From: Kevin Wolf <kwolf@redhat.com>
To: qemu-block@nongnu.org
Cc: kwolf@redhat.com, qemu-devel@nongnu.org
Subject: [Qemu-devel] [PULL 06/31] iscsi: Use block size as minimum zero/discard alignment
Date: Wed, 8 Jun 2016 11:16:32 +0200 [thread overview]
Message-ID: <1465377417-5012-7-git-send-email-kwolf@redhat.com> (raw)
In-Reply-To: <1465377417-5012-1-git-send-email-kwolf@redhat.com>
From: Eric Blake <eblake@redhat.com>
If hardware does not advertise a minimum zero/discard
alignment, we still want to guarantee that the block layer
will align requests to our blocks, rather than the arbitrary
512-byte BDRV sector size.
Signed-off-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
block/iscsi.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/block/iscsi.c b/block/iscsi.c
index e7d5f7b..94f9974 100644
--- a/block/iscsi.c
+++ b/block/iscsi.c
@@ -1711,6 +1711,8 @@ static void iscsi_refresh_limits(BlockDriverState *bs, Error **errp)
}
bs->bl.discard_alignment =
sector_limits_lun2qemu(iscsilun->bl.opt_unmap_gran, iscsilun);
+ } else {
+ bs->bl.discard_alignment = iscsilun->block_size >> BDRV_SECTOR_BITS;
}
if (iscsilun->bl.max_ws_len < 0xffffffff) {
@@ -1720,6 +1722,9 @@ static void iscsi_refresh_limits(BlockDriverState *bs, Error **errp)
if (iscsilun->lbp.lbpws) {
bs->bl.write_zeroes_alignment =
sector_limits_lun2qemu(iscsilun->bl.opt_unmap_gran, iscsilun);
+ } else {
+ bs->bl.write_zeroes_alignment =
+ iscsilun->block_size >> BDRV_SECTOR_BITS;
}
bs->bl.opt_transfer_length =
sector_limits_lun2qemu(iscsilun->bl.opt_xfer_len, iscsilun);
--
1.8.3.1
next prev parent reply other threads:[~2016-06-08 9:17 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-06-08 9:16 [Qemu-devel] [PULL 00/31] Block layer patches Kevin Wolf
2016-06-08 9:16 ` [Qemu-devel] [PULL 01/31] block: split write_zeroes always Kevin Wolf
2016-06-08 9:16 ` [Qemu-devel] [PULL 02/31] qcow2: simplify logic in qcow2_co_write_zeroes Kevin Wolf
2016-06-08 9:16 ` [Qemu-devel] [PULL 03/31] qcow2: add tracepoints for qcow2_co_write_zeroes Kevin Wolf
2016-06-08 9:16 ` [Qemu-devel] [PULL 04/31] qemu-iotests: Test one more spot for optimizing write_zeroes Kevin Wolf
2016-06-08 9:16 ` [Qemu-devel] [PULL 05/31] qcow2: Catch more unaligned write_zero into zero cluster Kevin Wolf
2016-06-08 9:16 ` Kevin Wolf [this message]
2016-06-08 9:16 ` [Qemu-devel] [PULL 07/31] block: Track write zero limits in bytes Kevin Wolf
2016-06-08 9:16 ` [Qemu-devel] [PULL 08/31] block: Add .bdrv_co_pwrite_zeroes() Kevin Wolf
2016-06-08 9:16 ` [Qemu-devel] [PULL 09/31] block: Switch bdrv_write_zeroes() to byte interface Kevin Wolf
2016-06-08 9:16 ` [Qemu-devel] [PULL 10/31] iscsi: Convert to bdrv_co_pwrite_zeroes() Kevin Wolf
2016-06-08 9:16 ` [Qemu-devel] [PULL 11/31] qcow2: " Kevin Wolf
2016-06-08 9:16 ` [Qemu-devel] [PULL 12/31] blkreplay: " Kevin Wolf
2016-06-08 9:16 ` [Qemu-devel] [PULL 13/31] gluster: " Kevin Wolf
2016-06-08 9:16 ` [Qemu-devel] [PULL 14/31] qed: " Kevin Wolf
2016-06-08 9:16 ` [Qemu-devel] [PULL 15/31] raw-posix: " Kevin Wolf
2016-06-08 9:16 ` [Qemu-devel] [PULL 16/31] raw_bsd: " Kevin Wolf
2016-06-08 9:16 ` [Qemu-devel] [PULL 17/31] vmdk: " Kevin Wolf
2016-06-08 9:16 ` [Qemu-devel] [PULL 18/31] block: Kill bdrv_co_write_zeroes() Kevin Wolf
2016-06-08 9:16 ` [Qemu-devel] [PULL 19/31] migration/block: Convert load to BlockBackend Kevin Wolf
2016-06-08 9:16 ` [Qemu-devel] [PULL 20/31] migration/block: Convert saving " Kevin Wolf
2016-06-08 9:16 ` [Qemu-devel] [PULL 21/31] block: assert that bs->request_alignment is a power of 2 Kevin Wolf
2016-06-08 9:16 ` [Qemu-devel] [PULL 22/31] raw-posix: Fetch max sectors for host block device Kevin Wolf
2016-06-08 9:16 ` [Qemu-devel] [PULL 23/31] qcow2: avoid extra flushes in qcow2 Kevin Wolf
2016-06-08 9:16 ` [Qemu-devel] [PULL 24/31] block: Fix bdrv_all_delete_snapshot() error handling Kevin Wolf
2016-06-08 9:16 ` [Qemu-devel] [PULL 25/31] blockdev: clean up error handling in do_open_tray Kevin Wolf
2016-06-08 9:16 ` [Qemu-devel] [PULL 26/31] block: Don't emulate natively supported pwritev flags Kevin Wolf
2016-06-08 9:16 ` [Qemu-devel] [PULL 27/31] qemu-img bench Kevin Wolf
2016-06-08 9:16 ` [Qemu-devel] [PULL 28/31] qemu-img bench: Sequential writes Kevin Wolf
2016-06-08 9:16 ` [Qemu-devel] [PULL 29/31] qemu-img bench: Make start offset configurable Kevin Wolf
2016-06-08 9:16 ` [Qemu-devel] [PULL 30/31] qemu-img bench: Implement -S (step size) Kevin Wolf
2016-06-08 9:16 ` [Qemu-devel] [PULL 31/31] qemu-img bench: Add --flush-interval Kevin Wolf
2016-06-08 17:27 ` [Qemu-devel] [PULL 00/31] Block layer patches Peter Maydell
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=1465377417-5012-7-git-send-email-kwolf@redhat.com \
--to=kwolf@redhat.com \
--cc=qemu-block@nongnu.org \
--cc=qemu-devel@nongnu.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).