block/io: optimize bdrv_co_pwritev for small requests

in a read-modify-write cycle a small request might cause
head and tail to fall into the same aligned block. Currently
QEMU reads the same block twice in this case which is
not necessary.

Signed-off-by: Peter Lieven <pl@kamp.de>
Message-id: 1464607873-28206-1-git-send-email-pl@kamp.de
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
diff --git a/block/io.c b/block/io.c
index 7ac9897..e12f303 100644
--- a/block/io.c
+++ b/block/io.c
@@ -1427,6 +1427,14 @@
 
         bytes += offset & (align - 1);
         offset = offset & ~(align - 1);
+
+        /* We have read the tail already if the request is smaller
+         * than one aligned block.
+         */
+        if (bytes < align) {
+            qemu_iovec_add(&local_qiov, head_buf + bytes, align - bytes);
+            bytes = align;
+        }
     }
 
     if ((offset + bytes) & (align - 1)) {
diff --git a/tests/qemu-iotests/077 b/tests/qemu-iotests/077
index 4dc680b..d2d2a2d 100755
--- a/tests/qemu-iotests/077
+++ b/tests/qemu-iotests/077
@@ -60,7 +60,7 @@
 
 # Sequential RMW requests on the same physical sector
 off=0x1000
-for ev in "head" "after_head" "tail" "after_tail"; do
+for ev in "head" "after_head"; do
 cat  <<EOF
 break pwritev_rmw_$ev A
 aio_write -P 10 $((off + 0x200)) 0x200
@@ -211,16 +211,6 @@
     echo read -P 11 0x2400 0x200
     echo read -P 0  0x2600 0xa00
 
-    echo read -P 0  0x3000 0x200
-    echo read -P 10 0x3200 0x200
-    echo read -P 11 0x3400 0x200
-    echo read -P 0  0x3600 0xa00
-
-    echo read -P 0  0x4000 0x200
-    echo read -P 10 0x4200 0x200
-    echo read -P 11 0x4400 0x200
-    echo read -P 0  0x4600 0xa00
-
     # Chained dependencies
     echo read -P 10 0x5000 0x200
     echo read -P 11 0x5200 0x200
diff --git a/tests/qemu-iotests/077.out b/tests/qemu-iotests/077.out
index eab14ae..16f951f 100644
--- a/tests/qemu-iotests/077.out
+++ b/tests/qemu-iotests/077.out
@@ -19,16 +19,6 @@
 XXX bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 wrote XXX/XXX bytes at offset XXX
 XXX bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-blkdebug: Resuming request 'A'
-wrote XXX/XXX bytes at offset XXX
-XXX bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-wrote XXX/XXX bytes at offset XXX
-XXX bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-blkdebug: Resuming request 'A'
-wrote XXX/XXX bytes at offset XXX
-XXX bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-wrote XXX/XXX bytes at offset XXX
-XXX bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 wrote XXX/XXX bytes at offset XXX
 XXX bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 wrote XXX/XXX bytes at offset XXX
@@ -114,22 +104,6 @@
 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 read 2560/2560 bytes at offset 9728
 2.500 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-read 512/512 bytes at offset 12288
-512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-read 512/512 bytes at offset 12800
-512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-read 512/512 bytes at offset 13312
-512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-read 2560/2560 bytes at offset 13824
-2.500 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-read 512/512 bytes at offset 16384
-512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-read 512/512 bytes at offset 16896
-512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-read 512/512 bytes at offset 17408
-512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
-read 2560/2560 bytes at offset 17920
-2.500 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 read 512/512 bytes at offset 20480
 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
 read 512/512 bytes at offset 20992