[Qemu-devel] [RFC 1/1] virtio: fix IO request length in virtio SCSI/block

[Qemu-devel] [RFC 1/1] virtio: fix IO request length in virtio SCSI/block

[Denis V. Lunev]

Linux guests submit IO requests no longer than PAGE_SIZE * max_seg
field reported by SCSI controler. Thus typical sequential read with
1 MB size results in the following pattern of the IO from the guest:
  8,16   1    15754     2.766095122  2071  D   R 2095104 + 1008 [dd]
  8,16   1    15755     2.766108785  2071  D   R 2096112 + 1008 [dd]
  8,16   1    15756     2.766113486  2071  D   R 2097120 + 32 [dd]
  8,16   1    15757     2.767668961     0  C   R 2095104 + 1008 [0]
  8,16   1    15758     2.768534315     0  C   R 2096112 + 1008 [0]
  8,16   1    15759     2.768539782     0  C   R 2097120 + 32 [0]
The IO was generated by
  dd if=/dev/sda of=/dev/null bs=1024 iflag=direct

This effectively means that on rotational disks we will observe 3 IOPS
for each 2 MBs processed. This definitely negatively affects both
guest and host IO performance.

The cure is relatively simple - we should report lengthy scatter-gather
ability of the SCSI controller. Fortunately the situation here is very
good. VirtIO transport layer can accomodate 1024 items in one request
while we are using only 128. This situation is present since almost
very beginning. 2 items are dedicated for request metadata thus we
should publish VIRTQUEUE_MAX_SIZE - 2 as max_seg.

The following pattern is observed after the patch:
  8,16   1     9921     2.662721340  2063  D   R 2095104 + 1024 [dd]
  8,16   1     9922     2.662737585  2063  D   R 2096128 + 1024 [dd]
  8,16   1     9923     2.665188167     0  C   R 2095104 + 1024 [0]
  8,16   1     9924     2.665198777     0  C   R 2096128 + 1024 [0]
which is much better.

The dark side of this patch is that we are tweaking guest visible
parameter, though this should be relatively safe as above transport
layer support is present in QEMU/host Linux for a very long time.
The patch adds configurable property for VirtIO SCSI with a new default
and hardcode option for VirtBlock which does not provide good
configurable framework.

Signed-off-by: Denis V. Lunev <den@openvz.org>
CC: "Michael S. Tsirkin" <mst@redhat.com>
CC: Stefan Hajnoczi <stefanha@redhat.com>
CC: Kevin Wolf <kwolf@redhat.com>
CC: Max Reitz <mreitz@redhat.com>
CC: Paolo Bonzini <pbonzini@redhat.com>
---
Guys, we should make a decision whether this is good to make such guest
visible change or we should link this to the machine type. We have made
very short discussion with Stefan on IRC but without final solution.
This patch is posted to start the discussion.

 include/hw/virtio/virtio-scsi.h | 1 +
 hw/block/virtio-blk.c           | 2 +-
 hw/scsi/vhost-scsi.c            | 2 ++
 hw/scsi/vhost-user-scsi.c       | 2 ++
 hw/scsi/virtio-scsi.c           | 4 +++-
 5 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/include/hw/virtio/virtio-scsi.h b/include/hw/virtio/virtio-scsi.h
index 4c0bcdb..1e5805e 100644
--- a/include/hw/virtio/virtio-scsi.h
+++ b/include/hw/virtio/virtio-scsi.h
@@ -49,6 +49,7 @@ struct VirtIOSCSIConf {
     uint32_t num_queues;
     uint32_t virtqueue_size;
     uint32_t max_sectors;
+    uint32_t max_segments;
     uint32_t cmd_per_lun;
 #ifdef CONFIG_VHOST_SCSI
     char *vhostfd;
diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c
index 05d1440..3f272e1 100644
--- a/hw/block/virtio-blk.c
+++ b/hw/block/virtio-blk.c
@@ -736,7 +736,7 @@ static void virtio_blk_update_config(VirtIODevice *vdev, uint8_t *config)
     blk_get_geometry(s->blk, &capacity);
     memset(&blkcfg, 0, sizeof(blkcfg));
     virtio_stq_p(vdev, &blkcfg.capacity, capacity);
-    virtio_stl_p(vdev, &blkcfg.seg_max, 128 - 2);
+    virtio_stl_p(vdev, &blkcfg.seg_max, VIRTQUEUE_MAX_SIZE - 2);
     virtio_stw_p(vdev, &blkcfg.geometry.cylinders, conf->cyls);
     virtio_stl_p(vdev, &blkcfg.blk_size, blk_size);
     virtio_stw_p(vdev, &blkcfg.min_io_size, conf->min_io_size / blk_size);
diff --git a/hw/scsi/vhost-scsi.c b/hw/scsi/vhost-scsi.c
index 9c1bea8..f93eac6 100644
--- a/hw/scsi/vhost-scsi.c
+++ b/hw/scsi/vhost-scsi.c
@@ -238,6 +238,8 @@ static Property vhost_scsi_properties[] = {
     DEFINE_PROP_UINT32("max_sectors", VirtIOSCSICommon, conf.max_sectors,
                        0xFFFF),
     DEFINE_PROP_UINT32("cmd_per_lun", VirtIOSCSICommon, conf.cmd_per_lun, 128),
+    DEFINE_PROP_UINT32("max_segments", VirtIOSCSICommon, conf.max_segments,
+                       VIRTQUEUE_MAX_SIZE - 2),
     DEFINE_PROP_END_OF_LIST(),
 };
 
diff --git a/hw/scsi/vhost-user-scsi.c b/hw/scsi/vhost-user-scsi.c
index f7561e2..8b02ab1 100644
--- a/hw/scsi/vhost-user-scsi.c
+++ b/hw/scsi/vhost-user-scsi.c
@@ -146,6 +146,8 @@ static Property vhost_user_scsi_properties[] = {
     DEFINE_PROP_BIT64("param_change", VHostUserSCSI, host_features,
                                                      VIRTIO_SCSI_F_CHANGE,
                                                      true),
+    DEFINE_PROP_UINT32("max_segments", VirtIOSCSICommon, conf.max_segments,
+                       VIRTQUEUE_MAX_SIZE - 2),
     DEFINE_PROP_END_OF_LIST(),
 };
 
diff --git a/hw/scsi/virtio-scsi.c b/hw/scsi/virtio-scsi.c
index 3aa9971..5404dde 100644
--- a/hw/scsi/virtio-scsi.c
+++ b/hw/scsi/virtio-scsi.c
@@ -644,7 +644,7 @@ static void virtio_scsi_get_config(VirtIODevice *vdev,
     VirtIOSCSICommon *s = VIRTIO_SCSI_COMMON(vdev);
 
     virtio_stl_p(vdev, &scsiconf->num_queues, s->conf.num_queues);
-    virtio_stl_p(vdev, &scsiconf->seg_max, 128 - 2);
+    virtio_stl_p(vdev, &scsiconf->seg_max, s->conf.max_segments);
     virtio_stl_p(vdev, &scsiconf->max_sectors, s->conf.max_sectors);
     virtio_stl_p(vdev, &scsiconf->cmd_per_lun, s->conf.cmd_per_lun);
     virtio_stl_p(vdev, &scsiconf->event_info_size, sizeof(VirtIOSCSIEvent));
@@ -929,6 +929,8 @@ static Property virtio_scsi_properties[] = {
                                                 VIRTIO_SCSI_F_CHANGE, true),
     DEFINE_PROP_LINK("iothread", VirtIOSCSI, parent_obj.conf.iothread,
                      TYPE_IOTHREAD, IOThread *),
+    DEFINE_PROP_UINT32("max_segments", VirtIOSCSI, parent_obj.conf.max_segments,
+                       VIRTQUEUE_MAX_SIZE - 2),
     DEFINE_PROP_END_OF_LIST(),
 };
 
-- 
2.7.4

Re: [Qemu-devel] [RFC 1/1] virtio: fix IO request length in virtio SCSI/block

[Paolo Bonzini]

On 12/12/2017 16:16, Denis V. Lunev wrote:
> The dark side of this patch is that we are tweaking guest visible
> parameter, though this should be relatively safe as above transport
> layer support is present in QEMU/host Linux for a very long time.
> The patch adds configurable property for VirtIO SCSI with a new default
> and hardcode option for VirtBlock which does not provide good
> configurable framework.

The dark side is fine, but you still need to do backwards-compatibility
properties and also use a property in virtio-blk.

Thanks,

Paolo