From: Kevin Wolf <kwolf@redhat.com>
To: anthony@codemonkey.ws
Cc: kwolf@redhat.com, qemu-devel@nongnu.org
Subject: [Qemu-devel] [PATCH 08/26] aio: use g_slice_alloc() for AIOCB pooling
Date: Wed, 14 Nov 2012 19:47:09 +0100 [thread overview]
Message-ID: <1352918847-3696-9-git-send-email-kwolf@redhat.com> (raw)
In-Reply-To: <1352918847-3696-1-git-send-email-kwolf@redhat.com>
From: Stefan Hajnoczi <stefanha@redhat.com>
AIO control blocks are frequently acquired and released because each aio
request involves at least one AIOCB. Therefore, we pool them to avoid
heap allocation overhead.
The problem with the freelist approach in AIOPool is thread-safety. If
we want BlockDriverStates to associate with AioContexts that execute in
multiple threads, then a global freelist becomes a problem.
This patch drops the freelist and instead uses g_slice_alloc() which is
tuned for per-thread fixed-size object pools. qemu_aio_get() and
qemu_aio_release() are now thread-safe.
Note that the change from g_malloc0() to g_slice_alloc() should be safe
since the freelist reuse case doesn't zero the AIOCB either.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
block.c | 15 ++++-----------
qemu-aio.h | 2 --
2 files changed, 4 insertions(+), 13 deletions(-)
diff --git a/block.c b/block.c
index da1fdca..ea0f7d8 100644
--- a/block.c
+++ b/block.c
@@ -3909,13 +3909,8 @@ void *qemu_aio_get(AIOPool *pool, BlockDriverState *bs,
{
BlockDriverAIOCB *acb;
- if (pool->free_aiocb) {
- acb = pool->free_aiocb;
- pool->free_aiocb = acb->next;
- } else {
- acb = g_malloc0(pool->aiocb_size);
- acb->pool = pool;
- }
+ acb = g_slice_alloc(pool->aiocb_size);
+ acb->pool = pool;
acb->bs = bs;
acb->cb = cb;
acb->opaque = opaque;
@@ -3924,10 +3919,8 @@ void *qemu_aio_get(AIOPool *pool, BlockDriverState *bs,
void qemu_aio_release(void *p)
{
- BlockDriverAIOCB *acb = (BlockDriverAIOCB *)p;
- AIOPool *pool = acb->pool;
- acb->next = pool->free_aiocb;
- pool->free_aiocb = acb;
+ BlockDriverAIOCB *acb = p;
+ g_slice_free1(acb->pool->aiocb_size, acb);
}
/**************************************************************/
diff --git a/qemu-aio.h b/qemu-aio.h
index 111b0b3..b29c509 100644
--- a/qemu-aio.h
+++ b/qemu-aio.h
@@ -24,7 +24,6 @@ typedef void BlockDriverCompletionFunc(void *opaque, int ret);
typedef struct AIOPool {
void (*cancel)(BlockDriverAIOCB *acb);
size_t aiocb_size;
- BlockDriverAIOCB *free_aiocb;
} AIOPool;
struct BlockDriverAIOCB {
@@ -32,7 +31,6 @@ struct BlockDriverAIOCB {
BlockDriverState *bs;
BlockDriverCompletionFunc *cb;
void *opaque;
- BlockDriverAIOCB *next;
};
void *qemu_aio_get(AIOPool *pool, BlockDriverState *bs,
--
1.7.6.5
next prev parent reply other threads:[~2012-11-14 18:47 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-11-14 18:47 [Qemu-devel] [PULL 00/26] Block patches Kevin Wolf
2012-11-14 18:47 ` [Qemu-devel] [PATCH 01/26] qemu: Document GlusterFS block driver usage Kevin Wolf
2012-11-14 18:47 ` [Qemu-devel] [PATCH 02/26] qcow2: Fix refcount table size calculation Kevin Wolf
2012-11-14 18:47 ` [Qemu-devel] [PATCH 03/26] qemu-iotests: qcow2: Test growing large refcount table Kevin Wolf
2012-11-14 18:47 ` [Qemu-devel] [PATCH 04/26] MAINTAINERS: add Stefan Hajnoczi as block and virtio-blk co-maintainer Kevin Wolf
2012-11-14 18:47 ` [Qemu-devel] [PATCH 05/26] block: Workaround for older versions of MinGW gcc Kevin Wolf
2012-11-14 18:47 ` [Qemu-devel] [PATCH 06/26] tests: allow qemu-iotests to be run against nbd backend Kevin Wolf
2012-11-14 18:47 ` [Qemu-devel] [PATCH 07/26] aio: switch aiocb_size type int -> size_t Kevin Wolf
2012-11-14 18:47 ` Kevin Wolf [this message]
2012-11-14 18:47 ` [Qemu-devel] [PATCH 09/26] aio: rename AIOPool to AIOCBInfo Kevin Wolf
2012-11-14 18:47 ` [Qemu-devel] [PATCH 10/26] fdc: Remove status0 parameter from fdctrl_set_fifo() Kevin Wolf
2012-11-14 18:47 ` [Qemu-devel] [PATCH 11/26] fdc-test: split test_media_change() test, so insert part can be reused Kevin Wolf
2012-11-14 18:47 ` [Qemu-devel] [PATCH 12/26] fdc-test: insert media before fuzzing registers Kevin Wolf
2012-11-14 18:47 ` [Qemu-devel] [PATCH 13/26] fdc-test: add tests for non-DMA READ command Kevin Wolf
2012-11-14 18:47 ` [Qemu-devel] [PATCH 14/26] fdc: use status0 field instead of a local variable Kevin Wolf
2012-11-14 18:47 ` [Qemu-devel] [PATCH 15/26] fdc: fix FD_SR0_SEEK for non-DMA transfers and multi sectors transfers Kevin Wolf
2012-11-14 18:47 ` [Qemu-devel] [PATCH 16/26] fdc: fix FD_SR0_SEEK for initial seek on DMA transfers Kevin Wolf
2012-11-14 18:47 ` [Qemu-devel] [PATCH 17/26] fdc: fix false FD_SR0_SEEK Kevin Wolf
2012-11-14 18:47 ` [Qemu-devel] [PATCH 18/26] fdc-test: Check READ ID Kevin Wolf
2012-11-14 18:47 ` [Qemu-devel] [PATCH 19/26] fdc: implement VERIFY command Kevin Wolf
2012-11-14 18:47 ` [Qemu-devel] [PATCH 20/26] fdc-tests: add tests for " Kevin Wolf
2012-11-14 18:47 ` [Qemu-devel] [PATCH 21/26] fdc: remove double affectation of FD_MSR_CMDBUSY flag Kevin Wolf
2012-11-14 18:47 ` [Qemu-devel] [PATCH 22/26] fdc: fix typo in zero constant Kevin Wolf
2012-11-14 18:47 ` [Qemu-devel] [PATCH 23/26] fdc: remove last usage of FD_STATE_SEEK Kevin Wolf
2012-11-14 18:47 ` [Qemu-devel] [PATCH 24/26] vmdk: Fix data corruption bug in WRITE and READ handling Kevin Wolf
2012-11-14 18:47 ` [Qemu-devel] [PATCH 25/26] megasas: Use bdrv_drain_all instead of qemu_aio_flush Kevin Wolf
2012-11-14 18:47 ` [Qemu-devel] [PATCH 26/26] qemu-io: " Kevin Wolf
2012-11-19 9:12 ` [Qemu-devel] [PULL 00/26] Block patches Kevin Wolf
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=1352918847-3696-9-git-send-email-kwolf@redhat.com \
--to=kwolf@redhat.com \
--cc=anthony@codemonkey.ws \
--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).