From: Darrick J. Wong <djwong@xxxxxxxxxx>
Currently, the xfs_scrub background service is configured to use -b,
which means that the program runs completely serially. However, even
using 100% of one CPU with idle priority may be enough to cause thermal
throttling and unwanted fan noise on smaller systems (e.g. laptops) with
fast IO systems.
Let's try to avoid this (at least on systemd) by using cgroups to limit
the program's usage to 60% of one CPU and lowering the nice priority in
the scheduler. What we /really/ want is to run steadily on an
efficiency core, but there doesn't seem to be a means to ask the
scheduler not to ramp up the CPU frequency for a particular task.
While we're at it, group the resource limit directives together.
Signed-off-by: Darrick J. Wong <djwong@xxxxxxxxxx>
Reviewed-by: Christoph Hellwig <hch@xxxxxx>
---
scrub/Makefile | 7 ++++++-
scrub/system-xfs_scrub.slice | 30 ++++++++++++++++++++++++++++++
scrub/xfs_scrub@xxxxxxxxxxx | 12 ++++++++++--
scrub/xfs_scrub_all.service.in | 4 ++++
scrub/xfs_scrub_fail@xxxxxxxxxxx | 4 ++++
5 files changed, 54 insertions(+), 3 deletions(-)
create mode 100644 scrub/system-xfs_scrub.slice
diff --git a/scrub/Makefile b/scrub/Makefile
index 472df48a720..42b27bfcad7 100644
--- a/scrub/Makefile
+++ b/scrub/Makefile
@@ -18,7 +18,12 @@ XFS_SCRUB_FAIL_PROG = xfs_scrub_fail
XFS_SCRUB_ARGS = -b -n
ifeq ($(HAVE_SYSTEMD),yes)
INSTALL_SCRUB += install-systemd
-SYSTEMD_SERVICES = $(scrub_svcname) xfs_scrub_all.service xfs_scrub_all.timer xfs_scrub_fail@.service
+SYSTEMD_SERVICES=\
+ $(scrub_svcname) \
+ xfs_scrub_fail@.service \
+ xfs_scrub_all.service \
+ xfs_scrub_all.timer \
+ system-xfs_scrub.slice
OPTIONAL_TARGETS += $(SYSTEMD_SERVICES)
endif
ifeq ($(HAVE_CROND),yes)
diff --git a/scrub/system-xfs_scrub.slice b/scrub/system-xfs_scrub.slice
new file mode 100644
index 00000000000..95cd4f74526
--- /dev/null
+++ b/scrub/system-xfs_scrub.slice
@@ -0,0 +1,30 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2022-2024 Oracle. All Rights Reserved.
+# Author: Darrick J. Wong <djwong@xxxxxxxxxx>
+
+[Unit]
+Description=xfs_scrub background service slice
+Before=slices.target
+
+[Slice]
+
+# If the CPU usage cgroup controller is available, don't use more than 60% of a
+# single core for all background processes.
+CPUQuota=60%
+CPUAccounting=true
+
+[Install]
+# As of systemd 249, the systemd cgroupv2 configuration code will drop resource
+# controllers from the root and system.slice cgroups at startup if it doesn't
+# find any direct dependencies that require a given controller. Newly
+# activated units with resource control directives are created under the system
+# slice but do not cause a reconfiguration of the slice's resource controllers.
+# Hence we cannot put CPUQuota= into the xfs_scrub service units directly.
+#
+# For the CPUQuota directive to have any effect, we must therefore create an
+# explicit definition file for the slice that systemd creates to contain the
+# xfs_scrub instance units (e.g. xfs_scrub@.service) and we must configure this
+# slice as a dependency of the system slice to establish the direct dependency
+# relation.
+WantedBy=system.slice
diff --git a/scrub/xfs_scrub@xxxxxxxxxxx b/scrub/xfs_scrub@xxxxxxxxxxx
index 043aad12f20..7306e173ebe 100644
--- a/scrub/xfs_scrub@xxxxxxxxxxx
+++ b/scrub/xfs_scrub@xxxxxxxxxxx
@@ -18,8 +18,16 @@ PrivateTmp=no
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@ %f
SyslogIdentifier=%N
+
+# Run scrub with minimal CPU and IO priority so that nothing else will starve.
+IOSchedulingClass=idle
+CPUSchedulingPolicy=idle
+CPUAccounting=true
+Nice=19
+
+# Create the service underneath the scrub background service slice so that we
+# can control resource usage.
+Slice=system-xfs_scrub.slice
diff --git a/scrub/xfs_scrub_all.service.in b/scrub/xfs_scrub_all.service.in
index 4011ed271f9..0f4bddf740a 100644
--- a/scrub/xfs_scrub_all.service.in
+++ b/scrub/xfs_scrub_all.service.in
@@ -14,3 +14,7 @@ Type=oneshot
Environment=SERVICE_MODE=1
ExecStart=@sbindir@/xfs_scrub_all
SyslogIdentifier=xfs_scrub_all
+
+# Create the service underneath the scrub background service slice so that we
+# can control resource usage.
+Slice=system-xfs_scrub.slice
diff --git a/scrub/xfs_scrub_fail@xxxxxxxxxxx b/scrub/xfs_scrub_fail@xxxxxxxxxxx
index 48a0f25b5f1..dfbbd3b8218 100644
--- a/scrub/xfs_scrub_fail@xxxxxxxxxxx
+++ b/scrub/xfs_scrub_fail@xxxxxxxxxxx
@@ -14,3 +14,7 @@ ExecStart=@pkg_libexec_dir@/xfs_scrub_fail "${EMAIL_ADDR}" %f
User=mail
Group=mail
SupplementaryGroups=systemd-journal
+
+# Create the service underneath the scrub background service slice so that we
+# can control resource usage.
+Slice=system-xfs_scrub.slice
