Compare commits

...

9 Commits

Author SHA1 Message Date
Christian Schwarz
318700600d refactor: lift inspection of CompactionError::Other(x) => x.root_cause() into CompactionError::is_cancel
There are a couple of places that call CompactionError::is_cancel but
don't check the Other variant for root cause. But they should, because
some cancellations are observed by code that results in ::Other errors.

I don't think there's a _serious_ case where this causes problems.
The worst case one is the circuit breaker which we do currently trip
on ::Other errors that are due to cancellation. Tripped circuit breaker
on shutting down timelines doesn't really matter practically, but
it's unaesthetic and might cause noise down the line, so, this
PR fixes that at least.

In any way, this PR forces future callers of is_cancel() to explicitly
recognize the suboptimal state of affairs wrt error handling in compaction,
thereby hopefully preventing errors of this kind from creeping in.

(The _right_ solution for the compaction code probably is the approach
I took in #11853: keep using anyhow but have a unified way / pattern
of bubbling up cancellation, so that we don't need to perform the downcast
trickery).
2025-06-27 14:10:24 +02:00
Christian Schwarz
75ef17e2f7 refactor: force explicit mapping to CreateImageLayersError::Other 2025-06-27 13:31:49 +02:00
Christian Schwarz
93026b7899 address most types of error that happen during creation of delta layers 2025-06-27 13:17:19 +02:00
Vlad Lazar
b69d103b90 pageserver: make import job max byte range size configurable (#12117)
## Problem

We want to repro an OOM situation, but large partial reads are required.

## Summary of Changes

Make the max partial read size configurable for import jobs.
2025-06-04 10:44:23 +00:00
a-masterov
208cbd52d4 Add postgis to the test image (#11672)
## Problem
We don't currently run tests for PostGIS in our test environment.

## Summary of Changes
- Added PostGIS test support for PostgreSQL v16 and v17
- Configured different PostGIS versions based on PostgreSQL version:
  - PostgreSQL v17: PostGIS 3.5.0
  - PostgreSQL v14/v15/v16: PostGIS 3.3.3
- Added necessary test scripts and configurations

This ensures our PostgreSQL implementation remains compatible with this
widely-used extension.

---------

Co-authored-by: Alexander Bayandin <alexander@neon.tech>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2025-06-04 09:57:31 +00:00
Alex Chi Z.
c567ed0de0 feat(pageserver): feature flag counter metrics (#12112)
## Problem

Part of https://github.com/neondatabase/neon/issues/11813

## Summary of changes

Add a counter on the feature evaluation outcome and we will set up
alerts for too many failed evaluations in the future.

Signed-off-by: Alex Chi Z <chi@neon.tech>
2025-06-04 06:41:42 +00:00
Mikhail
c698cee19a ComputeSpec: prewarm_lfc_on_startup -> autoprewarm (#12120)
https://github.com/neondatabase/cloud/pull/29472
https://github.com/neondatabase/cloud/issues/26346
2025-06-04 05:38:03 +00:00
Tristan Partin
4a3f32bf4a Clean up compute_tools::http::JsonResponse::invalid_status() (#12110)
JsonResponse::error() properly logs an error message which can be read
in the compute logs. invalid_status() was not going through that helper
function, thus not logging anything.

Signed-off-by: Tristan Partin <tristan@neon.tech>
2025-06-03 16:00:56 +00:00
Vlad Lazar
a963aab14b pagserver: set default wal receiver proto to interpreted (#12100)
## Problem

This is already the default in production and in our test suite.

## Summary of changes

Set the default proto to interpreted to reduce friction when spinning up
new regions or cells.
2025-06-03 14:57:36 +00:00
30 changed files with 814 additions and 112 deletions

View File

@@ -297,6 +297,7 @@ RUN ./autogen.sh && \
./configure --with-sfcgal=/usr/local/bin/sfcgal-config && \
make -j $(getconf _NPROCESSORS_ONLN) && \
make -j $(getconf _NPROCESSORS_ONLN) install && \
make staged-install && \
cd extensions/postgis && \
make clean && \
make -j $(getconf _NPROCESSORS_ONLN) install && \
@@ -1842,10 +1843,25 @@ RUN make PG_VERSION="${PG_VERSION:?}" -C compute
FROM pg-build AS extension-tests
ARG PG_VERSION
# This is required for the PostGIS test
RUN apt-get update && case $DEBIAN_VERSION in \
bullseye) \
apt-get install -y libproj19 libgdal28 time; \
;; \
bookworm) \
apt-get install -y libgdal32 libproj25 time; \
;; \
*) \
echo "Unknown Debian version ${DEBIAN_VERSION}" && exit 1 \
;; \
esac
COPY docker-compose/ext-src/ /ext-src/
COPY --from=pg-build /postgres /postgres
#COPY --from=postgis-src /ext-src/ /ext-src/
COPY --from=postgis-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=postgis-build /ext-src/postgis-src /ext-src/postgis-src
COPY --from=postgis-build /sfcgal/* /usr
COPY --from=plv8-src /ext-src/ /ext-src/
COPY --from=h3-pg-src /ext-src/h3-pg-src /ext-src/h3-pg-src
COPY --from=postgresql-unit-src /ext-src/ /ext-src/

View File

@@ -396,7 +396,7 @@ impl ComputeNode {
// because QEMU will already have its memory allocated from the host, and
// the necessary binaries will already be cached.
if cli_spec.is_none() {
this.prewarm_postgres()?;
this.prewarm_postgres_vm_memory()?;
}
// Set the up metric with Empty status before starting the HTTP server.
@@ -779,7 +779,7 @@ impl ComputeNode {
// Spawn the extension stats background task
self.spawn_extension_stats_task();
if pspec.spec.prewarm_lfc_on_startup {
if pspec.spec.autoprewarm {
self.prewarm_lfc();
}
Ok(())
@@ -1307,8 +1307,8 @@ impl ComputeNode {
}
/// Start and stop a postgres process to warm up the VM for startup.
pub fn prewarm_postgres(&self) -> Result<()> {
info!("prewarming");
pub fn prewarm_postgres_vm_memory(&self) -> Result<()> {
info!("prewarming VM memory");
// Create pgdata
let pgdata = &format!("{}.warmup", self.params.pgdata);
@@ -1350,7 +1350,7 @@ impl ComputeNode {
kill(pm_pid, Signal::SIGQUIT)?;
info!("sent SIGQUIT signal");
pg.wait()?;
info!("done prewarming");
info!("done prewarming vm memory");
// clean up
let _ok = fs::remove_dir_all(pgdata);

View File

@@ -48,11 +48,9 @@ impl JsonResponse {
/// Create an error response related to the compute being in an invalid state
pub(self) fn invalid_status(status: ComputeStatus) -> Response {
Self::create_response(
Self::error(
StatusCode::PRECONDITION_FAILED,
&GenericAPIError {
error: format!("invalid compute status: {status}"),
},
format!("invalid compute status: {status}"),
)
}
}

View File

@@ -30,7 +30,7 @@ mod pg_helpers_tests {
r#"fsync = off
wal_level = logical
hot_standby = on
prewarm_lfc_on_startup = off
autoprewarm = off
neon.safekeepers = '127.0.0.1:6502,127.0.0.1:6503,127.0.0.1:6501'
wal_log_hints = on
log_connections = on

View File

@@ -747,7 +747,7 @@ impl Endpoint {
logs_export_host: None::<String>,
endpoint_storage_addr: Some(endpoint_storage_addr),
endpoint_storage_token: Some(endpoint_storage_token),
prewarm_lfc_on_startup: false,
autoprewarm: false,
};
// this strange code is needed to support respec() in tests

View File

@@ -13,6 +13,6 @@ RUN echo 'Acquire::Retries "5";' > /etc/apt/apt.conf.d/80-retries && \
jq \
netcat-openbsd
#This is required for the pg_hintplan test
RUN mkdir -p /ext-src/pg_hint_plan-src /postgres/contrib/file_fdw && chown postgres /ext-src/pg_hint_plan-src /postgres/contrib/file_fdw
RUN mkdir -p /ext-src/pg_hint_plan-src /postgres/contrib/file_fdw /ext-src/postgis-src/ && chown postgres /ext-src/pg_hint_plan-src /postgres/contrib/file_fdw /ext-src/postgis-src
USER postgres

View File

@@ -186,13 +186,14 @@ services:
neon-test-extensions:
profiles: ["test-extensions"]
image: ${REPOSITORY:-ghcr.io/neondatabase}/neon-test-extensions-v${PG_TEST_VERSION:-16}:${TEST_EXTENSIONS_TAG:-${TAG:-latest}}
image: ${REPOSITORY:-ghcr.io/neondatabase}/neon-test-extensions-v${PG_TEST_VERSION:-${PG_VERSION:-16}}:${TEST_EXTENSIONS_TAG:-${TAG:-latest}}
environment:
- PGPASSWORD=cloud_admin
- PGUSER=${PGUSER:-cloud_admin}
- PGPASSWORD=${PGPASSWORD:-cloud_admin}
entrypoint:
- "/bin/bash"
- "-c"
command:
- sleep 1800
- sleep 3600
depends_on:
- compute

View File

@@ -54,6 +54,15 @@ for pg_version in ${TEST_VERSION_ONLY-14 15 16 17}; do
# It cannot be moved to Dockerfile now because the database directory is created after the start of the container
echo Adding dummy config
docker compose exec compute touch /var/db/postgres/compute/compute_ctl_temp_override.conf
# Prepare for the PostGIS test
docker compose exec compute mkdir -p /tmp/pgis_reg/pgis_reg_tmp
TMPDIR=$(mktemp -d)
docker compose cp neon-test-extensions:/ext-src/postgis-src/raster/test "${TMPDIR}"
docker compose cp neon-test-extensions:/ext-src/postgis-src/regress/00-regress-install "${TMPDIR}"
docker compose exec compute mkdir -p /ext-src/postgis-src/raster /ext-src/postgis-src/regress /ext-src/postgis-src/regress/00-regress-install
docker compose cp "${TMPDIR}/test" compute:/ext-src/postgis-src/raster/test
docker compose cp "${TMPDIR}/00-regress-install" compute:/ext-src/postgis-src/regress
rm -rf "${TMPDIR}"
# The following block copies the files for the pg_hintplan test to the compute node for the extension test in an isolated docker-compose environment
TMPDIR=$(mktemp -d)
docker compose cp neon-test-extensions:/ext-src/pg_hint_plan-src/data "${TMPDIR}/data"
@@ -68,7 +77,7 @@ for pg_version in ${TEST_VERSION_ONLY-14 15 16 17}; do
docker compose exec -T neon-test-extensions bash -c "(cd /postgres && patch -p1)" <"../compute/patches/contrib_pg${pg_version}.patch"
# We are running tests now
rm -f testout.txt testout_contrib.txt
docker compose exec -e USE_PGXS=1 -e SKIP=timescaledb-src,rdkit-src,postgis-src,pg_jsonschema-src,kq_imcx-src,wal2json_2_5-src,rag_jina_reranker_v1_tiny_en-src,rag_bge_small_en_v15-src \
docker compose exec -e USE_PGXS=1 -e SKIP=timescaledb-src,rdkit-src,pg_jsonschema-src,kq_imcx-src,wal2json_2_5-src,rag_jina_reranker_v1_tiny_en-src,rag_bge_small_en_v15-src \
neon-test-extensions /run-tests.sh /ext-src | tee testout.txt && EXT_SUCCESS=1 || EXT_SUCCESS=0
docker compose exec -e SKIP=start-scripts,postgres_fdw,ltree_plpython,jsonb_plpython,jsonb_plperl,hstore_plpython,hstore_plperl,dblink,bool_plperl \
neon-test-extensions /run-tests.sh /postgres/contrib | tee testout_contrib.txt && CONTRIB_SUCCESS=1 || CONTRIB_SUCCESS=0

View File

@@ -0,0 +1,70 @@
# PostGIS Testing in Neon
This directory contains configuration files and patches for running PostGIS tests in the Neon database environment.
## Overview
PostGIS is a spatial database extension for PostgreSQL that adds support for geographic objects. Testing PostGIS compatibility ensures that Neon's modifications to PostgreSQL don't break compatibility with this critical extension.
## PostGIS Versions
- PostgreSQL v17: PostGIS 3.5.0
- PostgreSQL v14/v15/v16: PostGIS 3.3.3
## Test Configuration
The test setup includes:
- `postgis-no-upgrade-test.patch`: Disables upgrade tests by removing the upgrade test section from regress/runtest.mk
- `postgis-regular-v16.patch`: Version-specific patch for PostgreSQL v16
- `postgis-regular-v17.patch`: Version-specific patch for PostgreSQL v17
- `regular-test.sh`: Script to run PostGIS tests as a regular user
- `neon-test.sh`: Script to handle version-specific test configurations
- `raster_outdb_template.sql`: Template for raster tests with explicit file paths
## Excluded Tests
**Important Note:** The test exclusions listed below are specifically for regular-user tests against staging instances. These exclusions are necessary because staging instances run with limited privileges and cannot perform operations requiring superuser access. Docker-compose based tests are not affected by these exclusions.
### Tests Requiring Superuser Permissions
These tests cannot be run as a regular user:
- `estimatedextent`
- `regress/core/legacy`
- `regress/core/typmod`
- `regress/loader/TestSkipANALYZE`
- `regress/loader/TestANALYZE`
### Tests Requiring Filesystem Access
These tests need direct filesystem access that is only possible for superusers:
- `loader/load_outdb`
### Tests with Flaky Results
These tests have assumptions that don't always hold true:
- `regress/core/computed_columns` - Assumes computed columns always outperform alternatives, which is not consistently true
### Tests Requiring Tunable Parameter Modifications
These tests attempt to modify the `postgis.gdal_enabled_drivers` parameter, which is only accessible to superusers:
- `raster/test/regress/rt_wkb`
- `raster/test/regress/rt_addband`
- `raster/test/regress/rt_setbandpath`
- `raster/test/regress/rt_fromgdalraster`
- `raster/test/regress/rt_asgdalraster`
- `raster/test/regress/rt_astiff`
- `raster/test/regress/rt_asjpeg`
- `raster/test/regress/rt_aspng`
- `raster/test/regress/permitted_gdal_drivers`
- Loader tests: `BasicOutDB`, `Tiled10x10`, `Tiled10x10Copy`, `Tiled8x8`, `TiledAuto`, `TiledAutoSkipNoData`, `TiledAutoCopyn`
### Topology Tests (v17 only)
- `populate_topology_layer`
- `renametopogeometrycolumn`
## Other Modifications
- Binary.sql tests are modified to use explicit file paths
- Server-side SQL COPY commands (which require superuser privileges) are converted to client-side `\copy` commands
- Upgrade tests are disabled

View File

@@ -0,0 +1,9 @@
#!/bin/bash
set -ex
cd "$(dirname "$0")"
if [[ ${PG_VERSION} = v17 ]]; then
sed -i '/computed_columns/d' regress/core/tests.mk
fi
patch -p1 <postgis-no-upgrade-test.patch
trap 'echo Cleaning up; patch -R -p1 <postgis-no-upgrade-test.patch' EXIT
make installcheck-base

View File

@@ -0,0 +1,21 @@
diff --git a/regress/runtest.mk b/regress/runtest.mk
index c051f03..010e493 100644
--- a/regress/runtest.mk
+++ b/regress/runtest.mk
@@ -24,16 +24,6 @@ check-regress:
POSTGIS_TOP_BUILD_DIR=$(abs_top_builddir) $(PERL) $(top_srcdir)/regress/run_test.pl $(RUNTESTFLAGS) $(RUNTESTFLAGS_INTERNAL) $(TESTS)
- @if echo "$(RUNTESTFLAGS)" | grep -vq -- --upgrade; then \
- echo "Running upgrade test as RUNTESTFLAGS did not contain that"; \
- POSTGIS_TOP_BUILD_DIR=$(abs_top_builddir) $(PERL) $(top_srcdir)/regress/run_test.pl \
- --upgrade \
- $(RUNTESTFLAGS) \
- $(RUNTESTFLAGS_INTERNAL) \
- $(TESTS); \
- else \
- echo "Skipping upgrade test as RUNTESTFLAGS already requested upgrades"; \
- fi
check-long:
$(PERL) $(top_srcdir)/regress/run_test.pl $(RUNTESTFLAGS) $(TESTS) $(TESTS_SLOW)

View File

@@ -0,0 +1,198 @@
diff --git a/raster/test/regress/tests.mk b/raster/test/regress/tests.mk
index 00918e1..7e2b6cd 100644
--- a/raster/test/regress/tests.mk
+++ b/raster/test/regress/tests.mk
@@ -17,9 +17,7 @@ override RUNTESTFLAGS_INTERNAL := \
$(RUNTESTFLAGS_INTERNAL) \
--after-upgrade-script $(top_srcdir)/raster/test/regress/hooks/hook-after-upgrade-raster.sql
-RASTER_TEST_FIRST = \
- $(top_srcdir)/raster/test/regress/check_gdal \
- $(top_srcdir)/raster/test/regress/loader/load_outdb
+RASTER_TEST_FIRST =
RASTER_TEST_LAST = \
$(top_srcdir)/raster/test/regress/clean
@@ -33,9 +31,7 @@ RASTER_TEST_IO = \
RASTER_TEST_BASIC_FUNC = \
$(top_srcdir)/raster/test/regress/rt_bytea \
- $(top_srcdir)/raster/test/regress/rt_wkb \
$(top_srcdir)/raster/test/regress/box3d \
- $(top_srcdir)/raster/test/regress/rt_addband \
$(top_srcdir)/raster/test/regress/rt_band \
$(top_srcdir)/raster/test/regress/rt_tile
@@ -73,16 +69,10 @@ RASTER_TEST_BANDPROPS = \
$(top_srcdir)/raster/test/regress/rt_neighborhood \
$(top_srcdir)/raster/test/regress/rt_nearestvalue \
$(top_srcdir)/raster/test/regress/rt_pixelofvalue \
- $(top_srcdir)/raster/test/regress/rt_polygon \
- $(top_srcdir)/raster/test/regress/rt_setbandpath
+ $(top_srcdir)/raster/test/regress/rt_polygon
RASTER_TEST_UTILITY = \
$(top_srcdir)/raster/test/regress/rt_utility \
- $(top_srcdir)/raster/test/regress/rt_fromgdalraster \
- $(top_srcdir)/raster/test/regress/rt_asgdalraster \
- $(top_srcdir)/raster/test/regress/rt_astiff \
- $(top_srcdir)/raster/test/regress/rt_asjpeg \
- $(top_srcdir)/raster/test/regress/rt_aspng \
$(top_srcdir)/raster/test/regress/rt_reclass \
$(top_srcdir)/raster/test/regress/rt_gdalwarp \
$(top_srcdir)/raster/test/regress/rt_gdalcontour \
@@ -120,21 +110,13 @@ RASTER_TEST_SREL = \
RASTER_TEST_BUGS = \
$(top_srcdir)/raster/test/regress/bug_test_car5 \
- $(top_srcdir)/raster/test/regress/permitted_gdal_drivers \
$(top_srcdir)/raster/test/regress/tickets
RASTER_TEST_LOADER = \
$(top_srcdir)/raster/test/regress/loader/Basic \
$(top_srcdir)/raster/test/regress/loader/Projected \
$(top_srcdir)/raster/test/regress/loader/BasicCopy \
- $(top_srcdir)/raster/test/regress/loader/BasicFilename \
- $(top_srcdir)/raster/test/regress/loader/BasicOutDB \
- $(top_srcdir)/raster/test/regress/loader/Tiled10x10 \
- $(top_srcdir)/raster/test/regress/loader/Tiled10x10Copy \
- $(top_srcdir)/raster/test/regress/loader/Tiled8x8 \
- $(top_srcdir)/raster/test/regress/loader/TiledAuto \
- $(top_srcdir)/raster/test/regress/loader/TiledAutoSkipNoData \
- $(top_srcdir)/raster/test/regress/loader/TiledAutoCopyn
+ $(top_srcdir)/raster/test/regress/loader/BasicFilename
RASTER_TESTS := $(RASTER_TEST_FIRST) \
$(RASTER_TEST_METADATA) $(RASTER_TEST_IO) $(RASTER_TEST_BASIC_FUNC) \
diff --git a/regress/core/binary.sql b/regress/core/binary.sql
index 7a36b65..ad78fc7 100644
--- a/regress/core/binary.sql
+++ b/regress/core/binary.sql
@@ -1,4 +1,5 @@
SET client_min_messages TO warning;
+
CREATE SCHEMA tm;
CREATE TABLE tm.geoms (id serial, g geometry);
@@ -31,24 +32,39 @@ SELECT st_force4d(g) FROM tm.geoms WHERE id < 15 ORDER BY id;
INSERT INTO tm.geoms(g)
SELECT st_setsrid(g,4326) FROM tm.geoms ORDER BY id;
-COPY tm.geoms TO :tmpfile WITH BINARY;
+-- define temp file path
+\set tmpfile '/tmp/postgis_binary_test.dat'
+
+-- export
+\set command '\\copy tm.geoms TO ':tmpfile' WITH (FORMAT BINARY)'
+:command
+
+-- import
CREATE TABLE tm.geoms_in AS SELECT * FROM tm.geoms LIMIT 0;
-COPY tm.geoms_in FROM :tmpfile WITH BINARY;
-SELECT 'geometry', count(*) FROM tm.geoms_in i, tm.geoms o WHERE i.id = o.id
- AND ST_OrderingEquals(i.g, o.g);
+\set command '\\copy tm.geoms_in FROM ':tmpfile' WITH (FORMAT BINARY)'
+:command
+
+SELECT 'geometry', count(*) FROM tm.geoms_in i, tm.geoms o
+WHERE i.id = o.id AND ST_OrderingEquals(i.g, o.g);
CREATE TABLE tm.geogs AS SELECT id,g::geography FROM tm.geoms
WHERE geometrytype(g) NOT LIKE '%CURVE%'
AND geometrytype(g) NOT LIKE '%CIRCULAR%'
AND geometrytype(g) NOT LIKE '%SURFACE%'
AND geometrytype(g) NOT LIKE 'TRIANGLE%'
- AND geometrytype(g) NOT LIKE 'TIN%'
-;
+ AND geometrytype(g) NOT LIKE 'TIN%';
-COPY tm.geogs TO :tmpfile WITH BINARY;
+-- export
+\set command '\\copy tm.geogs TO ':tmpfile' WITH (FORMAT BINARY)'
+:command
+
+-- import
CREATE TABLE tm.geogs_in AS SELECT * FROM tm.geogs LIMIT 0;
-COPY tm.geogs_in FROM :tmpfile WITH BINARY;
-SELECT 'geometry', count(*) FROM tm.geogs_in i, tm.geogs o WHERE i.id = o.id
- AND ST_OrderingEquals(i.g::geometry, o.g::geometry);
+\set command '\\copy tm.geogs_in FROM ':tmpfile' WITH (FORMAT BINARY)'
+:command
+
+SELECT 'geometry', count(*) FROM tm.geogs_in i, tm.geogs o
+WHERE i.id = o.id AND ST_OrderingEquals(i.g::geometry, o.g::geometry);
DROP SCHEMA tm CASCADE;
+
diff --git a/regress/core/tests.mk b/regress/core/tests.mk
index 3abd7bc..94903c3 100644
--- a/regress/core/tests.mk
+++ b/regress/core/tests.mk
@@ -23,7 +23,6 @@ current_dir := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))
RUNTESTFLAGS_INTERNAL += \
--before-upgrade-script $(top_srcdir)/regress/hooks/hook-before-upgrade.sql \
--after-upgrade-script $(top_srcdir)/regress/hooks/hook-after-upgrade.sql \
- --after-create-script $(top_srcdir)/regress/hooks/hook-after-create.sql \
--before-uninstall-script $(top_srcdir)/regress/hooks/hook-before-uninstall.sql
TESTS += \
@@ -40,7 +39,6 @@ TESTS += \
$(top_srcdir)/regress/core/dumppoints \
$(top_srcdir)/regress/core/dumpsegments \
$(top_srcdir)/regress/core/empty \
- $(top_srcdir)/regress/core/estimatedextent \
$(top_srcdir)/regress/core/forcecurve \
$(top_srcdir)/regress/core/flatgeobuf \
$(top_srcdir)/regress/core/geography \
@@ -55,7 +53,6 @@ TESTS += \
$(top_srcdir)/regress/core/out_marc21 \
$(top_srcdir)/regress/core/in_encodedpolyline \
$(top_srcdir)/regress/core/iscollection \
- $(top_srcdir)/regress/core/legacy \
$(top_srcdir)/regress/core/letters \
$(top_srcdir)/regress/core/long_xact \
$(top_srcdir)/regress/core/lwgeom_regress \
@@ -112,7 +109,6 @@ TESTS += \
$(top_srcdir)/regress/core/temporal_knn \
$(top_srcdir)/regress/core/tickets \
$(top_srcdir)/regress/core/twkb \
- $(top_srcdir)/regress/core/typmod \
$(top_srcdir)/regress/core/wkb \
$(top_srcdir)/regress/core/wkt \
$(top_srcdir)/regress/core/wmsservers \
@@ -144,11 +140,6 @@ TESTS_SLOW = \
$(top_srcdir)/regress/core/concave_hull_hard \
$(top_srcdir)/regress/core/knn_recheck
-ifeq ($(shell expr "$(POSTGIS_PGSQL_VERSION)" ">=" 120),1)
- TESTS += \
- $(top_srcdir)/regress/core/computed_columns
-endif
-
ifeq ($(shell expr "$(POSTGIS_GEOS_VERSION)" ">=" 30700),1)
# GEOS-3.7 adds:
# ST_FrechetDistance
diff --git a/regress/loader/tests.mk b/regress/loader/tests.mk
index 1fc77ac..c3cb9de 100644
--- a/regress/loader/tests.mk
+++ b/regress/loader/tests.mk
@@ -38,7 +38,5 @@ TESTS += \
$(top_srcdir)/regress/loader/Latin1 \
$(top_srcdir)/regress/loader/Latin1-implicit \
$(top_srcdir)/regress/loader/mfile \
- $(top_srcdir)/regress/loader/TestSkipANALYZE \
- $(top_srcdir)/regress/loader/TestANALYZE \
$(top_srcdir)/regress/loader/CharNoWidth
diff --git a/regress/run_test.pl b/regress/run_test.pl
index 0ec5b2d..1c331f4 100755
--- a/regress/run_test.pl
+++ b/regress/run_test.pl
@@ -147,7 +147,6 @@ $ENV{"LANG"} = "C";
# Add locale info to the psql options
# Add pg12 precision suppression
my $PGOPTIONS = $ENV{"PGOPTIONS"};
-$PGOPTIONS .= " -c lc_messages=C";
$PGOPTIONS .= " -c client_min_messages=NOTICE";
$PGOPTIONS .= " -c extra_float_digits=0";
$ENV{"PGOPTIONS"} = $PGOPTIONS;

View File

@@ -0,0 +1,218 @@
diff --git a/raster/test/regress/tests.mk b/raster/test/regress/tests.mk
index 00918e1..7e2b6cd 100644
--- a/raster/test/regress/tests.mk
+++ b/raster/test/regress/tests.mk
@@ -17,9 +17,7 @@ override RUNTESTFLAGS_INTERNAL := \
$(RUNTESTFLAGS_INTERNAL) \
--after-upgrade-script $(top_srcdir)/raster/test/regress/hooks/hook-after-upgrade-raster.sql
-RASTER_TEST_FIRST = \
- $(top_srcdir)/raster/test/regress/check_gdal \
- $(top_srcdir)/raster/test/regress/loader/load_outdb
+RASTER_TEST_FIRST =
RASTER_TEST_LAST = \
$(top_srcdir)/raster/test/regress/clean
@@ -33,9 +31,7 @@ RASTER_TEST_IO = \
RASTER_TEST_BASIC_FUNC = \
$(top_srcdir)/raster/test/regress/rt_bytea \
- $(top_srcdir)/raster/test/regress/rt_wkb \
$(top_srcdir)/raster/test/regress/box3d \
- $(top_srcdir)/raster/test/regress/rt_addband \
$(top_srcdir)/raster/test/regress/rt_band \
$(top_srcdir)/raster/test/regress/rt_tile
@@ -73,16 +69,10 @@ RASTER_TEST_BANDPROPS = \
$(top_srcdir)/raster/test/regress/rt_neighborhood \
$(top_srcdir)/raster/test/regress/rt_nearestvalue \
$(top_srcdir)/raster/test/regress/rt_pixelofvalue \
- $(top_srcdir)/raster/test/regress/rt_polygon \
- $(top_srcdir)/raster/test/regress/rt_setbandpath
+ $(top_srcdir)/raster/test/regress/rt_polygon
RASTER_TEST_UTILITY = \
$(top_srcdir)/raster/test/regress/rt_utility \
- $(top_srcdir)/raster/test/regress/rt_fromgdalraster \
- $(top_srcdir)/raster/test/regress/rt_asgdalraster \
- $(top_srcdir)/raster/test/regress/rt_astiff \
- $(top_srcdir)/raster/test/regress/rt_asjpeg \
- $(top_srcdir)/raster/test/regress/rt_aspng \
$(top_srcdir)/raster/test/regress/rt_reclass \
$(top_srcdir)/raster/test/regress/rt_gdalwarp \
$(top_srcdir)/raster/test/regress/rt_gdalcontour \
@@ -120,21 +110,13 @@ RASTER_TEST_SREL = \
RASTER_TEST_BUGS = \
$(top_srcdir)/raster/test/regress/bug_test_car5 \
- $(top_srcdir)/raster/test/regress/permitted_gdal_drivers \
$(top_srcdir)/raster/test/regress/tickets
RASTER_TEST_LOADER = \
$(top_srcdir)/raster/test/regress/loader/Basic \
$(top_srcdir)/raster/test/regress/loader/Projected \
$(top_srcdir)/raster/test/regress/loader/BasicCopy \
- $(top_srcdir)/raster/test/regress/loader/BasicFilename \
- $(top_srcdir)/raster/test/regress/loader/BasicOutDB \
- $(top_srcdir)/raster/test/regress/loader/Tiled10x10 \
- $(top_srcdir)/raster/test/regress/loader/Tiled10x10Copy \
- $(top_srcdir)/raster/test/regress/loader/Tiled8x8 \
- $(top_srcdir)/raster/test/regress/loader/TiledAuto \
- $(top_srcdir)/raster/test/regress/loader/TiledAutoSkipNoData \
- $(top_srcdir)/raster/test/regress/loader/TiledAutoCopyn
+ $(top_srcdir)/raster/test/regress/loader/BasicFilename
RASTER_TESTS := $(RASTER_TEST_FIRST) \
$(RASTER_TEST_METADATA) $(RASTER_TEST_IO) $(RASTER_TEST_BASIC_FUNC) \
diff --git a/regress/core/binary.sql b/regress/core/binary.sql
index 7a36b65..ad78fc7 100644
--- a/regress/core/binary.sql
+++ b/regress/core/binary.sql
@@ -1,4 +1,5 @@
SET client_min_messages TO warning;
+
CREATE SCHEMA tm;
CREATE TABLE tm.geoms (id serial, g geometry);
@@ -31,24 +32,39 @@ SELECT st_force4d(g) FROM tm.geoms WHERE id < 15 ORDER BY id;
INSERT INTO tm.geoms(g)
SELECT st_setsrid(g,4326) FROM tm.geoms ORDER BY id;
-COPY tm.geoms TO :tmpfile WITH BINARY;
+-- define temp file path
+\set tmpfile '/tmp/postgis_binary_test.dat'
+
+-- export
+\set command '\\copy tm.geoms TO ':tmpfile' WITH (FORMAT BINARY)'
+:command
+
+-- import
CREATE TABLE tm.geoms_in AS SELECT * FROM tm.geoms LIMIT 0;
-COPY tm.geoms_in FROM :tmpfile WITH BINARY;
-SELECT 'geometry', count(*) FROM tm.geoms_in i, tm.geoms o WHERE i.id = o.id
- AND ST_OrderingEquals(i.g, o.g);
+\set command '\\copy tm.geoms_in FROM ':tmpfile' WITH (FORMAT BINARY)'
+:command
+
+SELECT 'geometry', count(*) FROM tm.geoms_in i, tm.geoms o
+WHERE i.id = o.id AND ST_OrderingEquals(i.g, o.g);
CREATE TABLE tm.geogs AS SELECT id,g::geography FROM tm.geoms
WHERE geometrytype(g) NOT LIKE '%CURVE%'
AND geometrytype(g) NOT LIKE '%CIRCULAR%'
AND geometrytype(g) NOT LIKE '%SURFACE%'
AND geometrytype(g) NOT LIKE 'TRIANGLE%'
- AND geometrytype(g) NOT LIKE 'TIN%'
-;
+ AND geometrytype(g) NOT LIKE 'TIN%';
-COPY tm.geogs TO :tmpfile WITH BINARY;
+-- export
+\set command '\\copy tm.geogs TO ':tmpfile' WITH (FORMAT BINARY)'
+:command
+
+-- import
CREATE TABLE tm.geogs_in AS SELECT * FROM tm.geogs LIMIT 0;
-COPY tm.geogs_in FROM :tmpfile WITH BINARY;
-SELECT 'geometry', count(*) FROM tm.geogs_in i, tm.geogs o WHERE i.id = o.id
- AND ST_OrderingEquals(i.g::geometry, o.g::geometry);
+\set command '\\copy tm.geogs_in FROM ':tmpfile' WITH (FORMAT BINARY)'
+:command
+
+SELECT 'geometry', count(*) FROM tm.geogs_in i, tm.geogs o
+WHERE i.id = o.id AND ST_OrderingEquals(i.g::geometry, o.g::geometry);
DROP SCHEMA tm CASCADE;
+
diff --git a/regress/core/tests.mk b/regress/core/tests.mk
index 9e05244..a63a3e1 100644
--- a/regress/core/tests.mk
+++ b/regress/core/tests.mk
@@ -16,14 +16,13 @@ POSTGIS_PGSQL_VERSION=170
POSTGIS_GEOS_VERSION=31101
HAVE_JSON=yes
HAVE_SPGIST=yes
-INTERRUPTTESTS=yes
+INTERRUPTTESTS=no
current_dir := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))
RUNTESTFLAGS_INTERNAL += \
--before-upgrade-script $(top_srcdir)/regress/hooks/hook-before-upgrade.sql \
--after-upgrade-script $(top_srcdir)/regress/hooks/hook-after-upgrade.sql \
- --after-create-script $(top_srcdir)/regress/hooks/hook-after-create.sql \
--before-uninstall-script $(top_srcdir)/regress/hooks/hook-before-uninstall.sql
TESTS += \
@@ -40,7 +39,6 @@ TESTS += \
$(top_srcdir)/regress/core/dumppoints \
$(top_srcdir)/regress/core/dumpsegments \
$(top_srcdir)/regress/core/empty \
- $(top_srcdir)/regress/core/estimatedextent \
$(top_srcdir)/regress/core/forcecurve \
$(top_srcdir)/regress/core/flatgeobuf \
$(top_srcdir)/regress/core/frechet \
@@ -60,7 +58,6 @@ TESTS += \
$(top_srcdir)/regress/core/out_marc21 \
$(top_srcdir)/regress/core/in_encodedpolyline \
$(top_srcdir)/regress/core/iscollection \
- $(top_srcdir)/regress/core/legacy \
$(top_srcdir)/regress/core/letters \
$(top_srcdir)/regress/core/lwgeom_regress \
$(top_srcdir)/regress/core/measures \
@@ -119,7 +116,6 @@ TESTS += \
$(top_srcdir)/regress/core/temporal_knn \
$(top_srcdir)/regress/core/tickets \
$(top_srcdir)/regress/core/twkb \
- $(top_srcdir)/regress/core/typmod \
$(top_srcdir)/regress/core/wkb \
$(top_srcdir)/regress/core/wkt \
$(top_srcdir)/regress/core/wmsservers \
@@ -143,8 +139,7 @@ TESTS += \
$(top_srcdir)/regress/core/oriented_envelope \
$(top_srcdir)/regress/core/point_coordinates \
$(top_srcdir)/regress/core/out_geojson \
- $(top_srcdir)/regress/core/wrapx \
- $(top_srcdir)/regress/core/computed_columns
+ $(top_srcdir)/regress/core/wrapx
# Slow slow tests
TESTS_SLOW = \
diff --git a/regress/loader/tests.mk b/regress/loader/tests.mk
index ac4f8ad..4bad4fc 100644
--- a/regress/loader/tests.mk
+++ b/regress/loader/tests.mk
@@ -38,7 +38,5 @@ TESTS += \
$(top_srcdir)/regress/loader/Latin1 \
$(top_srcdir)/regress/loader/Latin1-implicit \
$(top_srcdir)/regress/loader/mfile \
- $(top_srcdir)/regress/loader/TestSkipANALYZE \
- $(top_srcdir)/regress/loader/TestANALYZE \
$(top_srcdir)/regress/loader/CharNoWidth \
diff --git a/regress/run_test.pl b/regress/run_test.pl
index cac4b2e..4c7c82b 100755
--- a/regress/run_test.pl
+++ b/regress/run_test.pl
@@ -238,7 +238,6 @@ $ENV{"LANG"} = "C";
# Add locale info to the psql options
# Add pg12 precision suppression
my $PGOPTIONS = $ENV{"PGOPTIONS"};
-$PGOPTIONS .= " -c lc_messages=C";
$PGOPTIONS .= " -c client_min_messages=NOTICE";
$PGOPTIONS .= " -c extra_float_digits=0";
$ENV{"PGOPTIONS"} = $PGOPTIONS;
diff --git a/topology/test/tests.mk b/topology/test/tests.mk
index cbe2633..2c7c18f 100644
--- a/topology/test/tests.mk
+++ b/topology/test/tests.mk
@@ -46,9 +46,7 @@ TESTS += \
$(top_srcdir)/topology/test/regress/legacy_query.sql \
$(top_srcdir)/topology/test/regress/legacy_validate.sql \
$(top_srcdir)/topology/test/regress/polygonize.sql \
- $(top_srcdir)/topology/test/regress/populate_topology_layer.sql \
$(top_srcdir)/topology/test/regress/removeunusedprimitives.sql \
- $(top_srcdir)/topology/test/regress/renametopogeometrycolumn.sql \
$(top_srcdir)/topology/test/regress/renametopology.sql \
$(top_srcdir)/topology/test/regress/share_sequences.sql \
$(top_srcdir)/topology/test/regress/sqlmm.sql \

File diff suppressed because one or more lines are too long

View File

@@ -0,0 +1,17 @@
#!/bin/bash
set -ex
cd "$(dirname "${0}")"
dropdb --if-exist contrib_regression
createdb contrib_regression
psql -d contrib_regression -c "ALTER DATABASE contrib_regression SET TimeZone='UTC'" \
-c "ALTER DATABASE contrib_regression SET DateStyle='ISO, MDY'" \
-c "CREATE EXTENSION postgis SCHEMA public" \
-c "CREATE EXTENSION postgis_topology" \
-c "CREATE EXTENSION postgis_tiger_geocoder CASCADE" \
-c "CREATE EXTENSION postgis_raster SCHEMA public" \
-c "CREATE EXTENSION postgis_sfcgal SCHEMA public"
patch -p1 <postgis-no-upgrade-test.patch
patch -p1 <"postgis-regular-${PG_VERSION}.patch"
psql -d contrib_regression -f raster_outdb_template.sql
trap 'patch -R -p1 <postgis-no-upgrade-test.patch && patch -R -p1 <"postgis-regular-${PG_VERSION}.patch"' EXIT
POSTGIS_REGRESS_DB=contrib_regression RUNTESTFLAGS=--nocreate make installcheck-base

View File

@@ -63,5 +63,9 @@ done
for d in ${FAILED}; do
cat "$(find $d -name regression.diffs)"
done
for postgis_diff in /tmp/pgis_reg/*_diff; do
echo "${postgis_diff}:"
cat "${postgis_diff}"
done
echo "${FAILED}"
exit 1

View File

@@ -178,9 +178,9 @@ pub struct ComputeSpec {
/// JWT for authorizing requests to endpoint storage service
pub endpoint_storage_token: Option<String>,
/// If true, download LFC state from endpoint_storage and pass it to Postgres on startup
/// Download LFC state from endpoint_storage and pass it to Postgres on startup
#[serde(default)]
pub prewarm_lfc_on_startup: bool,
pub autoprewarm: bool,
}
/// Feature flag to signal `compute_ctl` to enable certain experimental functionality.

View File

@@ -85,7 +85,7 @@
"vartype": "bool"
},
{
"name": "prewarm_lfc_on_startup",
"name": "autoprewarm",
"value": "off",
"vartype": "bool"
},

View File

@@ -330,6 +330,8 @@ pub struct TimelineImportConfig {
pub import_job_concurrency: NonZeroUsize,
pub import_job_soft_size_limit: NonZeroUsize,
pub import_job_checkpoint_threshold: NonZeroUsize,
/// Max size of the remote storage partial read done by any job
pub import_job_max_byte_range_size: NonZeroUsize,
}
#[derive(Debug, Clone, PartialEq, Eq, serde::Serialize, serde::Deserialize)]
@@ -608,7 +610,10 @@ pub mod defaults {
pub const DEFAULT_IO_BUFFER_ALIGNMENT: usize = 512;
pub const DEFAULT_WAL_RECEIVER_PROTOCOL: utils::postgres_client::PostgresClientProtocol =
utils::postgres_client::PostgresClientProtocol::Vanilla;
utils::postgres_client::PostgresClientProtocol::Interpreted {
format: utils::postgres_client::InterpretedFormat::Protobuf,
compression: Some(utils::postgres_client::Compression::Zstd { level: 1 }),
};
pub const DEFAULT_SSL_KEY_FILE: &str = "server.key";
pub const DEFAULT_SSL_CERT_FILE: &str = "server.crt";
@@ -732,6 +737,7 @@ impl Default for ConfigToml {
import_job_concurrency: NonZeroUsize::new(32).unwrap(),
import_job_soft_size_limit: NonZeroUsize::new(256 * 1024 * 1024).unwrap(),
import_job_checkpoint_threshold: NonZeroUsize::new(32).unwrap(),
import_job_max_byte_range_size: NonZeroUsize::new(4 * 1024 * 1024).unwrap(),
},
basebackup_cache_config: None,
posthog_config: None,

View File

@@ -22,6 +22,16 @@ pub enum PostHogEvaluationError {
Internal(String),
}
impl PostHogEvaluationError {
pub fn as_variant_str(&self) -> &'static str {
match self {
PostHogEvaluationError::NotAvailable(_) => "not_available",
PostHogEvaluationError::NoConditionGroupMatched => "no_condition_group_matched",
PostHogEvaluationError::Internal(_) => "internal",
}
}
}
#[derive(Deserialize)]
pub struct LocalEvaluationResponse {
pub flags: Vec<LocalEvaluationFlag>,

View File

@@ -86,6 +86,14 @@ pub enum GateError {
GateClosed,
}
impl GateError {
pub fn is_cancel(&self) -> bool {
match self {
GateError::GateClosed => true,
}
}
}
impl Default for Gate {
fn default() -> Self {
Self {

View File

@@ -6,7 +6,7 @@ use posthog_client_lite::{
use tokio_util::sync::CancellationToken;
use utils::id::TenantId;
use crate::config::PageServerConf;
use crate::{config::PageServerConf, metrics::FEATURE_FLAG_EVALUATION};
#[derive(Clone)]
pub struct FeatureResolver {
@@ -55,11 +55,24 @@ impl FeatureResolver {
tenant_id: TenantId,
) -> Result<String, PostHogEvaluationError> {
if let Some(inner) = &self.inner {
inner.feature_store().evaluate_multivariate(
let res = inner.feature_store().evaluate_multivariate(
flag_key,
&tenant_id.to_string(),
&HashMap::new(),
)
);
match &res {
Ok(value) => {
FEATURE_FLAG_EVALUATION
.with_label_values(&[flag_key, "ok", value])
.inc();
}
Err(e) => {
FEATURE_FLAG_EVALUATION
.with_label_values(&[flag_key, "error", e.as_variant_str()])
.inc();
}
}
res
} else {
Err(PostHogEvaluationError::NotAvailable(
"PostHog integration is not enabled".to_string(),
@@ -80,11 +93,24 @@ impl FeatureResolver {
tenant_id: TenantId,
) -> Result<(), PostHogEvaluationError> {
if let Some(inner) = &self.inner {
inner.feature_store().evaluate_boolean(
let res = inner.feature_store().evaluate_boolean(
flag_key,
&tenant_id.to_string(),
&HashMap::new(),
)
);
match &res {
Ok(()) => {
FEATURE_FLAG_EVALUATION
.with_label_values(&[flag_key, "ok", "true"])
.inc();
}
Err(e) => {
FEATURE_FLAG_EVALUATION
.with_label_values(&[flag_key, "error", e.as_variant_str()])
.inc();
}
}
res
} else {
Err(PostHogEvaluationError::NotAvailable(
"PostHog integration is not enabled".to_string(),

View File

@@ -446,6 +446,15 @@ static PAGE_CACHE_ERRORS: Lazy<IntCounterVec> = Lazy::new(|| {
.expect("failed to define a metric")
});
pub(crate) static FEATURE_FLAG_EVALUATION: Lazy<CounterVec> = Lazy::new(|| {
register_counter_vec!(
"pageserver_feature_flag_evaluation",
"Number of times a feature flag is evaluated",
&["flag_key", "status", "value"],
)
.unwrap()
});
#[derive(IntoStaticStr)]
#[strum(serialize_all = "kebab_case")]
pub(crate) enum PageCacheErrorKind {

View File

@@ -99,6 +99,7 @@ use crate::tenant::remote_timeline_client::{
INITDB_PATH, MaybeDeletedIndexPart, remote_initdb_archive_path,
};
use crate::tenant::storage_layer::{DeltaLayer, ImageLayer};
use crate::tenant::timeline::CheckOtherForCancel;
use crate::tenant::timeline::delete::DeleteTimelineFlow;
use crate::tenant::timeline::uninit::cleanup_timeline_directory;
use crate::virtual_file::VirtualFile;
@@ -3261,11 +3262,11 @@ impl TenantShard {
/// Trips the compaction circuit breaker if appropriate.
pub(crate) fn maybe_trip_compaction_breaker(&self, err: &CompactionError) {
if err.is_cancel(CheckOtherForCancel::No /* XXX flip this to Yes so that all the Other() errors that are cancel don't trip the circuit breaker? */) {
return;
}
match err {
err if err.is_cancel() => {}
CompactionError::ShuttingDown => (),
// Offload failures don't trip the circuit breaker, since they're cheap to retry and
// shouldn't block compaction.
CompactionError::ShuttingDown => unreachable!("is_cancel"),
CompactionError::Offload(_) => {}
CompactionError::CollectKeySpaceError(err) => {
// CollectKeySpaceError::Cancelled and PageRead::Cancelled are handled in `err.is_cancel` branch.
@@ -3280,7 +3281,7 @@ impl TenantShard {
.unwrap()
.fail(&CIRCUIT_BREAKERS_BROKEN, err);
}
CompactionError::AlreadyRunning(_) => {}
CompactionError::AlreadyRunning(_) => unreachable!("is_cancel, but XXX why?"),
}
}

View File

@@ -55,11 +55,11 @@ pub struct BatchLayerWriter {
}
impl BatchLayerWriter {
pub async fn new(conf: &'static PageServerConf) -> anyhow::Result<Self> {
Ok(Self {
pub fn new(conf: &'static PageServerConf) -> Self {
Self {
generated_layer_writers: Vec::new(),
conf,
})
}
}
pub fn add_unfinished_image_writer(
@@ -209,6 +209,7 @@ impl<'a> SplitImageLayerWriter<'a> {
) -> anyhow::Result<Self> {
Ok(Self {
target_layer_size,
// XXX make this lazy like in SplitDeltaLayerWriter?
inner: ImageLayerWriter::new(
conf,
timeline_id,
@@ -223,7 +224,7 @@ impl<'a> SplitImageLayerWriter<'a> {
conf,
timeline_id,
tenant_shard_id,
batches: BatchLayerWriter::new(conf).await?,
batches: BatchLayerWriter::new(conf),
lsn,
start_key,
gate,
@@ -319,7 +320,7 @@ pub struct SplitDeltaLayerWriter<'a> {
}
impl<'a> SplitDeltaLayerWriter<'a> {
pub async fn new(
pub fn new(
conf: &'static PageServerConf,
timeline_id: TimelineId,
tenant_shard_id: TenantShardId,
@@ -327,8 +328,8 @@ impl<'a> SplitDeltaLayerWriter<'a> {
target_layer_size: u64,
gate: &'a utils::sync::gate::Gate,
cancel: CancellationToken,
) -> anyhow::Result<Self> {
Ok(Self {
) -> Self {
Self {
target_layer_size,
inner: None,
conf,
@@ -336,10 +337,10 @@ impl<'a> SplitDeltaLayerWriter<'a> {
tenant_shard_id,
lsn_range,
last_key_written: Key::MIN,
batches: BatchLayerWriter::new(conf).await?,
batches: BatchLayerWriter::new(conf),
gate,
cancel,
})
}
}
pub async fn put_value(
@@ -510,9 +511,7 @@ mod tests {
4 * 1024 * 1024,
&tline.gate,
tline.cancel.clone(),
)
.await
.unwrap();
);
image_writer
.put_image(get_key(0), get_img(0), &ctx)
@@ -590,9 +589,7 @@ mod tests {
4 * 1024 * 1024,
&tline.gate,
tline.cancel.clone(),
)
.await
.unwrap();
);
const N: usize = 2000;
for i in 0..N {
let i = i as u32;
@@ -692,9 +689,7 @@ mod tests {
4 * 1024,
&tline.gate,
tline.cancel.clone(),
)
.await
.unwrap();
);
image_writer
.put_image(get_key(0), get_img(0), &ctx)
@@ -770,9 +765,7 @@ mod tests {
4 * 1024 * 1024,
&tline.gate,
tline.cancel.clone(),
)
.await
.unwrap();
);
for i in 0..N {
let i = i as u32;

View File

@@ -22,8 +22,8 @@ use crate::context::{DownloadBehavior, RequestContext};
use crate::metrics::{self, BackgroundLoopSemaphoreMetricsRecorder, TENANT_TASK_EVENTS};
use crate::task_mgr::{self, BACKGROUND_RUNTIME, TOKIO_WORKER_THREADS, TaskKind};
use crate::tenant::throttle::Stats;
use crate::tenant::timeline::CompactionError;
use crate::tenant::timeline::compaction::CompactionOutcome;
use crate::tenant::timeline::{CheckOtherForCancel, CompactionError};
use crate::tenant::{TenantShard, TenantState};
/// Semaphore limiting concurrent background tasks (across all tenants).
@@ -292,35 +292,12 @@ pub(crate) fn log_compaction_error(
task_cancelled: bool,
degrade_to_warning: bool,
) {
use CompactionError::*;
let is_cancel = err.is_cancel(CheckOtherForCancel::Yes);
use crate::tenant::PageReconstructError;
use crate::tenant::upload_queue::NotInitialized;
let level = match err {
e if e.is_cancel() => return,
ShuttingDown => return,
Offload(_) => Level::ERROR,
AlreadyRunning(_) => Level::ERROR,
CollectKeySpaceError(_) => Level::ERROR,
_ if task_cancelled => Level::INFO,
Other(err) => {
let root_cause = err.root_cause();
let upload_queue = root_cause
.downcast_ref::<NotInitialized>()
.is_some_and(|e| e.is_stopping());
let timeline = root_cause
.downcast_ref::<PageReconstructError>()
.is_some_and(|e| e.is_stopping());
let is_stopping = upload_queue || timeline;
if is_stopping {
Level::INFO
} else {
Level::ERROR
}
}
let level = if is_cancel || task_cancelled {
Level::INFO
} else {
Level::ERROR
};
if let Some((error_count, sleep_duration)) = retry_info {

View File

@@ -75,7 +75,7 @@ use utils::postgres_client::PostgresClientProtocol;
use utils::rate_limit::RateLimit;
use utils::seqwait::SeqWait;
use utils::simple_rcu::{Rcu, RcuReadGuard};
use utils::sync::gate::{Gate, GateGuard};
use utils::sync::gate::{Gate, GateError, GateGuard};
use utils::{completion, critical, fs_ext, pausable_failpoint};
use wal_decoder::serialized_batch::{SerializedValueBatch, ValueMeta};
@@ -116,6 +116,7 @@ use crate::pgdatadir_mapping::{
MAX_AUX_FILE_V2_DELTAS, MetricsUpdate,
};
use crate::task_mgr::TaskKind;
use crate::tenant::blob_io::WriteBlobError;
use crate::tenant::config::AttachmentMode;
use crate::tenant::gc_result::GcResult;
use crate::tenant::layer_map::LayerMap;
@@ -130,6 +131,7 @@ use crate::tenant::storage_layer::{
};
use crate::tenant::tasks::BackgroundLoopKind;
use crate::tenant::timeline::logical_size::CurrentLogicalSize;
use crate::virtual_file::owned_buffers_io::write::FlushTaskError;
use crate::virtual_file::{MaybeFatalIo, VirtualFile};
use crate::walingest::WalLagCooldown;
use crate::walredo::RedoAttemptType;
@@ -760,7 +762,7 @@ pub(crate) enum CreateImageLayersError {
PageReconstructError(#[source] PageReconstructError),
#[error(transparent)]
Other(#[from] anyhow::Error),
Other(anyhow::Error),
}
impl From<layer_manager::Shutdown> for CreateImageLayersError {
@@ -2061,9 +2063,10 @@ impl Timeline {
};
// Signal compaction failure to avoid L0 flush stalls when it's broken.
// XXX this looks an awful lot like the circuit breaker code? Can we dedupe classification?
match &result {
Ok(_) => self.compaction_failed.store(false, AtomicOrdering::Relaxed),
Err(e) if e.is_cancel() => {}
Err(e) if e.is_cancel(CheckOtherForCancel::No /* XXX flip this to Yes so that all the Other() errors that are cancel don't trip the circuit breaker? */) => {}
Err(CompactionError::ShuttingDown) => {
// Covered by the `Err(e) if e.is_cancel()` branch.
}
@@ -5530,7 +5533,7 @@ impl Timeline {
self.should_check_if_image_layers_required(lsn)
};
let mut batch_image_writer = BatchLayerWriter::new(self.conf).await?;
let mut batch_image_writer = BatchLayerWriter::new(self.conf);
let mut all_generated = true;
@@ -5634,7 +5637,8 @@ impl Timeline {
self.cancel.clone(),
ctx,
)
.await?;
.await
.map_err(CreateImageLayersError::Other)?;
fail_point!("image-layer-writer-fail-before-finish", |_| {
Err(CreateImageLayersError::Other(anyhow::anyhow!(
@@ -5729,7 +5733,10 @@ impl Timeline {
}
}
let image_layers = batch_image_writer.finish(self, ctx).await?;
let image_layers = batch_image_writer
.finish(self, ctx)
.await
.map_err(CreateImageLayersError::Other)?;
let mut guard = self.layers.write().await;
@@ -5931,19 +5938,61 @@ pub(crate) enum CompactionError {
AlreadyRunning(&'static str),
}
/// Whether [`CompactionError::is_cancel`] should inspect the
/// [`CompactionError::Other`] anyhow Error's root cause for
/// typical causes of cancellation.
pub(crate) enum CheckOtherForCancel {
No,
Yes,
}
impl CompactionError {
/// Errors that can be ignored, i.e., cancel and shutdown.
pub fn is_cancel(&self) -> bool {
matches!(
pub fn is_cancel(&self, check_other: CheckOtherForCancel) -> bool {
if matches!(
self,
Self::ShuttingDown
| Self::AlreadyRunning(_)
| Self::AlreadyRunning(_) // XXX why do we treat AlreadyRunning as cancel?
| Self::CollectKeySpaceError(CollectKeySpaceError::Cancelled)
| Self::CollectKeySpaceError(CollectKeySpaceError::PageRead(
PageReconstructError::Cancelled
))
| Self::Offload(OffloadError::Cancelled)
)
) {
return true;
}
let root_cause = match &check_other {
CheckOtherForCancel::No => return false,
CheckOtherForCancel::Yes => {
if let Self::Other(other) = self {
other.root_cause()
} else {
return false;
}
}
};
let upload_queue = root_cause
.downcast_ref::<NotInitialized>()
.is_some_and(|e| e.is_stopping());
let timeline = root_cause
.downcast_ref::<PageReconstructError>()
.is_some_and(|e| e.is_stopping());
let buffered_writer_flush_task_canelled = root_cause
.downcast_ref::<FlushTaskError>()
.is_some_and(|e| e.is_cancel());
let write_blob_cancelled = root_cause
.downcast_ref::<WriteBlobError>()
.is_some_and(|e| e.is_cancel());
let gate_closed = root_cause
.downcast_ref::<GateError>()
.is_some_and(|e| e.is_cancel());
upload_queue
|| timeline
|| buffered_writer_flush_task_canelled
|| write_blob_cancelled
|| gate_closed
}
/// Critical errors that indicate data corruption.

View File

@@ -11,9 +11,9 @@ use std::time::{Duration, Instant};
use super::layer_manager::LayerManager;
use super::{
CompactFlags, CompactOptions, CompactionError, CreateImageLayersError, DurationRecorder,
GetVectoredError, ImageLayerCreationMode, LastImageLayerCreationStatus, RecordedDuration,
Timeline,
CheckOtherForCancel, CompactFlags, CompactOptions, CompactionError, CreateImageLayersError,
DurationRecorder, GetVectoredError, ImageLayerCreationMode, LastImageLayerCreationStatus,
RecordedDuration, Timeline,
};
use crate::tenant::timeline::DeltaEntry;
@@ -1396,7 +1396,7 @@ impl Timeline {
// Suppress errors when cancelled.
Err(_) if self.cancel.is_cancelled() => {}
Err(err) if err.is_cancel() => {}
Err(err) if err.is_cancel(CheckOtherForCancel::No) => {}
// Alert on critical errors that indicate data corruption.
Err(err) if err.is_critical() => {
@@ -3516,10 +3516,7 @@ impl Timeline {
self.get_compaction_target_size(),
&self.gate,
self.cancel.clone(),
)
.await
.context("failed to create delta layer writer")
.map_err(CompactionError::Other)?;
);
#[derive(Default)]
struct RewritingLayers {
@@ -4297,7 +4294,8 @@ impl TimelineAdaptor {
self.timeline.cancel.clone(),
ctx,
)
.await?;
.await
.map_err(CreateImageLayersError::Other)?;
fail_point!("image-layer-writer-fail-before-finish", |_| {
Err(CreateImageLayersError::Other(anyhow::anyhow!(
@@ -4306,7 +4304,10 @@ impl TimelineAdaptor {
});
let keyspace = KeySpace {
ranges: self.get_keyspace(key_range, lsn, ctx).await?,
ranges: self
.get_keyspace(key_range, lsn, ctx)
.await
.map_err(CreateImageLayersError::Other)?,
};
// TODO set proper (stateful) start. The create_image_layer_for_rel_blocks function mostly
let outcome = self
@@ -4325,9 +4326,13 @@ impl TimelineAdaptor {
unfinished_image_layer,
} = outcome
{
let (desc, path) = unfinished_image_layer.finish(ctx).await?;
let (desc, path) = unfinished_image_layer
.finish(ctx)
.await
.map_err(CreateImageLayersError::Other)?;
let image_layer =
Layer::finish_creating(self.timeline.conf, &self.timeline, desc, &path)?;
Layer::finish_creating(self.timeline.conf, &self.timeline, desc, &path)
.map_err(CreateImageLayersError::Other)?;
self.new_images.push(image_layer);
}

View File

@@ -100,6 +100,7 @@ async fn run_v1(
.unwrap(),
import_job_concurrency: base.import_job_concurrency,
import_job_checkpoint_threshold: base.import_job_checkpoint_threshold,
import_job_max_byte_range_size: base.import_job_max_byte_range_size,
}
}
None => timeline.conf.timeline_import_config.clone(),
@@ -441,6 +442,7 @@ impl Plan {
let mut last_completed_job_idx = start_after_job_idx.unwrap_or(0);
let checkpoint_every: usize = import_config.import_job_checkpoint_threshold.into();
let max_byte_range_size: usize = import_config.import_job_max_byte_range_size.into();
// Run import jobs concurrently up to the limit specified by the pageserver configuration.
// Note that we process completed futures in the oreder of insertion. This will be the
@@ -456,7 +458,7 @@ impl Plan {
work.push_back(tokio::task::spawn(async move {
let _permit = permit;
let res = job.run(job_timeline, &ctx).await;
let res = job.run(job_timeline, max_byte_range_size, &ctx).await;
(job_idx, res)
}));
},
@@ -679,6 +681,7 @@ trait ImportTask {
async fn doit(
self,
layer_writer: &mut ImageLayerWriter,
max_byte_range_size: usize,
ctx: &RequestContext,
) -> anyhow::Result<usize>;
}
@@ -715,6 +718,7 @@ impl ImportTask for ImportSingleKeyTask {
async fn doit(
self,
layer_writer: &mut ImageLayerWriter,
_max_byte_range_size: usize,
ctx: &RequestContext,
) -> anyhow::Result<usize> {
layer_writer.put_image(self.key, self.buf, ctx).await?;
@@ -768,10 +772,9 @@ impl ImportTask for ImportRelBlocksTask {
async fn doit(
self,
layer_writer: &mut ImageLayerWriter,
max_byte_range_size: usize,
ctx: &RequestContext,
) -> anyhow::Result<usize> {
const MAX_BYTE_RANGE_SIZE: usize = 4 * 1024 * 1024;
debug!("Importing relation file");
let (rel_tag, start_blk) = self.key_range.start.to_rel_block()?;
@@ -796,7 +799,7 @@ impl ImportTask for ImportRelBlocksTask {
assert_eq!(key.len(), 1);
assert!(!acc.is_empty());
assert!(acc_end > acc_start);
if acc_end == start && end - acc_start <= MAX_BYTE_RANGE_SIZE {
if acc_end == start && end - acc_start <= max_byte_range_size {
acc.push(key.pop().unwrap());
Ok((acc, acc_start, end))
} else {
@@ -860,6 +863,7 @@ impl ImportTask for ImportSlruBlocksTask {
async fn doit(
self,
layer_writer: &mut ImageLayerWriter,
_max_byte_range_size: usize,
ctx: &RequestContext,
) -> anyhow::Result<usize> {
debug!("Importing SLRU segment file {}", self.path);
@@ -906,12 +910,13 @@ impl ImportTask for AnyImportTask {
async fn doit(
self,
layer_writer: &mut ImageLayerWriter,
max_byte_range_size: usize,
ctx: &RequestContext,
) -> anyhow::Result<usize> {
match self {
Self::SingleKey(t) => t.doit(layer_writer, ctx).await,
Self::RelBlocks(t) => t.doit(layer_writer, ctx).await,
Self::SlruBlocks(t) => t.doit(layer_writer, ctx).await,
Self::SingleKey(t) => t.doit(layer_writer, max_byte_range_size, ctx).await,
Self::RelBlocks(t) => t.doit(layer_writer, max_byte_range_size, ctx).await,
Self::SlruBlocks(t) => t.doit(layer_writer, max_byte_range_size, ctx).await,
}
}
}
@@ -952,7 +957,12 @@ impl ChunkProcessingJob {
}
}
async fn run(self, timeline: Arc<Timeline>, ctx: &RequestContext) -> anyhow::Result<()> {
async fn run(
self,
timeline: Arc<Timeline>,
max_byte_range_size: usize,
ctx: &RequestContext,
) -> anyhow::Result<()> {
let mut writer = ImageLayerWriter::new(
timeline.conf,
timeline.timeline_id,
@@ -967,7 +977,7 @@ impl ChunkProcessingJob {
let mut nimages = 0;
for task in self.tasks {
nimages += task.doit(&mut writer, ctx).await?;
nimages += task.doit(&mut writer, max_byte_range_size, ctx).await?;
}
let resident_layer = if nimages > 0 {

View File

@@ -423,6 +423,7 @@ class PageserverImportConfig:
"import_job_concurrency": self.import_job_concurrency,
"import_job_soft_size_limit": self.import_job_soft_size_limit,
"import_job_checkpoint_threshold": self.import_job_checkpoint_threshold,
"import_job_max_byte_range_size": 4 * 1024 * 1024, # Pageserver default
}
return ("timeline_import_config", value)