABASE);
InitDbTableIfNeeded();
entry = hash_search(CurrentDdlTable->db_table,
stmt->subname,
HASH_FIND,
&found);
bool found = false;
DbEntry *entry = hash_search(
CurrentDdlTable->db_table,
stmt->subname,
HASH_FIND,
&found);
DbEntry *entry_for_new_name = hash_search(
CurrentDdlTable->db_table,
stmt->newname,
HASH_ENTER,
NULL);
entry_for_new_name = hash_search(CurrentDdlTable->db_table,
stmt->newname,
HASH_ENTER,
NULL);
entry_for_new_name->type = Op_Set;
if (found)
{
if (entry->old_name[0] != '\0')
@@ -605,7 +600,8 @@ HandleDbRename(RenameStmt *stmt)
else
strlcpy(entry_for_new_name->old_name, entry->name, NAMEDATALEN);
entry_for_new_name->owner = entry->owner;
hash_search(CurrentDdlTable->db_table,
hash_search(
CurrentDdlTable->db_table,
stmt->subname,
HASH_REMOVE,
NULL);
@@ -620,15 +616,14 @@ HandleDbRename(RenameStmt *stmt)
static void
HandleDropDb(DropdbStmt *stmt)
{
bool found = false;
DbEntry *entry;
InitDbTableIfNeeded();
bool found = false;
DbEntry *entry = hash_search(
CurrentDdlTable->db_table,
stmt->dbname,
HASH_ENTER,
&found);
entry = hash_search(CurrentDdlTable->db_table,
stmt->dbname,
HASH_ENTER,
&found);
entry->type = Op_Delete;
entry->owner = InvalidOid;
if (!found)
@@ -638,14 +633,16 @@ HandleDropDb(DropdbStmt *stmt)
static void
HandleCreateRole(CreateRoleStmt *stmt)
{
InitRoleTableIfNeeded();
bool found = false;
RoleEntry *entry;
DefElem *dpass;
RoleEntry *entry = hash_search(
CurrentDdlTable->role_table,
stmt->role,
HASH_ENTER,
&found);
DefElem *dpass = NULL;
ListCell *option;
InitRoleTableIfNeeded();
dpass = NULL;
foreach(option, stmt->options)
{
DefElem *defel = lfirst(option);
@@ -653,11 +650,6 @@ HandleCreateRole(CreateRoleStmt *stmt)
if (strcmp(defel->defname, "password") == 0)
dpass = defel;
}
entry = hash_search(CurrentDdlTable->role_table,
stmt->role,
HASH_ENTER,
&found);
if (!found)
memset(entry->old_name, 0, sizeof(entry->old_name));
if (dpass && dpass->arg)
@@ -670,18 +662,14 @@ HandleCreateRole(CreateRoleStmt *stmt)
static void
HandleAlterRole(AlterRoleStmt *stmt)
{
const char *role_name = stmt->role->rolename;
DefElem *dpass;
ListCell *option;
bool found = false;
RoleEntry *entry;
InitRoleTableIfNeeded();
DefElem *dpass = NULL;
ListCell *option;
const char *role_name = stmt->role->rolename;
if (RoleIsNeonSuperuser(role_name) && !superuser())
elog(ERROR, "can't ALTER neon_superuser");
dpass = NULL;
foreach(option, stmt->options)
{
DefElem *defel = lfirst(option);
@@ -692,11 +680,13 @@ HandleAlterRole(AlterRoleStmt *stmt)
/* We only care about updates to the password */
if (!dpass)
return;
bool found = false;
RoleEntry *entry = hash_search(
CurrentDdlTable->role_table,
role_name,
HASH_ENTER,
&found);
entry = hash_search(CurrentDdlTable->role_table,
role_name,
HASH_ENTER,
&found);
if (!found)
memset(entry->old_name, 0, sizeof(entry->old_name));
if (dpass->arg)
@@ -709,22 +699,20 @@ HandleAlterRole(AlterRoleStmt *stmt)
static void
HandleRoleRename(RenameStmt *stmt)
{
bool found = false;
RoleEntry *entry;
RoleEntry *entry_for_new_name;
Assert(stmt->renameType == OBJECT_ROLE);
InitRoleTableIfNeeded();
Assert(stmt->renameType == OBJECT_ROLE);
bool found = false;
RoleEntry *entry = hash_search(
CurrentDdlTable->role_table,
stmt->subname,
HASH_FIND,
&found);
entry = hash_search(CurrentDdlTable->role_table,
stmt->subname,
HASH_FIND,
&found);
entry_for_new_name = hash_search(CurrentDdlTable->role_table,
stmt->newname,
HASH_ENTER,
NULL);
RoleEntry *entry_for_new_name = hash_search(
CurrentDdlTable->role_table,
stmt->newname,
HASH_ENTER,
NULL);
entry_for_new_name->type = Op_Set;
if (found)
@@ -750,9 +738,8 @@ HandleRoleRename(RenameStmt *stmt)
static void
HandleDropRole(DropRoleStmt *stmt)
{
ListCell *item;
InitRoleTableIfNeeded();
ListCell *item;
foreach(item, stmt->roles)
{

View File

@@ -170,14 +170,12 @@ lfc_disable(char const *op)
if (lfc_desc > 0)
{
int rc;
/*
* If the reason of error is ENOSPC, then truncation of file may
* help to reclaim some space
*/
pgstat_report_wait_start(WAIT_EVENT_NEON_LFC_TRUNCATE);
rc = ftruncate(lfc_desc, 0);
int rc = ftruncate(lfc_desc, 0);
pgstat_report_wait_end();
if (rc < 0)
@@ -668,6 +666,7 @@ lfc_readv_select(NRelFileInfo rinfo, ForkNumber forkNum, BlockNumber blkno,
BufferTag tag;
FileCacheEntry *entry;
ssize_t rc;
bool result = true;
uint32 hash;
uint64 generation;
uint32 entry_offset;
@@ -926,10 +925,10 @@ lfc_writev(NRelFileInfo rinfo, ForkNumber forkNum, BlockNumber blkno,
/* We can reuse a hole that was left behind when the LFC was shrunk previously */
FileCacheEntry *hole = dlist_container(FileCacheEntry, list_node, dlist_pop_head_node(&lfc_ctl->holes));
uint32 offset = hole->offset;
bool hole_found;
bool found;
hash_search_with_hash_value(lfc_hash, &hole->key, hole->hash, HASH_REMOVE, &hole_found);
CriticalAssert(hole_found);
hash_search_with_hash_value(lfc_hash, &hole->key, hole->hash, HASH_REMOVE, &found);
CriticalAssert(found);
lfc_ctl->used += 1;
entry->offset = offset; /* reuse the hole */
@@ -1005,7 +1004,7 @@ neon_get_lfc_stats(PG_FUNCTION_ARGS)
Datum result;
HeapTuple tuple;
char const *key;
uint64 value = 0;
uint64 value;
Datum values[NUM_NEON_GET_STATS_COLS];
bool nulls[NUM_NEON_GET_STATS_COLS];

View File

@@ -116,6 +116,8 @@ addSHLL(HyperLogLogState *cState, uint32 hash)
{
uint8 count;
uint32 index;
size_t i;
size_t j;
TimestampTz now = GetCurrentTimestamp();
/* Use the first "k" (registerWidth) bits as a zero based index */

View File

@@ -89,6 +89,7 @@ typedef struct
#if PG_VERSION_NUM >= 150000
static shmem_request_hook_type prev_shmem_request_hook = NULL;
static void walproposer_shmem_request(void);
#endif
static shmem_startup_hook_type prev_shmem_startup_hook;
static PagestoreShmemState *pagestore_shared;
@@ -440,8 +441,8 @@ pageserver_connect(shardno_t shard_no, int elevel)
return false;
}
shard->state = PS_Connecting_Startup;
/* fallthrough */
}
/* FALLTHROUGH */
case PS_Connecting_Startup:
{
char *pagestream_query;
@@ -452,6 +453,8 @@ pageserver_connect(shardno_t shard_no, int elevel)
do
{
WaitEvent event;
switch (poll_result)
{
default: /* unknown/unused states are handled as a failed connection */
@@ -582,8 +585,8 @@ pageserver_connect(shardno_t shard_no, int elevel)
}
shard->state = PS_Connecting_PageStream;
/* fallthrough */
}
/* FALLTHROUGH */
case PS_Connecting_PageStream:
{
neon_shard_log(shard_no, DEBUG5, "Connection state: Connecting_PageStream");
@@ -628,8 +631,8 @@ pageserver_connect(shardno_t shard_no, int elevel)
}
shard->state = PS_Connected;
/* fallthrough */
}
/* FALLTHROUGH */
case PS_Connected:
/*
* We successfully connected. Future connections to this PageServer

View File

@@ -94,6 +94,7 @@ neon_perf_counters_to_metrics(neon_per_backend_counters *counters)
metric_t *metrics = palloc((NUM_METRICS + 1) * sizeof(metric_t));
uint64 bucket_accum;
int i = 0;
Datum getpage_wait_str;
metrics[i].name = "getpage_wait_seconds_count";
metrics[i].is_bucket = false;
@@ -223,6 +224,7 @@ neon_get_perf_counters(PG_FUNCTION_ARGS)
ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
Datum values[3];
bool nulls[3];
Datum getpage_wait_str;
neon_per_backend_counters totals = {0};
metric_t *metrics;

View File

@@ -7,7 +7,6 @@
#define NEON_PGVERSIONCOMPAT_H
#include "fmgr.h"
#include "storage/buf_internals.h"
#if PG_MAJORVERSION_NUM < 17
#define NRelFileInfoBackendIsTemp(rinfo) (rinfo.backend != InvalidBackendId)
@@ -21,24 +20,11 @@
NInfoGetRelNumber(a) == NInfoGetRelNumber(b) \
)
/* These macros were turned into static inline functions in v16 */
/* buftag population & RelFileNode/RelFileLocator rework */
#if PG_MAJORVERSION_NUM < 16
static inline bool
BufferTagsEqual(const BufferTag *tag1, const BufferTag *tag2)
{
return BUFFERTAGS_EQUAL(*tag1, *tag2);
}
static inline void
InitBufferTag(BufferTag *tag, const RelFileNode *rnode,
ForkNumber forkNum, BlockNumber blockNum)
{
INIT_BUFFERTAG(*tag, *rnode, forkNum, blockNum);
}
#endif
#define InitBufferTag(tag, rfn, fn, bn) INIT_BUFFERTAG(*tag, *rfn, fn, bn)
/* RelFileNode -> RelFileLocator rework */
#if PG_MAJORVERSION_NUM < 16
#define USE_RELFILENODE
#define RELFILEINFO_HDR "storage/relfilenode.h"
@@ -87,6 +73,8 @@ InitBufferTag(BufferTag *tag, const RelFileNode *rnode,
#define USE_RELFILELOCATOR
#define BUFFERTAGS_EQUAL(a, b) BufferTagsEqual(&(a), &(b))
#define RELFILEINFO_HDR "storage/relfilelocator.h"
#define NRelFileInfo RelFileLocator

View File

@@ -213,6 +213,32 @@ extern const f_smgr *smgr_neon(ProcNumber backend, NRelFileInfo rinfo);
extern void smgr_init_neon(void);
extern void readahead_buffer_resize(int newsize, void *extra);
/* Neon storage manager functionality */
extern void neon_init(void);
extern void neon_open(SMgrRelation reln);
extern void neon_close(SMgrRelation reln, ForkNumber forknum);
extern void neon_create(SMgrRelation reln, ForkNumber forknum, bool isRedo);
extern bool neon_exists(SMgrRelation reln, ForkNumber forknum);
extern void neon_unlink(NRelFileInfoBackend rnode, ForkNumber forknum, bool isRedo);
#if PG_MAJORVERSION_NUM < 16
extern void neon_extend(SMgrRelation reln, ForkNumber forknum,
BlockNumber blocknum, char *buffer, bool skipFsync);
#else
extern void neon_extend(SMgrRelation reln, ForkNumber forknum,
BlockNumber blocknum, const void *buffer, bool skipFsync);
extern void neon_zeroextend(SMgrRelation reln, ForkNumber forknum,
BlockNumber blocknum, int nbuffers, bool skipFsync);
#endif
#if PG_MAJORVERSION_NUM >=17
extern bool neon_prefetch(SMgrRelation reln, ForkNumber forknum,
BlockNumber blocknum, int nblocks);
#else
extern bool neon_prefetch(SMgrRelation reln, ForkNumber forknum,
BlockNumber blocknum);
#endif
/*
* LSN values associated with each request to the pageserver
*/
@@ -252,7 +278,13 @@ extern PGDLLEXPORT void neon_read_at_lsn(NRelFileInfo rnode, ForkNumber forkNum,
extern PGDLLEXPORT void neon_read_at_lsn(NRelFileInfo rnode, ForkNumber forkNum, BlockNumber blkno,
neon_request_lsns request_lsns, void *buffer);
#endif
extern void neon_writeback(SMgrRelation reln, ForkNumber forknum,
BlockNumber blocknum, BlockNumber nblocks);
extern BlockNumber neon_nblocks(SMgrRelation reln, ForkNumber forknum);
extern int64 neon_dbsize(Oid dbNode);
extern void neon_truncate(SMgrRelation reln, ForkNumber forknum,
BlockNumber nblocks);
extern void neon_immedsync(SMgrRelation reln, ForkNumber forknum);
/* utils for neon relsize cache */
extern void relsize_hash_init(void);

View File

@@ -118,8 +118,6 @@ static UnloggedBuildPhase unlogged_build_phase = UNLOGGED_BUILD_NOT_IN_PROGRESS;
static bool neon_redo_read_buffer_filter(XLogReaderState *record, uint8 block_id);
static bool (*old_redo_read_buffer_filter) (XLogReaderState *record, uint8 block_id) = NULL;
static BlockNumber neon_nblocks(SMgrRelation reln, ForkNumber forknum);
/*
* Prefetch implementation:
*
@@ -217,7 +215,7 @@ typedef struct PrfHashEntry
sizeof(BufferTag) \
)
#define SH_EQUAL(tb, a, b) (BufferTagsEqual(&(a)->buftag, &(b)->buftag))
#define SH_EQUAL(tb, a, b) (BUFFERTAGS_EQUAL((a)->buftag, (b)->buftag))
#define SH_SCOPE static inline
#define SH_DEFINE
#define SH_DECLARE
@@ -738,7 +736,7 @@ static void
prefetch_do_request(PrefetchRequest *slot, neon_request_lsns *force_request_lsns)
{
bool found;
uint64 mySlotNo PG_USED_FOR_ASSERTS_ONLY = slot->my_ring_index;
uint64 mySlotNo = slot->my_ring_index;
NeonGetPageRequest request = {
.req.tag = T_NeonGetPageRequest,
@@ -805,19 +803,15 @@ prefetch_register_bufferv(BufferTag tag, neon_request_lsns *frlsns,
bool is_prefetch)
{
uint64 min_ring_index;
PrefetchRequest hashkey;
PrefetchRequest req;
#if USE_ASSERT_CHECKING
bool any_hits = false;
#endif
/* We will never read further ahead than our buffer can store. */
nblocks = Max(1, Min(nblocks, readahead_buffer_size));
/*
* Use an intermediate PrefetchRequest struct as the hash key to ensure
* correct alignment and that the padding bytes are cleared.
*/
memset(&hashkey.buftag, 0, sizeof(BufferTag));
hashkey.buftag = tag;
/* use an intermediate PrefetchRequest struct to ensure correct alignment */
req.buftag = tag;
Retry:
min_ring_index = UINT64_MAX;
@@ -843,8 +837,8 @@ Retry:
slot = NULL;
entry = NULL;
hashkey.buftag.blockNum = tag.blockNum + i;
entry = prfh_lookup(MyPState->prf_hash, &hashkey);
req.buftag.blockNum = tag.blockNum + i;
entry = prfh_lookup(MyPState->prf_hash, (PrefetchRequest *) &req);
if (entry != NULL)
{
@@ -855,7 +849,7 @@ Retry:
Assert(slot->status != PRFS_UNUSED);
Assert(MyPState->ring_last <= ring_index &&
ring_index < MyPState->ring_unused);
Assert(BufferTagsEqual(&slot->buftag, &hashkey.buftag));
Assert(BUFFERTAGS_EQUAL(slot->buftag, req.buftag));
/*
* If the caller specified a request LSN to use, only accept
@@ -892,19 +886,12 @@ Retry:
{
min_ring_index = Min(min_ring_index, ring_index);
/* The buffered request is good enough, return that index */
if (is_prefetch)
pgBufferUsage.prefetch.duplicates++;
else
pgBufferUsage.prefetch.hits++;
pgBufferUsage.prefetch.duplicates++;
continue;
}
}
}
else if (!is_prefetch)
{
pgBufferUsage.prefetch.misses += 1;
MyNeonCounters->getpage_prefetch_misses_total++;
}
/*
* We can only leave the block above by finding that there's
* no entry that can satisfy this request, either because there
@@ -987,7 +974,7 @@ Retry:
* We must update the slot data before insertion, because the hash
* function reads the buffer tag from the slot.
*/
slot->buftag = hashkey.buftag;
slot->buftag = req.buftag;
slot->shard_no = get_shard_number(&tag);
slot->my_ring_index = ring_index;
@@ -1465,6 +1452,7 @@ log_newpages_copy(NRelFileInfo * rinfo, ForkNumber forkNum, BlockNumber blkno,
BlockNumber blknos[XLR_MAX_BLOCK_ID];
Page pageptrs[XLR_MAX_BLOCK_ID];
int nregistered = 0;
XLogRecPtr result = 0;
for (int i = 0; i < nblocks; i++)
{
@@ -1777,7 +1765,7 @@ neon_wallog_page(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum, co
/*
* neon_init() -- Initialize private state
*/
static void
void
neon_init(void)
{
Size prfs_size;
@@ -2167,7 +2155,7 @@ neon_prefetch_response_usable(neon_request_lsns *request_lsns,
/*
* neon_exists() -- Does the physical file exist?
*/
static bool
bool
neon_exists(SMgrRelation reln, ForkNumber forkNum)
{
bool exists;
@@ -2273,7 +2261,7 @@ neon_exists(SMgrRelation reln, ForkNumber forkNum)
*
* If isRedo is true, it's okay for the relation to exist already.
*/
static void
void
neon_create(SMgrRelation reln, ForkNumber forkNum, bool isRedo)
{
switch (reln->smgr_relpersistence)
@@ -2349,7 +2337,7 @@ neon_create(SMgrRelation reln, ForkNumber forkNum, bool isRedo)
* Note: any failure should be reported as WARNING not ERROR, because
* we are usually not in a transaction anymore when this is called.
*/
static void
void
neon_unlink(NRelFileInfoBackend rinfo, ForkNumber forkNum, bool isRedo)
{
/*
@@ -2373,7 +2361,7 @@ neon_unlink(NRelFileInfoBackend rinfo, ForkNumber forkNum, bool isRedo)
* EOF). Note that we assume writing a block beyond current EOF
* causes intervening file space to become filled with zeroes.
*/
static void
void
#if PG_MAJORVERSION_NUM < 16
neon_extend(SMgrRelation reln, ForkNumber forkNum, BlockNumber blkno,
char *buffer, bool skipFsync)
@@ -2465,7 +2453,7 @@ neon_extend(SMgrRelation reln, ForkNumber forkNum, BlockNumber blkno,
}
#if PG_MAJORVERSION_NUM >= 16
static void
void
neon_zeroextend(SMgrRelation reln, ForkNumber forkNum, BlockNumber blocknum,
int nblocks, bool skipFsync)
{
@@ -2561,7 +2549,7 @@ neon_zeroextend(SMgrRelation reln, ForkNumber forkNum, BlockNumber blocknum,
/*
* neon_open() -- Initialize newly-opened relation.
*/
static void
void
neon_open(SMgrRelation reln)
{
/*
@@ -2579,7 +2567,7 @@ neon_open(SMgrRelation reln)
/*
* neon_close() -- Close the specified relation, if it isn't closed already.
*/
static void
void
neon_close(SMgrRelation reln, ForkNumber forknum)
{
/*
@@ -2594,12 +2582,13 @@ neon_close(SMgrRelation reln, ForkNumber forknum)
/*
* neon_prefetch() -- Initiate asynchronous read of the specified block of a relation
*/
static bool
bool
neon_prefetch(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
int nblocks)
{
uint64 ring_index PG_USED_FOR_ASSERTS_ONLY;
BufferTag tag;
bool io_initiated = false;
switch (reln->smgr_relpersistence)
{
@@ -2623,6 +2612,7 @@ neon_prefetch(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
while (nblocks > 0)
{
int iterblocks = Min(nblocks, PG_IOV_MAX);
int seqlen = 0;
bits8 lfc_present[PG_IOV_MAX / 8];
memset(lfc_present, 0, sizeof(lfc_present));
@@ -2634,6 +2624,8 @@ neon_prefetch(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
continue;
}
io_initiated = true;
tag.blockNum = blocknum;
for (int i = 0; i < PG_IOV_MAX / 8; i++)
@@ -2656,7 +2648,7 @@ neon_prefetch(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
/*
* neon_prefetch() -- Initiate asynchronous read of the specified block of a relation
*/
static bool
bool
neon_prefetch(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum)
{
uint64 ring_index PG_USED_FOR_ASSERTS_ONLY;
@@ -2700,7 +2692,7 @@ neon_prefetch(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum)
* This accepts a range of blocks because flushing several pages at once is
* considerably more efficient than doing so individually.
*/
static void
void
neon_writeback(SMgrRelation reln, ForkNumber forknum,
BlockNumber blocknum, BlockNumber nblocks)
{
@@ -2750,19 +2742,14 @@ neon_read_at_lsnv(NRelFileInfo rinfo, ForkNumber forkNum, BlockNumber base_block
uint64 ring_index;
PrfHashEntry *entry;
PrefetchRequest *slot;
PrefetchRequest hashkey;
BufferTag buftag = {0};
Assert(PointerIsValid(request_lsns));
Assert(nblocks >= 1);
/*
* Use an intermediate PrefetchRequest struct as the hash key to ensure
* correct alignment and that the padding bytes are cleared.
*/
memset(&hashkey.buftag, 0, sizeof(BufferTag));
CopyNRelFileInfoToBufTag(hashkey.buftag, rinfo);
hashkey.buftag.forkNum = forkNum;
hashkey.buftag.blockNum = base_blockno;
CopyNRelFileInfoToBufTag(buftag, rinfo);
buftag.forkNum = forkNum;
buftag.blockNum = base_blockno;
/*
* The redo process does not lock pages that it needs to replay but are
@@ -2780,7 +2767,7 @@ neon_read_at_lsnv(NRelFileInfo rinfo, ForkNumber forkNum, BlockNumber base_block
* weren't for the behaviour of the LwLsn cache that uses the highest
* value of the LwLsn cache when the entry is not found.
*/
prefetch_register_bufferv(hashkey.buftag, request_lsns, nblocks, mask, false);
prefetch_register_bufferv(buftag, request_lsns, nblocks, mask, false);
for (int i = 0; i < nblocks; i++)
{
@@ -2801,8 +2788,8 @@ neon_read_at_lsnv(NRelFileInfo rinfo, ForkNumber forkNum, BlockNumber base_block
* Try to find prefetched page in the list of received pages.
*/
Retry:
hashkey.buftag.blockNum = blockno;
entry = prfh_lookup(MyPState->prf_hash, &hashkey);
buftag.blockNum = blockno;
entry = prfh_lookup(MyPState->prf_hash, (PrefetchRequest *) &buftag);
if (entry != NULL)
{
@@ -2810,6 +2797,7 @@ Retry:
if (neon_prefetch_response_usable(reqlsns, slot))
{
ring_index = slot->my_ring_index;
pgBufferUsage.prefetch.hits += 1;
}
else
{
@@ -2839,7 +2827,10 @@ Retry:
{
if (entry == NULL)
{
ring_index = prefetch_register_bufferv(hashkey.buftag, reqlsns, 1, NULL, false);
pgBufferUsage.prefetch.misses += 1;
MyNeonCounters->getpage_prefetch_misses_total++;
ring_index = prefetch_register_bufferv(buftag, reqlsns, 1, NULL, false);
Assert(ring_index != UINT64_MAX);
slot = GetPrfSlot(ring_index);
}
@@ -2864,8 +2855,8 @@ Retry:
} while (!prefetch_wait_for(ring_index));
Assert(slot->status == PRFS_RECEIVED);
Assert(memcmp(&hashkey.buftag, &slot->buftag, sizeof(BufferTag)) == 0);
Assert(hashkey.buftag.blockNum == base_blockno + i);
Assert(memcmp(&buftag, &slot->buftag, sizeof(BufferTag)) == 0);
Assert(buftag.blockNum == base_blockno + i);
resp = slot->response;
@@ -2921,10 +2912,10 @@ neon_read_at_lsn(NRelFileInfo rinfo, ForkNumber forkNum, BlockNumber blkno,
* neon_read() -- Read the specified block from a relation.
*/
#if PG_MAJORVERSION_NUM < 16
static void
void
neon_read(SMgrRelation reln, ForkNumber forkNum, BlockNumber blkno, char *buffer)
#else
static void
void
neon_read(SMgrRelation reln, ForkNumber forkNum, BlockNumber blkno, void *buffer)
#endif
{
@@ -3033,7 +3024,7 @@ neon_read(SMgrRelation reln, ForkNumber forkNum, BlockNumber blkno, void *buffer
#endif /* PG_MAJORVERSION_NUM <= 16 */
#if PG_MAJORVERSION_NUM >= 17
static void
void
neon_readv(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
void **buffers, BlockNumber nblocks)
{
@@ -3068,9 +3059,6 @@ neon_readv(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
lfc_result = lfc_readv_select(InfoFromSMgrRel(reln), forknum, blocknum, buffers,
nblocks, read);
if (lfc_result > 0)
MyNeonCounters->file_cache_hits_total += lfc_result;
/* Read all blocks from LFC, so we're done */
if (lfc_result == nblocks)
return;
@@ -3197,7 +3185,6 @@ hexdump_page(char *page)
}
#endif
#if PG_MAJORVERSION_NUM < 17
/*
* neon_write() -- Write the supplied block at the appropriate location.
*
@@ -3205,7 +3192,7 @@ hexdump_page(char *page)
* relation (ie, those before the current EOF). To extend a relation,
* use mdextend().
*/
static void
void
#if PG_MAJORVERSION_NUM < 16
neon_write(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum, char *buffer, bool skipFsync)
#else
@@ -3271,12 +3258,11 @@ neon_write(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum, const vo
#endif
#endif
}
#endif
#if PG_MAJORVERSION_NUM >= 17
static void
void
neon_writev(SMgrRelation reln, ForkNumber forknum, BlockNumber blkno,
const void **buffers, BlockNumber nblocks, bool skipFsync)
{
@@ -3326,7 +3312,7 @@ neon_writev(SMgrRelation reln, ForkNumber forknum, BlockNumber blkno,
/*
* neon_nblocks() -- Get the number of blocks stored in a relation.
*/
static BlockNumber
BlockNumber
neon_nblocks(SMgrRelation reln, ForkNumber forknum)
{
NeonResponse *resp;
@@ -3463,7 +3449,7 @@ neon_dbsize(Oid dbNode)
/*
* neon_truncate() -- Truncate relation to specified number of blocks.
*/
static void
void
neon_truncate(SMgrRelation reln, ForkNumber forknum, BlockNumber nblocks)
{
XLogRecPtr lsn;
@@ -3532,7 +3518,7 @@ neon_truncate(SMgrRelation reln, ForkNumber forknum, BlockNumber nblocks)
* crash before the next checkpoint syncs the newly-inactive segment, that
* segment may survive recovery, reintroducing unwanted data into the table.
*/
static void
void
neon_immedsync(SMgrRelation reln, ForkNumber forknum)
{
switch (reln->smgr_relpersistence)
@@ -3562,8 +3548,8 @@ neon_immedsync(SMgrRelation reln, ForkNumber forknum)
}
#if PG_MAJORVERSION_NUM >= 17
static void
neon_registersync(SMgrRelation reln, ForkNumber forknum)
void
neon_regisersync(SMgrRelation reln, ForkNumber forknum)
{
switch (reln->smgr_relpersistence)
{
@@ -3747,8 +3733,6 @@ neon_read_slru_segment(SMgrRelation reln, const char* path, int segno, void* buf
SlruKind kind;
int n_blocks;
shardno_t shard_no = 0; /* All SLRUs are at shard 0 */
NeonResponse *resp;
NeonGetSlruSegmentRequest request;
/*
* Compute a request LSN to use, similar to neon_get_request_lsns() but the
@@ -3787,7 +3771,8 @@ neon_read_slru_segment(SMgrRelation reln, const char* path, int segno, void* buf
else
return -1;
request = (NeonGetSlruSegmentRequest) {
NeonResponse *resp;
NeonGetSlruSegmentRequest request = {
.req.tag = T_NeonGetSlruSegmentRequest,
.req.lsn = request_lsn,
.req.not_modified_since = not_modified_since,
@@ -3894,7 +3879,7 @@ static const struct f_smgr neon_smgr =
.smgr_truncate = neon_truncate,
.smgr_immedsync = neon_immedsync,
#if PG_MAJORVERSION_NUM >= 17
.smgr_registersync = neon_registersync,
.smgr_registersync = neon_regisersync,
#endif
.smgr_start_unlogged_build = neon_start_unlogged_build,
.smgr_finish_unlogged_build_phase_1 = neon_finish_unlogged_build_phase_1,

View File

@@ -252,6 +252,8 @@ WalProposerPoll(WalProposer *wp)
/* timeout expired: poll state */
if (rc == 0 || TimeToReconnect(wp, now) <= 0)
{
TimestampTz now;
/*
* If no WAL was generated during timeout (and we have already
* collected the quorum), then send empty keepalive message
@@ -267,7 +269,8 @@ WalProposerPoll(WalProposer *wp)
now = wp->api.get_current_timestamp(wp);
for (int i = 0; i < wp->n_safekeepers; i++)
{
sk = &wp->safekeeper[i];
Safekeeper *sk = &wp->safekeeper[i];
if (TimestampDifferenceExceeds(sk->latestMsgReceivedAt, now,
wp->config->safekeeper_connection_timeout))
{
@@ -1077,7 +1080,7 @@ SendProposerElected(Safekeeper *sk)
ProposerElected msg;
TermHistory *th;
term_t lastCommonTerm;
int idx;
int i;
/* Now that we are ready to send it's a good moment to create WAL reader */
wp->api.wal_reader_allocate(sk);
@@ -1096,15 +1099,15 @@ SendProposerElected(Safekeeper *sk)
/* We must start somewhere. */
Assert(wp->propTermHistory.n_entries >= 1);
for (idx = 0; idx < Min(wp->propTermHistory.n_entries, th->n_entries); idx++)
for (i = 0; i < Min(wp->propTermHistory.n_entries, th->n_entries); i++)
{
if (wp->propTermHistory.entries[idx].term != th->entries[idx].term)
if (wp->propTermHistory.entries[i].term != th->entries[i].term)
break;
/* term must begin everywhere at the same point */
Assert(wp->propTermHistory.entries[idx].lsn == th->entries[idx].lsn);
Assert(wp->propTermHistory.entries[i].lsn == th->entries[i].lsn);
}
idx--; /* step back to the last common term */
if (idx < 0)
i--; /* step back to the last common term */
if (i < 0)
{
/* safekeeper is empty or no common point, start from the beginning */
sk->startStreamingAt = wp->propTermHistory.entries[0].lsn;
@@ -1125,14 +1128,14 @@ SendProposerElected(Safekeeper *sk)
* proposer, LSN it is currently writing, but then we just pick
* safekeeper pos as it obviously can't be higher.
*/
if (wp->propTermHistory.entries[idx].term == wp->propTerm)
if (wp->propTermHistory.entries[i].term == wp->propTerm)
{
sk->startStreamingAt = sk->voteResponse.flushLsn;
}
else
{
XLogRecPtr propEndLsn = wp->propTermHistory.entries[idx + 1].lsn;
XLogRecPtr skEndLsn = (idx + 1 < th->n_entries ? th->entries[idx + 1].lsn : sk->voteResponse.flushLsn);
XLogRecPtr propEndLsn = wp->propTermHistory.entries[i + 1].lsn;
XLogRecPtr skEndLsn = (i + 1 < th->n_entries ? th->entries[i + 1].lsn : sk->voteResponse.flushLsn);
sk->startStreamingAt = Min(propEndLsn, skEndLsn);
}
@@ -1146,7 +1149,7 @@ SendProposerElected(Safekeeper *sk)
msg.termHistory = &wp->propTermHistory;
msg.timelineStartLsn = wp->timelineStartLsn;
lastCommonTerm = idx >= 0 ? wp->propTermHistory.entries[idx].term : 0;
lastCommonTerm = i >= 0 ? wp->propTermHistory.entries[i].term : 0;
wp_log(LOG,
"sending elected msg to node " UINT64_FORMAT " term=" UINT64_FORMAT ", startStreamingAt=%X/%X (lastCommonTerm=" UINT64_FORMAT "), termHistory.n_entries=%u to %s:%s, timelineStartLsn=%X/%X",
sk->greetResponse.nodeId, msg.term, LSN_FORMAT_ARGS(msg.startStreamingAt), lastCommonTerm, msg.termHistory->n_entries, sk->host, sk->port, LSN_FORMAT_ARGS(msg.timelineStartLsn));
@@ -1638,7 +1641,7 @@ UpdateDonorShmem(WalProposer *wp)
* Process AppendResponse message from safekeeper.
*/
static void
HandleSafekeeperResponse(WalProposer *wp, Safekeeper *fromsk)
HandleSafekeeperResponse(WalProposer *wp, Safekeeper *sk)
{
XLogRecPtr candidateTruncateLsn;
XLogRecPtr newCommitLsn;
@@ -1657,7 +1660,7 @@ HandleSafekeeperResponse(WalProposer *wp, Safekeeper *fromsk)
* and WAL is committed by the quorum. BroadcastAppendRequest() should be
* called to notify safekeepers about the new commitLsn.
*/
wp->api.process_safekeeper_feedback(wp, fromsk);
wp->api.process_safekeeper_feedback(wp, sk);
/*
* Try to advance truncateLsn -- the last record flushed to all

View File

@@ -725,7 +725,7 @@ extern void WalProposerBroadcast(WalProposer *wp, XLogRecPtr startpos, XLogRecPt
extern void WalProposerPoll(WalProposer *wp);
extern void WalProposerFree(WalProposer *wp);
extern WalproposerShmemState *GetWalpropShmemState(void);
extern WalproposerShmemState *GetWalpropShmemState();
/*
* WaitEventSet API doesn't allow to remove socket, so walproposer_pg uses it to
@@ -745,7 +745,7 @@ extern TimeLineID walprop_pg_get_timeline_id(void);
* catch logging.
*/
#ifdef WALPROPOSER_LIB
extern void WalProposerLibLog(WalProposer *wp, int elevel, char *fmt,...) pg_attribute_printf(3, 4);
extern void WalProposerLibLog(WalProposer *wp, int elevel, char *fmt,...);
#define wp_log(elevel, fmt, ...) WalProposerLibLog(wp, elevel, fmt, ## __VA_ARGS__)
#else
#define wp_log(elevel, fmt, ...) elog(elevel, WP_LOG_PREFIX fmt, ## __VA_ARGS__)

View File

@@ -286,9 +286,6 @@ safekeepers_cmp(char *old, char *new)
static void
assign_neon_safekeepers(const char *newval, void *extra)
{
char *newval_copy;
char *oldval;
if (!am_walproposer)
return;
@@ -298,8 +295,8 @@ assign_neon_safekeepers(const char *newval, void *extra)
}
/* Copy values because we will modify them in split_safekeepers_list() */
newval_copy = pstrdup(newval);
oldval = pstrdup(wal_acceptors_list);
char *newval_copy = pstrdup(newval);
char *oldval = pstrdup(wal_acceptors_list);
/*
* TODO: restarting through FATAL is stupid and introduces 1s delay before
@@ -541,7 +538,7 @@ nwp_shmem_startup_hook(void)
}
WalproposerShmemState *
GetWalpropShmemState(void)
GetWalpropShmemState()
{
Assert(walprop_shared != NULL);
return walprop_shared;

View File

@@ -191,14 +191,13 @@ NeonOnDemandXLogReaderRoutines(XLogReaderRoutine *xlr)
if (!wal_reader)
{
XLogRecPtr basebackupLsn = GetRedoStartLsn();
XLogRecPtr epochStartLsn = pg_atomic_read_u64(&GetWalpropShmemState()->propEpochStartLsn);
/* should never happen */
if (basebackupLsn == 0)
if (epochStartLsn == 0)
{
elog(ERROR, "unable to start walsender when basebackupLsn is 0");
elog(ERROR, "Unable to start walsender when propEpochStartLsn is 0!");
}
wal_reader = NeonWALReaderAllocate(wal_segment_size, basebackupLsn, "[walsender] ");
wal_reader = NeonWALReaderAllocate(wal_segment_size, epochStartLsn, "[walsender] ");
}
xlr->page_read = NeonWALPageRead;
xlr->segment_open = NeonWALReadSegmentOpen;

View File

@@ -44,6 +44,27 @@ infobits_desc(StringInfo buf, uint8 infobits, const char *keyname)
appendStringInfoString(buf, "]");
}
static void
truncate_flags_desc(StringInfo buf, uint8 flags)
{
appendStringInfoString(buf, "flags: [");
if (flags & XLH_TRUNCATE_CASCADE)
appendStringInfoString(buf, "CASCADE, ");
if (flags & XLH_TRUNCATE_RESTART_SEQS)
appendStringInfoString(buf, "RESTART_SEQS, ");
if (buf->data[buf->len - 1] == ' ')
{
/* Truncate-away final unneeded ", " */
Assert(buf->data[buf->len - 2] == ',');
buf->len -= 2;
buf->data[buf->len] = '\0';
}
appendStringInfoString(buf, "]");
}
void
neon_rm_desc(StringInfo buf, XLogReaderState *record)
{

View File

@@ -136,7 +136,7 @@ static bool redo_block_filter(XLogReaderState *record, uint8 block_id);
static void GetPage(StringInfo input_message);
static void Ping(StringInfo input_message);
static ssize_t buffered_read(void *buf, size_t count);
static void CreateFakeSharedMemoryAndSemaphores(void);
static void CreateFakeSharedMemoryAndSemaphores();
static BufferTag target_redo_tag;
@@ -170,40 +170,6 @@ close_range_syscall(unsigned int start_fd, unsigned int count, unsigned int flag
return syscall(__NR_close_range, start_fd, count, flags);
}
static PgSeccompRule allowed_syscalls[] =
{
/* Hard requirements */
PG_SCMP_ALLOW(exit_group),
PG_SCMP_ALLOW(pselect6),
PG_SCMP_ALLOW(read),
PG_SCMP_ALLOW(select),
PG_SCMP_ALLOW(write),
/* Memory allocation */
PG_SCMP_ALLOW(brk),
#ifndef MALLOC_NO_MMAP
/* TODO: musl doesn't have mallopt */
PG_SCMP_ALLOW(mmap),
PG_SCMP_ALLOW(munmap),
#endif
/*
* getpid() is called on assertion failure, in ExceptionalCondition.
* It's not really needed, but seems pointless to hide it either. The
* system call unlikely to expose a kernel vulnerability, and the PID
* is stored in MyProcPid anyway.
*/
PG_SCMP_ALLOW(getpid),
/* Enable those for a proper shutdown. */
#if 0
PG_SCMP_ALLOW(munmap),
PG_SCMP_ALLOW(shmctl),
PG_SCMP_ALLOW(shmdt),
PG_SCMP_ALLOW(unlink), /* shm_unlink */
#endif
};
static void
enter_seccomp_mode(void)
{
@@ -217,12 +183,44 @@ enter_seccomp_mode(void)
(errcode(ERRCODE_SYSTEM_ERROR),
errmsg("seccomp: could not close files >= fd 3")));
PgSeccompRule syscalls[] =
{
/* Hard requirements */
PG_SCMP_ALLOW(exit_group),
PG_SCMP_ALLOW(pselect6),
PG_SCMP_ALLOW(read),
PG_SCMP_ALLOW(select),
PG_SCMP_ALLOW(write),
/* Memory allocation */
PG_SCMP_ALLOW(brk),
#ifndef MALLOC_NO_MMAP
/* TODO: musl doesn't have mallopt */
PG_SCMP_ALLOW(mmap),
PG_SCMP_ALLOW(munmap),
#endif
/*
* getpid() is called on assertion failure, in ExceptionalCondition.
* It's not really needed, but seems pointless to hide it either. The
* system call unlikely to expose a kernel vulnerability, and the PID
* is stored in MyProcPid anyway.
*/
PG_SCMP_ALLOW(getpid),
/* Enable those for a proper shutdown.
PG_SCMP_ALLOW(munmap),
PG_SCMP_ALLOW(shmctl),
PG_SCMP_ALLOW(shmdt),
PG_SCMP_ALLOW(unlink), // shm_unlink
*/
};
#ifdef MALLOC_NO_MMAP
/* Ask glibc not to use mmap() */
mallopt(M_MMAP_MAX, 0);
#endif
seccomp_load_rules(allowed_syscalls, lengthof(allowed_syscalls));
seccomp_load_rules(syscalls, lengthof(syscalls));
}
#endif /* HAVE_LIBSECCOMP */
@@ -451,7 +449,7 @@ WalRedoMain(int argc, char *argv[])
* half-initialized postgres.
*/
static void
CreateFakeSharedMemoryAndSemaphores(void)
CreateFakeSharedMemoryAndSemaphores()
{
PGShmemHeader *shim = NULL;
PGShmemHeader *hdr;
@@ -994,7 +992,7 @@ redo_block_filter(XLogReaderState *record, uint8 block_id)
* If this block isn't one we are currently restoring, then return 'true'
* so that this gets ignored
*/
return !BufferTagsEqual(&target_tag, &target_redo_tag);
return !BUFFERTAGS_EQUAL(target_tag, target_redo_tag);
}
/*

View File

@@ -38,7 +38,7 @@ hostname.workspace = true
http.workspace = true
humantime.workspace = true
humantime-serde.workspace = true
hyper0.workspace = true
hyper.workspace = true
hyper1 = { package = "hyper", version = "1.2", features = ["server"] }
hyper-util = { version = "0.1", features = ["server", "http1", "http2", "tokio"] }
http-body-util = { version = "0.1" }

View File

@@ -18,7 +18,7 @@ pub(crate) use flow::*;
use tokio::time::error::Elapsed;
use crate::{
control_plane,
console,
error::{ReportableError, UserFacingError},
};
use std::{io, net::IpAddr};
@@ -34,7 +34,7 @@ pub(crate) enum AuthErrorImpl {
Web(#[from] backend::WebAuthError),
#[error(transparent)]
GetAuthInfo(#[from] control_plane::errors::GetAuthInfoError),
GetAuthInfo(#[from] console::errors::GetAuthInfoError),
/// SASL protocol errors (includes [SCRAM](crate::scram)).
#[error(transparent)]

View File

@@ -1,27 +1,27 @@
mod classic;
mod console_redirect;
mod hacks;
pub mod jwt;
pub mod local;
mod web;
use std::net::IpAddr;
use std::sync::Arc;
use std::time::Duration;
pub(crate) use console_redirect::WebAuthError;
use ipnet::{Ipv4Net, Ipv6Net};
use local::LocalBackend;
use tokio::io::{AsyncRead, AsyncWrite};
use tokio_postgres::config::AuthKeys;
use tracing::{info, warn};
pub(crate) use web::WebAuthError;
use crate::auth::credentials::check_peer_addr_is_in_list;
use crate::auth::{validate_password_and_exchange, AuthError};
use crate::cache::Cached;
use crate::console::errors::GetAuthInfoError;
use crate::console::provider::{CachedRoleSecret, ConsoleBackend};
use crate::console::{AuthSecret, NodeInfo};
use crate::context::RequestMonitoring;
use crate::control_plane::errors::GetAuthInfoError;
use crate::control_plane::provider::{CachedRoleSecret, ControlPlaneBackend};
use crate::control_plane::{AuthSecret, NodeInfo};
use crate::intern::EndpointIdInt;
use crate::metrics::Metrics;
use crate::proxy::connect_compute::ComputeConnectBackend;
@@ -31,7 +31,7 @@ use crate::stream::Stream;
use crate::{
auth::{self, ComputeUserInfoMaybeEndpoint},
config::AuthenticationConfig,
control_plane::{
console::{
self,
provider::{CachedAllowedIps, CachedNodeInfo},
Api,
@@ -67,19 +67,19 @@ impl<T> std::ops::Deref for MaybeOwned<'_, T> {
/// backends which require them for the authentication process.
pub enum Backend<'a, T, D> {
/// Cloud API (V2).
ControlPlane(MaybeOwned<'a, ControlPlaneBackend>, T),
Console(MaybeOwned<'a, ConsoleBackend>, T),
/// Authentication via a web browser.
ConsoleRedirect(MaybeOwned<'a, url::ApiUrl>, D),
Web(MaybeOwned<'a, url::ApiUrl>, D),
/// Local proxy uses configured auth credentials and does not wake compute
Local(MaybeOwned<'a, LocalBackend>),
}
#[cfg(test)]
pub(crate) trait TestBackend: Send + Sync + 'static {
fn wake_compute(&self) -> Result<CachedNodeInfo, control_plane::errors::WakeComputeError>;
fn wake_compute(&self) -> Result<CachedNodeInfo, console::errors::WakeComputeError>;
fn get_allowed_ips_and_secret(
&self,
) -> Result<(CachedAllowedIps, Option<CachedRoleSecret>), control_plane::errors::GetAuthInfoError>;
) -> Result<(CachedAllowedIps, Option<CachedRoleSecret>), console::errors::GetAuthInfoError>;
fn dyn_clone(&self) -> Box<dyn TestBackend>;
}
@@ -93,23 +93,18 @@ impl Clone for Box<dyn TestBackend> {
impl std::fmt::Display for Backend<'_, (), ()> {
fn fmt(&self, fmt: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
match self {
Self::ControlPlane(api, ()) => match &**api {
ControlPlaneBackend::Management(endpoint) => fmt
.debug_tuple("ControlPlane::Management")
.field(&endpoint.url())
.finish(),
Self::Console(api, ()) => match &**api {
ConsoleBackend::Console(endpoint) => {
fmt.debug_tuple("Console").field(&endpoint.url()).finish()
}
#[cfg(any(test, feature = "testing"))]
ControlPlaneBackend::PostgresMock(endpoint) => fmt
.debug_tuple("ControlPlane::PostgresMock")
.field(&endpoint.url())
.finish(),
ConsoleBackend::Postgres(endpoint) => {
fmt.debug_tuple("Postgres").field(&endpoint.url()).finish()
}
#[cfg(test)]
ControlPlaneBackend::Test(_) => fmt.debug_tuple("ControlPlane::Test").finish(),
ConsoleBackend::Test(_) => fmt.debug_tuple("Test").finish(),
},
Self::ConsoleRedirect(url, ()) => fmt
.debug_tuple("ConsoleRedirect")
.field(&url.as_str())
.finish(),
Self::Web(url, ()) => fmt.debug_tuple("Web").field(&url.as_str()).finish(),
Self::Local(_) => fmt.debug_tuple("Local").finish(),
}
}
@@ -120,8 +115,8 @@ impl<T, D> Backend<'_, T, D> {
/// This helps us pass structured config to async tasks.
pub(crate) fn as_ref(&self) -> Backend<'_, &T, &D> {
match self {
Self::ControlPlane(c, x) => Backend::ControlPlane(MaybeOwned::Borrowed(c), x),
Self::ConsoleRedirect(c, x) => Backend::ConsoleRedirect(MaybeOwned::Borrowed(c), x),
Self::Console(c, x) => Backend::Console(MaybeOwned::Borrowed(c), x),
Self::Web(c, x) => Backend::Web(MaybeOwned::Borrowed(c), x),
Self::Local(l) => Backend::Local(MaybeOwned::Borrowed(l)),
}
}
@@ -133,8 +128,8 @@ impl<'a, T, D> Backend<'a, T, D> {
/// a function to a contained value.
pub(crate) fn map<R>(self, f: impl FnOnce(T) -> R) -> Backend<'a, R, D> {
match self {
Self::ControlPlane(c, x) => Backend::ControlPlane(c, f(x)),
Self::ConsoleRedirect(c, x) => Backend::ConsoleRedirect(c, x),
Self::Console(c, x) => Backend::Console(c, f(x)),
Self::Web(c, x) => Backend::Web(c, x),
Self::Local(l) => Backend::Local(l),
}
}
@@ -144,8 +139,8 @@ impl<'a, T, D, E> Backend<'a, Result<T, E>, D> {
/// This is most useful for error handling.
pub(crate) fn transpose(self) -> Result<Backend<'a, T, D>, E> {
match self {
Self::ControlPlane(c, x) => x.map(|x| Backend::ControlPlane(c, x)),
Self::ConsoleRedirect(c, x) => Ok(Backend::ConsoleRedirect(c, x)),
Self::Console(c, x) => x.map(|x| Backend::Console(c, x)),
Self::Web(c, x) => Ok(Backend::Web(c, x)),
Self::Local(l) => Ok(Backend::Local(l)),
}
}
@@ -295,7 +290,7 @@ impl AuthenticationConfig {
/// All authentication flows will emit an AuthenticationOk message if successful.
async fn auth_quirks(
ctx: &RequestMonitoring,
api: &impl control_plane::Api,
api: &impl console::Api,
user_info: ComputeUserInfoMaybeEndpoint,
client: &mut stream::PqStream<Stream<impl AsyncRead + AsyncWrite + Unpin>>,
allow_cleartext: bool,
@@ -417,8 +412,8 @@ impl<'a> Backend<'a, ComputeUserInfoMaybeEndpoint, &()> {
/// Get username from the credentials.
pub(crate) fn get_user(&self) -> &str {
match self {
Self::ControlPlane(_, user_info) => &user_info.user,
Self::ConsoleRedirect(_, ()) => "web",
Self::Console(_, user_info) => &user_info.user,
Self::Web(_, ()) => "web",
Self::Local(_) => "local",
}
}
@@ -434,7 +429,7 @@ impl<'a> Backend<'a, ComputeUserInfoMaybeEndpoint, &()> {
endpoint_rate_limiter: Arc<EndpointRateLimiter>,
) -> auth::Result<Backend<'a, ComputeCredentials, NodeInfo>> {
let res = match self {
Self::ControlPlane(api, user_info) => {
Self::Console(api, user_info) => {
info!(
user = &*user_info.user,
project = user_info.endpoint(),
@@ -451,15 +446,15 @@ impl<'a> Backend<'a, ComputeUserInfoMaybeEndpoint, &()> {
endpoint_rate_limiter,
)
.await?;
Backend::ControlPlane(api, credentials)
Backend::Console(api, credentials)
}
// NOTE: this auth backend doesn't use client credentials.
Self::ConsoleRedirect(url, ()) => {
Self::Web(url, ()) => {
info!("performing web authentication");
let info = console_redirect::authenticate(ctx, config, &url, client).await?;
let info = web::authenticate(ctx, config, &url, client).await?;
Backend::ConsoleRedirect(url, info)
Backend::Web(url, info)
}
Self::Local(_) => {
return Err(auth::AuthError::bad_auth_method("invalid for local proxy"))
@@ -477,8 +472,8 @@ impl Backend<'_, ComputeUserInfo, &()> {
ctx: &RequestMonitoring,
) -> Result<CachedRoleSecret, GetAuthInfoError> {
match self {
Self::ControlPlane(api, user_info) => api.get_role_secret(ctx, user_info).await,
Self::ConsoleRedirect(_, ()) => Ok(Cached::new_uncached(None)),
Self::Console(api, user_info) => api.get_role_secret(ctx, user_info).await,
Self::Web(_, ()) => Ok(Cached::new_uncached(None)),
Self::Local(_) => Ok(Cached::new_uncached(None)),
}
}
@@ -488,10 +483,8 @@ impl Backend<'_, ComputeUserInfo, &()> {
ctx: &RequestMonitoring,
) -> Result<(CachedAllowedIps, Option<CachedRoleSecret>), GetAuthInfoError> {
match self {
Self::ControlPlane(api, user_info) => {
api.get_allowed_ips_and_secret(ctx, user_info).await
}
Self::ConsoleRedirect(_, ()) => Ok((Cached::new_uncached(Arc::new(vec![])), None)),
Self::Console(api, user_info) => api.get_allowed_ips_and_secret(ctx, user_info).await,
Self::Web(_, ()) => Ok((Cached::new_uncached(Arc::new(vec![])), None)),
Self::Local(_) => Ok((Cached::new_uncached(Arc::new(vec![])), None)),
}
}
@@ -502,18 +495,18 @@ impl ComputeConnectBackend for Backend<'_, ComputeCredentials, NodeInfo> {
async fn wake_compute(
&self,
ctx: &RequestMonitoring,
) -> Result<CachedNodeInfo, control_plane::errors::WakeComputeError> {
) -> Result<CachedNodeInfo, console::errors::WakeComputeError> {
match self {
Self::ControlPlane(api, creds) => api.wake_compute(ctx, &creds.info).await,
Self::ConsoleRedirect(_, info) => Ok(Cached::new_uncached(info.clone())),
Self::Console(api, creds) => api.wake_compute(ctx, &creds.info).await,
Self::Web(_, info) => Ok(Cached::new_uncached(info.clone())),
Self::Local(local) => Ok(Cached::new_uncached(local.node_info.clone())),
}
}
fn get_keys(&self) -> &ComputeCredentialKeys {
match self {
Self::ControlPlane(_, creds) => &creds.keys,
Self::ConsoleRedirect(_, _) => &ComputeCredentialKeys::None,
Self::Console(_, creds) => &creds.keys,
Self::Web(_, _) => &ComputeCredentialKeys::None,
Self::Local(_) => &ComputeCredentialKeys::None,
}
}
@@ -524,10 +517,10 @@ impl ComputeConnectBackend for Backend<'_, ComputeCredentials, &()> {
async fn wake_compute(
&self,
ctx: &RequestMonitoring,
) -> Result<CachedNodeInfo, control_plane::errors::WakeComputeError> {
) -> Result<CachedNodeInfo, console::errors::WakeComputeError> {
match self {
Self::ControlPlane(api, creds) => api.wake_compute(ctx, &creds.info).await,
Self::ConsoleRedirect(_, ()) => {
Self::Console(api, creds) => api.wake_compute(ctx, &creds.info).await,
Self::Web(_, ()) => {
unreachable!("web auth flow doesn't support waking the compute")
}
Self::Local(local) => Ok(Cached::new_uncached(local.node_info.clone())),
@@ -536,8 +529,8 @@ impl ComputeConnectBackend for Backend<'_, ComputeCredentials, &()> {
fn get_keys(&self) -> &ComputeCredentialKeys {
match self {
Self::ControlPlane(_, creds) => &creds.keys,
Self::ConsoleRedirect(_, ()) => &ComputeCredentialKeys::None,
Self::Console(_, creds) => &creds.keys,
Self::Web(_, ()) => &ComputeCredentialKeys::None,
Self::Local(_) => &ComputeCredentialKeys::None,
}
}
@@ -560,12 +553,12 @@ mod tests {
use crate::{
auth::{backend::MaskedIp, ComputeUserInfoMaybeEndpoint, IpPattern},
config::AuthenticationConfig,
context::RequestMonitoring,
control_plane::{
console::{
self,
provider::{self, CachedAllowedIps, CachedRoleSecret},
CachedNodeInfo,
},
context::RequestMonitoring,
proxy::NeonOptions,
rate_limiter::{EndpointRateLimiter, RateBucketInfo},
scram::{threadpool::ThreadPool, ServerSecret},
@@ -579,12 +572,12 @@ mod tests {
secret: AuthSecret,
}
impl control_plane::Api for Auth {
impl console::Api for Auth {
async fn get_role_secret(
&self,
_ctx: &RequestMonitoring,
_user_info: &super::ComputeUserInfo,
) -> Result<CachedRoleSecret, control_plane::errors::GetAuthInfoError> {
) -> Result<CachedRoleSecret, console::errors::GetAuthInfoError> {
Ok(CachedRoleSecret::new_uncached(Some(self.secret.clone())))
}
@@ -592,10 +585,8 @@ mod tests {
&self,
_ctx: &RequestMonitoring,
_user_info: &super::ComputeUserInfo,
) -> Result<
(CachedAllowedIps, Option<CachedRoleSecret>),
control_plane::errors::GetAuthInfoError,
> {
) -> Result<(CachedAllowedIps, Option<CachedRoleSecret>), console::errors::GetAuthInfoError>
{
Ok((
CachedAllowedIps::new_uncached(Arc::new(self.ips.clone())),
Some(CachedRoleSecret::new_uncached(Some(self.secret.clone()))),
@@ -614,7 +605,7 @@ mod tests {
&self,
_ctx: &RequestMonitoring,
_user_info: &super::ComputeUserInfo,
) -> Result<CachedNodeInfo, control_plane::errors::WakeComputeError> {
) -> Result<CachedNodeInfo, console::errors::WakeComputeError> {
unimplemented!()
}
}

View File

@@ -3,8 +3,8 @@ use crate::{
auth::{self, backend::ComputeCredentialKeys, AuthFlow},
compute,
config::AuthenticationConfig,
console::AuthSecret,
context::RequestMonitoring,
control_plane::AuthSecret,
sasl,
stream::{PqStream, Stream},
};

View File

@@ -2,8 +2,8 @@ use super::{ComputeCredentials, ComputeUserInfo, ComputeUserInfoNoEndpoint};
use crate::{
auth::{self, AuthFlow},
config::AuthenticationConfig,
console::AuthSecret,
context::RequestMonitoring,
control_plane::AuthSecret,
intern::EndpointIdInt,
sasl,
stream::{self, Stream},

View File

@@ -5,11 +5,11 @@ use arc_swap::ArcSwapOption;
use crate::{
compute::ConnCfg,
context::RequestMonitoring,
control_plane::{
console::{
messages::{ColdStartInfo, EndpointJwksResponse, MetricsAuxInfo},
NodeInfo,
},
context::RequestMonitoring,
intern::{BranchIdTag, EndpointIdTag, InternId, ProjectIdTag},
EndpointId,
};

View File

@@ -1,8 +1,8 @@
use crate::{
auth, compute,
config::AuthenticationConfig,
console::{self, provider::NodeInfo},
context::RequestMonitoring,
control_plane::{self, provider::NodeInfo},
error::{ReportableError, UserFacingError},
stream::PqStream,
waiters,
@@ -70,7 +70,7 @@ pub(super) async fn authenticate(
let (psql_session_id, waiter) = loop {
let psql_session_id = new_psql_session_id();
match control_plane::mgmt::get_waiter(&psql_session_id) {
match console::mgmt::get_waiter(&psql_session_id) {
Ok(waiter) => break (psql_session_id, waiter),
Err(_e) => continue,
}

View File

@@ -3,8 +3,8 @@
use super::{backend::ComputeCredentialKeys, AuthErrorImpl, PasswordHackPayload};
use crate::{
config::TlsServerEndPoint,
console::AuthSecret,
context::RequestMonitoring,
control_plane::AuthSecret,
intern::EndpointIdInt,
sasl,
scram::{self, threadpool::ThreadPool},

View File

@@ -12,7 +12,7 @@ use proxy::{
},
cancellation::CancellationHandlerMain,
config::{self, AuthenticationConfig, HttpConfig, ProxyConfig, RetryConfig},
control_plane::{
console::{
locks::ApiLocks,
messages::{EndpointJwksResponse, JwksSettings},
},
@@ -77,10 +77,10 @@ struct LocalProxyCliArgs {
#[clap(long, default_value = "127.0.0.1:5432")]
compute: SocketAddr,
/// Path of the local proxy config file
#[clap(long, default_value = "./local_proxy.json")]
#[clap(long, default_value = "./localproxy.json")]
config_path: Utf8PathBuf,
/// Path of the local proxy PID file
#[clap(long, default_value = "./local_proxy.pid")]
#[clap(long, default_value = "./localproxy.pid")]
pid_path: Utf8PathBuf,
}
@@ -109,7 +109,7 @@ struct SqlOverHttpArgs {
#[tokio::main]
async fn main() -> anyhow::Result<()> {
let _logging_guard = proxy::logging::init_local_proxy()?;
let _logging_guard = proxy::logging::init().await?;
let _panic_hook_guard = utils::logging::replace_panic_hook_with_tracing_panic_hook();
let _sentry_guard = init_sentry(Some(GIT_VERSION.into()), &[]);
@@ -138,7 +138,7 @@ async fn main() -> anyhow::Result<()> {
// in order to trigger the appropriate SIGHUP on config change.
//
// This also claims a "lock" that makes sure only one instance
// of local_proxy runs at a time.
// of local-proxy runs at a time.
let _process_guard = loop {
match pid_file::claim_for_current_process(&args.pid_path) {
Ok(guard) => break guard,
@@ -164,6 +164,12 @@ async fn main() -> anyhow::Result<()> {
16,
));
// write the process ID to a file so that compute-ctl can find our process later
// in order to trigger the appropriate SIGHUP on config change.
let pid = std::process::id();
info!("process running in PID {pid}");
std::fs::write(args.pid_path, format!("{pid}\n")).context("writing PID to file")?;
let mut maintenance_tasks = JoinSet::new();
let refresh_config_notify = Arc::new(Notify::new());
@@ -176,9 +182,9 @@ async fn main() -> anyhow::Result<()> {
// trigger the first config load **after** setting up the signal hook
// to avoid the race condition where:
// 1. No config file registered when local_proxy starts up
// 1. No config file registered when local-proxy starts up
// 2. The config file is written but the signal hook is not yet received
// 3. local_proxy completes startup but has no config loaded, despite there being a registerd config.
// 3. local-proxy completes startup but has no config loaded, despite there being a registerd config.
refresh_config_notify.notify_one();
tokio::spawn(refresh_config_loop(args.config_path, refresh_config_notify));
@@ -305,7 +311,7 @@ async fn refresh_config_inner(path: &Utf8Path) -> anyhow::Result<()> {
let mut jwks_set = vec![];
for jwks in data.jwks.into_iter().flatten() {
for jwks in data.jwks {
let mut jwks_url = url::Url::from_str(&jwks.jwks_url).context("parsing JWKS url")?;
ensure!(

View File

@@ -19,8 +19,8 @@ use proxy::config::CacheOptions;
use proxy::config::HttpConfig;
use proxy::config::ProjectInfoCacheOptions;
use proxy::config::ProxyProtocolV2;
use proxy::console;
use proxy::context::parquet::ParquetUploadArgs;
use proxy::control_plane;
use proxy::http;
use proxy::http::health_server::AppMetrics;
use proxy::metrics::Metrics;
@@ -495,7 +495,7 @@ async fn main() -> anyhow::Result<()> {
proxy: proxy::metrics::Metrics::get(),
},
));
maintenance_tasks.spawn(control_plane::mgmt::task_main(mgmt_listener));
maintenance_tasks.spawn(console::mgmt::task_main(mgmt_listener));
if let Some(metrics_config) = &config.metric_collection {
// TODO: Add gc regardles of the metric collection being enabled.
@@ -506,8 +506,8 @@ async fn main() -> anyhow::Result<()> {
));
}
if let auth::Backend::ControlPlane(api, _) = &config.auth_backend {
if let proxy::control_plane::provider::ControlPlaneBackend::Management(api) = &**api {
if let auth::Backend::Console(api, _) = &config.auth_backend {
if let proxy::console::provider::ConsoleBackend::Console(api) = &**api {
match (redis_notifications_client, regional_redis_client.clone()) {
(None, None) => {}
(client1, client2) => {
@@ -623,7 +623,7 @@ fn build_config(args: &ProxyCliArgs) -> anyhow::Result<&'static ProxyConfig> {
"Using AllowedIpsCache (wake_compute) with options={project_info_cache_config:?}"
);
info!("Using EndpointCacheConfig with options={endpoint_cache_config:?}");
let caches = Box::leak(Box::new(control_plane::caches::ApiCaches::new(
let caches = Box::leak(Box::new(console::caches::ApiCaches::new(
wake_compute_cache_config,
project_info_cache_config,
endpoint_cache_config,
@@ -636,7 +636,7 @@ fn build_config(args: &ProxyCliArgs) -> anyhow::Result<&'static ProxyConfig> {
timeout,
} = args.wake_compute_lock.parse()?;
info!(?limiter, shards, ?epoch, "Using NodeLocks (wake_compute)");
let locks = Box::leak(Box::new(control_plane::locks::ApiLocks::new(
let locks = Box::leak(Box::new(console::locks::ApiLocks::new(
"wake_compute_lock",
limiter,
shards,
@@ -653,27 +653,27 @@ fn build_config(args: &ProxyCliArgs) -> anyhow::Result<&'static ProxyConfig> {
RateBucketInfo::validate(&mut wake_compute_rps_limit)?;
let wake_compute_endpoint_rate_limiter =
Arc::new(WakeComputeRateLimiter::new(wake_compute_rps_limit));
let api = control_plane::provider::neon::Api::new(
let api = console::provider::neon::Api::new(
endpoint,
caches,
locks,
wake_compute_endpoint_rate_limiter,
);
let api = control_plane::provider::ControlPlaneBackend::Management(api);
auth::Backend::ControlPlane(MaybeOwned::Owned(api), ())
let api = console::provider::ConsoleBackend::Console(api);
auth::Backend::Console(MaybeOwned::Owned(api), ())
}
AuthBackendType::Web => {
let url = args.uri.parse()?;
auth::Backend::ConsoleRedirect(MaybeOwned::Owned(url), ())
auth::Backend::Web(MaybeOwned::Owned(url), ())
}
#[cfg(feature = "testing")]
AuthBackendType::Postgres => {
let url = args.auth_endpoint.parse()?;
let api = control_plane::provider::mock::Api::new(url, !args.is_private_access_proxy);
let api = control_plane::provider::ControlPlaneBackend::PostgresMock(api);
auth::Backend::ControlPlane(MaybeOwned::Owned(api), ())
let api = console::provider::mock::Api::new(url, !args.is_private_access_proxy);
let api = console::provider::ConsoleBackend::Postgres(api);
auth::Backend::Console(MaybeOwned::Owned(api), ())
}
};
@@ -689,7 +689,7 @@ fn build_config(args: &ProxyCliArgs) -> anyhow::Result<&'static ProxyConfig> {
?epoch,
"Using NodeLocks (connect_compute)"
);
let connect_compute_locks = control_plane::locks::ApiLocks::new(
let connect_compute_locks = console::locks::ApiLocks::new(
"connect_compute_lock",
limiter,
shards,

View File

@@ -16,7 +16,7 @@ use tracing::{debug, info};
use crate::{
auth::IpPattern,
config::ProjectInfoCacheOptions,
control_plane::AuthSecret,
console::AuthSecret,
intern::{EndpointIdInt, ProjectIdInt, RoleNameInt},
EndpointId, RoleName,
};

View File

@@ -1,8 +1,8 @@
use crate::{
auth::parse_endpoint_param,
cancellation::CancelClosure,
console::{errors::WakeComputeError, messages::MetricsAuxInfo, provider::ApiLockError},
context::RequestMonitoring,
control_plane::{errors::WakeComputeError, messages::MetricsAuxInfo, provider::ApiLockError},
error::{ReportableError, UserFacingError},
metrics::{Metrics, NumDbConnectionsGuard},
proxy::neon_option,
@@ -20,7 +20,7 @@ use tokio_postgres::tls::MakeTlsConnect;
use tokio_postgres_rustls::MakeRustlsConnect;
use tracing::{error, info, warn};
pub const COULD_NOT_CONNECT: &str = "Couldn't connect to compute node";
const COULD_NOT_CONNECT: &str = "Couldn't connect to compute node";
#[derive(Debug, Error)]
pub(crate) enum ConnectionError {

View File

@@ -3,7 +3,7 @@ use crate::{
self,
backend::{jwt::JwkCache, AuthRateLimiter},
},
control_plane::locks::ApiLocks,
console::locks::ApiLocks,
rate_limiter::{RateBucketInfo, RateLimitAlgorithm, RateLimiterConfig},
scram::threadpool::ThreadPool,
serverless::{cancel_set::CancelSet, GlobalConnPoolOptions},
@@ -372,7 +372,7 @@ pub struct EndpointCacheConfig {
}
impl EndpointCacheConfig {
/// Default options for [`crate::control_plane::provider::NodeInfoCache`].
/// Default options for [`crate::console::provider::NodeInfoCache`].
/// Notice that by default the limiter is empty, which means that cache is disabled.
pub const CACHE_DEFAULT_OPTIONS: &'static str =
"initial_batch_size=1000,default_batch_size=10,xread_timeout=5m,stream_name=controlPlane,disable_cache=true,limiter_info=1000@1s,retry_interval=1s";
@@ -447,7 +447,7 @@ pub struct CacheOptions {
}
impl CacheOptions {
/// Default options for [`crate::control_plane::provider::NodeInfoCache`].
/// Default options for [`crate::console::provider::NodeInfoCache`].
pub const CACHE_DEFAULT_OPTIONS: &'static str = "size=4000,ttl=4m";
/// Parse cache options passed via cmdline.
@@ -503,7 +503,7 @@ pub struct ProjectInfoCacheOptions {
}
impl ProjectInfoCacheOptions {
/// Default options for [`crate::control_plane::provider::NodeInfoCache`].
/// Default options for [`crate::console::provider::NodeInfoCache`].
pub const CACHE_DEFAULT_OPTIONS: &'static str =
"size=10000,ttl=4m,max_roles=10,gc_interval=60m";
@@ -622,9 +622,9 @@ pub struct ConcurrencyLockOptions {
}
impl ConcurrencyLockOptions {
/// Default options for [`crate::control_plane::provider::ApiLocks`].
/// Default options for [`crate::console::provider::ApiLocks`].
pub const DEFAULT_OPTIONS_WAKE_COMPUTE_LOCK: &'static str = "permits=0";
/// Default options for [`crate::control_plane::provider::ApiLocks`].
/// Default options for [`crate::console::provider::ApiLocks`].
pub const DEFAULT_OPTIONS_CONNECT_COMPUTE_LOCK: &'static str =
"shards=64,permits=100,epoch=10m,timeout=10ms";

View File

@@ -10,14 +10,14 @@ use crate::proxy::retry::CouldRetry;
/// Generic error response with human-readable description.
/// Note that we can't always present it to user as is.
#[derive(Debug, Deserialize, Clone)]
pub(crate) struct ControlPlaneError {
pub(crate) struct ConsoleError {
pub(crate) error: Box<str>,
#[serde(skip)]
pub(crate) http_status_code: http::StatusCode,
pub(crate) status: Option<Status>,
}
impl ControlPlaneError {
impl ConsoleError {
pub(crate) fn get_reason(&self) -> Reason {
self.status
.as_ref()
@@ -51,7 +51,7 @@ impl ControlPlaneError {
}
}
impl Display for ControlPlaneError {
impl Display for ConsoleError {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
let msg: &str = self
.status
@@ -62,7 +62,7 @@ impl Display for ControlPlaneError {
}
}
impl CouldRetry for ControlPlaneError {
impl CouldRetry for ConsoleError {
fn could_retry(&self) -> bool {
// If the error message does not have a status,
// the error is unknown and probably should not retry automatically

View File

@@ -1,5 +1,5 @@
use crate::{
control_plane::messages::{DatabaseInfo, KickSession},
console::messages::{DatabaseInfo, KickSession},
waiters::{self, Waiter, Waiters},
};
use anyhow::Context;

View File

@@ -2,7 +2,7 @@
pub mod mock;
pub mod neon;
use super::messages::{ControlPlaneError, MetricsAuxInfo};
use super::messages::{ConsoleError, MetricsAuxInfo};
use crate::{
auth::{
backend::{
@@ -28,7 +28,7 @@ use tracing::info;
pub(crate) mod errors {
use crate::{
control_plane::messages::{self, ControlPlaneError, Reason},
console::messages::{self, ConsoleError, Reason},
error::{io_error, ErrorKind, ReportableError, UserFacingError},
proxy::retry::CouldRetry,
};
@@ -44,7 +44,7 @@ pub(crate) mod errors {
pub(crate) enum ApiError {
/// Error returned by the console itself.
#[error("{REQUEST_FAILED} with {0}")]
ControlPlane(ControlPlaneError),
Console(ConsoleError),
/// Various IO errors like broken pipe or malformed payload.
#[error("{REQUEST_FAILED}: {0}")]
@@ -55,7 +55,7 @@ pub(crate) mod errors {
/// Returns HTTP status code if it's the reason for failure.
pub(crate) fn get_reason(&self) -> messages::Reason {
match self {
ApiError::ControlPlane(e) => e.get_reason(),
ApiError::Console(e) => e.get_reason(),
ApiError::Transport(_) => messages::Reason::Unknown,
}
}
@@ -65,7 +65,7 @@ pub(crate) mod errors {
fn to_string_client(&self) -> String {
match self {
// To minimize risks, only select errors are forwarded to users.
ApiError::ControlPlane(c) => c.get_user_facing_message(),
ApiError::Console(c) => c.get_user_facing_message(),
ApiError::Transport(_) => REQUEST_FAILED.to_owned(),
}
}
@@ -74,7 +74,7 @@ pub(crate) mod errors {
impl ReportableError for ApiError {
fn get_error_kind(&self) -> crate::error::ErrorKind {
match self {
ApiError::ControlPlane(e) => match e.get_reason() {
ApiError::Console(e) => match e.get_reason() {
Reason::RoleProtected => ErrorKind::User,
Reason::ResourceNotFound => ErrorKind::User,
Reason::ProjectNotFound => ErrorKind::User,
@@ -91,12 +91,12 @@ pub(crate) mod errors {
Reason::LockAlreadyTaken => ErrorKind::ControlPlane,
Reason::RunningOperations => ErrorKind::ControlPlane,
Reason::Unknown => match &e {
ControlPlaneError {
ConsoleError {
http_status_code:
http::StatusCode::NOT_FOUND | http::StatusCode::NOT_ACCEPTABLE,
..
} => crate::error::ErrorKind::User,
ControlPlaneError {
ConsoleError {
http_status_code: http::StatusCode::UNPROCESSABLE_ENTITY,
error,
..
@@ -105,7 +105,7 @@ pub(crate) mod errors {
{
crate::error::ErrorKind::User
}
ControlPlaneError {
ConsoleError {
http_status_code: http::StatusCode::LOCKED,
error,
..
@@ -114,11 +114,11 @@ pub(crate) mod errors {
{
crate::error::ErrorKind::User
}
ControlPlaneError {
ConsoleError {
http_status_code: http::StatusCode::TOO_MANY_REQUESTS,
..
} => crate::error::ErrorKind::ServiceRateLimit,
ControlPlaneError { .. } => crate::error::ErrorKind::ControlPlane,
ConsoleError { .. } => crate::error::ErrorKind::ControlPlane,
},
},
ApiError::Transport(_) => crate::error::ErrorKind::ControlPlane,
@@ -131,7 +131,7 @@ pub(crate) mod errors {
match self {
// retry some transport errors
Self::Transport(io) => io.could_retry(),
Self::ControlPlane(e) => e.could_retry(),
Self::Console(e) => e.could_retry(),
}
}
}
@@ -314,8 +314,7 @@ impl NodeInfo {
}
}
pub(crate) type NodeInfoCache =
TimedLru<EndpointCacheKey, Result<NodeInfo, Box<ControlPlaneError>>>;
pub(crate) type NodeInfoCache = TimedLru<EndpointCacheKey, Result<NodeInfo, Box<ConsoleError>>>;
pub(crate) type CachedNodeInfo = Cached<&'static NodeInfoCache, NodeInfo>;
pub(crate) type CachedRoleSecret = Cached<&'static ProjectInfoCacheImpl, Option<AuthSecret>>;
pub(crate) type CachedAllowedIps = Cached<&'static ProjectInfoCacheImpl, Arc<Vec<IpPattern>>>;
@@ -354,28 +353,28 @@ pub(crate) trait Api {
#[non_exhaustive]
#[derive(Clone)]
pub enum ControlPlaneBackend {
/// Current Management API (V2).
Management(neon::Api),
/// Local mock control plane.
pub enum ConsoleBackend {
/// Current Cloud API (V2).
Console(neon::Api),
/// Local mock of Cloud API (V2).
#[cfg(any(test, feature = "testing"))]
PostgresMock(mock::Api),
Postgres(mock::Api),
/// Internal testing
#[cfg(test)]
#[allow(private_interfaces)]
Test(Box<dyn crate::auth::backend::TestBackend>),
}
impl Api for ControlPlaneBackend {
impl Api for ConsoleBackend {
async fn get_role_secret(
&self,
ctx: &RequestMonitoring,
user_info: &ComputeUserInfo,
) -> Result<CachedRoleSecret, errors::GetAuthInfoError> {
match self {
Self::Management(api) => api.get_role_secret(ctx, user_info).await,
Self::Console(api) => api.get_role_secret(ctx, user_info).await,
#[cfg(any(test, feature = "testing"))]
Self::PostgresMock(api) => api.get_role_secret(ctx, user_info).await,
Self::Postgres(api) => api.get_role_secret(ctx, user_info).await,
#[cfg(test)]
Self::Test(_) => {
unreachable!("this function should never be called in the test backend")
@@ -389,9 +388,9 @@ impl Api for ControlPlaneBackend {
user_info: &ComputeUserInfo,
) -> Result<(CachedAllowedIps, Option<CachedRoleSecret>), errors::GetAuthInfoError> {
match self {
Self::Management(api) => api.get_allowed_ips_and_secret(ctx, user_info).await,
Self::Console(api) => api.get_allowed_ips_and_secret(ctx, user_info).await,
#[cfg(any(test, feature = "testing"))]
Self::PostgresMock(api) => api.get_allowed_ips_and_secret(ctx, user_info).await,
Self::Postgres(api) => api.get_allowed_ips_and_secret(ctx, user_info).await,
#[cfg(test)]
Self::Test(api) => api.get_allowed_ips_and_secret(),
}
@@ -403,9 +402,9 @@ impl Api for ControlPlaneBackend {
endpoint: EndpointId,
) -> anyhow::Result<Vec<AuthRule>> {
match self {
Self::Management(api) => api.get_endpoint_jwks(ctx, endpoint).await,
Self::Console(api) => api.get_endpoint_jwks(ctx, endpoint).await,
#[cfg(any(test, feature = "testing"))]
Self::PostgresMock(api) => api.get_endpoint_jwks(ctx, endpoint).await,
Self::Postgres(api) => api.get_endpoint_jwks(ctx, endpoint).await,
#[cfg(test)]
Self::Test(_api) => Ok(vec![]),
}
@@ -417,16 +416,16 @@ impl Api for ControlPlaneBackend {
user_info: &ComputeUserInfo,
) -> Result<CachedNodeInfo, errors::WakeComputeError> {
match self {
Self::Management(api) => api.wake_compute(ctx, user_info).await,
Self::Console(api) => api.wake_compute(ctx, user_info).await,
#[cfg(any(test, feature = "testing"))]
Self::PostgresMock(api) => api.wake_compute(ctx, user_info).await,
Self::Postgres(api) => api.wake_compute(ctx, user_info).await,
#[cfg(test)]
Self::Test(api) => api.wake_compute(),
}
}
}
/// Various caches for [`control_plane`](super).
/// Various caches for [`console`](super).
pub struct ApiCaches {
/// Cache for the `wake_compute` API method.
pub(crate) node_info: NodeInfoCache,
@@ -455,7 +454,7 @@ impl ApiCaches {
}
}
/// Various caches for [`control_plane`](super).
/// Various caches for [`console`](super).
pub struct ApiLocks<K> {
name: &'static str,
node_locks: DashMap<K, Arc<DynamicLimiter>>,
@@ -578,7 +577,7 @@ impl WakeComputePermit {
}
}
impl FetchAuthRules for ControlPlaneBackend {
impl FetchAuthRules for ConsoleBackend {
async fn fetch_auth_rules(
&self,
ctx: &RequestMonitoring,

View File

@@ -10,7 +10,7 @@ use crate::{
use crate::{auth::backend::ComputeUserInfo, compute, error::io_error, scram, url::ApiUrl};
use crate::{auth::IpPattern, cache::Cached};
use crate::{
control_plane::{
console::{
messages::MetricsAuxInfo,
provider::{CachedAllowedIps, CachedRoleSecret},
},
@@ -166,7 +166,7 @@ impl Api {
endpoint_id: (&EndpointId::from("endpoint")).into(),
project_id: (&ProjectId::from("project")).into(),
branch_id: (&BranchId::from("branch")).into(),
cold_start_info: crate::control_plane::messages::ColdStartInfo::Warm,
cold_start_info: crate::console::messages::ColdStartInfo::Warm,
},
allow_self_signed_compute: false,
};

View File

@@ -1,7 +1,7 @@
//! Production console backend.
use super::{
super::messages::{ControlPlaneError, GetRoleSecret, WakeCompute},
super::messages::{ConsoleError, GetRoleSecret, WakeCompute},
errors::{ApiError, GetAuthInfoError, WakeComputeError},
ApiCaches, ApiLocks, AuthInfo, AuthSecret, CachedAllowedIps, CachedNodeInfo, CachedRoleSecret,
NodeInfo,
@@ -9,7 +9,7 @@ use super::{
use crate::{
auth::backend::{jwt::AuthRule, ComputeUserInfo},
compute,
control_plane::messages::{ColdStartInfo, EndpointJwksResponse, Reason},
console::messages::{ColdStartInfo, EndpointJwksResponse, Reason},
http,
metrics::{CacheOutcome, Metrics},
rate_limiter::WakeComputeRateLimiter,
@@ -348,7 +348,7 @@ impl super::Api for Api {
let (cached, info) = cached.take_value();
let info = info.map_err(|c| {
info!(key = &*key, "found cached wake_compute error");
WakeComputeError::ApiError(ApiError::ControlPlane(*c))
WakeComputeError::ApiError(ApiError::Console(*c))
})?;
debug!(key = &*key, "found cached compute node info");
@@ -395,9 +395,9 @@ impl super::Api for Api {
Ok(cached.map(|()| node))
}
Err(err) => match err {
WakeComputeError::ApiError(ApiError::ControlPlane(err)) => {
WakeComputeError::ApiError(ApiError::Console(err)) => {
let Some(status) = &err.status else {
return Err(WakeComputeError::ApiError(ApiError::ControlPlane(err)));
return Err(WakeComputeError::ApiError(ApiError::Console(err)));
};
let reason = status
@@ -407,7 +407,7 @@ impl super::Api for Api {
// if we can retry this error, do not cache it.
if reason.can_retry() {
return Err(WakeComputeError::ApiError(ApiError::ControlPlane(err)));
return Err(WakeComputeError::ApiError(ApiError::Console(err)));
}
// at this point, we should only have quota errors.
@@ -422,7 +422,7 @@ impl super::Api for Api {
Duration::from_secs(30),
);
Err(WakeComputeError::ApiError(ApiError::ControlPlane(err)))
Err(WakeComputeError::ApiError(ApiError::Console(err)))
}
err => return Err(err),
},
@@ -448,7 +448,7 @@ async fn parse_body<T: for<'a> serde::Deserialize<'a>>(
// as the fact that the request itself has failed.
let mut body = serde_json::from_slice(&s).unwrap_or_else(|e| {
warn!("failed to parse error body: {e}");
ControlPlaneError {
ConsoleError {
error: "reason unclear (malformed error message)".into(),
http_status_code: status,
status: None,
@@ -457,7 +457,7 @@ async fn parse_body<T: for<'a> serde::Deserialize<'a>>(
body.http_status_code = status;
error!("console responded with an error ({status}): {body:?}");
Err(ApiError::ControlPlane(body))
Err(ApiError::Console(body))
}
fn parse_host_port(input: &str) -> Option<(&str, u16)> {

View File

@@ -11,7 +11,7 @@ use try_lock::TryLock;
use uuid::Uuid;
use crate::{
control_plane::messages::{ColdStartInfo, MetricsAuxInfo},
console::messages::{ColdStartInfo, MetricsAuxInfo},
error::ErrorKind,
intern::{BranchIdInt, ProjectIdInt},
metrics::{ConnectOutcome, InvalidEndpointsGroup, LatencyTimer, Metrics, Protocol, Waiting},

View File

@@ -90,15 +90,13 @@ use tokio::task::JoinError;
use tokio_util::sync::CancellationToken;
use tracing::warn;
extern crate hyper0 as hyper;
pub mod auth;
pub mod cache;
pub mod cancellation;
pub mod compute;
pub mod config;
pub mod console;
pub mod context;
pub mod control_plane;
pub mod error;
pub mod http;
pub mod intern;

View File

@@ -1,13 +1,6 @@
use tracing::Subscriber;
use tracing_subscriber::{
filter::{EnvFilter, LevelFilter},
fmt::{
format::{Format, Full},
time::SystemTime,
FormatEvent, FormatFields,
},
prelude::*,
registry::LookupSpan,
};
/// Initialize logging and OpenTelemetry tracing and exporter.
@@ -40,45 +33,6 @@ pub async fn init() -> anyhow::Result<LoggingGuard> {
Ok(LoggingGuard)
}
/// Initialize logging for local_proxy with log prefix and no opentelemetry.
///
/// Logging can be configured using `RUST_LOG` environment variable.
pub fn init_local_proxy() -> anyhow::Result<LoggingGuard> {
let env_filter = EnvFilter::builder()
.with_default_directive(LevelFilter::INFO.into())
.from_env_lossy();
let fmt_layer = tracing_subscriber::fmt::layer()
.with_ansi(false)
.with_writer(std::io::stderr)
.event_format(LocalProxyFormatter(Format::default().with_target(false)));
tracing_subscriber::registry()
.with(env_filter)
.with(fmt_layer)
.try_init()?;
Ok(LoggingGuard)
}
pub struct LocalProxyFormatter(Format<Full, SystemTime>);
impl<S, N> FormatEvent<S, N> for LocalProxyFormatter
where
S: Subscriber + for<'a> LookupSpan<'a>,
N: for<'a> FormatFields<'a> + 'static,
{
fn format_event(
&self,
ctx: &tracing_subscriber::fmt::FmtContext<'_, S, N>,
mut writer: tracing_subscriber::fmt::format::Writer<'_>,
event: &tracing::Event<'_>,
) -> std::fmt::Result {
writer.write_str("[local_proxy] ")?;
self.0.format_event(ctx, writer, event)
}
}
pub struct LoggingGuard;
impl Drop for LoggingGuard {

View File

@@ -11,7 +11,7 @@ use metrics::{CounterPairAssoc, CounterPairVec, HyperLogLog, HyperLogLogVec};
use tokio::time::{self, Instant};
use crate::control_plane::messages::ColdStartInfo;
use crate::console::messages::ColdStartInfo;
#[derive(MetricGroup)]
#[metric(new(thread_pool: Arc<ThreadPoolMetrics>))]

View File

@@ -1,10 +1,9 @@
use crate::{
auth::backend::ComputeCredentialKeys,
compute::COULD_NOT_CONNECT,
compute::{self, PostgresConnection},
config::RetryConfig,
console::{self, errors::WakeComputeError, locks::ApiLocks, CachedNodeInfo, NodeInfo},
context::RequestMonitoring,
control_plane::{self, errors::WakeComputeError, locks::ApiLocks, CachedNodeInfo, NodeInfo},
error::ReportableError,
metrics::{ConnectOutcome, ConnectionFailureKind, Metrics, RetriesMetricGroup, RetryType},
proxy::{
@@ -16,7 +15,7 @@ use crate::{
use async_trait::async_trait;
use pq_proto::StartupMessageParams;
use tokio::time;
use tracing::{debug, info, warn};
use tracing::{error, info, warn};
use super::retry::ShouldRetryWakeCompute;
@@ -26,7 +25,7 @@ const CONNECT_TIMEOUT: time::Duration = time::Duration::from_secs(2);
/// (e.g. the compute node's address might've changed at the wrong time).
/// Invalidate the cache entry (if any) to prevent subsequent errors.
#[tracing::instrument(name = "invalidate_cache", skip_all)]
pub(crate) fn invalidate_cache(node_info: control_plane::CachedNodeInfo) -> NodeInfo {
pub(crate) fn invalidate_cache(node_info: console::CachedNodeInfo) -> NodeInfo {
let is_cached = node_info.cached();
if is_cached {
warn!("invalidating stalled compute node info cache entry");
@@ -49,7 +48,7 @@ pub(crate) trait ConnectMechanism {
async fn connect_once(
&self,
ctx: &RequestMonitoring,
node_info: &control_plane::CachedNodeInfo,
node_info: &console::CachedNodeInfo,
timeout: time::Duration,
) -> Result<Self::Connection, Self::ConnectError>;
@@ -61,7 +60,7 @@ pub(crate) trait ComputeConnectBackend {
async fn wake_compute(
&self,
ctx: &RequestMonitoring,
) -> Result<CachedNodeInfo, control_plane::errors::WakeComputeError>;
) -> Result<CachedNodeInfo, console::errors::WakeComputeError>;
fn get_keys(&self) -> &ComputeCredentialKeys;
}
@@ -84,7 +83,7 @@ impl ConnectMechanism for TcpMechanism<'_> {
async fn connect_once(
&self,
ctx: &RequestMonitoring,
node_info: &control_plane::CachedNodeInfo,
node_info: &console::CachedNodeInfo,
timeout: time::Duration,
) -> Result<PostgresConnection, Self::Error> {
let host = node_info.config.get_host()?;
@@ -117,6 +116,7 @@ where
node_info.set_keys(user_info.get_keys());
node_info.allow_self_signed_compute = allow_self_signed_compute;
// let mut node_info = credentials.get_node_info(ctx, user_info).await?;
mechanism.update_connect_config(&mut node_info.config);
let retry_type = RetryType::ConnectToCompute;
@@ -139,10 +139,10 @@ where
Err(e) => e,
};
debug!(error = ?err, COULD_NOT_CONNECT);
error!(error = ?err, "could not connect to compute node");
let node_info = if !node_info.cached() || !err.should_retry_wake_compute() {
// If we just recieved this from cplane and didn't get it from cache, we shouldn't retry.
// If we just recieved this from cplane and dodn't get it from cache, we shouldn't retry.
// Do not need to retrieve a new node_info, just return the old one.
if should_retry(&err, num_retries, connect_to_compute_retry_config) {
Metrics::get().proxy.retries_metric.observe(
@@ -191,7 +191,7 @@ where
}
Err(e) => {
if !should_retry(&e, num_retries, connect_to_compute_retry_config) {
// Don't log an error here, caller will print the error
error!(error = ?e, num_retries, retriable = false, "couldn't connect to compute node");
Metrics::get().proxy.retries_metric.observe(
RetriesMetricGroup {
outcome: ConnectOutcome::Failed,
@@ -202,7 +202,7 @@ where
return Err(e.into());
}
warn!(error = ?e, num_retries, retriable = true, COULD_NOT_CONNECT);
warn!(error = ?e, num_retries, retriable = true, "couldn't connect to compute node");
}
};

View File

@@ -1,7 +1,7 @@
use crate::{
cancellation,
compute::PostgresConnection,
control_plane::messages::MetricsAuxInfo,
console::messages::MetricsAuxInfo,
metrics::{Direction, Metrics, NumClientConnectionsGuard, NumConnectionRequestsGuard},
stream::Stream,
usage_metrics::{Ids, MetricCounterRecorder, USAGE_METRICS},

View File

@@ -11,11 +11,9 @@ use crate::auth::backend::{
ComputeCredentialKeys, ComputeCredentials, ComputeUserInfo, MaybeOwned, TestBackend,
};
use crate::config::{CertResolver, RetryConfig};
use crate::control_plane::messages::{ControlPlaneError, Details, MetricsAuxInfo, Status};
use crate::control_plane::provider::{
CachedAllowedIps, CachedRoleSecret, ControlPlaneBackend, NodeInfoCache,
};
use crate::control_plane::{self, CachedNodeInfo, NodeInfo};
use crate::console::messages::{ConsoleError, Details, MetricsAuxInfo, Status};
use crate::console::provider::{CachedAllowedIps, CachedRoleSecret, ConsoleBackend, NodeInfoCache};
use crate::console::{self, CachedNodeInfo, NodeInfo};
use crate::error::ErrorKind;
use crate::{sasl, scram, BranchId, EndpointId, ProjectId};
use anyhow::{bail, Context};
@@ -461,7 +459,7 @@ impl ConnectMechanism for TestConnectMechanism {
async fn connect_once(
&self,
_ctx: &RequestMonitoring,
_node_info: &control_plane::CachedNodeInfo,
_node_info: &console::CachedNodeInfo,
_timeout: std::time::Duration,
) -> Result<Self::Connection, Self::ConnectError> {
let mut counter = self.counter.lock().unwrap();
@@ -485,23 +483,23 @@ impl ConnectMechanism for TestConnectMechanism {
}
impl TestBackend for TestConnectMechanism {
fn wake_compute(&self) -> Result<CachedNodeInfo, control_plane::errors::WakeComputeError> {
fn wake_compute(&self) -> Result<CachedNodeInfo, console::errors::WakeComputeError> {
let mut counter = self.counter.lock().unwrap();
let action = self.sequence[*counter];
*counter += 1;
match action {
ConnectAction::Wake => Ok(helper_create_cached_node_info(self.cache)),
ConnectAction::WakeFail => {
let err = control_plane::errors::ApiError::ControlPlane(ControlPlaneError {
let err = console::errors::ApiError::Console(ConsoleError {
http_status_code: StatusCode::BAD_REQUEST,
error: "TEST".into(),
status: None,
});
assert!(!err.could_retry());
Err(control_plane::errors::WakeComputeError::ApiError(err))
Err(console::errors::WakeComputeError::ApiError(err))
}
ConnectAction::WakeRetry => {
let err = control_plane::errors::ApiError::ControlPlane(ControlPlaneError {
let err = console::errors::ApiError::Console(ConsoleError {
http_status_code: StatusCode::BAD_REQUEST,
error: "TEST".into(),
status: Some(Status {
@@ -509,15 +507,13 @@ impl TestBackend for TestConnectMechanism {
message: "error".into(),
details: Details {
error_info: None,
retry_info: Some(control_plane::messages::RetryInfo {
retry_delay_ms: 1,
}),
retry_info: Some(console::messages::RetryInfo { retry_delay_ms: 1 }),
user_facing_message: None,
},
}),
});
assert!(err.could_retry());
Err(control_plane::errors::WakeComputeError::ApiError(err))
Err(console::errors::WakeComputeError::ApiError(err))
}
x => panic!("expecting action {x:?}, wake_compute is called instead"),
}
@@ -525,7 +521,7 @@ impl TestBackend for TestConnectMechanism {
fn get_allowed_ips_and_secret(
&self,
) -> Result<(CachedAllowedIps, Option<CachedRoleSecret>), control_plane::errors::GetAuthInfoError>
) -> Result<(CachedAllowedIps, Option<CachedRoleSecret>), console::errors::GetAuthInfoError>
{
unimplemented!("not used in tests")
}
@@ -542,7 +538,7 @@ fn helper_create_cached_node_info(cache: &'static NodeInfoCache) -> CachedNodeIn
endpoint_id: (&EndpointId::from("endpoint")).into(),
project_id: (&ProjectId::from("project")).into(),
branch_id: (&BranchId::from("branch")).into(),
cold_start_info: crate::control_plane::messages::ColdStartInfo::Warm,
cold_start_info: crate::console::messages::ColdStartInfo::Warm,
},
allow_self_signed_compute: false,
};
@@ -553,8 +549,8 @@ fn helper_create_cached_node_info(cache: &'static NodeInfoCache) -> CachedNodeIn
fn helper_create_connect_info(
mechanism: &TestConnectMechanism,
) -> auth::Backend<'static, ComputeCredentials, &()> {
let user_info = auth::Backend::ControlPlane(
MaybeOwned::Owned(ControlPlaneBackend::Test(Box::new(mechanism.clone()))),
let user_info = auth::Backend::Console(
MaybeOwned::Owned(ConsoleBackend::Test(Box::new(mechanism.clone()))),
ComputeCredentials {
info: ComputeUserInfo {
endpoint: "endpoint".into(),

View File

@@ -1,7 +1,7 @@
use crate::config::RetryConfig;
use crate::console::messages::{ConsoleError, Reason};
use crate::console::{errors::WakeComputeError, provider::CachedNodeInfo};
use crate::context::RequestMonitoring;
use crate::control_plane::messages::{ControlPlaneError, Reason};
use crate::control_plane::{errors::WakeComputeError, provider::CachedNodeInfo};
use crate::metrics::{
ConnectOutcome, ConnectionFailuresBreakdownGroup, Metrics, RetriesMetricGroup, RetryType,
WakeupFailureKind,
@@ -59,11 +59,11 @@ pub(crate) async fn wake_compute<B: ComputeConnectBackend>(
}
fn report_error(e: &WakeComputeError, retry: bool) {
use crate::control_plane::errors::ApiError;
use crate::console::errors::ApiError;
let kind = match e {
WakeComputeError::BadComputeAddress(_) => WakeupFailureKind::BadComputeAddress,
WakeComputeError::ApiError(ApiError::Transport(_)) => WakeupFailureKind::ApiTransportError,
WakeComputeError::ApiError(ApiError::ControlPlane(e)) => match e.get_reason() {
WakeComputeError::ApiError(ApiError::Console(e)) => match e.get_reason() {
Reason::RoleProtected => WakeupFailureKind::ApiConsoleBadRequest,
Reason::ResourceNotFound => WakeupFailureKind::ApiConsoleBadRequest,
Reason::ProjectNotFound => WakeupFailureKind::ApiConsoleBadRequest,
@@ -80,7 +80,7 @@ fn report_error(e: &WakeComputeError, retry: bool) {
Reason::LockAlreadyTaken => WakeupFailureKind::ApiConsoleLocked,
Reason::RunningOperations => WakeupFailureKind::ApiConsoleLocked,
Reason::Unknown => match e {
ControlPlaneError {
ConsoleError {
http_status_code: StatusCode::LOCKED,
ref error,
..
@@ -89,27 +89,27 @@ fn report_error(e: &WakeComputeError, retry: bool) {
{
WakeupFailureKind::QuotaExceeded
}
ControlPlaneError {
ConsoleError {
http_status_code: StatusCode::UNPROCESSABLE_ENTITY,
ref error,
..
} if error.contains("compute time quota of non-primary branches is exceeded") => {
WakeupFailureKind::QuotaExceeded
}
ControlPlaneError {
ConsoleError {
http_status_code: StatusCode::LOCKED,
..
} => WakeupFailureKind::ApiConsoleLocked,
ControlPlaneError {
ConsoleError {
http_status_code: StatusCode::BAD_REQUEST,
..
} => WakeupFailureKind::ApiConsoleBadRequest,
ControlPlaneError {
ConsoleError {
http_status_code, ..
} if http_status_code.is_server_error() => {
WakeupFailureKind::ApiConsoleOtherServerError
}
ControlPlaneError { .. } => WakeupFailureKind::ApiConsoleOtherError,
ConsoleError { .. } => WakeupFailureKind::ApiConsoleOtherError,
},
},
WakeComputeError::TooManyConnections => WakeupFailureKind::ApiConsoleLocked,

Some files were not shown because too many files have changed in this diff Show More