Merge pull request #17417 from anitazha/more_systoomd

More systemd-oomd tweaks

src/oom/oomd.c

@@ -117,6 +117,8 @@ static int parse_argv(int argc, char *argv[]) {
 static int run(int argc, char *argv[]) {
         _cleanup_(notify_on_cleanup) const char *notify_msg = NULL;
         _cleanup_(manager_freep) Manager *m = NULL;
+        _cleanup_free_ char *swap = NULL;
+        unsigned long long s = 0;
         int r;
 
         log_setup_service();
@@ -131,8 +133,17 @@ static int run(int argc, char *argv[]) {
 
         /* Do some basic requirement checks for running systemd-oomd. It's not exhaustive as some of the other
          * requirements do not have a reliable means to check for in code. */
-        if (access("/proc/swaps", F_OK) < 0)
-                return log_error_errno(errno, "Swap not enabled: %m");
+
+        /* SwapTotal is always available in /proc/meminfo and defaults to 0, even on swap-disabled kernels. */
+        r = get_proc_field("/proc/meminfo", "SwapTotal", WHITESPACE, &swap);
+        if (r < 0)
+                return log_error_errno(r, "Failed to get SwapTotal from /proc/meminfo: %m");
+
+        r = safe_atollu(swap, &s);
+        if (r < 0)
+                return log_error_errno(r, "Failed to parse SwapTotal from /proc/meminfo: %s: %m", swap);
+        if (s == 0)
+                return log_error_errno(SYNTHETIC_ERRNO(EOPNOTSUPP), "Requires swap to operate");
 
         if (!is_pressure_supported())
                 return log_error_errno(SYNTHETIC_ERRNO(EOPNOTSUPP), "Pressure Stall Information (PSI) is not supported");

src/oom/test-oomd-util.c

@@ -57,7 +57,7 @@ static void test_oomd_cgroup_kill(void) {
 
         /* If we don't have permissions to set xattrs we're likely in a userns or missing capabilities */
         r = cg_set_xattr(SYSTEMD_CGROUP_CONTROLLER, cgroup, "user.oomd_test", "test", 4, 0);
-        if (IN_SET(r, -EPERM, -ENOTSUP))
+        if (ERRNO_IS_PRIVILEGE(r) || ERRNO_IS_NOT_SUPPORTED(r))
                 return (void) log_tests_skipped("Cannot set user xattrs");
 
         /* Do this twice to also check the increment behavior on the xattrs */

test/TEST-56-OOMD/Makefile

@@ -0,0 +1 @@
+../TEST-01-BASIC/Makefile

test/TEST-56-OOMD/test.sh

@@ -0,0 +1,48 @@
+#!/usr/bin/env bash
+set -e
+TEST_DESCRIPTION="systemd-oomd Memory Pressure Test"
+
+. $TEST_BASE_DIR/test-functions
+
+check_result_nspawn() {
+    local ret=1
+    local journald_report=""
+    local pids=""
+    [[ -e $1/testok ]] && ret=0
+    if [[ -e $1/skipped ]]; then
+        echo "TEST-56-OOMD was skipped:"
+        cat $1/skipped
+        ret=0
+    fi
+    [[ -f $1/failed ]] && cp -a $1/failed $TESTDIR
+    save_journal $1/var/log/journal
+    [[ -f $TESTDIR/failed ]] && cat $TESTDIR/failed
+    echo $JOURNAL_LIST
+    test -s $TESTDIR/failed && ret=$(($ret+1))
+    [ -n "$TIMED_OUT" ] && ret=$(($ret+1))
+    check_asan_reports "$1" || ret=$(($ret+1))
+    _umount_dir $initdir
+    return $ret
+}
+
+check_result_qemu() {
+    local ret=1
+    mount_initdir
+    [[ -e $initdir/testok ]] && ret=0
+    if [[ -e $initdir/skipped ]]; then
+        echo "TEST-56-OOMD was skipped:"
+        cat $initdir/skipped
+        ret=0
+    fi
+    [[ -f $initdir/failed ]] && cp -a $initdir/failed $TESTDIR
+    save_journal $initdir/var/log/journal
+    check_asan_reports "$initdir" || ret=$(($ret+1))
+    _umount_dir $initdir
+    [[ -f $TESTDIR/failed ]] && cat $TESTDIR/failed
+    echo $JOURNAL_LIST
+    test -s $TESTDIR/failed && ret=$(($ret+1))
+    [ -n "$TIMED_OUT" ] && ret=$(($ret+1))
+    return $ret
+}
+
+do_test "$@" 56

test/test-functions

@@ -65,6 +65,7 @@ BASICTOOLS=(
     echo
     env
     false
+    getconf
     getent
     getfacl
     grep

test/units/testsuite-56-slowgrowth.sh

@@ -0,0 +1,34 @@
+#!/usr/bin/env bash
+set -eu -o pipefail
+
+PAGE_SIZE=$(getconf PAGE_SIZE)
+BLOAT_ITERATION_TARGET=$(( 100 << 20 )) # 100 MB
+BLOAT_HOLDER=()
+PID="$$"
+
+function bloat {
+        local set_size=$(cat "/proc/$PID/statm" | cut -d " " -f2)
+        local mem_usage=$(( "$set_size" * "$PAGE_SIZE" ))
+        local target_mem_size=$(( "$mem_usage" + "$1" ))
+
+        BLOAT_HOLDER=()
+        while [[ "$mem_usage" -lt "$target_mem_size" ]]; do
+                echo "target $target_mem_size"
+                echo "mem usage $mem_usage"
+                BLOAT_HOLDER+=( $(printf "%0.sg" {1..1000000}) )
+                set_size=$(cat "/proc/$PID/statm" | cut -d " " -f2)
+                mem_usage=$(( "$set_size" * "$PAGE_SIZE" ))
+        done
+}
+
+function run {
+        local arr=()
+
+        while [[ true ]]; do
+                bloat "$BLOAT_ITERATION_TARGET"
+                arr+=( "$BLOAT_HOLDER" )
+                sleep 1
+        done
+}
+
+run

test/units/testsuite-56.service

@@ -0,0 +1,7 @@
+[Unit]
+Description=TESTSUITE-56-OOMD
+
+[Service]
+ExecStartPre=rm -f /failed /skipped /testok
+ExecStart=/usr/lib/systemd/tests/testdata/units/%N.sh
+Type=oneshot

test/units/testsuite-56.sh

@@ -0,0 +1,70 @@
+#!/usr/bin/env bash
+set -ex
+set -o pipefail
+
+systemd-analyze log-level debug
+systemd-analyze log-target console
+
+# Loose checks to ensure the environment has the necessary features for systemd-oomd
+[[ "$( awk '/SwapTotal/ { print $2 }' /proc/meminfo )" != "0" ]] || echo "no swap" >> /skipped
+[[ -e /proc/pressure ]] || echo "no PSI" >> /skipped
+cgroup_type=$(stat -fc %T /sys/fs/cgroup/)
+if [[ "$cgroup_type" != *"cgroup2"* ]] && [[ "$cgroup_type" != *"0x63677270"* ]]; then
+    echo "no cgroup2" >> /skipped
+fi
+[[ -e /skipped ]] && exit 0 || true
+
+cat > /etc/systemd/system/testworkload.slice <<EOF
+[Slice]
+CPUAccounting=true
+MemoryAccounting=true
+IOAccounting=true
+TasksAccounting=true
+ManagedOOMMemoryPressure=kill
+ManagedOOMMemoryPressureLimitPercent=50%
+EOF
+
+# Create a lot of memory pressure by setting memory.high to a very small value
+cat > /etc/systemd/system/testbloat.service <<EOF
+[Service]
+MemoryHigh=2M
+Slice=testworkload.slice
+ExecStart=/usr/lib/systemd/tests/testdata/units/testsuite-56-slowgrowth.sh
+EOF
+
+# This generates no memory pressure
+cat > /etc/systemd/system/testchill.service <<EOF
+[Service]
+MemoryHigh=2M
+Slice=testworkload.slice
+ExecStart=sleep infinity
+EOF
+
+systemctl daemon-reload
+
+systemctl start testbloat.service
+systemctl start testchill.service
+
+# Verify systemd-oomd is monitoring the expected units
+oomctl | grep "/testworkload.slice"
+oomctl | grep "50%"
+
+# systemd-oomd watches for elevated pressure for 30 seconds before acting.
+# It can take time to build up pressure so either wait 5 minutes or for the service to fail.
+timeout=$(date -ud "5 minutes" +%s)
+while [[ $(date -u +%s) -le $timeout ]]; do
+    if ! systemctl status testbloat.service; then
+        break
+    fi
+    sleep 15
+done
+
+# testbloat should be killed and testchill should be fine
+if systemctl status testbloat.service; then exit 42; fi
+if ! systemctl status testchill.service; then exit 24; fi
+
+systemd-analyze log-level info
+
+echo OK > /testok
+
+exit 0