ivampiresp/Spdk
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

doc/virtio: minor doc updates

Browse Source 
Reworded some sentences, updated current limitation
list, and dropped the outdated `Multiqueue` section.

Change-Id: Id57777430f00b80c68cadf4c600e4ec89fa3c4e0
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/397082
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This commit is contained in:
Dariusz Stojaczyk 2018-01-30 13:53:45 +01:00 committed by Jim Harris
parent 11130d09c8
commit d9243af2b1
1 changed files with 5 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
doc/virtio.md
View File

@ -12,11 +12,6 @@ controller. The host, after sending I/O to the real drive, will put the response
back into the Virtio queue. Then, the response is received by the Virtio SCSI
driver.
The driver, just like the SPDK @ref vhost, is using pollers instead of standard
interrupts to check for an I/O response. It bypasses kernel interrupt and context
switching overhead of QEMU and guest kernel, significantly boosting the overall
I/O performance.
Virtio SCSI driver supports two different usage models:
* PCI - This is the standard mode of operation when used in a guest virtual
machine, where QEMU has presented the virtio-scsi controller as a virtual
@ -24,18 +19,14 @@ PCI device.
* User vhost - Can be used to connect to a vhost-scsi socket directly on the
same host.
# Multiqueue {#virtio_multiqueue}
The Virtio SCSI controller will automatically manage virtio queue distribution.
Currently each thread doing an I/O on a single bdev will get an exclusive queue.
Multi-threaded I/O on bdevs from a single Virtio-SCSI controller is not supported.
The driver, just like the SPDK @ref vhost, is using pollers instead of standard
interrupts to check for an I/O response. If used inside a VM, it bypasses interrupt
and context switching overhead of QEMU and guest kernel, significantly boosting
the overall I/O performance.
# Limitations {#virtio_limitations}
The Virtio SCSI driver is still experimental. Current implementation has many
limitations:
Current Virtio-SCSI implementation has a couple of limitations:
* supports only up to 8 hugepages (implies only 1GB sized pages are practical)
* single LUN per target
* only SPDK vhost-scsi controllers supported
* no RPC
* no multi-threaded I/O for single-queue virtio devices