From: Rafael Tinoco <rafael.tinoco@canonical.com>
To: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Paul McKenney <paulmck@linux.vnet.ibm.com>,
Dave Chiluk <chiluk@canonical.com>,
linux-kernel@vger.kernel.org, davem@davemloft.net,
Christopher Arges <chris.j.arges@canonical.com>,
Jay Vosburgh <jay.vosburgh@canonical.com>
Subject: Re: Possible netns creation and execution performance/scalability regression since v3.8 due to rcu callbacks being offloaded to multiple cpus
Date: Wed, 11 Jun 2014 21:25:52 -0300 [thread overview]
Message-ID: <CAJE_dJzzj2uf+YEXhAngJDKev=Lc4O6fyKfHoO2PbzD90VuuVw@mail.gmail.com> (raw)
In-Reply-To: <87bntzt24g.fsf@x220.int.ebiederm.org>
I'm getting a kernel panic with your patch:
-- panic
-- mount_block_root
-- mount_root
-- prepare_namespace
-- kernel_init_freeable
It is giving me an unknown block device for the same config file i
used on other builds. Since my test is running on a kvm guest under a
ramdisk, i'm still checking if there are any differences between this
build and other ones but I think there aren't.
Any chances that "prepare_namespace" might be breaking mount_root ?
Tks
On Wed, Jun 11, 2014 at 9:14 PM, Eric W. Biederman
<ebiederm@xmission.com> wrote:
> "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> writes:
>
>> On Wed, Jun 11, 2014 at 04:12:15PM -0700, Eric W. Biederman wrote:
>>> "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> writes:
>>>
>>> > On Wed, Jun 11, 2014 at 01:46:08PM -0700, Eric W. Biederman wrote:
>>> >> On the chance it is dropping the old nsproxy which calls syncrhonize_rcu
>>> >> in switch_task_namespaces that is causing you problems I have attached
>>> >> a patch that changes from rcu_read_lock to task_lock for code that
>>> >> calls task_nsproxy from a different task. The code should be safe
>>> >> and it should be an unquestions performance improvement but I have only
>>> >> compile tested it.
>>> >>
>>> >> If you can try the patch it will tell is if the problem is the rcu
>>> >> access in switch_task_namespaces (the only one I am aware of network
>>> >> namespace creation) or if the problem rcu case is somewhere else.
>>> >>
>>> >> If nothing else knowing which rcu accesses are causing the slow down
>>> >> seem important at the end of the day.
>>> >>
>>> >> Eric
>>> >>
>>> >
>>> > If this is the culprit, another approach would be to use workqueues from
>>> > RCU callbacks. The following (untested, probably does not even build)
>>> > patch illustrates one such approach.
>>>
>>> For reference the only reason we are using rcu_lock today for nsproxy is
>>> an old lock ordering problem that does not exist anymore.
>>>
>>> I can say that in some workloads setns is a bit heavy today because of
>>> the synchronize_rcu and setns is more important that I had previously
>>> thought because pthreads break the classic unix ability to do things in
>>> your process after fork() (sigh).
>>>
>>> Today daemonize is gone, and notify the parent process with a signal
>>> relies on task_active_pid_ns which does not use nsproxy. So the old
>>> lock ordering problem/race is gone.
>>>
>>> The description of what was happening when the code switched from
>>> task_lock to rcu_read_lock to protect nsproxy.
>>
>> OK, never mind, then! ;-)
>
> I appreciate you posting your approach. I just figured I should do
> my homework, and verify my fuzzy memory.
>
> Who knows there might be different performance problems with my
> approach. But I am hoping this is one of those happy instances where we
> can just make everything simpler.
>
> Eric
--
--
Rafael David Tinoco
Software Sustaining Engineer @ Canonical
Canonical Technical Services Engineering Team
# Email: rafael.tinoco@canonical.com (GPG: 87683FC0)
# Phone: +55.11.9.6777.2727 (Americas/Sao_Paulo)
# LP: ~inaddy | IRC: tinoco | Skype: rafael.tinoco
next prev parent reply other threads:[~2014-06-12 0:25 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-06-11 5:52 Rafael Tinoco
2014-06-11 7:07 ` Eric W. Biederman
2014-06-11 13:39 ` Paul E. McKenney
2014-06-11 15:17 ` Rafael Tinoco
2014-06-11 15:46 ` David Chiluk
2014-06-11 16:18 ` Paul E. McKenney
2014-06-11 18:27 ` Dave Chiluk
2014-06-11 19:48 ` Paul E. McKenney
2014-06-11 20:55 ` Eric W. Biederman
2014-06-11 21:03 ` Rafael Tinoco
2014-06-11 20:46 ` Eric W. Biederman
2014-06-11 21:14 ` Dave Chiluk
2014-06-11 22:52 ` Paul E. McKenney
2014-06-11 23:12 ` Eric W. Biederman
2014-06-11 23:49 ` Paul E. McKenney
2014-06-12 0:14 ` Eric W. Biederman
2014-06-12 0:25 ` Rafael Tinoco [this message]
2014-06-12 1:09 ` Eric W. Biederman
2014-06-12 1:14 ` Rafael Tinoco
[not found] ` <CAJE_dJzjcWP=e_CPM1M64URVHiEFFb+fP6g2YKZVdoFntkQMZg@mail.gmail.com>
2014-06-13 18:22 ` Rafael Tinoco
2014-06-14 0:02 ` Eric W. Biederman
2014-06-16 15:01 ` Rafael Tinoco
2014-07-17 12:05 ` Rafael David Tinoco
2014-07-24 7:01 ` Eric W. Biederman
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='CAJE_dJzzj2uf+YEXhAngJDKev=Lc4O6fyKfHoO2PbzD90VuuVw@mail.gmail.com' \
--to=rafael.tinoco@canonical.com \
--cc=chiluk@canonical.com \
--cc=chris.j.arges@canonical.com \
--cc=davem@davemloft.net \
--cc=ebiederm@xmission.com \
--cc=jay.vosburgh@canonical.com \
--cc=linux-kernel@vger.kernel.org \
--cc=paulmck@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
all inboxes | Powered by JetHome®