[systemd-devel] [help] Benchmarking software shows degraded performance

[Cristian Rodríguez]

On Thu, Nov 30, 2023 at 1:17 AM <Nayabbasha.Sayed at microchip.com> wrote:

> Hi all,
>
> We have decided to replace buysbox init with systemd in our development
> boards Buildroot images.
>
> One of the boards -
> https://www.microchip.com/en-us/development-tool/atsama5d27-som1-ek1
>
> While we notice the reduction in boot time as well as the systemd
> features useful (ex: systemd-networkd), we notice the degraded
> performance when we run bench-marking software.
>
> Benchmarking software uri - https://github.com/linux4sam/egt-benchmark.
>
> One of the benchmark case is, where it simply opens graphical window on
> LCD screen and then simply closes it. For this case, the egt-benchmark
> shows 9 iterations/sec for busybox init. And it's only 5 iterations/sec
> for systemd init.
>
> We have gone through some of the techniques mentioned in the bootlin's
> debugging slides
> (https://bootlin.com/doc/training/debugging/debugging-slides.pdf) to
> optimize the system performance. Didn't help much.
>
> Note that all the development boards we use are single core SoCs.
>
> Any pointers that would lead to narrow down the issue would be grateful
> here. Thanks in advance.
>
> --
> Thanks,
> Nayab
>
>
Nayab:

Without profiler data before/after it is just speculation that systemd got
anything to do with this.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.freedesktop.org/archives/systemd-devel/attachments/20231130/9142a7fb/attachment.htm>