From: Kent Overstreet <koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
To: Tejun Heo <tj-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
Cc: linux-bcache-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
dm-devel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org,
axboe-tSWWG44O7X1aa/9Udqfwiw@public.gmane.org,
neilb-l3A5Bk7waGM@public.gmane.org,
Vivek Goyal <vgoyal-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
Subject: Re: [PATCH v2 03/26] block: Refactor blk_update_request()
Date: Thu, 20 Sep 2012 16:50:16 -0700 [thread overview]
Message-ID: <20120920235016.GG5519@google.com> (raw)
In-Reply-To: <20120920234133.GM7264-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
On Thu, Sep 20, 2012 at 04:41:33PM -0700, Tejun Heo wrote:
> Hey,
>
> On Thu, Sep 20, 2012 at 04:36:32PM -0700, Kent Overstreet wrote:
> > > Other than that, I definitely like this. It would be nice to note
> > > that the custom partial bio advancing in blk_update_request() is
> > > replaced with multiple calls to req_bio_endio(). I don't think it has
> > > any meaningful performance implications. It's just nice to future
> > > readers of the commit.
> >
> > The number of calls to req_bio_endio() isn't changing...
> > blk_update_request() called it for partial completions before. It's just
> > where the bio itself is updated that's getting shuffled around.
> >
> > Or did you mean that bio_advance() is getting called on every bio
> > instead of the custom advancing in blk_update_request() before? That is
> > different, yeah - it's now always looping over the iovec, not just for
> > partial completions.
> >
> > Yeah, I will note that in the commit message, in case Jens sees a
> > performance regression from it :)
>
> I don't think there's any performance implication. It's just nice to
> explain how the complexity went away. If for nothing else, to point
> out how silly the original code was. :)
New patch below - that commit message have what you're after?
> > > Also, it would be really nice if you can verify this actually works
> > > with partial blk_update_request(). sector update bug in the previous
> > > patch scares me a bit. Implementing some debug hacks in the
> > > completion path might be the easiest way to verify. A subtle bug here
> > > could be pretty painful.
> >
> > Any suggestions on how to trigger partial updates?
>
> ide along with many legacy drivers do it. Any SCSI driver including
> libata only does full completion. I don't know. Even just trying to
> call the function and comparing before & after with the original code
> would be good. I'd like to see at least some form of verification
> because the manifested bugs could be extremely nasty and difficult to
> track down.
Multiple partial completions should have the same semantics as a single
full completion, so maybe I'll try rigging up some test code that wraps
blk_update_request(), turning full completions into partial completions,
and verifies stuff...
commit fef0ddc82214f87de71ec6fb051eb28a6de0be74
Author: Kent Overstreet <koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
Date: Thu Sep 20 16:38:30 2012 -0700
block: Refactor blk_update_request()
Converts it to use bio_advance(), simplifying it quite a bit in the
process.
Note that req_bio_endio() now always calls bio_advance() - which means
it always loops over the biovec, not just on partial completions. Don't
expect it to affect performance, but worth noting.
Signed-off-by: Kent Overstreet <koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
CC: Jens Axboe <axboe-tSWWG44O7X1aa/9Udqfwiw@public.gmane.org>
diff --git a/block/blk-core.c b/block/blk-core.c
index 2d739ca..9f8cb16 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -158,20 +158,10 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
error = -EIO;
- if (unlikely(nbytes > bio->bi_size)) {
- printk(KERN_ERR "%s: want %u bytes done, %u left\n",
- __func__, nbytes, bio->bi_size);
- nbytes = bio->bi_size;
- }
-
if (unlikely(rq->cmd_flags & REQ_QUIET))
set_bit(BIO_QUIET, &bio->bi_flags);
- bio->bi_size -= nbytes;
- bio->bi_sector += (nbytes >> 9);
-
- if (bio_integrity(bio))
- bio_integrity_advance(bio, nbytes);
+ bio_advance(bio, nbytes);
/* don't actually finish bio if it's part of flush sequence */
if (bio->bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ))
@@ -2214,8 +2204,7 @@ EXPORT_SYMBOL(blk_fetch_request);
**/
bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
{
- int total_bytes, bio_nbytes, next_idx = 0;
- struct bio *bio;
+ int total_bytes;
if (!req->bio)
return false;
@@ -2259,56 +2248,21 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
blk_account_io_completion(req, nr_bytes);
- total_bytes = bio_nbytes = 0;
- while ((bio = req->bio) != NULL) {
- int nbytes;
+ total_bytes = 0;
+ while (req->bio) {
+ struct bio *bio = req->bio;
+ unsigned bio_bytes = min(bio->bi_size, nr_bytes);
- if (nr_bytes >= bio->bi_size) {
+ if (bio_bytes == bio->bi_size)
req->bio = bio->bi_next;
- nbytes = bio->bi_size;
- req_bio_endio(req, bio, nbytes, error);
- next_idx = 0;
- bio_nbytes = 0;
- } else {
- int idx = bio->bi_idx + next_idx;
-
- if (unlikely(idx >= bio->bi_vcnt)) {
- blk_dump_rq_flags(req, "__end_that");
- printk(KERN_ERR "%s: bio idx %d >= vcnt %d\n",
- __func__, idx, bio->bi_vcnt);
- break;
- }
-
- nbytes = bio_iovec_idx(bio, idx)->bv_len;
- BIO_BUG_ON(nbytes > bio->bi_size);
-
- /*
- * not a complete bvec done
- */
- if (unlikely(nbytes > nr_bytes)) {
- bio_nbytes += nr_bytes;
- total_bytes += nr_bytes;
- break;
- }
- /*
- * advance to the next vector
- */
- next_idx++;
- bio_nbytes += nbytes;
- }
+ req_bio_endio(req, bio, bio_bytes, error);
- total_bytes += nbytes;
- nr_bytes -= nbytes;
+ total_bytes += bio_bytes;
+ nr_bytes -= bio_bytes;
- bio = req->bio;
- if (bio) {
- /*
- * end more in this run, or just return 'not-done'
- */
- if (unlikely(nr_bytes <= 0))
- break;
- }
+ if (!nr_bytes)
+ break;
}
/*
@@ -2324,16 +2278,6 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
return false;
}
- /*
- * if the request wasn't completed, update state
- */
- if (bio_nbytes) {
- req_bio_endio(req, bio, bio_nbytes, error);
- bio->bi_idx += next_idx;
- bio_iovec(bio)->bv_offset += nr_bytes;
- bio_iovec(bio)->bv_len -= nr_bytes;
- }
-
req->__data_len -= total_bytes;
req->buffer = bio_data(req->bio);
next prev parent reply other threads:[~2012-09-20 23:50 UTC|newest]
Thread overview: 81+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-09-11 0:22 [PATCH v2 00/26] Prep work for immutable bio vecs Kent Overstreet
2012-09-11 0:22 ` [PATCH v2 01/26] block: Convert integrity to bvec_alloc_bs(), and a bugfix Kent Overstreet
[not found] ` <1347322957-25260-2-git-send-email-koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-11 20:36 ` [dm-devel] " Vivek Goyal
2012-09-11 20:48 ` Kent Overstreet
2012-09-11 22:07 ` Kent Overstreet
[not found] ` <20120911220750.GM19739-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-12 19:39 ` Martin K. Petersen
[not found] ` <yq1wqzzrpy1.fsf-+q57XtR/GgMb6DWv4sQWN6xOck334EZe@public.gmane.org>
2012-09-17 21:08 ` Kent Overstreet
2012-09-20 21:53 ` Tejun Heo
2012-09-11 0:22 ` [PATCH v2 02/26] block: Add bio_advance() Kent Overstreet
[not found] ` <1347322957-25260-3-git-send-email-koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-20 21:58 ` Tejun Heo
2012-09-20 23:13 ` Kent Overstreet
[not found] ` <20120920231308.GB5519-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-20 23:25 ` Tejun Heo
[not found] ` <20120920232506.GI7264-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-20 23:38 ` Kent Overstreet
2012-09-11 0:22 ` [PATCH v2 03/26] block: Refactor blk_update_request() Kent Overstreet
[not found] ` <1347322957-25260-4-git-send-email-koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-20 23:20 ` Tejun Heo
2012-09-20 23:36 ` Kent Overstreet
[not found] ` <20120920233632.GC5519-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-20 23:41 ` Tejun Heo
[not found] ` <20120920234133.GM7264-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-20 23:50 ` Kent Overstreet [this message]
2012-09-11 0:22 ` [PATCH v2 04/26] md: Convert md_trim_bio() to use bio_advance() Kent Overstreet
[not found] ` <1347322957-25260-5-git-send-email-koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-20 23:27 ` Tejun Heo
2012-09-11 0:22 ` [PATCH v2 05/26] block: Add bio_end() Kent Overstreet
[not found] ` <1347322957-25260-6-git-send-email-koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-17 9:17 ` Steven Whitehouse
2012-09-20 23:32 ` Tejun Heo
[not found] ` <20120920233225.GK7264-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-20 23:44 ` Kent Overstreet
2012-09-11 0:22 ` [PATCH v2 06/26] block: Use bio_sectors() more consistently Kent Overstreet
[not found] ` <1347322957-25260-7-git-send-email-koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-20 23:36 ` Tejun Heo
[not found] ` <20120920233618.GL7264-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-20 23:47 ` Kent Overstreet
2012-09-11 0:22 ` [PATCH v2 07/26] block: Don't use bi_idx in bio_split() or require it to be 0 Kent Overstreet
[not found] ` <1347322957-25260-8-git-send-email-koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-20 23:45 ` Tejun Heo
[not found] ` <20120920234544.GN7264-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-21 0:00 ` Kent Overstreet
2012-09-11 0:22 ` [PATCH v2 09/26] block: Remove some unnecessary bi_vcnt usage Kent Overstreet
[not found] ` <1347322957-25260-10-git-send-email-koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-20 23:51 ` Tejun Heo
2012-09-11 0:22 ` [PATCH v2 10/26] block: Add submit_bio_wait(), remove from md Kent Overstreet
[not found] ` <1347322957-25260-11-git-send-email-koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-20 23:56 ` Tejun Heo
[not found] ` <20120920235643.GQ7264-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-21 0:06 ` Kent Overstreet
2012-09-11 0:22 ` [PATCH v2 11/26] raid10: Use bio_reset() Kent Overstreet
2012-09-20 23:59 ` Tejun Heo
2012-09-11 0:22 ` [PATCH v2 13/26] raid5: use bio_reset() Kent Overstreet
[not found] ` <1347322957-25260-14-git-send-email-koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-11 5:03 ` NeilBrown
[not found] ` <20120911150326.79f066c0-wvvUuzkyo1EYVZTmpyfIwg@public.gmane.org>
2012-09-11 19:26 ` Kent Overstreet
2012-09-11 0:22 ` [PATCH v2 14/26] raid1: Refactor narrow_write_error() to not use bi_idx Kent Overstreet
2012-09-11 0:22 ` [PATCH v2 15/26] block: Add bio_copy_data() Kent Overstreet
[not found] ` <1347322957-25260-16-git-send-email-koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-21 0:06 ` Tejun Heo
2012-09-21 0:09 ` Kent Overstreet
[not found] ` <20120921000945.GK5519-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-21 0:15 ` Tejun Heo
2012-09-21 0:09 ` Tejun Heo
[not found] ` <20120921000947.GT7264-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-21 0:13 ` Kent Overstreet
2012-09-11 0:22 ` [PATCH v2 16/26] pktcdvd: use bio_copy_data() Kent Overstreet
2012-09-11 0:22 ` [PATCH v2 17/26] pktcdvd: Use bio_reset() in disabled code to kill bi_idx usage Kent Overstreet
2012-09-11 0:22 ` [PATCH v2 18/26] raid1: use bio_copy_data() Kent Overstreet
2012-09-11 0:22 ` [PATCH v2 20/26] block: Add bio_for_each_segment_all() Kent Overstreet
[not found] ` <1347322957-25260-21-git-send-email-koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-21 0:35 ` Tejun Heo
2012-09-11 0:22 ` [PATCH v2 22/26] block: Add bio_alloc_pages() Kent Overstreet
[not found] ` <1347322957-25260-23-git-send-email-koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-21 0:47 ` Tejun Heo
[not found] ` <20120921004711.GZ7264-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-21 4:50 ` Kent Overstreet
2012-09-11 0:22 ` [PATCH v2 24/26] block: Add an explicit bio flag for bios that own their bvec Kent Overstreet
[not found] ` <1347322957-25260-1-git-send-email-koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-11 0:22 ` [PATCH v2 08/26] block: Remove bi_idx references Kent Overstreet
[not found] ` <1347322957-25260-9-git-send-email-koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-20 23:49 ` Tejun Heo
2012-09-21 0:04 ` Kent Overstreet
2012-09-11 0:22 ` [PATCH v2 12/26] raid1: use bio_reset() Kent Overstreet
[not found] ` <1347322957-25260-13-git-send-email-koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-11 4:59 ` NeilBrown
2012-09-11 18:28 ` Kent Overstreet
[not found] ` <20120911182825.GG19739-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-11 21:17 ` NeilBrown
2012-09-11 0:22 ` [PATCH v2 19/26] bounce: Refactor __blk_queue_bounce to not use bi_io_vec Kent Overstreet
[not found] ` <1347322957-25260-20-git-send-email-koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-21 0:25 ` Tejun Heo
2012-09-21 0:29 ` Kent Overstreet
2012-09-21 0:27 ` Tejun Heo
2012-09-21 0:34 ` Kent Overstreet
2012-09-11 0:22 ` [PATCH v2 21/26] block: Convert some code to bio_for_each_segment_all() Kent Overstreet
[not found] ` <1347322957-25260-22-git-send-email-koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-21 0:38 ` Tejun Heo
[not found] ` <20120921003832.GY7264-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-21 0:50 ` Kent Overstreet
2012-09-11 0:22 ` [PATCH v2 23/26] raid1: use bio_alloc_pages() Kent Overstreet
[not found] ` <1347322957-25260-24-git-send-email-koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-21 0:48 ` Tejun Heo
[not found] ` <20120921004827.GA7264-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-21 4:51 ` Kent Overstreet
2012-09-11 0:22 ` [PATCH v2 25/26] bio-integrity: Add explicit field for owner of bip_buf Kent Overstreet
[not found] ` <1347322957-25260-26-git-send-email-koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-12 19:41 ` Martin K. Petersen
[not found] ` <yq1sjanrpu7.fsf-+q57XtR/GgMb6DWv4sQWN6xOck334EZe@public.gmane.org>
2012-09-17 21:09 ` Kent Overstreet
2012-09-11 0:22 ` [PATCH v2 26/26] block: Add BIO_SUBMITTED flag, kill BIO_CLONED Kent Overstreet
2012-09-11 5:22 ` [PATCH v2 00/26] Prep work for immutable bio vecs NeilBrown
2012-09-20 23:22 ` Tejun Heo
2012-10-15 20:08 [PATCH v4 00/24] " Kent Overstreet
2012-10-15 20:09 ` [PATCH v2 03/26] block: Refactor blk_update_request() 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=20120920235016.GG5519@google.com \
--to=koverstreet-hpiqsd4aklfqt0dzr+alfa@public.gmane.org \
--cc=axboe-tSWWG44O7X1aa/9Udqfwiw@public.gmane.org \
--cc=dm-devel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org \
--cc=linux-bcache-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=neilb-l3A5Bk7waGM@public.gmane.org \
--cc=tj-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org \
--cc=vgoyal-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.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).