lkml.org 
[lkml]   [2017]   [Dec]   [13]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH] IPI performance benchmark
On Mon, Dec 11, 2017 at 05:30:25PM +0100, Christian Borntraeger wrote:
>
>
> On 12/11/2017 03:55 PM, Yury Norov wrote:
> > On Mon, Dec 11, 2017 at 03:35:02PM +0100, Christian Borntraeger wrote:
> >>
> >>
> >> On 12/11/2017 03:16 PM, Yury Norov wrote:
> >>> This benchmark sends many IPIs in different modes and measures
> >>> time for IPI delivery (first column), and total time, ie including
> >>> time to acknowledge the receive by sender (second column).
> >>>
> >>> The scenarios are:
> >>> Dry-run: do everything except actually sending IPI. Useful
> >>> to estimate system overhead.
> >>> Self-IPI: Send IPI to self CPU.
> >>> Normal IPI: Send IPI to some other CPU.
> >>> Broadcast IPI: Send broadcast IPI to all online CPUs.
> >>>
> >>> For virtualized guests, sending and reveiving IPIs causes guest exit.
> >>> I used this test to measure performance impact on KVM subsystem of
> >>> Christoffer Dall's series "Optimize KVM/ARM for VHE systems".
> >>>
> >>> https://www.spinics.net/lists/kvm/msg156755.html
> >>>
> >>> Test machine is ThunderX2, 112 online CPUs. Below the results normalized
> >>> to host dry-run time. Smaller - better.
> >>>
> >>> Host, v4.14:
> >>> Dry-run: 0 1
> >>> Self-IPI: 9 18
> >>> Normal IPI: 81 110
> >>> Broadcast IPI: 0 2106
> >>>
> >>> Guest, v4.14:
> >>> Dry-run: 0 1
> >>> Self-IPI: 10 18
> >>> Normal IPI: 305 525
> >>> Broadcast IPI: 0 9729
> >>>
> >>> Guest, v4.14 + VHE:
> >>> Dry-run: 0 1
> >>> Self-IPI: 9 18
> >>> Normal IPI: 176 343
> >>> Broadcast IPI: 0 9885
> [...]
> >>> +static int __init init_bench_ipi(void)
> >>> +{
> >>> + ktime_t ipi, total;
> >>> + int ret;
> >>> +
> >>> + ret = bench_ipi(NTIMES, DRY_RUN, &ipi, &total);
> >>> + if (ret)
> >>> + pr_err("Dry-run FAILED: %d\n", ret);
> >>> + else
> >>> + pr_err("Dry-run: %18llu, %18llu ns\n", ipi, total);
> >>
> >> you do not use NTIMES here to calculate the average value. Is that intended?
> >
> > I think, it's more visually to represent all results in number of dry-run
> > times, like I did in patch description. So on kernel side I expose raw data
> > and calculate final values after finishing tests.
>
> I think it is highly confusing that the output from the patch description does not
> match the output from the real module. So can you make that match at least?

I think so. That's why I noticed that results are normalized to host dry-run
time, even more, they are small and better for human perception.

I was recommended not to public raw data, you'd understand. If this is
the blocker, I can post results from QEMU-hosted kernel.

> > If you think that average values are preferable, I can do that in v2.
>
> The raw numbers a propably fine, but then you might want to print the number of
> loop iterations in the output.

It's easy to do. But this number is the same for all tests, and what
really interesting is relative numbers, so I decided not to trash output.
If you insist on printing iterations number, just let me know and I'll add it.

> If we want to do something fancy, we could do a combination of a smaller inner
> loop doing the test, then an outer loops redoing the inner loop and then you
> can do some min/max/average calculation. Not s

\
 
 \ /
  Last update: 2017-12-13 12:24    [W:0.068 / U:2.832 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site