block: avoid recursive block_status call if possible

drv_co_block_status digs bs->file for additional, more accurate search
for hole inside region, reported as DATA by bs since 5daa74a6ebc.

This accuracy is not free: assume we have qcow2 disk. Actually, qcow2
knows, where are holes and where is data. But every block_status
request calls lseek additionally. Assume a big disk, full of
data, in any iterative copying block job (or img convert) we'll call
lseek(HOLE) on every iteration, and each of these lseeks will have to
iterate through all metadata up to the end of file. It's obviously
ineffective behavior. And for many scenarios we don't need this lseek
at all.

However, lseek is needed when we have metadata-preallocated image.

So, let's detect metadata-preallocation case and don't dig qcow2's
protocol file in other cases.

The idea is to compare allocation size in POV of filesystem with
allocations size in POV of Qcow2 (by refcounts). If allocation in fs is
significantly lower, consider it as metadata-preallocation case.

102 iotest changed, as our detector can't detect shrinked file as
metadata-preallocation, which don't seem to be wrong, as with metadata
preallocation we always have valid file length.

Two other iotests have a slight change in their QMP output sequence:
Active 'block-commit' returns earlier because the job coroutine yields
earlier on a blocking operation. This operation is loading the refcount
blocks in qcow2_detect_metadata_preallocation().

Suggested-by: Denis V. Lunev <den@openvz.org>
Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

4 files changed, 55 insertions, 1 deletions

diff --git a/block/io.c b/block/io.c
index 3134a60a48..150358c3b1 100644
--- a/block/io.c
+++ b/block/io.c
@@ -2092,6 +2092,12 @@ static int coroutine_fn bdrv_co_block_status(BlockDriverState *bs,
      */
     assert(*pnum && QEMU_IS_ALIGNED(*pnum, align) &&
            align > offset - aligned_offset);
+    if (ret & BDRV_BLOCK_RECURSE) {
+        assert(ret & BDRV_BLOCK_DATA);
+        assert(ret & BDRV_BLOCK_OFFSET_VALID);
+        assert(!(ret & BDRV_BLOCK_ZERO));
+    }
+
     *pnum -= offset - aligned_offset;
     if (*pnum > bytes) {
         *pnum = bytes;
@@ -2122,7 +2128,8 @@ static int coroutine_fn bdrv_co_block_status(BlockDriverState *bs,
         }
     }
 
-    if (want_zero && local_file && local_file != bs &&
+    if (want_zero && ret & BDRV_BLOCK_RECURSE &&
+        local_file && local_file != bs &&
         (ret & BDRV_BLOCK_DATA) && !(ret & BDRV_BLOCK_ZERO) &&
         (ret & BDRV_BLOCK_OFFSET_VALID)) {
         int64_t file_pnum;
diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c
index 4c1794f9af..3a2c673a5e 100644
--- a/block/qcow2-refcount.c
+++ b/block/qcow2-refcount.c
@@ -3444,3 +3444,35 @@ int64_t qcow2_get_last_cluster(BlockDriverState *bs, int64_t size)
                             "There are no references in the refcount table.");
     return -EIO;
 }
+
+int qcow2_detect_metadata_preallocation(BlockDriverState *bs)
+{
+    BDRVQcow2State *s = bs->opaque;
+    int64_t i, end_cluster, cluster_count = 0, threshold;
+    int64_t file_length, real_allocation, real_clusters;
+
+    file_length = bdrv_getlength(bs->file->bs);
+    if (file_length < 0) {
+        return file_length;
+    }
+
+    real_allocation = bdrv_get_allocated_file_size(bs->file->bs);
+    if (real_allocation < 0) {
+        return real_allocation;
+    }
+
+    real_clusters = real_allocation / s->cluster_size;
+    threshold = MAX(real_clusters * 10 / 9, real_clusters + 2);
+
+    end_cluster = size_to_clusters(s, file_length);
+    for (i = 0; i < end_cluster && cluster_count < threshold; i++) {
+        uint64_t refcount;
+        int ret = qcow2_get_refcount(bs, i, &refcount);
+        if (ret < 0) {
+            return ret;
+        }
+        cluster_count += !!refcount;
+    }
+
+    return cluster_count >= threshold;
+}
diff --git a/block/qcow2.c b/block/qcow2.c
index f2cb131048..14f914117f 100644
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -1895,6 +1895,12 @@ static int coroutine_fn qcow2_co_block_status(BlockDriverState *bs,
     unsigned int bytes;
     int status = 0;
 
+    if (!s->metadata_preallocation_checked) {
+        ret = qcow2_detect_metadata_preallocation(bs);
+        s->metadata_preallocation = (ret == 1);
+        s->metadata_preallocation_checked = true;
+    }
+
     bytes = MIN(INT_MAX, count);
     qemu_co_mutex_lock(&s->lock);
     ret = qcow2_get_cluster_offset(bs, offset, &bytes, &cluster_offset);
@@ -1917,6 +1923,11 @@ static int coroutine_fn qcow2_co_block_status(BlockDriverState *bs,
     } else if (ret != QCOW2_CLUSTER_UNALLOCATED) {
         status |= BDRV_BLOCK_DATA;
     }
+    if (s->metadata_preallocation && (status & BDRV_BLOCK_DATA) &&
+        (status & BDRV_BLOCK_OFFSET_VALID))
+    {
+        status |= BDRV_BLOCK_RECURSE;
+    }
     return status;
 }
 
diff --git a/block/qcow2.h b/block/qcow2.h
index 567375e56c..fc1b0d3c1e 100644
--- a/block/qcow2.h
+++ b/block/qcow2.h
@@ -356,6 +356,9 @@ typedef struct BDRVQcow2State {
     int nb_threads;
 
     BdrvChild *data_file;
+
+    bool metadata_preallocation_checked;
+    bool metadata_preallocation;
 } BDRVQcow2State;
 
 typedef struct Qcow2COWRegion {
@@ -655,6 +658,7 @@ int qcow2_change_refcount_order(BlockDriverState *bs, int refcount_order,
                                 void *cb_opaque, Error **errp);
 int qcow2_shrink_reftable(BlockDriverState *bs);
 int64_t qcow2_get_last_cluster(BlockDriverState *bs, int64_t size);
+int qcow2_detect_metadata_preallocation(BlockDriverState *bs);
 
 /* qcow2-cluster.c functions */
 int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,