util: adjust coroutine pool size to virtio block queue

Coroutine pool size was 64 from long ago, and the basis was organized in the commit message in 4d68e86b.

At that time, virtio-blk queue-size and num-queue were not configuable, and equivalent values were 128 and 1.

Coroutine pool size 64 was fine then.

Later queue-size and num-queue got configuable, and default values were increased.

Coroutine pool with size 64 exhausts frequently with random disk IO in new size, and slows down.

This commit adjusts coroutine pool size adaptively with new values.

This commit adds 64 by default, but now coroutine is not only for block devices,

and is not too much burdon comparing with new default.

pool size of 128 * vCPUs.

Signed-off-by: Hiroki Narukawa <hnarukaw@yahoo-corp.jp>
Message-id: 20220214115302.13294-2-hnarukaw@yahoo-corp.jp
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c
index 82676cdd01cea3d306893ed735b27192d6d1472b..540c38f829f690cbcdc6bf7541a0007933f5a5d5 100644 (file)
--- a/hw/block/virtio-blk.c
+++ b/hw/block/virtio-blk.c
@@ -32,6 +32,7 @@
 #include "hw/virtio/virtio-bus.h"
 #include "migration/qemu-file-types.h"
 #include "hw/virtio/virtio-access.h"
+#include "qemu/coroutine.h"
 
 /* Config size before the discard support (hide associated config fields) */
 #define VIRTIO_BLK_CFG_SIZE offsetof(struct virtio_blk_config, \
@@ -1214,6 +1215,8 @@ static void virtio_blk_device_realize(DeviceState *dev, Error **errp)
     for (i = 0; i < conf->num_queues; i++) {
         virtio_add_queue(vdev, conf->queue_size, virtio_blk_handle_output);
     }
+    qemu_coroutine_increase_pool_batch_size(conf->num_queues * conf->queue_size
+                                            / 2);
     virtio_blk_data_plane_create(vdev, conf, &s->dataplane, &err);
     if (err != NULL) {
         error_propagate(errp, err);
@@ -1250,6 +1253,8 @@ static void virtio_blk_device_unrealize(DeviceState *dev)
     for (i = 0; i < conf->num_queues; i++) {
         virtio_del_queue(vdev, i);
     }
+    qemu_coroutine_decrease_pool_batch_size(conf->num_queues * conf->queue_size
+                                            / 2);
     qemu_del_vm_change_state_handler(s->change);
     blockdev_mark_auto_del(s->blk);
     virtio_cleanup(vdev);

diff --git a/include/qemu/coroutine.h b/include/qemu/coroutine.h
index 4829ff373d3c5daf6f2e959a28be962ff17a9073..c828a95ee0923e43e31791484ad0401c20966836 100644 (file)
--- a/include/qemu/coroutine.h
+++ b/include/qemu/coroutine.h
@@ -331,6 +331,16 @@ void qemu_co_sleep_wake(QemuCoSleep *w);
  */
 void coroutine_fn yield_until_fd_readable(int fd);
 
+/**
+ * Increase coroutine pool size
+ */
+void qemu_coroutine_increase_pool_batch_size(unsigned int additional_pool_size);
+
+/**
+ * Devcrease coroutine pool size
+ */
+void qemu_coroutine_decrease_pool_batch_size(unsigned int additional_pool_size);
+
 #include "qemu/lockable.h"
 
 #endif /* QEMU_COROUTINE_H */

diff --git a/util/qemu-coroutine.c b/util/qemu-coroutine.c
index 38fb6d3084dad2dd2145134d9e5da8f03d7169fe..c03b2422ff686e7138bf7bf0abba7aae6efeed53 100644 (file)
--- a/util/qemu-coroutine.c
+++ b/util/qemu-coroutine.c
@@ -20,12 +20,14 @@
 #include "qemu/coroutine_int.h"
 #include "block/aio.h"
 
+/** Initial batch size is 64, and is increased on demand */
 enum {
-    POOL_BATCH_SIZE = 64,
+    POOL_INITIAL_BATCH_SIZE = 64,
 };
 
 /** Free list to speed up creation */
 static QSLIST_HEAD(, Coroutine) release_pool = QSLIST_HEAD_INITIALIZER(pool);
+static unsigned int pool_batch_size = POOL_INITIAL_BATCH_SIZE;
 static unsigned int release_pool_size;
 static __thread QSLIST_HEAD(, Coroutine) alloc_pool = QSLIST_HEAD_INITIALIZER(pool);
 static __thread unsigned int alloc_pool_size;
@@ -49,7 +51,7 @@ Coroutine *qemu_coroutine_create(CoroutineEntry *entry, void *opaque)
     if (CONFIG_COROUTINE_POOL) {
         co = QSLIST_FIRST(&alloc_pool);
         if (!co) {
-            if (release_pool_size > POOL_BATCH_SIZE) {
+            if (release_pool_size > qatomic_read(&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;
@@ -86,12 +88,12 @@ static void coroutine_delete(Coroutine *co)
     co->caller = NULL;
 
     if (CONFIG_COROUTINE_POOL) {
-        if (release_pool_size < POOL_BATCH_SIZE * 2) {
+        if (release_pool_size < qatomic_read(&pool_batch_size) * 2) {
             QSLIST_INSERT_HEAD_ATOMIC(&release_pool, co, pool_next);
             qatomic_inc(&release_pool_size);
             return;
         }
-        if (alloc_pool_size < POOL_BATCH_SIZE) {
+        if (alloc_pool_size < qatomic_read(&pool_batch_size)) {
             QSLIST_INSERT_HEAD(&alloc_pool, co, pool_next);
             alloc_pool_size++;
             return;
@@ -202,3 +204,13 @@ AioContext *coroutine_fn qemu_coroutine_get_aio_context(Coroutine *co)
 {
     return co->ctx;
 }
+
+void qemu_coroutine_increase_pool_batch_size(unsigned int additional_pool_size)
+{
+    qatomic_add(&pool_batch_size, additional_pool_size);
+}
+
+void qemu_coroutine_decrease_pool_batch_size(unsigned int removing_pool_size)
+{
+    qatomic_sub(&pool_batch_size, removing_pool_size);
+}