[pve-devel] [PATCH qemu v3 05/22] copy-before-write: allow specifying minimum cluster size

[Fiona Ebner]

Useful to make discard-source work in the context of backup fleecing
when the fleecing image has a larger granularity than the backup
target.

Copy-before-write operations will use at least this granularity and in
particular, discard requests to the source node will too. If the
granularity is too small, they will just be aligned down in
cbw_co_pdiscard_snapshot() and thus effectively ignored.

The QAPI uses uint32 so the value will be non-negative, but still fit
into a uint64_t.

Signed-off-by: Fiona Ebner <f.ebner at proxmox.com>
---
 block/block-copy.c         | 17 +++++++++++++----
 block/copy-before-write.c  |  3 ++-
 include/block/block-copy.h |  1 +
 qapi/block-core.json       |  8 +++++++-
 4 files changed, 23 insertions(+), 6 deletions(-)

diff --git a/block/block-copy.c b/block/block-copy.c
index 3c61e52bae..c9a722a5a6 100644
--- a/block/block-copy.c
+++ b/block/block-copy.c
@@ -310,6 +310,7 @@ void block_copy_set_copy_opts(BlockCopyState *s, bool use_copy_range,
 }
 
 static int64_t block_copy_calculate_cluster_size(BlockDriverState *target,
+                                                 int64_t min_cluster_size,
                                                  Error **errp)
 {
     int ret;
@@ -330,7 +331,7 @@ static int64_t block_copy_calculate_cluster_size(BlockDriverState *target,
                     "used. If the actual block size of the target exceeds "
                     "this default, the backup may be unusable",
                     BLOCK_COPY_CLUSTER_SIZE_DEFAULT);
-        return BLOCK_COPY_CLUSTER_SIZE_DEFAULT;
+        return MAX(min_cluster_size, BLOCK_COPY_CLUSTER_SIZE_DEFAULT);
     } else if (ret < 0 && !target_does_cow) {
         error_setg_errno(errp, -ret,
             "Couldn't determine the cluster size of the target image, "
@@ -340,16 +341,18 @@ static int64_t block_copy_calculate_cluster_size(BlockDriverState *target,
         return ret;
     } else if (ret < 0 && target_does_cow) {
         /* Not fatal; just trudge on ahead. */
-        return BLOCK_COPY_CLUSTER_SIZE_DEFAULT;
+        return MAX(min_cluster_size, BLOCK_COPY_CLUSTER_SIZE_DEFAULT);
     }
 
-    return MAX(BLOCK_COPY_CLUSTER_SIZE_DEFAULT, bdi.cluster_size);
+    return MAX(min_cluster_size,
+               MAX(BLOCK_COPY_CLUSTER_SIZE_DEFAULT, bdi.cluster_size));
 }
 
 BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target,
                                      BlockDriverState *copy_bitmap_bs,
                                      const BdrvDirtyBitmap *bitmap,
                                      bool discard_source,
+                                     int64_t min_cluster_size,
                                      Error **errp)
 {
     ERRP_GUARD();
@@ -358,7 +361,13 @@ BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target,
     BdrvDirtyBitmap *copy_bitmap;
     bool is_fleecing;
 
-    cluster_size = block_copy_calculate_cluster_size(target->bs, errp);
+    if (min_cluster_size && !is_power_of_2(min_cluster_size)) {
+        error_setg(errp, "min-cluster-size needs to be a power of 2");
+        return NULL;
+    }
+
+    cluster_size = block_copy_calculate_cluster_size(target->bs,
+                                                     min_cluster_size, errp);
     if (cluster_size < 0) {
         return NULL;
     }
diff --git a/block/copy-before-write.c b/block/copy-before-write.c
index 3503702d71..4a8c5bdb62 100644
--- a/block/copy-before-write.c
+++ b/block/copy-before-write.c
@@ -479,7 +479,8 @@ static int cbw_open(BlockDriverState *bs, QDict *options, int flags,
 
     s->discard_source = flags & BDRV_O_CBW_DISCARD_SOURCE;
     s->bcs = block_copy_state_new(bs->file, s->target, bs, bitmap,
-                                  flags & BDRV_O_CBW_DISCARD_SOURCE, errp);
+                                  flags & BDRV_O_CBW_DISCARD_SOURCE,
+                                  opts->min_cluster_size, errp);
     if (!s->bcs) {
         error_prepend(errp, "Cannot create block-copy-state: ");
         ret = -EINVAL;
diff --git a/include/block/block-copy.h b/include/block/block-copy.h
index bdc703bacd..77857c6c68 100644
--- a/include/block/block-copy.h
+++ b/include/block/block-copy.h
@@ -28,6 +28,7 @@ BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target,
                                      BlockDriverState *copy_bitmap_bs,
                                      const BdrvDirtyBitmap *bitmap,
                                      bool discard_source,
+                                     int64_t min_cluster_size,
                                      Error **errp);
 
 /* Function should be called prior any actual copy request */
diff --git a/qapi/block-core.json b/qapi/block-core.json
index 4297e5beda..33e7e3c090 100644
--- a/qapi/block-core.json
+++ b/qapi/block-core.json
@@ -4825,12 +4825,18 @@
 #     @on-cbw-error parameter will decide how this failure is handled.
 #     Default 0. (Since 7.1)
 #
+# @min-cluster-size: Minimum size of blocks used by copy-before-write
+#     operations.  Has to be a power of 2.  No effect if smaller than
+#     the maximum of the target's cluster size and 64 KiB.  Default 0.
+#     (Since 8.1)
+#
 # Since: 6.2
 ##
 { 'struct': 'BlockdevOptionsCbw',
   'base': 'BlockdevOptionsGenericFormat',
   'data': { 'target': 'BlockdevRef', '*bitmap': 'BlockDirtyBitmap',
-            '*on-cbw-error': 'OnCbwError', '*cbw-timeout': 'uint32' } }
+            '*on-cbw-error': 'OnCbwError', '*cbw-timeout': 'uint32',
+            '*min-cluster-size': 'uint32' } }
 
 ##
 # @BlockdevOptions:
-- 
2.39.2