[PATCH v4] shell: enable OOM protection by default
Andrea Cervesato <[email protected]>
| Newsgroups | gmane.linux.ltp |
|---|---|
| Message-ID | <[email protected]> |
From: Andrea Cervesato <andrea.cervesato-IBi9RG/[email protected]> The shell harness shields itself from the OOM killer and runs the test in a child process, so it survives memory pressure and can still report results (e.g. during memcg stress tests). Suggested-by: Li Wang <[email protected]> Signed-off-by: Andrea Cervesato <andrea.cervesato-IBi9RG/[email protected]> --- Under Li's idea, implement a OOM protection mechanism for the shell tests so we can avoid OOM for memcg stress tests. --- Changes in v4: - fix with Petr suggestions - fix with AI agent suggestions - Link to v3: https://lore.kernel.org/20260804-shell_oom_protection-v3-1-fe42b15d034c-IBi9RG/[email protected] Changes in v3: - simplify oom code - enable OOM protection by default - Link to v2: https://lore.kernel.org/20260730-shell_oom_protection-v2-0-be1de2baa83d-IBi9RG/[email protected] Changes in v2: - update shell OOM protection functional test - Link to v1: https://lore.kernel.org/20260713-shell_oom_protection-v1-0-b732e8647894-IBi9RG/[email protected] To: Linux Test Project <[email protected]> --- lib/newlib_tests/runtest.sh | 1 + lib/newlib_tests/shell/tst_oom_protection.sh | 34 +++++++++++ testcases/lib/tst_test.sh | 84 ++++++++++++++++++++++++++-- 3 files changed, 115 insertions(+), 4 deletions(-) diff --git a/lib/newlib_tests/runtest.sh b/lib/newlib_tests/runtest.sh index 71808ef8b..7e2d0a2ac 100755 --- a/lib/newlib_tests/runtest.sh +++ b/lib/newlib_tests/runtest.sh @@ -44,6 +44,7 @@ shell/tst_check_driver.sh shell/tst_check_kconfig0[1-5].sh shell/tst_mount_device.sh shell/tst_mount_device_tmpfs.sh +shell/tst_oom_protection.sh shell/tst_skip_filesystems.sh shell/net/*.sh}" diff --git a/lib/newlib_tests/shell/tst_oom_protection.sh b/lib/newlib_tests/shell/tst_oom_protection.sh new file mode 100755 index 000000000..564680700 --- /dev/null +++ b/lib/newlib_tests/shell/tst_oom_protection.sh @@ -0,0 +1,34 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0-or-later +# Copyright (c) 2026 Linux Test Project + +TST_TESTFUNC=do_test + +read_oom_score_adj() { + cat "/proc/$1/oom_score_adj" +} + +do_test() { + local harness_score body_score + + # $$ points to the protected harness, while /proc/self is the + # unprotected child that actually runs the test body. + harness_score=$(read_oom_score_adj "$$") + body_score=$(read_oom_score_adj self) + + if [ "$harness_score" != -1000 ]; then + tst_res TCONF "shell harness OOM protection unavailable" + return + fi + + tst_res TPASS "shell harness is protected from OOM by default" + + if [ "$body_score" = 0 ]; then + tst_res TPASS "test body runs in an unprotected child (oom_score_adj=0)" + else + tst_res TFAIL "test body oom_score_adj is $body_score, expected 0" + fi +} + +. tst_test.sh +tst_run diff --git a/testcases/lib/tst_test.sh b/testcases/lib/tst_test.sh index b3e7e29bb..e42e562f5 100644 --- a/testcases/lib/tst_test.sh +++ b/testcases/lib/tst_test.sh @@ -28,6 +28,48 @@ export TST_USR_GID="${LTP_USR_GID:-65534}" trap "tst_brk TBROK 'test interrupted'" INT trap "unset _tst_setup_timer_pid; tst_brk TBROK 'test terminated'" TERM +_tst_set_oom_score_adj() +{ + local value="$1" + local path="/proc/self/oom_score_adj" + + if [ ! -e "$path" ]; then + tst_res TINFO "oom_score_adj does not exist, skipping the adjustment" + return + fi + + if ! echo "$value" > "$path"; then + tst_res TWARN "Can't adjust score" + fi +} + +_tst_enable_oom_protection() +{ + _tst_set_oom_score_adj -1000 +} + +_tst_disable_oom_protection() +{ + _tst_set_oom_score_adj 0 +} + +_tst_write_results() +{ + [ "$TST_CHILD" = 1 ] || return 0 + [ -n "$TST_RESULTS_FILE" ] || return 0 + + echo "$TST_PASS $TST_FAIL $TST_BROK $TST_WARN $TST_CONF $TST_COUNT" \ + > "$TST_RESULTS_FILE" +} + +_tst_read_results() +{ + [ -s "$TST_RESULTS_FILE" ] || return 0 + + read TST_PASS TST_FAIL TST_BROK TST_WARN TST_CONF TST_COUNT \ + < "$TST_RESULTS_FILE" +} + _tst_do_cleanup() { if [ -n "$TST_DO_CLEANUP" -a -n "$TST_CLEANUP" -a -z "$LTP_NO_CLEANUP" ]; then @@ -48,6 +90,15 @@ _tst_do_exit() _tst_do_cleanup + # When running as the unprotected test child, only propagate the + # results back to the protected harness which does the teardown and + # prints the summary. + if [ "$TST_CHILD" = 1 ]; then + _tst_cleanup_timer + _tst_write_results + exit 0 + fi + cd "$LTPROOT" [ "$TST_MOUNT_FLAG" = 1 ] && tst_umount @@ -788,10 +839,34 @@ tst_run() TST_MNTPOINT="${TST_MNTPOINT:-$PWD/mntpoint}" - if [ "$TST_ALL_FILESYSTEMS" = 1 ]; then - _tst_run_tcases_per_fs - else - _tst_run_iterations + # Protect the harness so it survives memory pressure and can + # still report results, then run the test body in a child that + # resets OOM protection. This way workloads forked by the test + # remain killable, mirroring the C test harness. + _tst_enable_oom_protection + + TST_RESULTS_FILE=$(mktemp "${TMPDIR:-/tmp}/ltp_${TST_ID}_res.XXXXXX") + + ( + TST_CHILD=1 + _tst_disable_oom_protection + trap '_tst_cleanup_timer; _tst_write_results' EXIT + + if [ "$TST_ALL_FILESYSTEMS" = 1 ]; then + _tst_run_tcases_per_fs + else + _tst_run_iterations + fi + ) & + + wait $! + ret=$? + + _tst_read_results + rm -f "$TST_RESULTS_FILE" + + if [ $ret -gt 128 ]; then + tst_res TBROK "Test killed by signal $((ret - 128))!" fi _tst_do_exit @@ -865,6 +940,7 @@ _tst_run_test() $_tst_fnc "$@" _tst_rescmp "$_tst_res" TST_COUNT=$((TST_COUNT+1)) + _tst_write_results } export LC_ALL=C --- base-commit: ee945bb71ba7015dace7d983cf98a530b3eb53a4 change-id: 20260713-shell_oom_protection-6221ab825220 Best regards, -- Andrea Cervesato <andrea.cervesato-IBi9RG/[email protected]> -- Mailing list info: https://lists.linux.it/listinfo/ltp