APPLIED: [SRU][Q/P/N:linux-azure][PATCH 0/1] [STORVSC] [Backport] Backport for Linux storage driver patch for fixing performance issues

John Cabaj john.cabaj at canonical.com
Fri Oct 24 19:07:25 UTC 2025


On 10/17/25 1:30 PM, John Cabaj wrote:
> BugLink: https://bugs.launchpad.net/bugs/2128842
> 
> SRU Justification
> 
> [Impact]
> 
> * Microsoft requested patch to improve efficiency of SCSI I/O on Hyper-V by issuing IO on same CPU as return CPU.
> 
> [Fix]
> 
> * clean cherry-pick of linux-next patch:
>      * b69ffeaa0ae4: "scsi: storvsc: Prefer returning channel with the same CPU as on the I/O issuing CPU"
> 
> [Test Plan]
> 
> * Compile tested
> * Microsoft to test
> 
> [Regression potential]
> 
> * Patch limited to SCSI module. Possible regressions could result in unexpected performance desegregation in non-Hyper-V cases.
> 
> [Other info]
> 
> * SF#00420316
> 
> Long Li (1):
>    scsi: storvsc: Prefer returning channel with the same CPU as on the
>      I/O issuing CPU
> 
>   drivers/scsi/storvsc_drv.c | 96 ++++++++++++++++++--------------------
>   1 file changed, 45 insertions(+), 51 deletions(-)
> 

Applied to Questing, Plucky, and Noble linux-azure master-next branches.


Thanks,
j-c




More information about the kernel-team mailing list