From: Andrii Tseglytskyi <andrii.tseglytskyi@globallogic.com>
To: "xen-devel@lists.xen.org" <xen-devel@lists.xen.org>,
Ian Campbell <Ian.Campbell@citrix.com>,
Julien Grall <julien.grall@linaro.org>,
Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Subject: Re: [RFC] Interrupt latency measurement technique
Date: Wed, 27 Aug 2014 13:07:36 +0300 [thread overview]
Message-ID: <CAH_mUMP56UPhEAFUDrbccA4qc-UiOBknZ3gcOdcK96LctcR3Bw@mail.gmail.com> (raw)
In-Reply-To: <CAH_mUMMTkfrT5vuMSqXKGwOYS_WuCb9ztzGU2d-StB8YsLrZ5w@mail.gmail.com>
Test setup is the following:
Platform - Jacinto6 (OMAP5) with two ARMv7 cores (Cortex A15), 1.5 Gb of RAM
Hypervisor - Xen 4.4 stable
Dom0 - Linux 3.8 running with 2 vcpus, 128 Mb RAM
DomU was not launched during the test
Regards,
Andrii
On Wed, Aug 27, 2014 at 12:14 PM, Andrii Tseglytskyi
<andrii.tseglytskyi@globallogic.com> wrote:
> Hi,
>
> I need to measure IRQ latency introduced by Xen: (GIC -> Xen IRQ
> handler -> Dom0 IRQ handler)
> I need to know how many time I spend in Xen IRQ handler.
>
> Can someone comment - is the following algorithm works:
>
> - in function xen/arch/arm/gic.c: gic_interrupt() store timer counter value:
> xen_timer_val = READ_SYSREG64(CNTPCT_EL0) - READ_SYSREG64(CNTVOFF_EL2)
>
> - in any IRQ handler in dom0 store timer counter value:
> dom0_timer_val = READ_SYSREG64(CNTPCT_EL0)
>
> - calculate time diff in nanoseconds:
> time_diff_ns = ticks_to_ns(dom0_timer_val - xen_timer_val)
>
> Using this technique I measured display IRQ latency and got about
> - 20 to 30 usec latency on 1 GHz MPU frequency
> - 10 to 20 usec latencyon 1.5 GHz MPU frequency
>
> Are these numbers expectable? Can this technique be used?
>
> Regards,
> Andrii
>
> --
>
> Andrii Tseglytskyi | Embedded Dev
> GlobalLogic
> www.globallogic.com
--
Andrii Tseglytskyi | Embedded Dev
GlobalLogic
www.globallogic.com
next prev parent reply other threads:[~2014-08-27 10:07 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-08-27 9:14 [RFC] Interrupt latency measurement technique Andrii Tseglytskyi
2014-08-27 10:07 ` Andrii Tseglytskyi [this message]
2014-08-29 18:07 ` Jonathan Fraser
2014-08-29 20:11 ` Andrii Tseglytskyi
2014-08-28 1:07 ` Ian Campbell
2014-08-28 7:58 ` Andrii Tseglytskyi
2014-08-28 17:47 ` Ian Campbell
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=CAH_mUMP56UPhEAFUDrbccA4qc-UiOBknZ3gcOdcK96LctcR3Bw@mail.gmail.com \
--to=andrii.tseglytskyi@globallogic.com \
--cc=Ian.Campbell@citrix.com \
--cc=julien.grall@linaro.org \
--cc=stefano.stabellini@eu.citrix.com \
--cc=xen-devel@lists.xen.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).