[PATCH 18/24] blkio_cgroup patches from Ryo to track async bios.

Ryo Tsuruta ryov at valinux.co.jp
Tue Aug 18 18:43:11 PDT 2009


Hi Vivek,

Vivek Goyal <vgoyal at redhat.com> wrote:
> On Tue, Aug 18, 2009 at 08:42:12PM +0900, Ryo Tsuruta wrote:
> > Hi Vivek,
> > 
> > Vivek Goyal <vgoyal at redhat.com> wrote:
> > > o blkio_cgroup patches from Ryo to track async bios.
> > > 
> > > o Fernando is also working on another IO tracking mechanism. We are not
> > >   particular about any IO tracking mechanism. This patchset can make use
> > >   of any mechanism which makes it to upstream. For the time being making
> > >   use of Ryo's posting.
> > 
> > The patch attached with your mail is obsolete and it may potentially
> > cause a deadlock when lock_page_cgroup() is called under radix_tree->lock.
> > http://git.kernel.org/?p=linux/kernel/git/torvalds/linux-2.6.git;a=commit;h=e767e0561d7fd2333df1921f1ab4176211f9036b
> > 
> > The latest blkio-cgroup fixes the above issue and reduces IO tracking
> > overhead since lock_page_cgroup() is no longer used. I would recommend
> > to update to the latest version.
> > 
> 
> Hi Ryo,
> 
> Thanks. In next posting I will move to latest version of io tracking
> patches.
> 
> > And I have a suggestion, how about moving get_cgroup_from_page() to
> > biotrack.c, I think this function would be useful for people who
> > want to make use of the IO tracking mechanism.
> > 
> > Please let me know your opinion.
> 
> Makes sense. In next posting, will move get_cgroup_from_page() to biotrack.c.

Thank you for your reply. I'll post the new blkio-cgroup reflected in
this change by the end of this week. Please use it if you would like to.

Thanks,
Ryo Tsuruta


More information about the Containers mailing list