[Qemu-devel] [PATCH 26/27] block/parallels: optimize linear image expansion

[Denis V. Lunev]

Plain image expansion spends a lot of time to update image file size.
This seriously affects the performance. The following simple test
  qemu_img create -f parallels -o cluster_size=64k ./1.hds 64G
  qemu_io -n -c "write -P 0x11 0 1024M" ./1.hds
could be improved if the format driver will pre-allocate some space
in the image file with a reasonable chunk.

This patch preallocates 128 Mb using bdrv_write_zeroes, which should
normally use fallocate() call inside. Fallback to older truncate()
could be used as a fallback using image open options thanks to the
previous patch.

The benefit is around 15%.

Signed-off-by: Denis V. Lunev <d...@openvz.org>
CC: Roman Karan <rka...@parallels.com>
CC: Kevin Wolf <kw...@redhat.com>
CC: Stefan Hajnoczi <stefa...@redhat.com>
---
 block/parallels.c | 35 ++++++++++++++++++++++++++++++++---
 1 file changed, 32 insertions(+), 3 deletions(-)

diff --git a/block/parallels.c b/block/parallels.c
index 989efe4..c6343c5 100644
--- a/block/parallels.c
+++ b/block/parallels.c
@@ -84,6 +84,7 @@ typedef struct BDRVParallelsState {
     uint32_t *bat_bitmap;
     unsigned int bat_size;
 
+    int64_t  data_end;
     uint64_t prealloc_size;
     ParallelsPreallocMode prealloc_mode;
 
@@ -194,7 +195,20 @@ static int64_t allocate_cluster(BlockDriverState *bs, 
int64_t sector_num)
     }
 
     pos = bdrv_getlength(bs->file) >> BDRV_SECTOR_BITS;
-    bdrv_truncate(bs->file, (pos + s->tracks) << BDRV_SECTOR_BITS);
+    if (s->data_end + s->tracks > pos) {
+        int ret;
+        if (s->prealloc_mode == PRL_PREALLOC_MODE_FALLOCATE)
+            ret = bdrv_write_zeroes(bs->file, s->data_end,
+                                    s->prealloc_size, 0);
+        else
+            ret = bdrv_truncate(bs->file,
+                    (s->data_end + s->prealloc_size) << BDRV_SECTOR_BITS);
+        if (ret < 0) {
+            return ret;
+        }
+    }
+    pos = s->data_end;
+    s->data_end += s->tracks;
 
     s->bat_bitmap[idx] = cpu_to_le32(pos / s->off_multiplier);
 
@@ -533,7 +547,7 @@ static int parallels_open(BlockDriverState *bs, QDict 
*options, int flags,
 {
     BDRVParallelsState *s = bs->opaque;
     ParallelsHeader ph;
-    int ret, size;
+    int ret, size, i;
     QemuOpts *opts = NULL;
     Error *local_err = NULL;
     char *buf;
@@ -583,7 +597,11 @@ static int parallels_open(BlockDriverState *bs, QDict 
*options, int flags,
         ret = -ENOMEM;
         goto fail;
     }
-    if (le32_to_cpu(ph.data_off) < s->header_size) {
+    s->data_end = le32_to_cpu(ph.data_off);
+    if (s->data_end == 0) {
+        s->data_end = ROUND_UP(bat_entry_off(s->bat_size), BDRV_SECTOR_SIZE);
+    }
+    if (s->data_end < s->header_size) {
         /* there is not enough unused space to fit to block align between BAT
            and actual data. We can't avoid read-modify-write... */
         s->header_size = size;
@@ -595,6 +613,13 @@ static int parallels_open(BlockDriverState *bs, QDict 
*options, int flags,
     }
     s->bat_bitmap = (uint32_t *)(s->header + 1);
 
+    for (i = 0; i < s->bat_size; i++) {
+        int64_t off = bat2sect(s, i);
+        if (off >= s->data_end) {
+            s->data_end = off + s->tracks;
+        }
+    }
+
     if (le32_to_cpu(ph.inuse) == HEADER_INUSE_MAGIC) {
         /* Image was not closed correctly. The check is mandatory */
         s->header_unclean = true;
@@ -665,6 +690,10 @@ static void parallels_close(BlockDriverState *bs)
         parallels_update_header(bs);
     }
 
+    if (bs->open_flags & BDRV_O_RDWR) {
+        bdrv_truncate(bs->file, s->data_end << BDRV_SECTOR_BITS);
+    }
+
     g_free(s->bat_dirty_bmap);
     qemu_vfree(s->header);
 }
-- 
1.9.1