On Fri, Jun 26, 2026 at 1:44 PM Niklas Cassel <[email protected]> wrote: > > Hello Sam, > > On Tue, Jun 23, 2026 at 08:48:28PM +0200, Sam Li wrote: > > virtio_blk_submit_multireq() fuses adjacent in-zone writes into a > > single request. On a zoned backend, a merged zone append request > > that straddles a zone boundary is rejected by the device because > > each write must stay within a single zone. > > > > Add a bail condition to the merge coalescer: if combining the > > candidate request into the current batch would cross a zone > > boundary, flush the current batch and start a new one. > > > > Signed-off-by: Sam Li <[email protected]> > > --- > > block/block-backend.c | 11 +++++++++++ > > hw/block/virtio-blk.c | 22 +++++++++++++++++++++- > > include/system/block-backend-io.h | 1 + > > 3 files changed, 33 insertions(+), 1 deletion(-) > > > > diff --git a/block/block-backend.c b/block/block-backend.c > > index 37ba7e9fc4..049e70ddcb 100644 > > --- a/block/block-backend.c > > +++ b/block/block-backend.c > > @@ -2326,6 +2326,17 @@ uint32_t blk_get_request_alignment(BlockBackend *blk) > > return bs ? bs->bl.request_alignment : BDRV_SECTOR_SIZE; > > } > > > > +/* > > + * Returns the zone size in bytes for a zoned backend, or 0 if @blk does > > + * not present zoned geometry. > > + */ > > +uint64_t blk_get_zone_size(BlockBackend *blk) > > +{ > > + BlockDriverState *bs = blk_bs(blk); > > + IO_CODE(); > > + return bs ? bs->bl.zone_size : 0; > > +} > > Personally, I would add this new API in a separate patch, but either way > is fine with me. > > > > + > > /* Returns the optimal write zeroes alignment, in bytes; guaranteed > > nonzero */ > > uint32_t blk_get_pwrite_zeroes_alignment(BlockBackend *blk) > > { > > diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c > > index 6b92066aff..39750fa1c0 100644 > > --- a/hw/block/virtio-blk.c > > +++ b/hw/block/virtio-blk.c > > @@ -294,6 +294,9 @@ static void virtio_blk_submit_multireq(VirtIOBlock *s, > > MultiReqBuffer *mrb) > > int i = 0, start = 0, num_reqs = 0, niov = 0, nb_sectors = 0; > > uint32_t max_transfer; > > int64_t sector_num = 0; > > + uint64_t zone_size = blk_get_zone_size(s->blk); > > + bool zone_cross; > > + int64_t zone_sector, end_sector; > > > > if (mrb->num_reqs == 1) { > > submit_requests(s, mrb, 0, 1, -1); > > @@ -309,17 +312,34 @@ static void virtio_blk_submit_multireq(VirtIOBlock > > *s, MultiReqBuffer *mrb) > > for (i = 0; i < mrb->num_reqs; i++) { > > VirtIOBlockReq *req = mrb->reqs[i]; > > if (num_reqs > 0) { > > + zone_cross = false; > > + > > + /* > > + * On zoned backends, a single backend write must not span a > > zone > > + * boundary. Bail out of merging if combining req into the > > current > > + * batch would straddle a zone. > > + */ > > Like Stefan said in v11, as per the virtio spec, this applies to both > reads and writes. The code is doing the right thing, but the comment > should probably be updated to reflect that.
Ok, thanks! I'll add the reads to the comment. > > > Kind regards, > Niklas
