qemu/block/export at 122a3dd50a75c729c408f4706b0b7517b02b8215 - qemu

mirror of https://github.com/qemu/qemu.git synced 2026-07-08 17:46:10 +00:00

Files

Max Makarov 99bfc1c754 vhost-user-blk-server: fix opt_io_size=1 causing severe Windows I/O degradation

The QSD vhost-user-blk export sets opt_io_size=1 and min_io_size=1 in
the virtio config. These values are reported to the guest through the
VPD Block Limits page as OptimalTransferLength=1 block (512 bytes)
and OptimalTransferLengthGranularity=1 block.

Windows respects these hints and splits all I/O into ~512-byte
requests, causing ~100x sequential throughput degradation (150 MB/s
instead of 15+ GB/s). Linux is unaffected as its block layer ignores
these values.

Set both to 0 which means "not reported" per the SCSI Block Limits
VPD spec, allowing Windows to use its own optimal I/O size defaults.

Signed-off-by: Max Makarov <maxpain@linux.com>
Message-ID: <20260330193451.76037-1-maxpain@linux.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

2026-03-31 15:45:32 +02:00

export.c

block/export: Add multi-threading interface

2026-03-10 12:11:57 +01:00

fuse.c

fuse: Implement multi-threading

2026-03-10 12:12:02 +01:00

meson.build

vduse-blk: Implement vduse-blk export

2022-06-24 17:07:06 +02:00

vduse-blk.c

block/export: Add multi-threading interface