From: Jens Axboe <axboe@kernel.dk>
To: Christoph Lameter <cl@linux.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
"Nicholas A. Bellinger" <nab@linux-iscsi.org>,
Kent Overstreet <kmo@daterainc.com>,
linux-kernel@vger.kernel.org, Tejun Heo <tj@kernel.org>,
Oleg Nesterov <oleg@redhat.com>, Ingo Molnar <mingo@redhat.com>,
Andi Kleen <andi@firstfloor.org>
Subject: Re: [PATCH] idr: Use this_cpu_ptr() for percpu_ida
Date: Thu, 22 Aug 2013 10:56:08 -0600 [thread overview]
Message-ID: <521642A8.2020103@kernel.dk> (raw)
In-Reply-To: <00000140a6e964d2-03ac778f-13ff-415d-bbfa-93cb2fddcaa5-000000@email.amazonses.com>
On 08/22/2013 10:44 AM, Christoph Lameter wrote:
> On Wed, 21 Aug 2013, Andrew Morton wrote:
>
>> The lock is needed so that one cpu can steal tags from another cpu's cache.
>> See (the needlessly inlined!) steal_tags().
>
> Stealing tags could also be done via IPIs or some other things.
That is actually the approach I took for blk-mq tagging. But that isn't
free either. I think it pretty much boils down to how much stealing you
expect. If the tag space is sufficiently large, you would not expect a
lot of stealing. And then it doesn't really matter if you use a lock or
an IPI, since it's the rare case - the lock cacheline isn't going to be
shared across processors anyway. The ticket locks aren't exactly free on
their own, however, so that cost is still paid. But I'd be surprised if
it was much of an issue.
If the tag space isn't large enough (common case), then yes, it matters
a lot what kind of mechanism is used. It's on my TODO to compare the two
under realistic scenarios and see how they fare.
--
Jens Axboe
next prev parent reply other threads:[~2013-08-22 16:56 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-08-07 17:34 IDA/IDR rewrite, percpu ida Kent Overstreet
2013-08-07 17:34 ` [PATCH 03/10] idr: Rewrite ida Kent Overstreet
2013-08-07 20:22 ` Tejun Heo
2013-08-07 20:51 ` [PATCH] idr: Document ida tree sections Kent Overstreet
2013-08-09 14:57 ` Tejun Heo
2013-08-13 22:13 ` Kent Overstreet
2013-08-13 22:19 ` Tejun Heo
2013-08-13 22:27 ` Kent Overstreet
2013-08-13 22:44 ` Tejun Heo
2013-08-13 22:59 ` Kent Overstreet
2013-08-13 23:22 ` Tejun Heo
2013-08-13 23:51 ` Kent Overstreet
2013-08-13 23:59 ` Tejun Heo
2013-08-15 0:04 ` Kent Overstreet
2013-08-15 0:22 ` Tejun Heo
2013-08-13 22:33 ` Kent Overstreet
2013-08-07 17:34 ` [PATCH 04/10] idr: Percpu ida Kent Overstreet
2013-08-07 17:56 ` Christoph Lameter
2013-08-07 18:33 ` Kent Overstreet
2013-08-07 19:40 ` Christoph Lameter
2013-08-07 19:57 ` [PATCH] idr: Use this_cpu_ptr() for percpu_ida Kent Overstreet
2013-08-08 14:32 ` Christoph Lameter
2013-08-20 21:19 ` Nicholas A. Bellinger
2013-08-20 21:29 ` Andrew Morton
2013-08-21 2:01 ` Kent Overstreet
2013-08-21 2:07 ` Tejun Heo
2013-08-21 2:31 ` Kent Overstreet
2013-08-21 11:59 ` Tejun Heo
2013-08-21 21:09 ` Kent Overstreet
2013-08-21 21:16 ` Tejun Heo
2013-08-21 21:24 ` Kent Overstreet
2013-08-21 21:31 ` Tejun Heo
2013-08-21 14:32 ` Christoph Lameter
2013-08-21 17:49 ` Nicholas A. Bellinger
2013-08-21 20:49 ` Andrew Morton
2013-08-22 16:44 ` Christoph Lameter
2013-08-22 16:56 ` Jens Axboe [this message]
2013-08-07 17:46 ` [PATCH 05/10] idr: Kill old deprecated idr interfaces Kent Overstreet
2013-08-07 17:46 ` [PATCH 06/10] idr: Rename idr_get_next() -> idr_find_next() Kent Overstreet
2013-08-07 17:46 ` [PATCH 08/10] idr: Reimplement idr on top of ida/radix trees Kent Overstreet
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=521642A8.2020103@kernel.dk \
--to=axboe@kernel.dk \
--cc=akpm@linux-foundation.org \
--cc=andi@firstfloor.org \
--cc=cl@linux.com \
--cc=kmo@daterainc.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=nab@linux-iscsi.org \
--cc=oleg@redhat.com \
--cc=tj@kernel.org \
/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).