block: split write_zeroes always

We should split requests even if they are less than write_zeroes_alignment.
For example we can have the following request:
  offset 62k
  size   4k
  write_zeroes_alignment 64k
The original code sent 1 request covering 2 qcow2 clusters, and resulted
in both clusters being allocated. But by splitting the request, we can
cater to the case where one of the two clusters can be zeroed as a
whole, for only 1 cluster allocated after the operation.

Signed-off-by: Denis V. Lunev <den@openvz.org>
CC: Eric Blake <eblake@redhat.com>
CC: Kevin Wolf <kwolf@redhat.com>
Message-Id: <1463476543-3087-2-git-send-email-den@openvz.org>

[eblake: Avoid exceeding nb_sectors, hoist alignment checks out of
loop, and update testsuite to show that patch works]

Signed-off-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

2 files changed, 29 insertions, 19 deletions

diff --git a/block/io.c b/block/io.c
index 6070e773b7..c73be55f86 100644
--- a/block/io.c
+++ b/block/io.c
@@ -1118,28 +1118,32 @@ static int coroutine_fn bdrv_co_do_write_zeroes(BlockDriverState *bs,
     struct iovec iov = {0};
     int ret = 0;
     bool need_flush = false;
+    int head = 0;
+    int tail = 0;
 
     int max_write_zeroes = MIN_NON_ZERO(bs->bl.max_write_zeroes,
                                         BDRV_REQUEST_MAX_SECTORS);
+    if (bs->bl.write_zeroes_alignment) {
+        assert(is_power_of_2(bs->bl.write_zeroes_alignment));
+        head = sector_num & (bs->bl.write_zeroes_alignment - 1);
+        tail = (sector_num + nb_sectors) & (bs->bl.write_zeroes_alignment - 1);
+        max_write_zeroes &= ~(bs->bl.write_zeroes_alignment - 1);
+    }
 
     while (nb_sectors > 0 && !ret) {
         int num = nb_sectors;
 
         /* Align request.  Block drivers can expect the "bulk" of the request
-         * to be aligned.
+         * to be aligned, and that unaligned requests do not cross cluster
+         * boundaries.
          */
-        if (bs->bl.write_zeroes_alignment
-            && num > bs->bl.write_zeroes_alignment) {
-            if (sector_num % bs->bl.write_zeroes_alignment != 0) {
-                /* Make a small request up to the first aligned sector.  */
-                num = bs->bl.write_zeroes_alignment;
-                num -= sector_num % bs->bl.write_zeroes_alignment;
-            } else if ((sector_num + num) % bs->bl.write_zeroes_alignment != 0) {
-                /* Shorten the request to the last aligned sector.  num cannot
-                 * underflow because num > bs->bl.write_zeroes_alignment.
-                 */
-                num -= (sector_num + num) % bs->bl.write_zeroes_alignment;
-            }
+        if (head) {
+            /* Make a small request up to the first aligned sector.  */
+            num = MIN(nb_sectors, bs->bl.write_zeroes_alignment - head);
+            head = 0;
+        } else if (tail && num > bs->bl.write_zeroes_alignment) {
+            /* Shorten the request to the last aligned sector.  */
+            num -= tail;
         }
 
         /* limit request size */
diff --git a/tests/qemu-iotests/154.out b/tests/qemu-iotests/154.out
index 8946b734ac..b9d27c501a 100644
--- a/tests/qemu-iotests/154.out
+++ b/tests/qemu-iotests/154.out
@@ -106,11 +106,14 @@ read 1024/1024 bytes at offset 67584
 read 5120/5120 bytes at offset 68608
 5 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 [{ "start": 0, "length": 32768, "depth": 1, "zero": true, "data": false},
-{ "start": 32768, "length": 8192, "depth": 0, "zero": false, "data": true, "offset": 20480},
+{ "start": 32768, "length": 4096, "depth": 0, "zero": false, "data": true, "offset": 20480},
+{ "start": 36864, "length": 4096, "depth": 0, "zero": true, "data": false},
 { "start": 40960, "length": 8192, "depth": 1, "zero": true, "data": false},
-{ "start": 49152, "length": 8192, "depth": 0, "zero": false, "data": true, "offset": 28672},
+{ "start": 49152, "length": 4096, "depth": 0, "zero": false, "data": true, "offset": 24576},
+{ "start": 53248, "length": 4096, "depth": 0, "zero": true, "data": false},
 { "start": 57344, "length": 8192, "depth": 1, "zero": true, "data": false},
-{ "start": 65536, "length": 8192, "depth": 0, "zero": false, "data": true, "offset": 36864},
+{ "start": 65536, "length": 4096, "depth": 0, "zero": false, "data": true, "offset": 28672},
+{ "start": 69632, "length": 4096, "depth": 0, "zero": true, "data": false},
 { "start": 73728, "length": 134144000, "depth": 1, "zero": true, "data": false}]
 
 == spanning two clusters, non-zero after request ==
@@ -145,11 +148,14 @@ read 7168/7168 bytes at offset 65536
 read 1024/1024 bytes at offset 72704
 1 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 [{ "start": 0, "length": 32768, "depth": 1, "zero": true, "data": false},
-{ "start": 32768, "length": 8192, "depth": 0, "zero": false, "data": true, "offset": 20480},
+{ "start": 32768, "length": 4096, "depth": 0, "zero": true, "data": false},
+{ "start": 36864, "length": 4096, "depth": 0, "zero": false, "data": true, "offset": 20480},
 { "start": 40960, "length": 8192, "depth": 1, "zero": true, "data": false},
-{ "start": 49152, "length": 8192, "depth": 0, "zero": false, "data": true, "offset": 28672},
+{ "start": 49152, "length": 4096, "depth": 0, "zero": true, "data": false},
+{ "start": 53248, "length": 4096, "depth": 0, "zero": false, "data": true, "offset": 24576},
 { "start": 57344, "length": 8192, "depth": 1, "zero": true, "data": false},
-{ "start": 65536, "length": 8192, "depth": 0, "zero": false, "data": true, "offset": 36864},
+{ "start": 65536, "length": 4096, "depth": 0, "zero": true, "data": false},
+{ "start": 69632, "length": 4096, "depth": 0, "zero": false, "data": true, "offset": 28672},
 { "start": 73728, "length": 134144000, "depth": 1, "zero": true, "data": false}]
 
 == spanning two clusters, partially overwriting backing file ==