[Qemu-devel] [PATCH v2 1/3] COW: Speed up writes

[Charlie Shepherd <charlie@ctshepherd.com>]

Process a whole sector's worth of COW bits by reading a sector, setting the bits, then writing it
out again. Make sure we only flush once, before writing metadata.

Signed-off-by: Charlie Shepherd <charlie@ctshepherd.com>
---
 block/cow.c | 79 ++++++++++++++++++++++++++++++++-----------------------------
 1 file changed, 41 insertions(+), 38 deletions(-)

diff --git a/block/cow.c b/block/cow.c
index 909c3e7..5dfffb0 100644
--- a/block/cow.c
+++ b/block/cow.c
@@ -103,40 +103,18 @@ static int cow_open(BlockDriverState *bs, QDict *options, int flags,
     return ret;
 }
 
-/*
- * XXX(hch): right now these functions are extremely inefficient.
- * We should just read the whole bitmap we'll need in one go instead.
- */
-static inline int cow_set_bit(BlockDriverState *bs, int64_t bitnum, bool *first)
+static inline void cow_set_bits(uint8_t *bitmap, int start, int64_t nb_sectors)
 {
-    uint64_t offset = sizeof(struct cow_header_v2) + bitnum / 8;
-    uint8_t bitmap;
-    int ret;
-
-    ret = bdrv_pread(bs->file, offset, &bitmap, sizeof(bitmap));
-    if (ret < 0) {
-       return ret;
-    }
-
-    if (bitmap & (1 << (bitnum % 8))) {
-        return 0;
-    }
-
-    if (*first) {
-        ret = bdrv_flush(bs->file);
-        if (ret < 0) {
-            return ret;
+    int64_t bitnum = start, last = start + nb_sectors;
+    while (bitnum < last) {
+        if ((bitnum & 7) == 0 && bitnum + 8 <= last) {
+            bitmap[bitnum / 8] = 0xFF;
+            bitnum += 8;
+            continue;
         }
-        *first = false;
-    }
-
-    bitmap |= (1 << (bitnum % 8));
-
-    ret = bdrv_pwrite(bs->file, offset, &bitmap, sizeof(bitmap));
-    if (ret < 0) {
-       return ret;
+        bitmap[bitnum/8] |= (1 << (bitnum % 8));
+        bitnum++;
     }
-    return 0;
 }
 
 #define BITS_PER_BITMAP_SECTOR (512 * 8)
@@ -204,18 +182,43 @@ static int64_t coroutine_fn cow_co_get_block_status(BlockDriverState *bs,
 static int cow_update_bitmap(BlockDriverState *bs, int64_t sector_num,
         int nb_sectors)
 {
-    int error = 0;
-    int i;
+    int64_t bitnum = sector_num + sizeof(struct cow_header_v2) * 8;
+    uint64_t offset = (bitnum / 8) & -BDRV_SECTOR_SIZE;
     bool first = true;
 
-    for (i = 0; i < nb_sectors; i++) {
-        error = cow_set_bit(bs, sector_num + i, &first);
-        if (error) {
-            break;
+    while (nb_sectors) {
+        int ret;
+        uint8_t bitmap[BDRV_SECTOR_SIZE];
+
+        bitnum &= BITS_PER_BITMAP_SECTOR - 1;
+        int sector_bits = MIN(nb_sectors, BITS_PER_BITMAP_SECTOR - bitnum);
+
+        ret = bdrv_pread(bs->file, offset, &bitmap, sizeof(bitmap));
+        if (ret < 0) {
+            return ret;
         }
+
+        if (first) {
+            ret = bdrv_flush(bs->file);
+            if (ret < 0) {
+                return ret;
+            }
+            first = false;
+        }
+
+        cow_set_bits(bitmap, bitnum, sector_bits);
+
+        ret = bdrv_pwrite(bs->file, offset, &bitmap, sizeof(bitmap));
+        if (ret < 0) {
+            return ret;
+        }
+
+        bitnum += sector_bits;
+        nb_sectors -= sector_bits;
+        offset += BDRV_SECTOR_SIZE;
     }
 
-    return error;
+    return 0;
 }
 
 static int coroutine_fn cow_read(BlockDriverState *bs, int64_t sector_num,
-- 
1.8.4.rc3