commit 7828169ef0ad9f2620ae2bfb9aeeb2d8535a6d9e tree f7815ecad59d4724887d6072c061ab24937dc8d2 parent 2130323875a8b0382ae6c67c8d8dcbad25c3fcca author Adhemerval Zanella 2026-09-10 11:19:38 -0300 committer Adhemerval Zanella 2026-09-10 11:19:38 -0300 round-robin.sh (probe_glibc_test_env): Record container capabilities The container the glibc testsuite runs in differs between the postcommit and precommit node pools, and nothing says so. On tcwg-g3-01 (tcwg-postcommit) every test that calls support_become_root() fails with error: xwrite.c:32: write of N bytes failed after 0: Operation not permitted -- the write to /proc/self/uid_map -- and every test-container test fails with "could not create a private mount namespace". On tcwg-g3-08 (tcwg-precommit) they pass. Both jobs pass the same --cap-add=SYS_ADMIN and --security-opt apparmor=unconfined, so the difference is in the host, not in ci-job-configs. That accounts for 100 of the 105 failures in the aarch64 baseline of tcwg_glibc_check and 115 on arm: all of resolv/, most of nss/, and every test-container test. They land in the baseline xfail list, where they hide any real regression in those tests. Probe for both capabilities before the glibc check and record the result in artifacts, so the next person to look at a 100-failure baseline can see why in one file. This only reports; it does not change the build result. :100644 100644 8fd33d87fab51fd22b73124a4f2e283b9c7f172b ef9ea4786eb4427bdb61feca520b07fd0b5c11de M round-robin.sh commit 2130323875a8b0382ae6c67c8d8dcbad25c3fcca tree 91c47dc75cf62609c2686418979a13f7f0840150 parent 56c86ab1c5179adf897872e3187ea72ca904fafd author Adhemerval Zanella 2026-09-10 11:19:38 -0300 committer Adhemerval Zanella 2026-09-10 11:19:38 -0300 round-robin.sh (check_regression): Don't call an XPASS a precommit regression An XPASS means the baseline and this build disagree about whether a test is expected to fail -- or whether it is built at all. When we track a branch that is worth reporting: the xfail entry has gone stale. In precommit the baseline comes from a different build, and since the postcommit and precommit pools were split it also comes from a different machine, so an XPASS describes the two environments rather than the patch under test. Builds 10630 and 10631 of tcwg_glibc_check--master-aarch64-precommit blamed a RISC-V patch for "XPASS: elf/tst-protected1a" and "XPASS: elf/tst-protected1b" on aarch64. Those tests do not appear in the baseline results at all, and their flaky entry had expired the day before. Pass --ignore_xpass to validate_failures.py in precommit mode. round-robin-notify.sh evaluates the same condition when it generates regressions.sum, so the report and this verdict cannot disagree; the two must be deployed together. Bisects are excluded: they have a meaningful baseline and want to see every difference. Requires the matching gcc-compare-results change adding --ignore_xpass. :100644 100644 fbf46c77ebb7b03e9929ae69ced61e7ab61f9583 8fd33d87fab51fd22b73124a4f2e283b9c7f172b M round-robin.sh commit 56c86ab1c5179adf897872e3187ea72ca904fafd tree f6299675e281a306bdb1bac1fd9f32cda8a9a558 parent c8070b9ee8e4298de94cebf724db927465a20a62 author Adhemerval Zanella 2026-09-09 13:52:07 -0300 committer Adhemerval Zanella 2026-09-09 13:52:07 -0300 round-robin.sh (build_abe): Scale glibc test timeouts glibc's test driver kills a test after TIMEOUT seconds, 20 by default (DEFAULT_TIMEOUT in support/test-driver.h), scaled by $TIMEOUTFACTOR. We run "make check" with -j $cpus, so on a 64-core machine the testsuite saturates every CPU and tests whose runtime depends on scheduling latency time out. posix/tst-affinity, tst-affinity-pid and tst-affinity-static are the usual victims: they pin the process to each CPU in turn and wait to be migrated, ~450 times over the various CPU set sizes. They were reported as regressions in 3 of the 9 failing tcwg_glibc_check--master-aarch64-precommit builds between 10563 and 10632, every time to a contributor whose patch had nothing to do with affinity. ABE already raises $TIMEOUTFACTOR by one on each re-run, so the base it scales is what we can usefully set from here. Its ramp alone does not help: a test needing more than twice the default fails on try #0 and try #1 alike, is classified as a stable fail rather than a flaky one, and is never re-run again. In build 10574 the affinity tests timed out at both 20s and 40s and were reported as regressions. Set TIMEOUTFACTOR_BASE=10 for the glibc check, giving 200s on the first try. It costs nothing for tests that pass; a test that really hangs now takes 200s rather than 20s to be killed. Requires the matching abe change adding $TIMEOUTFACTOR_BASE. :100644 100644 7bcab54a42d55dc8e484c888148546794faabc27 fbf46c77ebb7b03e9929ae69ced61e7ab61f9583 M round-robin.sh commit c8070b9ee8e4298de94cebf724db927465a20a62 tree 0901248ad2a09963a854e4755ab8f7d062adf41c parent 617c1dc37fccf87c8013cbd0869999c85b249a08 author Maxim Kuvyrkov 2026-08-05 04:08:58 +0000 committer Maxim Kuvyrkov 2026-08-05 04:08:58 +0000 .gitlab-ci.yml: Add sprinto slscan :100644 100644 1694d8355769364bc8afc85f8ce7edec44316351 d00683dd60f48acc1006aa24c46c38e5796bde57 M .gitlab-ci.yml commit 617c1dc37fccf87c8013cbd0869999c85b249a08 tree cc7bd509586ef126a0112ad3ab3e870b43c3b27a parent 5803cc15b27e924d2b322eb2ee1fca8583b0cc82 author Leandro Lupori 2026-07-07 16:54:08 -0300 committer Leandro Lupori 2026-07-13 21:41:45 +0000 Remove flang-aarch64-debug-reverse-iteration bot It tests a very specific case and the worker is not being able to keep up with the build requests. This should also free some precious memory and disk space on tcwg-amp-01. :100755 100755 b874e796b4c65b6ed5e2a0cab28813baa7d59e3b 275e63e5d51773cfa1b0a1f38091b68246b1b82b M tcwg-update-llvmbot-containers.sh commit 5803cc15b27e924d2b322eb2ee1fca8583b0cc82 tree cb5df6b822339ecbca0663366f91aa3b542fba1f parent 798fac7ba31cf07f6fded2476791665b542d7b58 author Laurent Alfonsi 2026-07-07 09:09:27 +0200 committer Laurent Alfonsi 2026-07-08 13:55:16 +0200 round-robin.sh: Detects "No space left on device", and report as external_failure Change-Id: I05265ea44e7a2f94389f748df54555919299f23d :100644 100644 7ee5310ab75f8b1bd1f3ceb7cf5e423bcf6ef629 7bcab54a42d55dc8e484c888148546794faabc27 M round-robin.sh commit 798fac7ba31cf07f6fded2476791665b542d7b58 tree e7d93d061c10fc14424f77419a2948f8b9d14674 parent f14f9aaa657608340acec732b16326ba806f742b author Laurent Alfonsi 2026-05-27 14:28:05 +0200 committer Laurent Alfonsi 2026-05-27 14:28:25 +0200 cimonitor-configs: Add precommit report and includes sme info : exec time and wait time Change-Id: I8d36256f5cdeb35884794e5d4cdd4e5910437a5e :100644 100644 349ff6683d9dfb981a2293fe9cc1fe8e6865f19e 6d4744894ff65f4c89487113ed4bbefbece24ee2 M cimonitor-configs/CI-TCWG-PRECOMMIT.yaml :100644 100644 8809bfeace55f578d86393267f1871c4a1733c50 c7b2239f0d83c109ddbc6e151cb62931400dcbc1 M cimonitor-configs/CI-TCWG.yaml :100755 100755 00181502b495a478b495872d5c3a81ba213e3f11 2cc143ec2dee10f58a37849d71c80158b0f43bdb M generate-cimonitor-dashboard.py commit f14f9aaa657608340acec732b16326ba806f742b tree b3c0642d127fa205eaa4c6784a2df010ef7f0c72 parent 2e7914f264fd86c3e5d9d0d32bbe9f56ff8cffd1 author Laurent Alfonsi 2026-05-19 09:04:31 +0200 committer Laurent Alfonsi 2026-05-19 09:05:43 +0200 tcwg-report-stale-rr-jobs.sh: remove tcwg_kernel projects as non in production anymore Change-Id: I38c39ee287fe3f6b87715c41916a48c5fb49447d :100755 100755 e56dee4cb761e7e6556f7d1d4a4cb3fc1bd329cf 00f603b1b3b33870a5e55b97ed32f62357b966ec M tcwg-report-stale-rr-jobs.sh commit 2e7914f264fd86c3e5d9d0d32bbe9f56ff8cffd1 tree 8a6ab72be0665eb45476e2de189e220cc7cbd195 parent c96f98f850dcf874dd66886ffd41ec8a8f60e4d3 author Laurent Alfonsi 2026-05-19 06:08:20 +0200 committer Laurent Alfonsi 2026-05-19 06:11:33 +0200 tcwg-report-stale-rr-jobs.sh: Fix job use bkp-02, and rewrite to avoid conflict between the 2 ssh connections Change-Id: I968b4645ae0bb6112de4b385d21fbd47c7f19b4e :100755 100755 924a6cc8a4ea5a424335657e3f1ad5b0020a28fe e56dee4cb761e7e6556f7d1d4a4cb3fc1bd329cf M tcwg-report-stale-rr-jobs.sh