qcow2: avoid extra flushes in qcow2

The problem with excessive flushing was found by a couple of performance
tests:
  - parallel directory tree creation (from 2 processes)
  - 32 cached writes + fsync at the end in a loop

For the first one results improved from 2.6 loops/sec to 3.5 loops/sec.
Each loop creates 10^3 directories with 10 files in each.

For the second one results improved from ~600 fsync/sec to ~1100
fsync/sec. Though, it was run on SSD so it probably won't show such
performance gain on rotational media.

qcow2_cache_flush() calls bdrv_flush() unconditionally after writing
cache entries of a particular cache. This can lead to as many as
2 additional fdatasyncs inside bdrv_flush.

We can simply skip all fdatasync calls inside qcow2_co_flush_to_os
as bdrv_flush for sure will do the job. These flushes are necessary to
keep the right order of writes to the different caches. Though this is
not necessary in the current code base as this ordering is ensured through
the flush in qcow2_cache_flush_dependency().

Signed-off-by: Denis V. Lunev <den@openvz.org>
CC: Pavel Borzenkov <pborzenkov@virtuozzo.com>
CC: Kevin Wolf <kwolf@redhat.com>
CC: Max Reitz <mreitz@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

diff --git a/block/qcow2-cache.c b/block/qcow2-cache.c
index 0fe8edae41192b95ba034886af572823ff0e905e..208a060421dbe85c9c06dbddddfa3fe682048a9f 100644 (file)
--- a/block/qcow2-cache.c
+++ b/block/qcow2-cache.c
@@ -226,7 +226,7 @@ static int qcow2_cache_entry_flush(BlockDriverState *bs, Qcow2Cache *c, int i)
     return 0;
 }
 
-int qcow2_cache_flush(BlockDriverState *bs, Qcow2Cache *c)
+int qcow2_cache_write(BlockDriverState *bs, Qcow2Cache *c)
 {
     BDRVQcow2State *s = bs->opaque;
     int result = 0;
@@ -242,8 +242,15 @@ int qcow2_cache_flush(BlockDriverState *bs, Qcow2Cache *c)
         }
     }
 
+    return result;
+}
+
+int qcow2_cache_flush(BlockDriverState *bs, Qcow2Cache *c)
+{
+    int result = qcow2_cache_write(bs, c);
+
     if (result == 0) {
-        ret = bdrv_flush(bs->file->bs);
+        int ret = bdrv_flush(bs->file->bs);
         if (ret < 0) {
             result = ret;
         }

diff --git a/block/qcow2.c b/block/qcow2.c
index 5e26c3d5b7e2061d7df9f922cd5d1f85f04f930a..6f5fb810e4fc7039d18b00251ebf43b9d75e253e 100644 (file)
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -2813,14 +2813,14 @@ static coroutine_fn int qcow2_co_flush_to_os(BlockDriverState *bs)
     int ret;
 
     qemu_co_mutex_lock(&s->lock);
-    ret = qcow2_cache_flush(bs, s->l2_table_cache);
+    ret = qcow2_cache_write(bs, s->l2_table_cache);
     if (ret < 0) {
         qemu_co_mutex_unlock(&s->lock);
         return ret;
     }
 
     if (qcow2_need_accurate_refcounts(s)) {
-        ret = qcow2_cache_flush(bs, s->refcount_block_cache);
+        ret = qcow2_cache_write(bs, s->refcount_block_cache);
         if (ret < 0) {
             qemu_co_mutex_unlock(&s->lock);
             return ret;

diff --git a/block/qcow2.h b/block/qcow2.h
index a063a3c1a1655f8d76d84f892ba90a97a23c56ec..7db9795d44feebb133dc87d90eca795e933ae25a 100644 (file)
--- a/block/qcow2.h
+++ b/block/qcow2.h
@@ -583,6 +583,7 @@ int qcow2_cache_destroy(BlockDriverState* bs, Qcow2Cache *c);
 void qcow2_cache_entry_mark_dirty(BlockDriverState *bs, Qcow2Cache *c,
      void *table);
 int qcow2_cache_flush(BlockDriverState *bs, Qcow2Cache *c);
+int qcow2_cache_write(BlockDriverState *bs, Qcow2Cache *c);
 int qcow2_cache_set_dependency(BlockDriverState *bs, Qcow2Cache *c,
     Qcow2Cache *dependency);
 void qcow2_cache_depends_on_flush(Qcow2Cache *c);