agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH 3/5] Move conversion of a "historic" to MVCC snapshot to a separate function.
210+ messages / 2 participants
[nested] [flat]

* [PATCH 3/5] Move conversion of a "historic" to MVCC snapshot to a separate function.
@ 2026-02-27 18:01  Antonin Houska <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw)

The conversion is now handled by SnapBuildMVCCFromHistoric(). REPACK
CONCURRENTLY will also need it.
---
 src/backend/replication/logical/snapbuild.c | 59 +++++++++++++++++----
 src/backend/utils/time/snapmgr.c            |  3 +-
 src/include/replication/snapbuild.h         |  1 +
 src/include/utils/snapmgr.h                 |  1 +
 4 files changed, 52 insertions(+), 12 deletions(-)

diff --git a/src/backend/replication/logical/snapbuild.c b/src/backend/replication/logical/snapbuild.c
index 7f79621b57e..a738ad8a864 100644
--- a/src/backend/replication/logical/snapbuild.c
+++ b/src/backend/replication/logical/snapbuild.c
@@ -440,10 +440,7 @@ Snapshot
 SnapBuildInitialSnapshot(SnapBuild *builder)
 {
 	Snapshot	snap;
-	TransactionId xid;
 	TransactionId safeXid;
-	TransactionId *newxip;
-	int			newxcnt = 0;
 
 	Assert(XactIsoLevel == XACT_REPEATABLE_READ);
 	Assert(builder->building_full_snapshot);
@@ -485,7 +482,35 @@ SnapBuildInitialSnapshot(SnapBuild *builder)
 
 	MyProc->xmin = snap->xmin;
 
-	/* allocate in transaction context */
+	/* Convert the historic snapshot to MVCC snapshot. */
+	return SnapBuildMVCCFromHistoric(snap, true);
+}
+
+/*
+ * Turn a historic MVCC snapshot into an ordinary MVCC snapshot.
+ *
+ * Unlike a regular (non-historic) MVCC snapshot, the 'xip' array of this
+ * snapshot contains not only running main transactions, but also their
+ * subtransactions. On the other hand, 'subxip' will usually be empty. This
+ * difference does not affect the result of XidInMVCCSnapshot() because it
+ * searches both in 'xip' and 'subxip'.
+ *
+ * Pass true for 'in_place' if you don't care about modifying the source
+ * snapshot. If you need a new instance, and one that was allocated as a
+ * single chunk of memory, pass false.
+ */
+Snapshot
+SnapBuildMVCCFromHistoric(Snapshot snapshot, bool in_place)
+{
+	TransactionId xid;
+	TransactionId *oldxip = snapshot->xip;
+	uint32		oldxcnt = snapshot->xcnt;
+	TransactionId *newxip;
+	int			newxcnt = 0;
+	Snapshot	result;
+
+	Assert(snapshot->snapshot_type == SNAPSHOT_HISTORIC_MVCC);
+
 	newxip = palloc_array(TransactionId, GetMaxSnapshotXidCount());
 
 	/*
@@ -494,7 +519,7 @@ SnapBuildInitialSnapshot(SnapBuild *builder)
 	 * classical snapshot by marking all non-committed transactions as
 	 * in-progress. This can be expensive.
 	 */
-	for (xid = snap->xmin; NormalTransactionIdPrecedes(xid, snap->xmax);)
+	for (xid = snapshot->xmin; NormalTransactionIdPrecedes(xid, snapshot->xmax);)
 	{
 		void	   *test;
 
@@ -502,7 +527,7 @@ SnapBuildInitialSnapshot(SnapBuild *builder)
 		 * Check whether transaction committed using the decoding snapshot
 		 * meaning of ->xip.
 		 */
-		test = bsearch(&xid, snap->xip, snap->xcnt,
+		test = bsearch(&xid, snapshot->xip, snapshot->xcnt,
 					   sizeof(TransactionId), xidComparator);
 
 		if (test == NULL)
@@ -519,11 +544,25 @@ SnapBuildInitialSnapshot(SnapBuild *builder)
 	}
 
 	/* adjust remaining snapshot fields as needed */
-	snap->snapshot_type = SNAPSHOT_MVCC;
-	snap->xcnt = newxcnt;
-	snap->xip = newxip;
+	snapshot->xcnt = newxcnt;
+	snapshot->xip = newxip;
+
+	if (in_place)
+		result = snapshot;
+	else
+	{
+		result = CopySnapshot(snapshot);
+
+		/* Restore the original values so the source is intact. */
+		snapshot->xip = oldxip;
+		snapshot->xcnt = oldxcnt;
+
+		/* newxip has been copied */
+		pfree(newxip);
+	}
+	result->snapshot_type = SNAPSHOT_MVCC;
 
-	return snap;
+	return result;
 }
 
 /*
diff --git a/src/backend/utils/time/snapmgr.c b/src/backend/utils/time/snapmgr.c
index 2e6197f5f35..3af1b366adf 100644
--- a/src/backend/utils/time/snapmgr.c
+++ b/src/backend/utils/time/snapmgr.c
@@ -213,7 +213,6 @@ typedef struct ExportedSnapshot
 static List *exportedSnapshots = NIL;
 
 /* Prototypes for local functions */
-static Snapshot CopySnapshot(Snapshot snapshot);
 static void UnregisterSnapshotNoOwner(Snapshot snapshot);
 static void FreeSnapshot(Snapshot snapshot);
 static void SnapshotResetXmin(void);
@@ -604,7 +603,7 @@ SetTransactionSnapshot(Snapshot sourcesnap, VirtualTransactionId *sourcevxid,
  * The copy is palloc'd in TopTransactionContext and has initial refcounts set
  * to 0.  The returned snapshot has the copied flag set.
  */
-static Snapshot
+Snapshot
 CopySnapshot(Snapshot snapshot)
 {
 	Snapshot	newsnap;
diff --git a/src/include/replication/snapbuild.h b/src/include/replication/snapbuild.h
index ccded021433..34383dea776 100644
--- a/src/include/replication/snapbuild.h
+++ b/src/include/replication/snapbuild.h
@@ -73,6 +73,7 @@ extern void FreeSnapshotBuilder(SnapBuild *builder);
 extern void SnapBuildSnapDecRefcount(Snapshot snap);
 
 extern Snapshot SnapBuildInitialSnapshot(SnapBuild *builder);
+extern Snapshot SnapBuildMVCCFromHistoric(Snapshot snapshot, bool in_place);
 extern const char *SnapBuildExportSnapshot(SnapBuild *builder);
 extern void SnapBuildClearExportedSnapshot(void);
 extern void SnapBuildResetExportedSnapshotState(void);
diff --git a/src/include/utils/snapmgr.h b/src/include/utils/snapmgr.h
index b8c01a291a1..de824945f0b 100644
--- a/src/include/utils/snapmgr.h
+++ b/src/include/utils/snapmgr.h
@@ -63,6 +63,7 @@ extern Snapshot GetTransactionSnapshot(void);
 extern Snapshot GetLatestSnapshot(void);
 extern void SnapshotSetCommandId(CommandId curcid);
 
+extern Snapshot CopySnapshot(Snapshot snapshot);
 extern Snapshot GetCatalogSnapshot(Oid relid);
 extern Snapshot GetNonHistoricCatalogSnapshot(Oid relid);
 extern void InvalidateCatalogSnapshot(void);
-- 
2.47.3


--=-=-=
Content-Type: text/plain
Content-Disposition: attachment;
 filename=v36-0004-Add-CONCURRENTLY-option-to-REPACK-command.patch



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread

* [PATCH v13a 7/9] ci: get build/test concurrency from environment
@ 2026-06-10 18:49  Andres Freund <[email protected]>
  0 siblings, 0 replies; 210+ messages in thread

From: Andres Freund @ 2026-06-10 18:49 UTC (permalink / raw)

Previously we hardcoded the amount of concurrency in the CI definition. This
practice IIRC originated from a) using make, where the concurrency is not
sourced from the current system b) early cirrus-ci macos runners, which slowed
down a lot with full concurrency.

Hardcoding the concurrency is problematic as e.g. private repositories have
lower concurrency and larger github runners have more cores.

For most of the jobs we can rely on just using meson's and ninja's logic for
getting the current core count. For the autoconf we can use the nproc helper.

To make this at least somewhat understandable, I added the existing sysinfo
step to show the number of cores (and made it a bit easier to understand the
information already printed).

Discussion: https://postgr.es/m/a2ejn7lfqolutzz7kozalbhy3bixdrujb4buc3pgbtlk4am2ba@wbv6v7riia33
---
 .github/workflows/pg-ci.yml | 47 +++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/.github/workflows/pg-ci.yml b/.github/workflows/pg-ci.yml
index ab7950f6f14..9384ec0d902 100644
--- a/.github/workflows/pg-ci.yml
+++ b/.github/workflows/pg-ci.yml
@@ -40,14 +40,6 @@ env:
   # concurrent jobs and retrying older runs have a chance of working.
   CLONE_DEPTH: 500
 
-  # At the moment all jobs use 4vcore runners, and none seems to benefit from
-  # increasing concurrency further.
-  BUILD_JOBS: 4
-
-  # It's possible that some jobs benefit from an increased test concurrency,
-  # but a default of 4 is a safe bet. Individual jobs can override.
-  TEST_JOBS: 4
-
   CCACHE_MAXSIZE: "250M"
   CCACHE_DIR: ${{ github.workspace }}/ccache_dir
 
@@ -215,10 +207,19 @@ jobs:
       - &nix_sysinfo_step
         name: sysinfo
         run: |
-          id
-          uname -a
+          echo -n "Number of cores: "
+          nproc 2> /dev/null || sysctl hw.physicalcpu hw.logicalcpu
+
+          echo "id: $(id)"
+          echo "uname: $(uname -a)"
+
+          echo ::group::ulimit
           ulimit -a -H && ulimit -a -S
+          echo ::endgroup::
+
+          echo ::group::env
           env
+          echo ::endgroup::
 
       - name: Parse ci-os-only
         id: os
@@ -352,7 +353,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: &ninja_build_cmd |
-          ninja -C build -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build ${{env.MBUILD_TARGET}}
           ninja -C build -t missingdeps
 
       # Decide if it's worth uploading a new version of the ccache cache. If
@@ -405,7 +406,7 @@ jobs:
           meson test ${{env.MTEST_ARGS}} --suite setup --logbase setup || exit 1
           echo ::endgroup::
 
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --no-suite setup ${{env.MTEST_TARGET}}
+          meson test ${{env.MTEST_ARGS}} --no-suite setup ${{env.MTEST_TARGET}}
 
       - &linux_collect_cores_step
         name: Core backtraces
@@ -511,7 +512,7 @@ jobs:
       - name: Build
         shell: *su_postgres_shell
         run: |
-          make -s -j${BUILD_JOBS} world-bin
+          make -s -j$(nproc) world-bin
 
       - *ccache_decide_save_step
       - *ccache_save_step
@@ -519,7 +520,7 @@ jobs:
       - name: Test world
         shell: *su_postgres_shell
         run: |
-          make -s ${CHECK} ${CHECKFLAGS} -j${TEST_JOBS}
+          make -s ${CHECK} ${CHECKFLAGS} -j$(nproc)
 
       - *linux_collect_cores_step
       - *upload_logs_step
@@ -611,7 +612,7 @@ jobs:
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -c -o '-c fsync=off' -D build/runningcheck -l build/testrun/runningcheck.log start
 
           # Run the tests supporting running against an already running
-          meson test ${{env.MTEST_ARGS}} --num-processes ${{env.TEST_JOBS}} --setup running
+          meson test ${{env.MTEST_ARGS}} --setup running
 
           build/tmp_install/usr/local/pgsql/bin/pg_ctl -D build/runningcheck stop
 
@@ -893,9 +894,19 @@ jobs:
 
       - name: Sysinfo
         run: |
+          echo Number of cores:
+          bash -c nproc
+
+          echo codepage:
           chcp
+
+          echo ::group::systeminfo
           systeminfo
+          echo ::endgroup::
+
+          echo ::group::env
           set
+          echo ::endgroup::
 
       # The TAP tests build an initdb template under build/tmp_install and
       # then `robocopy` it into per-test data directories. Robocopy with the
@@ -1198,7 +1209,7 @@ jobs:
           meson setup -Dwerror=true $CONF build-meson
           echo "::endgroup::"
 
-          ninja -C build-meson --quiet -j${{env.BUILD_JOBS}} ${{env.MBUILD_TARGET}}
+          ninja -C build-meson --quiet ${{env.MBUILD_TARGET}}
 
       # gcc, cassert on, dtrace off
       - name: gcc warnings + (cassert)
@@ -1266,8 +1277,8 @@ jobs:
             CC="ccache gcc" CXX="ccache g++" CLANG="ccache clang"
           echo "::endgroup::"
 
-          make -s -j${{env.BUILD_JOBS}} clean
-          make -s -j${{env.BUILD_JOBS}} -k ${{env.CHECKFLAGS}} \
+          make -s -j$(nproc) clean
+          make -s -j$(nproc) -k ${{env.CHECKFLAGS}} \
             headerscheck cpluspluscheck \
             EXTRAFLAGS='-fmax-errors=10'
 
-- 
2.54.0.450.g9ac3f193c0


--mr2uqtieh2e2xvha
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v13a-0008-ci-Make-runs-on-overridable.patch"



^ permalink  raw  reply  [nested|flat] 210+ messages in thread