[Qemu-devel] [PATCH] vmdk: Optimize cluster allocation

[Fam Zheng]

On mounted NFS filesystem, ftruncate is much much slower than doing a
zero write. Changing this significantly speeds up cluster allocation.

Comparing by converting a cirros image (296M) to VMDK on an NFS mount
point, over 1Gbe LAN:

    $ time qemu-img convert cirros-0.3.1.img /mnt/a.raw -O vmdk

Before:
    real    0m26.464s
    user    0m0.133s
    sys     0m0.527s

After:
    real    0m2.120s
    user    0m0.080s
    sys     0m0.197s

Signed-off-by: Fam Zheng <address@hidden>
---
 block/vmdk.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/block/vmdk.c b/block/vmdk.c
index b69988d..b829265 100644
--- a/block/vmdk.c
+++ b/block/vmdk.c
@@ -1036,6 +1036,7 @@ static int get_cluster_offset(BlockDriverState *bs,
     int min_index, i, j;
     uint32_t min_count, *l2_table;
     bool zeroed = false;
+    int ret;
 
     if (m_data) {
         m_data->valid = 0;
@@ -1110,11 +1111,15 @@ static int get_cluster_offset(BlockDriverState *bs,
 
         /* Avoid the L2 tables update for the images that have snapshots. */
         *cluster_offset = bdrv_getlength(extent->file);
+        assert(0 == (*cluster_offset & (extent->cluster_sectors - 1)));
         if (!extent->compressed) {
-            bdrv_truncate(
-                extent->file,
-                *cluster_offset + (extent->cluster_sectors << 9)
-            );
+            ret = bdrv_write_zeroes(extent->file,
+                                    *cluster_offset >> BDRV_SECTOR_BITS,
+                                    extent->cluster_sectors,
+                                    0);
+            if (ret) {
+                return VMDK_ERROR;
+            }
         }
 
         *cluster_offset >>= 9;
-- 
1.9.2