From: Jeff Moyer <jmoyer@redhat.com>
To: Andi Kleen <andi@firstfloor.org>
Cc: linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org,
hch@infradead.org, Andi Kleen <ak@linux.intel.com>
Subject: Re: [PATCH 11/11] DIO: optimize cache misses in the submission path
Date: Mon, 08 Aug 2011 15:38:03 -0400 [thread overview]
Message-ID: <x49vcu7g0dg.fsf@segfault.boston.devel.redhat.com> (raw)
In-Reply-To: <20110808193231.GM5782@one.firstfloor.org> (Andi Kleen's message of "Mon, 8 Aug 2011 21:32:31 +0200")
Andi Kleen <andi@firstfloor.org> writes:
>> I bet we could default to using the smaller block size all the time, and
>> still be able to detect when we don't have to do the sub-block zeroing.
>> Maybe that would be a good follow-on patch.
>
> It doesn't really matter because it's out of the fast path now.
>
>> > + /*
>> > + * Avoid references to bdev if not absolutely needed to give
>> > + * the early prefetch in the caller enough time.
>> > + */
>> >
>> > - if (offset & blocksize_mask) {
>> > + if (unlikely(offset & blocksize_mask)) {
>>
>> You can't make this assumption. Userspace controls what size/alignment
>> of blocks to send in.
>
> What assumption do you mean?
Sorry, I meant that we don't know whether the offset & blocksize_mask
check is unlikely.
Cheers,
Jeff
next prev parent reply other threads:[~2011-08-08 19:38 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-08-02 4:38 Updated direct IO optimization patchkit v2 Andi Kleen
2011-08-02 4:38 ` [PATCH 01/11] DIO: Separate fields only used in the submission path from struct dio Andi Kleen
2011-08-08 17:59 ` Jeff Moyer
2011-08-08 19:43 ` Andi Kleen
2011-08-08 19:46 ` Jeff Moyer
2011-08-02 4:38 ` [PATCH 02/11] DIO: Fix a wrong comment Andi Kleen
2011-08-08 17:59 ` Jeff Moyer
2011-08-02 4:38 ` [PATCH 03/11] DIO: Rearrange fields in dio/dio_submit to avoid holes Andi Kleen
2011-08-08 18:00 ` Jeff Moyer
2011-08-02 4:38 ` [PATCH 04/11] DIO: Use a slab cache for struct dio Andi Kleen
2011-08-08 18:01 ` Jeff Moyer
2011-08-02 4:38 ` [PATCH 05/11] DIO: Separate map_bh from dio v2 Andi Kleen
2011-08-08 18:11 ` Jeff Moyer
2011-08-02 4:38 ` [PATCH 06/11] DIO: Inline the complete submission path v2 Andi Kleen
2011-08-08 18:14 ` Jeff Moyer
2011-08-02 4:38 ` [PATCH 07/11] DIO: Merge direct_io_walker into __blockdev_direct_IO Andi Kleen
2011-08-08 18:20 ` Jeff Moyer
2011-08-02 4:38 ` [PATCH 08/11] DIO: Remove unnecessary dio argument from dio_pages_present() Andi Kleen
2011-08-08 18:21 ` Jeff Moyer
2011-08-02 4:38 ` [PATCH 09/11] DIO: Remove unused dio parameter from dio_bio_add_page Andi Kleen
2011-08-08 18:21 ` Jeff Moyer
2011-08-02 4:38 ` [PATCH 10/11] VFS: Cache request_queue in struct block_device Andi Kleen
2011-08-08 18:22 ` Jeff Moyer
2011-08-18 19:42 ` Vivek Goyal
2011-08-18 21:03 ` Andi Kleen
2011-08-19 14:14 ` Vivek Goyal
2011-08-19 15:36 ` Andi Kleen
2011-08-19 15:55 ` Vivek Goyal
2011-08-19 16:23 ` Andi Kleen
2011-08-19 16:51 ` Vivek Goyal
2011-08-02 4:38 ` [PATCH 11/11] DIO: optimize cache misses in the submission path Andi Kleen
2011-08-08 18:43 ` Jeff Moyer
2011-08-08 19:32 ` Andi Kleen
2011-08-08 19:38 ` Jeff Moyer [this message]
2011-08-18 17:53 ` Updated direct IO optimization patchkit v2 Jeff Moyer
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=x49vcu7g0dg.fsf@segfault.boston.devel.redhat.com \
--to=jmoyer@redhat.com \
--cc=ak@linux.intel.com \
--cc=andi@firstfloor.org \
--cc=hch@infradead.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.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).