[Qemu-devel] [PATCH v2 2/3] block/stream: use BDRV_REQ_PREFETCH

[Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>]

This helps to avoid extra io, allocations and memory copying.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
---
 block/stream.c | 20 +++++++-------------
 1 file changed, 7 insertions(+), 13 deletions(-)

diff --git a/block/stream.c b/block/stream.c
index 1a906fd860..b316bfb290 100644
--- a/block/stream.c
+++ b/block/stream.c
@@ -22,11 +22,11 @@
 
 enum {
     /*
-     * Size of data buffer for populating the image file.  This should be large
+     * Maximum chunk size to feed it to copy-on-read.  This should be large
      * enough to process multiple clusters in a single call, so that populating
      * contiguous regions of the image is efficient.
      */
-    STREAM_BUFFER_SIZE = 512 * 1024, /* in bytes */
+    STREAM_CHUNK = 512 * 1024, /* in bytes */
 };
 
 typedef struct StreamBlockJob {
@@ -39,13 +39,12 @@ typedef struct StreamBlockJob {
 } StreamBlockJob;
 
 static int coroutine_fn stream_populate(BlockBackend *blk,
-                                        int64_t offset, uint64_t bytes,
-                                        void *buf)
+                                        int64_t offset, uint64_t bytes)
 {
     assert(bytes < SIZE_MAX);
 
-    /* Copy-on-read the unallocated clusters */
-    return blk_co_pread(blk, offset, bytes, buf, BDRV_REQ_COPY_ON_READ);
+    return blk_co_preadv(blk, offset, bytes, NULL,
+                         BDRV_REQ_COPY_ON_READ | BDRV_REQ_PREFETCH);
 }
 
 static void stream_abort(Job *job)
@@ -117,7 +116,6 @@ static int coroutine_fn stream_run(Job *job, Error **errp)
     int error = 0;
     int ret = 0;
     int64_t n = 0; /* bytes */
-    void *buf;
 
     if (!bs->backing) {
         goto out;
@@ -130,8 +128,6 @@ static int coroutine_fn stream_run(Job *job, Error **errp)
     }
     job_progress_set_remaining(&s->common.job, len);
 
-    buf = qemu_blockalign(bs, STREAM_BUFFER_SIZE);
-
     /* Turn on copy-on-read for the whole block device so that guest read
      * requests help us make progress.  Only do this when copying the entire
      * backing chain since the copy-on-read operation does not take base into
@@ -154,7 +150,7 @@ static int coroutine_fn stream_run(Job *job, Error **errp)
 
         copy = false;
 
-        ret = bdrv_is_allocated(bs, offset, STREAM_BUFFER_SIZE, &n);
+        ret = bdrv_is_allocated(bs, offset, STREAM_CHUNK, &n);
         if (ret == 1) {
             /* Allocated in the top, no need to copy.  */
         } else if (ret >= 0) {
@@ -172,7 +168,7 @@ static int coroutine_fn stream_run(Job *job, Error **errp)
         }
         trace_stream_one_iteration(s, offset, n, ret);
         if (copy) {
-            ret = stream_populate(blk, offset, n, buf);
+            ret = stream_populate(blk, offset, n);
         }
         if (ret < 0) {
             BlockErrorAction action =
@@ -206,8 +202,6 @@ static int coroutine_fn stream_run(Job *job, Error **errp)
     /* Do not remove the backing file if an error was there but ignored.  */
     ret = error;
 
-    qemu_vfree(buf);
-
 out:
     /* Modify backing chain and close BDSes in main loop */
     return ret;
-- 
2.18.0