From: Leonid Bloch <lbloch@janustech.com>
To: qemu-devel@nongnu.org
Cc: qemu-block@nongnu.org, Kevin Wolf <kwolf@redhat.com>,
Max Reitz <mreitz@redhat.com>, Eric Blake <eblake@redhat.com>,
Alberto Garcia <berto@igalia.com>,
Leonid Bloch <lbloch@janustech.com>
Subject: [Qemu-devel] [PATCH v4 0/5] qcow2: Take the image size into account when allocating the L2 cache
Date: Thu, 9 Aug 2018 01:11:33 +0300 [thread overview]
Message-ID: <20180808221138.5770-1-lbloch@janustech.com> (raw)
This series makes the qcow2 L2 cache assignment aware of the image size,
with the intention for it to cover the entire image. The importance of
this change is in noticeable performance improvement, especially with
heavy random I/O. The memory overhead is not big in most cases, as only
1 MB of cache for every 8 GB of image size is used. For cases with very
large images and/or small cluster sizes, or systems with limited RAM
resources, there is an upper limit on the default L2 cache: 32 MB. To
modify this limit one can use the already existing 'l2-cache-size' and
'cache-size' options. Moreover, this fixes the behavior of 'l2-cache-size',
as it was documented as the *maximum* L2 cache size, but in practice
behaved as the absolute size.
To compensate the memory overhead which may be increased following this
behavior, the default cache-clean-interval is set to 10 minutes by default
(was disabled by default before).
The L2 cache is also resized accordingly, by default, if the image is
resized.
Additionally, few minor changes are made (refactoring and documentation
fixes).
Differences from v1:
* .gitignore modification patch removed (unneeded).
* The grammar fix in conflicting cache sizing patch removed (merged).
* The update total_sectors when resizing patch squashed with the
resizing patch.
* L2 cache is now capped at 32 MB.
* The default cache-clean-interval is set to 30 seconds.
Differences from v2:
* Made it clear in the documentation that setting cache-clean-interval
to 0 disables this feature.
Differences from v3:
* The default cache-clean-interval is set to 10 minutes instead of 30
seconds before.
* Commit message changes to better explain the patches.
* Some refactoring.
Leonid Bloch (5):
qcow2: Options' documentation fixes
qcow2: Assign the L2 cache relatively to image size
qcow2: Resize the cache upon image resizing
qcow2: Set the default cache-clean-interval to 10 minutes
qcow2: Explicit number replaced by a constant
block/qcow2.c | 49 ++++++++++++++++++++------------------
block/qcow2.h | 5 ++--
docs/qcow2-cache.txt | 31 ++++++++++++++----------
qapi/block-core.json | 3 ++-
qemu-options.hx | 11 +++++----
tests/qemu-iotests/137 | 1 -
tests/qemu-iotests/137.out | 1 -
7 files changed, 56 insertions(+), 45 deletions(-)
--
2.17.1
next reply other threads:[~2018-08-08 22:12 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-08-08 22:11 Leonid Bloch [this message]
2018-08-08 22:11 ` [Qemu-devel] [PATCH v4 1/5] qcow2: Options' documentation fixes Leonid Bloch
2018-08-09 9:00 ` Alberto Garcia
2018-08-09 9:04 ` Leonid Bloch
2018-08-08 22:11 ` [Qemu-devel] [PATCH v4 2/5] qcow2: Assign the L2 cache relatively to image size Leonid Bloch
2018-08-09 12:14 ` Alberto Garcia
2018-08-09 14:04 ` Leonid Bloch
2018-08-09 15:31 ` Alberto Garcia
2018-08-09 16:46 ` Leonid Bloch
2018-08-09 17:37 ` Eric Blake
2018-08-09 21:51 ` Leonid Bloch
2018-08-08 22:11 ` [Qemu-devel] [PATCH v4 3/5] qcow2: Resize the cache upon image resizing Leonid Bloch
2018-08-09 8:55 ` Alberto Garcia
2018-08-08 22:11 ` [Qemu-devel] [PATCH v4 4/5] qcow2: Set the default cache-clean-interval to 10 minutes Leonid Bloch
2018-08-09 9:33 ` Alberto Garcia
2018-08-09 10:52 ` Leonid Bloch
2018-08-09 10:58 ` Alberto Garcia
2018-08-08 22:11 ` [Qemu-devel] [PATCH v4 5/5] qcow2: Explicit number replaced by a constant Leonid Bloch
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=20180808221138.5770-1-lbloch@janustech.com \
--to=lbloch@janustech.com \
--cc=berto@igalia.com \
--cc=eblake@redhat.com \
--cc=kwolf@redhat.com \
--cc=mreitz@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.