dsg/vhost-device
2
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
vhost-device/vhost-device-scsi
History
Exact
Davíð Steinn Geirsson 1c021aaea6 Use our vhost fork for all crates and add GPU flake package 
Use our vhost fork for all crates. It has SHMEM and GPU backend support.
Add a Nix flake package for vhost-device-gpu with the virgl backend enabled.

Also fixes duplicate imports in vhost-device-gpu/src/backend/virgl.rs.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-22 19:10:55 +00:00
..
src chore: remove pub visibility from exit event fields 2025-11-19 12:09:37 +02:00
test Move all crates to workspace root 2023-10-16 12:03:57 +05:30
ARCHITECTURE.md Move all crates to workspace root 2023-10-16 12:03:57 +05:30
Cargo.toml Use our vhost fork for all crates and add GPU flake package 2026-03-22 19:10:55 +00:00
CHANGELOG.md chore: standardize changelogs 2024-07-24 19:37:19 +05:30
LICENSE-APACHE Move all crates to workspace root 2023-10-16 12:03:57 +05:30
LICENSE-BSD-3-Clause Move all crates to workspace root 2023-10-16 12:03:57 +05:30
README.md scsi: README.md document --solid-state CLI option 2026-03-02 14:37:48 +01:00

README.md

vhost-device-scsi

This is a Rust implementation of a vhost-device-scsi daemon.

Usage

Run the vhost-device-scsi daemon:

vhost-device-scsi -r --socket-path /tmp/vhost-user-scsi.sock /path/to/image.raw /path/to/second-image.raw ...

Run QEMU:

qemu-system-x86_64 ... \
  -device vhost-user-scsi-pci,num_queues=1,param_change=off,chardev=vus \
  -chardev socket,id=vus,path=/tmp/vhost-user-scsi.sock \
  # must match total guest memory
  -object memory-backend-memfd,id=mem,size=384M,share=on \
  -numa node,memdev=mem

Options

  • -r, --read-only: Treat the disk images as read-only.

  • --solid-state: Tell the guest that this disk is non-rotational

  • -s, --socket-path: Location of vhost-user socket (required)

Limitations

We are currently only supporting a single request queue and do not support dynamic reconfiguration of LUN parameters (VIRTIO_SCSI_F_CHANGE).

Features

This crate is a work-in-progress. Currently, it's possible to mount and read up to 256 read-only raw disk images. Some features we might like to add at some point, roughly ordered from sooner to later:

  • Write support. This should just be a matter of implementing the WRITE command, but there's a bit of complexity around writeback caching we need to make sure we get right.
  • Support more LUNs. virtio-scsi supports up to 16384 LUNs per target. After 256, the LUN encoding format is different; it's nothing too complicated, but I haven't gotten around to implementing it.
  • Concurrency. Currently, we process SCSI commands one at a time. Eventually, it'd be a good idea to use threads or some fancy async/io_uring stuff to concurrently handle multiple commands. virtio-scsi also allows for multiple request queues, allowing the guest to submit requests from multiple cores in parallel; we should support that.
  • iSCSI passthrough. This shouldn't be too bad, but it might be a good idea to decide on a concurrency model (threads or async) before we spend too much time here.