From: Paolo Bonzini <pbonzini@redhat.com>
To: Stefan Hajnoczi <stefanha@gmail.com>
Cc: kwolf@redhat.com, pl@kamp.de, qemu-devel@nongnu.org, stefanha@redhat.com
Subject: Re: [Qemu-devel] [PATCH v2 06/20] block: make bdrv_co_do_write_zeroes stricter in producing aligned requests
Date: Wed, 20 Nov 2013 12:01:46 +0100 [thread overview]
Message-ID: <528C969A.1090704@redhat.com> (raw)
In-Reply-To: <20131120102256.GC25447@stefanha-thinkpad.muc.redhat.com>
Il 20/11/2013 11:22, Stefan Hajnoczi ha scritto:
>> > + && num > bs->bl.write_zeroes_alignment) {
> Here '>' is used...
>
>> > + if (sector_num % bs->bl.write_zeroes_alignment != 0) {
>> > + /* Make a small request up to the first aligned sector. */
>> > num = bs->bl.write_zeroes_alignment;
>> > + num -= sector_num % bs->bl.write_zeroes_alignment;
>> > + } else if (num >= bs->bl.write_zeroes_alignment) {
> ...but here '>=' is used.
>
> The == case here cannot happen. Did you mean '>=' in both places?
I meant what I wrote, in the sense that the two "if"s make sense the
way I wrote them. However, it is not too clear indeed.
> if (bs->bl.write_zeroes_alignment
> && num > bs->bl.write_zeroes_alignment) {
Here, '>' is a necessary (though not sufficient) for being able to
split the operation in one misaligned request and one aligned request.
If '<', the request is misaligned in either the starting sector
or the ending sector (or both), and there's no need to split it.
If '==', either the request is aligned or we can only split it
in two parts but they remain misaligned. In either case there's
no need to do anyting.
Because the condition is not sufficient, we may end up splitting a
request that cannot be aligned anyway (e.g. sector_num = 1, num = 129,
alignment = 128; will be split into [1,128) and [128,130) which are
both misaligned. This is not important.
> if (sector_num % bs->bl.write_zeroes_alignment != 0) {
> /* Make a small request up to the first aligned sector. */
> num = bs->bl.write_zeroes_alignment;
> num -= sector_num % bs->bl.write_zeroes_alignment;
> } else if (num >= bs->bl.write_zeroes_alignment) {
> /* Shorten the request to the last aligned sector. */
> num -= (sector_num + num) % bs->bl.write_zeroes_alignment;
Here, the "if" checks that we can have no underflow in the subtraction.
However, in addition to what you pointed out, it's not immediately obvious
that the subtraction has no effect if sector_num and num are correctly aligned.
So I will rewrite the "if" this way:
if (sector_num % bs->bl.write_zeroes_alignment != 0) {
/* Make a small request up to the first aligned sector. */
num = bs->bl.write_zeroes_alignment;
num -= sector_num % bs->bl.write_zeroes_alignment;
} else if ((sector_num + num) % bs->bl.write_zeroes_alignment != 0) {
/* Shorten the request to the last aligned sector. num cannot
* underflow because num > bs->bl.write_zeroes_alignment.
*/
num -= (sector_num + num) % bs->bl.write_zeroes_alignment;
}
Paolo
next prev parent reply other threads:[~2013-11-20 11:02 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-11-19 17:07 [Qemu-devel] [PATCH v2 00/20] block & scsi: write_zeroes support through the whole stack Paolo Bonzini
2013-11-19 17:07 ` [Qemu-devel] [PATCH v2 01/20] block: generalize BlockLimits handling to cover bdrv_aio_discard too Paolo Bonzini
2013-11-19 17:07 ` [Qemu-devel] [PATCH v2 02/20] block: add flags to BlockRequest Paolo Bonzini
2013-11-19 17:07 ` [Qemu-devel] [PATCH v2 03/20] block: add flags argument to bdrv_co_write_zeroes tracepoint Paolo Bonzini
2013-11-20 9:59 ` Stefan Hajnoczi
2013-11-19 17:07 ` [Qemu-devel] [PATCH v2 04/20] block: add bdrv_aio_write_zeroes Paolo Bonzini
2013-11-20 10:02 ` Stefan Hajnoczi
2013-11-19 17:07 ` [Qemu-devel] [PATCH v2 05/20] block: handle ENOTSUP from discard in generic code Paolo Bonzini
2013-11-19 17:07 ` [Qemu-devel] [PATCH v2 06/20] block: make bdrv_co_do_write_zeroes stricter in producing aligned requests Paolo Bonzini
2013-11-20 10:22 ` Stefan Hajnoczi
2013-11-20 11:01 ` Paolo Bonzini [this message]
2013-11-20 14:29 ` Stefan Hajnoczi
2013-11-21 11:30 ` Peter Lieven
2013-11-21 11:37 ` Paolo Bonzini
2013-11-19 17:07 ` [Qemu-devel] [PATCH v2 07/20] vpc, vhdx: add get_info Paolo Bonzini
2013-11-20 12:39 ` Stefan Hajnoczi
2013-11-20 12:50 ` Paolo Bonzini
2013-11-19 17:07 ` [Qemu-devel] [PATCH v2 08/20] block drivers: add discard/write_zeroes properties to bdrv_get_info implementation Paolo Bonzini
2013-11-21 11:33 ` Peter Lieven
2013-11-21 11:39 ` Paolo Bonzini
2013-11-21 11:48 ` Peter Lieven
2013-11-19 17:07 ` [Qemu-devel] [PATCH v2 09/20] block drivers: expose requirement for write same alignment from formats Paolo Bonzini
2013-11-19 17:07 ` [Qemu-devel] [PATCH v2 10/20] block/iscsi: remove .bdrv_has_zero_init Paolo Bonzini
2013-11-19 17:07 ` [Qemu-devel] [PATCH v2 11/20] block/iscsi: updated copyright Paolo Bonzini
2013-11-19 17:07 ` [Qemu-devel] [PATCH v2 12/20] block/iscsi: check WRITE SAME support differently depending on MAY_UNMAP Paolo Bonzini
2013-11-19 17:07 ` [Qemu-devel] [PATCH v2 13/20] block/iscsi: use UNMAP to write zeroes if LBPRZ=1 Paolo Bonzini
2013-11-21 11:43 ` Peter Lieven
2013-11-21 11:49 ` Paolo Bonzini
2013-11-21 11:54 ` Peter Lieven
2013-11-21 12:05 ` Paolo Bonzini
2013-11-19 17:07 ` [Qemu-devel] [PATCH v2 14/20] raw-posix: implement write_zeroes with MAY_UNMAP for files Paolo Bonzini
2013-11-19 17:07 ` [Qemu-devel] [PATCH v2 15/20] raw-posix: implement write_zeroes with MAY_UNMAP for block devices Paolo Bonzini
2013-11-19 17:07 ` [Qemu-devel] [PATCH v2 16/20] raw-posix: add support for write_zeroes on XFS and " Paolo Bonzini
2013-11-19 17:07 ` [Qemu-devel] [PATCH v2 17/20] qemu-iotests: 033 is fast Paolo Bonzini
2013-11-19 17:07 ` [Qemu-devel] [PATCH v2 18/20] scsi-disk: catch write protection errors in UNMAP Paolo Bonzini
2013-11-19 17:07 ` [Qemu-devel] [PATCH v2 19/20] scsi-disk: reject ANCHOR=1 for UNMAP and WRITE SAME commands Paolo Bonzini
2013-11-19 17:07 ` [Qemu-devel] [PATCH v2 20/20] scsi-disk: correctly implement WRITE SAME Paolo Bonzini
2013-11-19 17:23 ` ronnie sahlberg
2013-11-19 17:27 ` ronnie sahlberg
2013-11-19 17:31 ` Paolo Bonzini
2013-11-20 14:18 ` Stefan Hajnoczi
2013-11-20 14:19 ` Paolo Bonzini
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=528C969A.1090704@redhat.com \
--to=pbonzini@redhat.com \
--cc=kwolf@redhat.com \
--cc=pl@kamp.de \
--cc=qemu-devel@nongnu.org \
--cc=stefanha@gmail.com \
--cc=stefanha@redhat.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;
as well as URLs for NNTP newsgroup(s).