From: Stefan Hajnoczi <stefanha@redhat.com>
To: qemu-devel@nongnu.org
Cc: Peter Maydell <peter.maydell@linaro.org>,
Peter Lieven <pl@kamp.de>, Stefan Hajnoczi <stefanha@redhat.com>,
Paolo Bonzini <pbonzini@redhat.com>
Subject: [Qemu-devel] [PULL 19/26] coroutine: try harder not to delete coroutines
Date: Fri, 9 Jan 2015 10:16:59 +0000 [thread overview]
Message-ID: <1420798626-11428-20-git-send-email-stefanha@redhat.com> (raw)
In-Reply-To: <1420798626-11428-1-git-send-email-stefanha@redhat.com>
From: Peter Lieven <pl@kamp.de>
Placing coroutines on the global pool should be preferrable, because it
can help all threads. But if the global pool is full, we can still
try to save some allocations by stashing completed coroutines on the
local pool. This is quite cheap too, because it does not require
atomic operations, and provides a gain of 15% in the best case.
Signed-off-by: Peter Lieven <pl@kamp.de>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
Message-id: 1417518350-6167-8-git-send-email-pbonzini@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
qemu-coroutine.c | 9 ++++++++-
1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/qemu-coroutine.c b/qemu-coroutine.c
index da1b961..525247b 100644
--- a/qemu-coroutine.c
+++ b/qemu-coroutine.c
@@ -27,6 +27,7 @@ enum {
static QSLIST_HEAD(, Coroutine) release_pool = QSLIST_HEAD_INITIALIZER(pool);
static unsigned int release_pool_size;
static __thread QSLIST_HEAD(, Coroutine) alloc_pool = QSLIST_HEAD_INITIALIZER(pool);
+static __thread unsigned int alloc_pool_size;
static __thread Notifier coroutine_pool_cleanup_notifier;
static void coroutine_pool_cleanup(Notifier *n, void *value)
@@ -58,13 +59,14 @@ Coroutine *qemu_coroutine_create(CoroutineEntry *entry)
* release_pool_size and the actual size of release_pool. But
* it is just a heuristic, it does not need to be perfect.
*/
- release_pool_size = 0;
+ alloc_pool_size = atomic_xchg(&release_pool_size, 0);
QSLIST_MOVE_ATOMIC(&alloc_pool, &release_pool);
co = QSLIST_FIRST(&alloc_pool);
}
}
if (co) {
QSLIST_REMOVE_HEAD(&alloc_pool, pool_next);
+ alloc_pool_size--;
}
}
@@ -87,6 +89,11 @@ static void coroutine_delete(Coroutine *co)
atomic_inc(&release_pool_size);
return;
}
+ if (alloc_pool_size < POOL_BATCH_SIZE) {
+ QSLIST_INSERT_HEAD(&alloc_pool, co, pool_next);
+ alloc_pool_size++;
+ return;
+ }
}
qemu_coroutine_delete(co);
--
2.1.0
next prev parent reply other threads:[~2015-01-09 10:18 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-01-09 10:16 [Qemu-devel] [PULL 00/26] Block patches Stefan Hajnoczi
2015-01-09 10:16 ` [Qemu-devel] [PULL 01/26] libqos: Convert malloc-pc allocator to a generic allocator Stefan Hajnoczi
2015-01-09 10:16 ` [Qemu-devel] [PULL 02/26] libqos: Change use of pointers to uint64_t in virtio Stefan Hajnoczi
2015-01-09 10:16 ` [Qemu-devel] [PULL 03/26] tests: Prepare virtio-blk-test for multi-arch implementation Stefan Hajnoczi
2015-01-09 10:16 ` [Qemu-devel] [PULL 04/26] libqos: Remove PCI assumptions in constants of virtio driver Stefan Hajnoczi
2015-01-09 10:16 ` [Qemu-devel] [PULL 05/26] libqos: Add malloc generic Stefan Hajnoczi
2015-01-09 10:16 ` [Qemu-devel] [PULL 06/26] libqos: Add virtio MMIO support Stefan Hajnoczi
2015-01-09 10:16 ` [Qemu-devel] [PULL 07/26] block/raw-posix.c: Fixes raw_getlength() on Mac OS X so that it reports the correct length of a real CD Stefan Hajnoczi
2015-01-09 10:16 ` [Qemu-devel] [PULL 08/26] .gitignore: Ignore generated "common.env" Stefan Hajnoczi
2015-01-09 10:16 ` [Qemu-devel] [PULL 09/26] qemu-iotests: Replace "/bin/true" with "true" Stefan Hajnoczi
2015-01-09 10:16 ` [Qemu-devel] [PULL 10/26] qemu-iotests: Add "_supported_os Linux" to 058 Stefan Hajnoczi
2015-01-09 10:16 ` [Qemu-devel] [PULL 11/26] tests/Makefile: Add check-block to make check on Linux Stefan Hajnoczi
2015-01-09 10:16 ` [Qemu-devel] [PULL 12/26] qemu-iotests: Add supported os parameter for python tests Stefan Hajnoczi
2015-01-09 10:16 ` [Qemu-devel] [PULL 13/26] coroutine-ucontext: use __thread Stefan Hajnoczi
2015-01-09 10:16 ` [Qemu-devel] [PULL 14/26] qemu-thread: add per-thread atexit functions Stefan Hajnoczi
2015-01-09 10:16 ` [Qemu-devel] [PULL 15/26] test-coroutine: avoid overflow on 32-bit systems Stefan Hajnoczi
2015-01-09 10:16 ` [Qemu-devel] [PULL 16/26] QSLIST: add lock-free operations Stefan Hajnoczi
2015-01-09 10:16 ` [Qemu-devel] [PULL 17/26] coroutine: rewrite pool to avoid mutex Stefan Hajnoczi
2015-01-09 10:16 ` [Qemu-devel] [PULL 18/26] coroutine: drop qemu_coroutine_adjust_pool_size Stefan Hajnoczi
2015-01-09 10:16 ` Stefan Hajnoczi [this message]
2015-01-09 10:17 ` [Qemu-devel] [PULL 20/26] block: limited request size in write zeroes unsupported path Stefan Hajnoczi
2015-01-09 10:17 ` [Qemu-devel] [PULL 21/26] block: Split BLOCK_OP_TYPE_COMMIT to BLOCK_OP_TYPE_COMMIT_{SOURCE, TARGET} Stefan Hajnoczi
2015-01-09 10:17 ` [Qemu-devel] [PULL 22/26] ide: Implement VPD response for ATAPI Stefan Hajnoczi
2015-01-09 10:17 ` [Qemu-devel] [PULL 23/26] nvme: Fix get/set number of queues feature Stefan Hajnoczi
2015-01-09 10:17 ` [Qemu-devel] [PULL 24/26] MAINTAINERS: Update email addresses for Chrysostomos Nanakos Stefan Hajnoczi
2015-01-09 10:17 ` [Qemu-devel] [PULL 25/26] MAINTAINERS: Add migration/block* to block subsystem Stefan Hajnoczi
2015-01-09 10:17 ` [Qemu-devel] [PULL 26/26] NVMe: Set correct VS Value for 1.1 Compliant Controllers Stefan Hajnoczi
2015-01-10 19:05 ` [Qemu-devel] [PULL 00/26] Block patches Peter Maydell
2015-01-10 19:10 ` Peter Maydell
2015-01-12 9:52 ` Fam Zheng
2015-01-12 10:32 ` Paolo Bonzini
2015-01-12 14:25 ` Stefan Hajnoczi
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=1420798626-11428-20-git-send-email-stefanha@redhat.com \
--to=stefanha@redhat.com \
--cc=pbonzini@redhat.com \
--cc=peter.maydell@linaro.org \
--cc=pl@kamp.de \
--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).