On Jun 20, 2016, at 13:25, Paul Mackerras <pau...@ozlabs.org> wrote:
On Mon, May 16, 2016 at 02:58:18PM +0800, Li Zhong wrote:
This patch tries to use smaller locks for each irq in the ics, instead
of a lock at the ics level, to provide better scalability.
This looks like a worth-while thing to do. Do you have any
performance measurements to justify the change? This will increase
the size of struct kvmppc_ics by 4kB, so it would be useful to show
the performance increase that justifies it.
Actually, I saw some “improvement” because of the vcpus were not binded, io jobs and irqs on the guest were not binded. After I fixed those random factors, the result became stable, but I couldn’t see any obvious improvements from the patches...
Maybe I need find some other test cases that could support this change.
Also, when you resend the patch, please make the patch description
more definite - say "With this patch, we use" rather than "this patch
tries to use", for instance.
OK, I will change that when doing a resend, if I can find some workload that could benefit from this change.
Thanks, Zhong
Regards,
Paul.
_______________________________________________
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev
|
_______________________________________________
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev
