From: "Srivatsa S. Bhat" <srivatsa.bhat@linux.vnet.ibm.com>
To: a.p.zijlstra@chello.nl, mingo@kernel.org, pjt@google.com,
paul@paulmenage.org, akpm@linux-foundation.org
Cc: rjw@sisk.pl, nacc@us.ibm.com, paulmck@linux.vnet.ibm.com,
tglx@linutronix.de, seto.hidetoshi@jp.fujitsu.com, tj@kernel.org,
mschmidt@redhat.com, berrange@redhat.com,
nikunj@linux.vnet.ibm.com, vatsa@linux.vnet.ibm.com,
liuj97@gmail.com, linux-kernel@vger.kernel.org,
linux-pm@vger.kernel.org, srivatsa.bhat@linux.vnet.ibm.com
Subject: [PATCH v3 0/5] CPU hotplug, cpusets: Fix issues with cpusets handling during suspend/resume
Date: Mon, 14 May 2012 04:44:31 +0530 [thread overview]
Message-ID: <20120513231325.3566.37740.stgit@srivatsabhat> (raw)
Currently the kernel doesn't handle cpusets properly during suspend/resume.
After a resume, all non-root cpusets end up having only 1 cpu (the boot cpu),
causing massive performance degradation of workloads. One major user of cpusets
is libvirt, which means that after a suspend/hibernation cycle, all VMs
suddenly end up running terribly slow!
Also, the kernel moves the tasks from one cpuset to another during CPU hotplug
in the suspend/resume path, leading to a task-management nightmare after
resume.
This patchset solves these problems by reworking the way cpusets are handled
during CPU hotplug in the suspend/resume path. This doesn't involve any
change in semantics as to how cpusets are handled during regular CPU hotplug
because it is correct as it is.
Patches 1 & 2 are cleanups that separate out hotplug handling so that we can
implement different logic for different hotplug events (CPU/Mem
online/offline). This also leads to some optimizations and more importantly
prepares the ground for any further work dealing with cpusets during hotplug.
Patch 3 is a bug fix - it ensures that the tasks attached to the root cpuset
see the updated cpus_allowed mask upon CPU hotplug.
Patches 4 and 5 implement the fix for cpusets handling during suspend/resume.
--
Srivatsa S. Bhat (5):
cpusets, hotplug: Implement cpuset tree traversal in a helper function
cpusets, hotplug: Restructure functions that are invoked during hotplug
cpusets: Update tasks' cpus_allowed mask upon updates to root cpuset
cpusets: Add provisions for distinguishing CPU Hotplug in suspend/resume path
cpusets, suspend: Save and restore cpusets during suspend/resume
include/linux/cpuset.h | 4 -
kernel/cpuset.c | 235 +++++++++++++++++++++++++++++++++++++++---------
kernel/sched/core.c | 29 +++++-
3 files changed, 218 insertions(+), 50 deletions(-)
Thanks,
Srivatsa S. Bhat
IBM Linux Technology Center
next reply other threads:[~2012-05-13 23:15 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-05-13 23:14 Srivatsa S. Bhat [this message]
2012-05-13 23:15 ` [PATCH v3 1/5] cpusets, hotplug: Implement cpuset tree traversal in a helper function Srivatsa S. Bhat
2012-05-15 0:03 ` David Rientjes
2012-05-15 12:15 ` Srivatsa S. Bhat
2012-05-15 18:04 ` David Rientjes
2012-05-13 23:15 ` [PATCH v3 2/5] cpusets, hotplug: Restructure functions that are invoked during hotplug Srivatsa S. Bhat
2012-05-15 0:27 ` David Rientjes
2012-05-15 12:25 ` Srivatsa S. Bhat
2012-05-13 23:16 ` [PATCH v3 3/5] cpusets: Update tasks' cpus_allowed mask upon updates to root cpuset Srivatsa S. Bhat
2012-05-15 0:31 ` David Rientjes
2012-05-13 23:16 ` [PATCH v3 4/5] cpusets: Add provisions for distinguishing CPU Hotplug in suspend/resume path Srivatsa S. Bhat
2012-05-15 0:33 ` David Rientjes
2012-05-15 12:29 ` Srivatsa S. Bhat
2012-05-15 18:34 ` David Rientjes
2012-05-15 19:17 ` Srivatsa S. Bhat
2012-05-15 20:39 ` David Rientjes
2012-05-13 23:17 ` [PATCH v3 5/5] cpusets, suspend: Save and restore cpusets during suspend/resume Srivatsa S. Bhat
2012-05-15 0:37 ` David Rientjes
2012-05-15 1:40 ` Nishanth Aravamudan
2012-05-15 4:04 ` David Rientjes
2012-05-15 4:45 ` Nishanth Aravamudan
2012-05-15 18:31 ` David Rientjes
2012-05-15 20:10 ` Peter Zijlstra
2012-05-15 21:05 ` David Rientjes
2012-05-15 21:08 ` Peter Zijlstra
2012-05-15 21:21 ` Srivatsa S. Bhat
2012-05-15 21:24 ` Peter Zijlstra
2012-05-15 21:24 ` David Rientjes
2012-05-15 21:42 ` Srivatsa S. Bhat
2012-05-15 21:49 ` David Rientjes
2012-05-15 22:16 ` Srivatsa S. Bhat
2012-05-15 22:32 ` David Rientjes
2012-05-16 8:20 ` Srivatsa S. Bhat
2012-05-16 8:42 ` Srivatsa S. Bhat
2012-05-16 21:24 ` Peter Zijlstra
2012-05-17 9:57 ` Srivatsa S. Bhat
2012-05-15 21:13 ` Peter Zijlstra
2012-05-15 21:37 ` David Rientjes
2012-05-15 9:24 ` Srivatsa S. Bhat
2012-05-14 23:58 ` [PATCH v3 0/5] CPU hotplug, cpusets: Fix issues with cpusets handling " David Rientjes
2012-05-15 12:10 ` Srivatsa S. Bhat
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20120513231325.3566.37740.stgit@srivatsabhat \
--to=srivatsa.bhat@linux.vnet.ibm.com \
--cc=a.p.zijlstra@chello.nl \
--cc=akpm@linux-foundation.org \
--cc=berrange@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=liuj97@gmail.com \
--cc=mingo@kernel.org \
--cc=mschmidt@redhat.com \
--cc=nacc@us.ibm.com \
--cc=nikunj@linux.vnet.ibm.com \
--cc=paul@paulmenage.org \
--cc=paulmck@linux.vnet.ibm.com \
--cc=pjt@google.com \
--cc=rjw@sisk.pl \
--cc=seto.hidetoshi@jp.fujitsu.com \
--cc=tglx@linutronix.de \
--cc=tj@kernel.org \
--cc=vatsa@linux.vnet.ibm.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).