[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-devel] [PULL 17/26] coroutine: rewrite pool to avoid mutex
From: |
Stefan Hajnoczi |
Subject: |
[Qemu-devel] [PULL 17/26] coroutine: rewrite pool to avoid mutex |
Date: |
Fri, 9 Jan 2015 10:16:57 +0000 |
From: Paolo Bonzini <address@hidden>
This patch removes the mutex by using fancy lock-free manipulation of
the pool. Lock-free stacks and queues are not hard, but they can suffer
from the ABA problem so they are better avoided unless you have some
deferred reclamation scheme like RCU. Otherwise you have to stick
with adding to a list, and emptying it completely. This is what this
patch does, by coupling a lock-free global list of available coroutines
with per-CPU lists that are actually used on coroutine creation.
Whenever the destruction pool is big enough, the next thread that runs
out of coroutines will steal the whole destruction pool. This is positive
in two ways:
1) the allocation does not have to do any atomic operation in the fast
path, it's entirely using thread-local storage. Once every POOL_BATCH_SIZE
allocations it will do a single atomic_xchg. Release does an atomic_cmpxchg
loop, that hopefully doesn't cause any starvation, and an atomic_inc.
A later patch will also remove atomic operations from the release path,
and try to avoid the atomic_xchg altogether---succeeding in doing so if
all devices either use ioeventfd or are not submitting requests actively.
2) in theory this should be completely adaptive. The number of coroutines
around should be a little more than POOL_BATCH_SIZE * number of allocating
threads; so this also empties qemu_coroutine_adjust_pool_size. (The previous
pool size was POOL_BATCH_SIZE * number of block backends, so it was a bit
more generous. But if you actually have many high-iodepth disks, it's better
to put them in different iothreads, which will also use separate thread
pools and aio=native file descriptors).
This speeds up perf/cost (in tests/test-coroutine) by a factor of ~1.33.
No matter if we end with some kind of coroutine bypass scheme or not,
it cannot hurt to optimize hot code.
Signed-off-by: Paolo Bonzini <address@hidden>
Reviewed-by: Fam Zheng <address@hidden>
Message-id: address@hidden
Signed-off-by: Stefan Hajnoczi <address@hidden>
---
qemu-coroutine.c | 92 +++++++++++++++++++++++++-------------------------------
1 file changed, 41 insertions(+), 51 deletions(-)
diff --git a/qemu-coroutine.c b/qemu-coroutine.c
index bd574aa..93fddc7 100644
--- a/qemu-coroutine.c
+++ b/qemu-coroutine.c
@@ -15,31 +15,57 @@
#include "trace.h"
#include "qemu-common.h"
#include "qemu/thread.h"
+#include "qemu/atomic.h"
#include "block/coroutine.h"
#include "block/coroutine_int.h"
enum {
- POOL_DEFAULT_SIZE = 64,
+ POOL_BATCH_SIZE = 64,
};
/** Free list to speed up creation */
-static QemuMutex pool_lock;
-static QSLIST_HEAD(, Coroutine) pool = QSLIST_HEAD_INITIALIZER(pool);
-static unsigned int pool_size;
-static unsigned int pool_max_size = POOL_DEFAULT_SIZE;
+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 Notifier coroutine_pool_cleanup_notifier;
+
+static void coroutine_pool_cleanup(Notifier *n, void *value)
+{
+ Coroutine *co;
+ Coroutine *tmp;
+
+ QSLIST_FOREACH_SAFE(co, &alloc_pool, pool_next, tmp) {
+ QSLIST_REMOVE_HEAD(&alloc_pool, pool_next);
+ qemu_coroutine_delete(co);
+ }
+}
Coroutine *qemu_coroutine_create(CoroutineEntry *entry)
{
Coroutine *co = NULL;
if (CONFIG_COROUTINE_POOL) {
- qemu_mutex_lock(&pool_lock);
- co = QSLIST_FIRST(&pool);
+ co = QSLIST_FIRST(&alloc_pool);
+ if (!co) {
+ if (release_pool_size > POOL_BATCH_SIZE) {
+ /* Slow path; a good place to register the destructor, too. */
+ if (!coroutine_pool_cleanup_notifier.notify) {
+ coroutine_pool_cleanup_notifier.notify =
coroutine_pool_cleanup;
+ qemu_thread_atexit_add(&coroutine_pool_cleanup_notifier);
+ }
+
+ /* This is not exact; there could be a little skew between
+ * 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;
+ QSLIST_MOVE_ATOMIC(&alloc_pool, &release_pool);
+ co = QSLIST_FIRST(&alloc_pool);
+ }
+ }
if (co) {
- QSLIST_REMOVE_HEAD(&pool, pool_next);
- pool_size--;
+ QSLIST_REMOVE_HEAD(&alloc_pool, pool_next);
}
- qemu_mutex_unlock(&pool_lock);
}
if (!co) {
@@ -53,39 +79,19 @@ Coroutine *qemu_coroutine_create(CoroutineEntry *entry)
static void coroutine_delete(Coroutine *co)
{
+ co->caller = NULL;
+
if (CONFIG_COROUTINE_POOL) {
- qemu_mutex_lock(&pool_lock);
- if (pool_size < pool_max_size) {
- QSLIST_INSERT_HEAD(&pool, co, pool_next);
- co->caller = NULL;
- pool_size++;
- qemu_mutex_unlock(&pool_lock);
+ if (release_pool_size < POOL_BATCH_SIZE * 2) {
+ QSLIST_INSERT_HEAD_ATOMIC(&release_pool, co, pool_next);
+ atomic_inc(&release_pool_size);
return;
}
- qemu_mutex_unlock(&pool_lock);
}
qemu_coroutine_delete(co);
}
-static void __attribute__((constructor)) coroutine_pool_init(void)
-{
- qemu_mutex_init(&pool_lock);
-}
-
-static void __attribute__((destructor)) coroutine_pool_cleanup(void)
-{
- Coroutine *co;
- Coroutine *tmp;
-
- QSLIST_FOREACH_SAFE(co, &pool, pool_next, tmp) {
- QSLIST_REMOVE_HEAD(&pool, pool_next);
- qemu_coroutine_delete(co);
- }
-
- qemu_mutex_destroy(&pool_lock);
-}
-
static void coroutine_swap(Coroutine *from, Coroutine *to)
{
CoroutineAction ret;
@@ -140,20 +146,4 @@ void coroutine_fn qemu_coroutine_yield(void)
void qemu_coroutine_adjust_pool_size(int n)
{
- qemu_mutex_lock(&pool_lock);
-
- pool_max_size += n;
-
- /* Callers should never take away more than they added */
- assert(pool_max_size >= POOL_DEFAULT_SIZE);
-
- /* Trim oversized pool down to new max */
- while (pool_size > pool_max_size) {
- Coroutine *co = QSLIST_FIRST(&pool);
- QSLIST_REMOVE_HEAD(&pool, pool_next);
- pool_size--;
- qemu_coroutine_delete(co);
- }
-
- qemu_mutex_unlock(&pool_lock);
}
--
2.1.0
- [Qemu-devel] [PULL 09/26] qemu-iotests: Replace "/bin/true" with "true", (continued)
- [Qemu-devel] [PULL 09/26] qemu-iotests: Replace "/bin/true" with "true", Stefan Hajnoczi, 2015/01/09
- [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
- [Qemu-devel] [PULL 10/26] qemu-iotests: Add "_supported_os Linux" to 058, Stefan Hajnoczi, 2015/01/09
- [Qemu-devel] [PULL 08/26] .gitignore: Ignore generated "common.env", Stefan Hajnoczi, 2015/01/09
- [Qemu-devel] [PULL 11/26] tests/Makefile: Add check-block to make check on Linux, Stefan Hajnoczi, 2015/01/09
- [Qemu-devel] [PULL 13/26] coroutine-ucontext: use __thread, Stefan Hajnoczi, 2015/01/09
- [Qemu-devel] [PULL 12/26] qemu-iotests: Add supported os parameter for python tests, Stefan Hajnoczi, 2015/01/09
- [Qemu-devel] [PULL 14/26] qemu-thread: add per-thread atexit functions, Stefan Hajnoczi, 2015/01/09
- [Qemu-devel] [PULL 16/26] QSLIST: add lock-free operations, Stefan Hajnoczi, 2015/01/09
- [Qemu-devel] [PULL 15/26] test-coroutine: avoid overflow on 32-bit systems, Stefan Hajnoczi, 2015/01/09
- [Qemu-devel] [PULL 17/26] coroutine: rewrite pool to avoid mutex,
Stefan Hajnoczi <=
- [Qemu-devel] [PULL 18/26] coroutine: drop qemu_coroutine_adjust_pool_size, Stefan Hajnoczi, 2015/01/09
- [Qemu-devel] [PULL 19/26] coroutine: try harder not to delete coroutines, Stefan Hajnoczi, 2015/01/09
- [Qemu-devel] [PULL 20/26] block: limited request size in write zeroes unsupported path, Stefan Hajnoczi, 2015/01/09
- [Qemu-devel] [PULL 22/26] ide: Implement VPD response for ATAPI, Stefan Hajnoczi, 2015/01/09
- [Qemu-devel] [PULL 21/26] block: Split BLOCK_OP_TYPE_COMMIT to BLOCK_OP_TYPE_COMMIT_{SOURCE, TARGET}, Stefan Hajnoczi, 2015/01/09
- [Qemu-devel] [PULL 23/26] nvme: Fix get/set number of queues feature, Stefan Hajnoczi, 2015/01/09
- [Qemu-devel] [PULL 26/26] NVMe: Set correct VS Value for 1.1 Compliant Controllers, Stefan Hajnoczi, 2015/01/09
- [Qemu-devel] [PULL 25/26] MAINTAINERS: Add migration/block* to block subsystem, Stefan Hajnoczi, 2015/01/09
- [Qemu-devel] [PULL 24/26] MAINTAINERS: Update email addresses for Chrysostomos Nanakos, Stefan Hajnoczi, 2015/01/09
- Re: [Qemu-devel] [PULL 00/26] Block patches, Peter Maydell, 2015/01/10