From: Darrick J. Wong <darrick.wong@xxxxxxxxxx>
Create a systemd service unit so that we can run the online scrubber
under systemd with (somewhat) appropriate containment.
Signed-off-by: Darrick J. Wong <darrick.wong@xxxxxxxxxx>
---
.gitignore | 4 +++
configure.ac | 15 +++++++++++
include/builddefs.in | 3 ++
scrub/Makefile | 32 ++++++++++++++++++++++-
scrub/xfs_scrub.c | 25 ++++++++++++++++++
scrub/xfs_scrub@xxxxxxxxxxx | 18 +++++++++++++
scrub/xfs_scrub_all.cron.in | 2 +
scrub/xfs_scrub_all.in | 53 ++++++++++++++++++++++++++++++++++++++
scrub/xfs_scrub_all.service.in | 8 ++++++
scrub/xfs_scrub_all.timer | 11 ++++++++
scrub/xfs_scrub_fail | 26 +++++++++++++++++++
scrub/xfs_scrub_fail@xxxxxxxxxxx | 10 +++++++
12 files changed, 206 insertions(+), 1 deletion(-)
create mode 100644 scrub/xfs_scrub@xxxxxxxxxxx
create mode 100644 scrub/xfs_scrub_all.cron.in
create mode 100644 scrub/xfs_scrub_all.service.in
create mode 100644 scrub/xfs_scrub_all.timer
create mode 100755 scrub/xfs_scrub_fail
create mode 100644 scrub/xfs_scrub_fail@xxxxxxxxxxx
diff --git a/.gitignore b/.gitignore
index a3db640..d887451 100644
--- a/.gitignore
+++ b/.gitignore
@@ -69,6 +69,10 @@ cscope.*
/rtcp/xfs_rtcp
/spaceman/xfs_spaceman
/scrub/xfs_scrub
+/scrub/xfs_scrub@.service
+/scrub/xfs_scrub_all
+/scrub/xfs_scrub_all.service
+/scrub/xfs_scrub_fail@.service
# generated crc files
/libxfs/crc32selftest
diff --git a/configure.ac b/configure.ac
index bb032e5..f7840db 100644
--- a/configure.ac
+++ b/configure.ac
@@ -121,6 +121,21 @@ esac
AC_SUBST([root_sbindir])
AC_SUBST([root_libdir])
+# Where do systemd services go?
+pkg_systemdsystemunitdir="$(pkg-config --variable=systemdsystemunitdir systemd 2>/dev/null)"
+case "${pkg_systemdsystemunitdir}" in
+"")
+ systemdsystemunitdir=""
+ have_systemd=no
+ ;;
+*)
+ systemdsystemunitdir="${pkg_systemdsystemunitdir}"
+ have_systemd=yes
+ ;;
+esac
+AC_SUBST([have_systemd])
+AC_SUBST([systemdsystemunitdir])
+
# Find localized files. Don't descend into any "dot directories"
# (like .git or .pc from quilt). Strangely, the "-print" argument
# to "find" is required, to avoid including such directories in the
diff --git a/include/builddefs.in b/include/builddefs.in
index d44faf9..4b4bf41 100644
--- a/include/builddefs.in
+++ b/include/builddefs.in
@@ -128,6 +128,9 @@ HAVE_FSTATAT = @have_fstatat@
HAVE_SG_IO = @have_sg_io@
HAVE_HDIO_GETGEO = @have_hdio_getgeo@
+HAVE_SYSTEMD = @have_systemd@
+SYSTEMDSYSTEMUNITDIR = @systemdsystemunitdir@
+
GCCFLAGS = -funsigned-char -fno-strict-aliasing -Wall
# -Wbitwise -Wno-transparent-union -Wno-old-initializer -Wno-decl
diff --git a/scrub/Makefile b/scrub/Makefile
index ca6dab0..597b2eb 100644
--- a/scrub/Makefile
+++ b/scrub/Makefile
@@ -15,6 +15,16 @@ LTCOMMAND = xfs_scrub
INSTALL_SCRUB = install-scrub
XFS_SCRUB_ALL_PROG = xfs_scrub_all
XFS_SCRUB_ARGS = -b -n
+ifeq ($(HAVE_SYSTEMD),yes)
+INSTALL_SCRUB += install-systemd
+SYSTEMDSERVICES = xfs_scrub@.service xfs_scrub_all.service xfs_scrub_all.timer xfs_scrub_fail@.service
+endif
+CRONSERVICES = xfs_scrub_all.cron
+CROND_DIR = /etc/cron.d
+
+# Disable all the crontabs for now
+CROND_DIR = $(PKG_LIB_DIR)/$(PKG_NAME)
+
endif # scrub_prereqs
HFILES = \
@@ -84,7 +94,8 @@ ifeq ($(HAVE_HDIO_GETGEO),yes)
LCFLAGS += -DHAVE_HDIO_GETGEO
endif
-default: depend $(LTCOMMAND) $(XFS_SCRUB_ALL_PROG)
+default: depend $(LTCOMMAND) $(XFS_SCRUB_ALL_PROG) $(SYSTEMDSERVICES) \
+ $(CRONSERVICES)
xfs_scrub_all: xfs_scrub_all.in
@echo " [SED] $@"
@@ -98,10 +109,29 @@ include $(BUILDRULES)
install: $(INSTALL_SCRUB)
+%.service: %.service.in
+ @echo " [SED] $@"
+ $(Q)$(SED) -e "s|@sbindir@|$(PKG_ROOT_SBIN_DIR)|g" \
+ -e "s|@scrub_args@|$(XFS_SCRUB_ARGS)|g" \
+ -e "s|@pkg_lib_dir@|$(PKG_LIB_DIR)|g" \
+ -e "s|@pkg_name@|$(PKG_NAME)|g" < $< > $@
+
+%.cron: %.cron.in
+ @echo " [SED] $@"
+ $(Q)$(SED) -e "s|@sbindir@|$(PKG_ROOT_SBIN_DIR)|g" < $< > $@
+
+install-systemd: default
+ $(INSTALL) -m 755 -d $(SYSTEMDSYSTEMUNITDIR)
+ $(INSTALL) -m 644 $(SYSTEMDSERVICES) $(SYSTEMDSYSTEMUNITDIR)
+ $(INSTALL) -m 755 -d $(PKG_LIB_DIR)/$(PKG_NAME)
+ $(INSTALL) -m 755 xfs_scrub_fail $(PKG_LIB_DIR)/$(PKG_NAME)
+
install-scrub: default
$(INSTALL) -m 755 -d $(PKG_ROOT_SBIN_DIR)
$(LTINSTALL) -m 755 $(LTCOMMAND) $(PKG_ROOT_SBIN_DIR)
$(INSTALL) -m 755 $(XFS_SCRUB_ALL_PROG) $(PKG_ROOT_SBIN_DIR)
+ $(INSTALL) -m 755 -d $(CROND_DIR)
+ $(INSTALL) -m 644 $(CRONSERVICES) $(CROND_DIR)
install-dev:
diff --git a/scrub/xfs_scrub.c b/scrub/xfs_scrub.c
index baf8760..a8d0927 100644
--- a/scrub/xfs_scrub.c
+++ b/scrub/xfs_scrub.c
@@ -154,6 +154,12 @@ bool want_fstrim = true;
bool stderr_isatty;
bool stdout_isatty;
+/*
+ * If we are running as a service, we need to be careful about what
+ * error codes we return to the calling process.
+ */
+static bool is_service;
+
static void __attribute__((noreturn))
usage(void)
{
@@ -617,6 +623,9 @@ _("Only one of the options -n or -y may be specified.\n"));
if (stdout_isatty && !progress_fp)
progress_fp = fdopen(1, "w+");
+ if (getenv("SERVICE_MODE"))
+ is_service = true;
+
/* Find the mount record for the passed-in argument. */
if (stat(argv[optind], &ctx.mnt_sb) < 0) {
fprintf(stderr,
@@ -717,5 +726,21 @@ _("%s: %llu warnings found.\n"),
free(ctx.blkdev);
free(ctx.mntpoint);
+ /*
+ * If we're running as a service, bump return code up by 150 to
+ * avoid conflicting with (sysvinit) service return codes.
+ */
+ if (is_service) {
+ /*
+ * journald queries /proc as part of taking in log
+ * messages; it uses this information to associate the
+ * message with systemd units, etc. This races with
+ * process exit, so delay that a couple of seconds so
+ * that we capture the summary outputs in the job log.
+ */
+ sleep(2);
+ if (ret)
+ ret += 150;
+ }
return ret;
}
diff --git a/scrub/xfs_scrub@xxxxxxxxxxx b/scrub/xfs_scrub@xxxxxxxxxxx
new file mode 100644
index 0000000..6b6992d
--- /dev/null
+++ b/scrub/xfs_scrub@xxxxxxxxxxx
@@ -0,0 +1,18 @@
+[Unit]
+Description=Online XFS Metadata Check for %I
+OnFailure=xfs_scrub_fail@%i.service
+
+[Service]
+Type=oneshot
+WorkingDirectory=%I
+PrivateNetwork=true
+ProtectSystem=full
+ProtectHome=read-only
+PrivateTmp=yes
+AmbientCapabilities=CAP_SYS_ADMIN CAP_FOWNER CAP_DAC_OVERRIDE CAP_DAC_READ_SEARCH CAP_SYS_RAWIO
+NoNewPrivileges=yes
+User=nobody
+IOSchedulingClass=idle
+CPUSchedulingPolicy=idle
+Environment=SERVICE_MODE=1
+ExecStart=@sbindir@/xfs_scrub @scrub_args@ %I
diff --git a/scrub/xfs_scrub_all.cron.in b/scrub/xfs_scrub_all.cron.in
new file mode 100644
index 0000000..ec82236
--- /dev/null
+++ b/scrub/xfs_scrub_all.cron.in
@@ -0,0 +1,2 @@
+SERVICE_MODE=1
+10 3 * * 0 root test -e /run/systemd/system || @sbindir@/xfs_scrub_all
diff --git a/scrub/xfs_scrub_all.in b/scrub/xfs_scrub_all.in
index 7738644..27cdc32 100644
--- a/scrub/xfs_scrub_all.in
+++ b/scrub/xfs_scrub_all.in
@@ -25,10 +25,19 @@ import json
import threading
import time
import sys
+import os
retcode = 0
terminate = False
+def DEVNULL():
+ '''Return /dev/null in subprocess writable format.'''
+ try:
+ from subprocess import DEVNULL
+ return DEVNULL
+ except ImportError:
+ return open(os.devnull, 'wb')
+
def find_mounts():
'''Map mountpoints to physical disks.'''
@@ -55,6 +64,13 @@ def find_mounts():
fs[mnt] = set([lastdisk])
return fs
+def kill_systemd(unit, proc):
+ '''Kill systemd unit.'''
+ proc.terminate()
+ cmd=['systemctl', 'stop', unit]
+ x = subprocess.Popen(cmd)
+ x.wait()
+
def run_killable(cmd, stdout, killfuncs, kill_fn):
'''Run a killable program. Returns program retcode or -1 if we can't start it.'''
try:
@@ -81,6 +97,19 @@ def run_scrub(mnt, cond, running_devs, mntdevs, killfuncs):
if terminate:
return
+ # Try it the systemd way
+ cmd=['systemctl', 'start', 'xfs_scrub@%s' % mnt]
+ ret = run_killable(cmd, DEVNULL(), killfuncs, \
+ lambda proc: kill_systemd('xfs_scrub@%s' % mnt, proc))
+ if ret == 0 or ret == 1:
+ print("Scrubbing %s done, (err=%d)" % (mnt, ret))
+ sys.stdout.flush()
+ retcode |= ret
+ return
+
+ if terminate:
+ return
+
# Invoke xfs_scrub manually
cmd=['@sbindir@/xfs_scrub', '@scrub_args@', mnt]
ret = run_killable(cmd, None, killfuncs, \
@@ -112,6 +141,17 @@ def main():
fs = find_mounts()
+ # Tail the journal if we ourselves aren't a service...
+ journalthread = None
+ if 'SERVICE_MODE' not in os.environ:
+ try:
+ cmd=['journalctl', '--no-pager', '-q', '-S', 'now', \
+ '-f', '-u', 'xfs_scrub@*', '-o', \
+ 'cat']
+ journalthread = subprocess.Popen(cmd)
+ except:
+ pass
+
# Schedule scrub jobs...
running_devs = set()
killfuncs = set()
@@ -148,6 +188,19 @@ def main():
fs = []
cond.release()
+ if journalthread is not None:
+ journalthread.terminate()
+
+ # journald queries /proc as part of taking in log
+ # messages; it uses this information to associate the
+ # message with systemd units, etc. This races with
+ # process exit, so delay that a couple of seconds so
+ # that we capture the summary outputs in the job log.
+ if 'SERVICE_MODE' in os.environ:
+ time.sleep(2)
+ if retcode:
+ retcode += 150
+
sys.exit(retcode)
if __name__ == '__main__':
diff --git a/scrub/xfs_scrub_all.service.in b/scrub/xfs_scrub_all.service.in
new file mode 100644
index 0000000..683804e
--- /dev/null
+++ b/scrub/xfs_scrub_all.service.in
@@ -0,0 +1,8 @@
+[Unit]
+Description=Online XFS Metadata Check for All Filesystems
+ConditionACPower=true
+
+[Service]
+Type=oneshot
+Environment=SERVICE_MODE=1
+ExecStart=@sbindir@/xfs_scrub_all
diff --git a/scrub/xfs_scrub_all.timer b/scrub/xfs_scrub_all.timer
new file mode 100644
index 0000000..2e4a33b
--- /dev/null
+++ b/scrub/xfs_scrub_all.timer
@@ -0,0 +1,11 @@
+[Unit]
+Description=Periodic XFS Online Metadata Check for All Filesystems
+
+[Timer]
+# Run on Sunday at 3:10am, to avoid running afoul of DST changes
+OnCalendar=Sun *-*-* 03:10:00
+RandomizedDelaySec=60
+Persistent=true
+
+[Install]
+WantedBy=timers.target
diff --git a/scrub/xfs_scrub_fail b/scrub/xfs_scrub_fail
new file mode 100755
index 0000000..36dd50e
--- /dev/null
+++ b/scrub/xfs_scrub_fail
@@ -0,0 +1,26 @@
+#!/bin/bash
+
+# Email logs of failed xfs_scrub unit runs
+
+mailer=/usr/sbin/sendmail
+recipient="$1"
+test -z "${recipient}" && exit 0
+mntpoint="$2"
+test -z "${mntpoint}" && exit 0
+hostname="$(hostname -f 2>/dev/null)"
+test -z "${hostname}" && hostname="${HOSTNAME}"
+if [ ! -x "${mailer}" ]; then
+ echo "${mailer}: Mailer program not found."
+ exit 1
+fi
+
+(cat << ENDL
+To: $1
+From: <xfs_scrub@${hostname}>
+Subject: xfs_scrub failure on ${mntpoint}
+
+So sorry, the automatic xfs_scrub of ${mntpoint} on ${hostname} failed.
+
+A log of what happened follows:
+ENDL
+systemctl status --full --lines 4294967295 "xfs_scrub@${mntpoint}") | "${mailer}" -t -i
diff --git a/scrub/xfs_scrub_fail@xxxxxxxxxxx b/scrub/xfs_scrub_fail@xxxxxxxxxxx
new file mode 100644
index 0000000..785f881
--- /dev/null
+++ b/scrub/xfs_scrub_fail@xxxxxxxxxxx
@@ -0,0 +1,10 @@
+[Unit]
+Description=Online XFS Metadata Check Failure Reporting for %I
+
+[Service]
+Type=oneshot
+Environment=EMAIL_ADDR=root
+ExecStart=@pkg_lib_dir@/@pkg_name@/xfs_scrub_fail "${EMAIL_ADDR}" %I
+User=mail
+Group=mail
+SupplementaryGroups=systemd-journal
--
To unsubscribe from this list: send the line "unsubscribe linux-xfs" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
