OpenVZ / Virtuozzo kernel development (devel@openvz.org)
 help / color / mirror / Atom feed
From: Konstantin Khorenko <khorenko@virtuozzo.com>
Subject: [Devel] [PATCH RHEL10 COMMIT] dm-qcow2: scan lower delta in one pass over empty L1 entry
Date: Tue, 25 Aug 2026 12:41:56 +0200	[thread overview]
Message-ID: <202608251041.67PAfugu774831@f0.sw.ru> (raw)
In-Reply-To: <20260819000745.28823-6-andrey.zhadchenko@virtuozzo.com>

The commit is pushed to "branch-rh10-6.12.0-211.39.1.16.x.vz10-ovz" and will appear at git at bitbucket.org:openvz/vzkernel.git
after rh10-6.12.0-211.39.1.16.9.vz10
------>
commit 7af917e3954e3085a2c0aed3d3d6cf9db7797cf8
Author: Andrey Zhadchenko <andrey.zhadchenko@virtuozzo.com>
Date:   Wed Aug 19 03:07:43 2026 +0300

    dm-qcow2: scan lower delta in one pass over empty L1 entry
    
    When an L1 entry is absent and there is a backing image, the seek
    code descends into the lower delta one cluster at a time.
    
    Change advance_and_spawn_lower_seek_qio() to take limit instead of
    a size. Pass bigger range if L1 entry is empty.
    
    On a 16G image (128K clusters, extended L2) with no L1 entries over a
    backing image with data at 15G, warm-cache SEEK_DATA improves from
    40.2 ms to 0.01 ms.
    
    https://virtuozzo.atlassian.net/browse/VSTOR-139407
    Feature: dm-qcow2: block device over QCOW2 files driver
    Signed-off-by: Andrey Zhadchenko <andrey.zhadchenko@virtuozzo.com>
    Reviewed-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
    Reviewed-by: Vasileios Almpanis <vasileios.almpanis@virtuozzo.com>
---
 drivers/md/dm-qcow2-map.c | 29 +++++++++++++++--------------
 1 file changed, 15 insertions(+), 14 deletions(-)

diff --git a/drivers/md/dm-qcow2-map.c b/drivers/md/dm-qcow2-map.c
index 43188ceebc9af..879d2f1827006 100644
--- a/drivers/md/dm-qcow2-map.c
+++ b/drivers/md/dm-qcow2-map.c
@@ -4439,26 +4439,19 @@ static inline void seek_qio_next_clu(struct qio *qio, struct qcow2_map *map)
 	seek_qio_set_sector(qio, bi_sector);
 }
 
-static struct qio *advance_and_spawn_lower_seek_qio(struct qio *old_qio, u32 size)
+static struct qio *advance_and_spawn_lower_seek_qio(struct qio *old_qio, loff_t end)
 {
+	struct qcow2 *lower = old_qio->qcow2->lower;
 	struct qio *new_qio;
-	loff_t start;
 
-	start = to_bytes(old_qio->bi_iter.bi_sector);
+	if (end > lower->hdr.size)
+		end = lower->hdr.size;
 
-	if (start + size > old_qio->qcow2->lower->hdr.size)
-		size = old_qio->qcow2->lower->hdr.size - start;
-
-	new_qio = alloc_seek_qio(old_qio->qcow2->lower, old_qio, start + size);
+	new_qio = alloc_seek_qio(lower, old_qio, end);
 	if (!new_qio)
 		return NULL;
 
-	if (old_qio->bi_iter.bi_size == size) {
-		seek_qio_next_clu(old_qio, NULL);
-	} else {
-		old_qio->bi_iter.bi_sector += to_sector(size);
-		old_qio->bi_iter.bi_size -= size;
-	}
+	seek_qio_set_sector(old_qio, to_sector(end));
 
 	return new_qio;
 }
@@ -4506,8 +4499,16 @@ static int qcow2_llseek_hole_qio(struct qio *qio, int whence, loff_t *result)
 			 */
 			if (to_bytes(qio->bi_iter.bi_sector) < qio->qcow2->lower->hdr.size) {
 				struct qio *new_qio;
+				loff_t end;
+
+				if (!(map.level & L2_LEVEL))
+					end = min_t(loff_t,
+						    to_bytes(get_next_l2(qio)),
+						    SEEK_QIO_DATA(qio)->lim);
+				else
+					end = to_bytes(qio->bi_iter.bi_sector) + size;
 
-				new_qio = advance_and_spawn_lower_seek_qio(qio, size);
+				new_qio = advance_and_spawn_lower_seek_qio(qio, end);
 				if (!new_qio) {
 					ret = -ENOMEM;
 					break;

  reply	other threads:[~2026-08-25 10:41 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-08-19  0:07 [Devel] [PATCH VZ10 v2 0/7] dm-qcow: lseek improvements Andrey Zhadchenko
2026-08-19  0:07 ` [Devel] [PATCH VZ10 v2 1/7] drivers/md/dm-qcow2: fix lower delta seek window clamp Andrey Zhadchenko
2026-08-25 10:41   ` [Devel] [PATCH RHEL10 COMMIT] dm-qcow2: " Konstantin Khorenko
2026-08-19  0:07 ` [Devel] [PATCH VZ10 v2 2/7] drivers/md/dm-qcow2: keep seek parse window within limit Andrey Zhadchenko
2026-08-25 10:41   ` [Devel] [PATCH RHEL10 COMMIT] dm-qcow2: " Konstantin Khorenko
2026-08-19  0:07 ` [Devel] [PATCH VZ10 v2 3/7] drivers/md/dm-qcow2: fix seek constant comparison Andrey Zhadchenko
2026-08-25 10:41   ` [Devel] [PATCH RHEL10 COMMIT] dm-qcow2: " Konstantin Khorenko
2026-08-19  0:07 ` [Devel] [PATCH VZ10 v2 4/7] drivers/md/dm-qcow2: fix seek skip to the next L2 table Andrey Zhadchenko
2026-08-25 10:41   ` [Devel] [PATCH RHEL10 COMMIT] dm-qcow2: " Konstantin Khorenko
2026-08-19  0:07 ` [Devel] [PATCH VZ10 v2 5/7] drivers/md/dm-qcow2: scan lower delta in one pass over empty L1 entry Andrey Zhadchenko
2026-08-25 10:41   ` Konstantin Khorenko [this message]
2026-08-19  0:07 ` [Devel] [PATCH VZ10 v2 6/7] drivers/md/dm-qcow2: seek unallocated L2 entries in one pass within md Andrey Zhadchenko
2026-08-25 10:41   ` [Devel] [PATCH RHEL10 COMMIT] dm-qcow2: " Konstantin Khorenko
2026-08-19  0:07 ` [Devel] [PATCH VZ10 v2 7/7] drivers/md/dm-qcow2: forbid unaligned virtual size for images Andrey Zhadchenko
2026-08-25 10:41   ` [Devel] [PATCH RHEL10 COMMIT] dm-qcow2: " Konstantin Khorenko
2026-08-19  8:54 ` [Devel] [PATCH VZ10 v2 0/7] dm-qcow: lseek improvements Vasileios Almpanis
2026-08-24 14:38 ` Pavel Tikhomirov

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=202608251041.67PAfugu774831@f0.sw.ru \
    --to=khorenko@virtuozzo.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