[Qemu-devel] [PATCH 1/3] block: ignore flush requests when storage is clean

[Denis V. Lunev]

From: Evgeny Yakovlev <address@hidden>

Some guests (win2008 server for example) do a lot of unnecessary
flushing when underlying media has not changed. This adds additional
overhead on host when calling fsync/fdatasync.

This change introduces a dirty flag in BlockDriverState which is set
in bdrv_set_dirty and is checked in bdrv_co_flush. This allows us to
avoid unnesessary flushing when storage is clean.

The problem with excessive flushing was found by a performance test
which does parallel directory tree creation (from 2 processes).
Results improved from 0.424 loops/sec to 0.432 loops/sec.
Each loop creates 10^3 directories with 10 files in each.

Signed-off-by: Evgeny Yakovlev <address@hidden>
Signed-off-by: Denis V. Lunev <address@hidden>
CC: Kevin Wolf <address@hidden>
CC: Max Reitz <address@hidden>
CC: Stefan Hajnoczi <address@hidden>
CC: Fam Zheng <address@hidden>
CC: John Snow <address@hidden>
---
 block.c                   |  1 +
 block/dirty-bitmap.c      |  3 +++
 block/io.c                | 19 +++++++++++++++++++
 include/block/block_int.h |  2 ++
 4 files changed, 25 insertions(+)

diff --git a/block.c b/block.c
index f4648e9..e36f148 100644
--- a/block.c
+++ b/block.c
@@ -2582,6 +2582,7 @@ int bdrv_truncate(BlockDriverState *bs, int64_t offset)
         ret = refresh_total_sectors(bs, offset >> BDRV_SECTOR_BITS);
         bdrv_dirty_bitmap_truncate(bs);
         bdrv_parent_cb_resize(bs);
+        bs->dirty = true; /* file node sync is needed after truncate */
     }
     return ret;
 }
diff --git a/block/dirty-bitmap.c b/block/dirty-bitmap.c
index 4902ca5..54e0413 100644
--- a/block/dirty-bitmap.c
+++ b/block/dirty-bitmap.c
@@ -370,6 +370,9 @@ void bdrv_set_dirty(BlockDriverState *bs, int64_t 
cur_sector,
         }
         hbitmap_set(bitmap->bitmap, cur_sector, nr_sectors);
     }
+
+    /* Set global block driver dirty flag even if bitmap is disabled */
+    bs->dirty = true;
 }
 
 /**
diff --git a/block/io.c b/block/io.c
index 7cf3645..8078af2 100644
--- a/block/io.c
+++ b/block/io.c
@@ -2239,6 +2239,25 @@ int coroutine_fn bdrv_co_flush(BlockDriverState *bs)
         goto flush_parent;
     }
 
+    /* Check if storage is actually dirty before flushing to disk */
+    if (!bs->dirty) {
+        /* Flush requests are appended to tracked request list in order so that
+         * most recent request is at the head of the list. Following code uses
+         * this ordering to wait for the most recent flush request to complete
+         * to ensure that requests return in order */
+        BdrvTrackedRequest *prev_req;
+        QLIST_FOREACH(prev_req, &bs->tracked_requests, list) {
+            if (prev_req == &req || prev_req->type != BDRV_TRACKED_FLUSH) {
+                continue;
+            }
+
+            qemu_co_queue_wait(&prev_req->wait_queue);
+            break;
+        }
+        goto flush_parent;
+    }
+    bs->dirty = false;
+
     BLKDBG_EVENT(bs->file, BLKDBG_FLUSH_TO_DISK);
     if (bs->drv->bdrv_co_flush_to_disk) {
         ret = bs->drv->bdrv_co_flush_to_disk(bs);
diff --git a/include/block/block_int.h b/include/block/block_int.h
index 2057156..616058b 100644
--- a/include/block/block_int.h
+++ b/include/block/block_int.h
@@ -418,6 +418,8 @@ struct BlockDriverState {
     int sg;        /* if true, the device is a /dev/sg* */
     int copy_on_read; /* if true, copy read backing sectors into image
                          note this is a reference count */
+
+    bool dirty;
     bool probed;
 
     BlockDriver *drv; /* NULL means no media */
-- 
2.1.4