block/copy-before-write: implement cbw-timeout option

In some scenarios, when copy-before-write operations lasts too long
time, it's better to cancel it.

Most useful would be to use the new option together with
on-cbw-error=break-snapshot: this way if cbw operation takes too long
time we'll just cancel backup process but do not disturb the guest too
much.

Note the tricky point of realization: we keep additional point in
bs->in_flight during block_copy operation even if it's timed-out.
Background "cancelled" block_copy operations will finish at some point
and will want to access state. We should care to not free the state in
.bdrv_close() earlier.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@openvz.org>
Reviewed-by: Hanna Reitz <hreitz@redhat.com>
  [vsementsov: use bdrv_inc_in_flight()/bdrv_dec_in_flight() instead of
   direct manipulation on bs->in_flight]
Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>

1 files changed, 21 insertions, 1 deletions

diff --git a/block/copy-before-write.c b/block/copy-before-write.c
index fc13c7c..c24b8dd 100644
--- a/block/copy-before-write.c
+++ b/block/copy-before-write.c
@@ -42,6 +42,7 @@ typedef struct BDRVCopyBeforeWriteState {
     BlockCopyState *bcs;
     BdrvChild *target;
     OnCbwError on_cbw_error;
+    uint32_t cbw_timeout_ns;
 
     /*
      * @lock: protects access to @access_bitmap, @done_bitmap and
@@ -83,6 +84,13 @@ static coroutine_fn int cbw_co_preadv(
     return bdrv_co_preadv(bs->file, offset, bytes, qiov, flags);
 }
 
+static void block_copy_cb(void *opaque)
+{
+    BlockDriverState *bs = opaque;
+
+    bdrv_dec_in_flight(bs);
+}
+
 /*
  * Do copy-before-write operation.
  *
@@ -111,7 +119,16 @@ static coroutine_fn int cbw_do_copy_before_write(BlockDriverState *bs,
     off = QEMU_ALIGN_DOWN(offset, cluster_size);
     end = QEMU_ALIGN_UP(offset + bytes, cluster_size);
 
-    ret = block_copy(s->bcs, off, end - off, true, 0, NULL, NULL);
+    /*
+     * Increase in_flight, so that in case of timed-out block-copy, the
+     * remaining background block_copy() request (which can't be immediately
+     * cancelled by timeout) is presented in bs->in_flight. This way we are
+     * sure that on bs close() we'll previously wait for all timed-out but yet
+     * running block_copy calls.
+     */
+    bdrv_inc_in_flight(bs);
+    ret = block_copy(s->bcs, off, end - off, true, s->cbw_timeout_ns,
+                     block_copy_cb, bs);
     if (ret < 0 && s->on_cbw_error == ON_CBW_ERROR_BREAK_GUEST_WRITE) {
         return ret;
     }
@@ -377,6 +394,7 @@ static BlockdevOptions *cbw_parse_options(QDict *options, Error **errp)
      */
     qdict_extract_subqdict(options, NULL, "bitmap");
     qdict_del(options, "on-cbw-error");
+    qdict_del(options, "cbw-timeout");
 
 out:
     visit_free(v);
@@ -423,6 +441,8 @@ static int cbw_open(BlockDriverState *bs, QDict *options, int flags,
     }
     s->on_cbw_error = opts->has_on_cbw_error ? opts->on_cbw_error :
             ON_CBW_ERROR_BREAK_GUEST_WRITE;
+    s->cbw_timeout_ns = opts->has_cbw_timeout ?
+        opts->cbw_timeout * NANOSECONDS_PER_SECOND : 0;
 
     bs->total_sectors = bs->file->bs->total_sectors;
     bs->supported_write_flags = BDRV_REQ_WRITE_UNCHANGED |