Re: [uml-devel] [PATCH v3] um: Switch clocksource to hrtimers

On 02/11/15 10:01, Richard Weinberger wrote: > Am 02.11.2015 um 10:53 schrieb Anton Ivanov: >> [snip] >> > I'm pretty sure that you don't see the issue as your Jessy userspace uses > nanosleep periodically. There are quite a few things running so this may indeed be the case.

Re: [uml-devel] [PATCH v3] um: Switch clocksource to hrtimers

Am 02.11.2015 um 15:30 schrieb Anton Ivanov: > On 02/11/15 10:01, Richard Weinberger wrote: >> Am 02.11.2015 um 10:53 schrieb Anton Ivanov: >>> [snip] >>> >> I'm pretty sure that you don't see the issue as your Jessy userspace >> uses nanosleep periodically. > There are quite a few

Re: [uml-devel] [PATCH v3] um: Switch clocksource to hrtimers

I was testing under similar conditions (CPU pinning using taskset -c 0 on a multicore). I have removed it and run some retests - I cannot reproduce the hang at this point with my config I am going to run a defconfig and compare the results to see if this will give me any insights on the root

Re: [uml-devel] [PATCH v3] um: Switch clocksource to hrtimers

On 02/11/15 08:37, Richard Weinberger wrote: > Hi! > > Am 02.11.2015 um 09:14 schrieb Anton Ivanov: >> I was testing under similar conditions (CPU pinning using taskset -c 0 on a >> multicore). >> >> I have removed it and run some retests - I cannot reproduce the hang at this >> point with my

Re: [uml-devel] [PATCH v3] um: Switch clocksource to hrtimers

Hi! Am 02.11.2015 um 09:14 schrieb Anton Ivanov: > I was testing under similar conditions (CPU pinning using taskset -c 0 on a > multicore). > > I have removed it and run some retests - I cannot reproduce the hang at this > point with my config > > I am going to run a defconfig and compare

Re: [uml-devel] [PATCH v3] um: Switch clocksource to hrtimers

On 02/11/15 15:25, Richard Weinberger wrote: > Am 02.11.2015 um 15:30 schrieb Anton Ivanov: >> On 02/11/15 10:01, Richard Weinberger wrote: >>> Am 02.11.2015 um 10:53 schrieb Anton Ivanov: [snip] >>> I'm pretty sure that you don't see the issue as your Jessy userspace >>> uses

Re: [uml-devel] [PATCH v3] um: Switch clocksource to hrtimers

On 02/11/15 08:52, Richard Weinberger wrote: > Am 02.11.2015 um 09:41 schrieb Anton Ivanov: >> On 02/11/15 08:37, Richard Weinberger wrote: >>> Hi! >>> >>> Am 02.11.2015 um 09:14 schrieb Anton Ivanov: I was testing under similar conditions (CPU pinning using taskset -c 0 on a

Re: [uml-devel] [PATCH v3] um: Switch clocksource to hrtimers

[snip] >>> I'm pretty sure that you don't see the issue as your Jessy userspace uses >>> nanosleep periodically. >> There are quite a few things running so this may indeed be the case. >> >> What do you use for userspace (so I can try to reproduce this and debug it)? > Debian Squeeze amd64 with

Re: [uml-devel] [PATCH v3] um: Switch clocksource to hrtimers

Am 02.11.2015 um 09:41 schrieb Anton Ivanov: > On 02/11/15 08:37, Richard Weinberger wrote: >> Hi! >> >> Am 02.11.2015 um 09:14 schrieb Anton Ivanov: >>> I was testing under similar conditions (CPU pinning using taskset -c 0 on a >>> multicore). >>> >>> I have removed it and run some retests - I

Re: [uml-devel] [PATCH v3] um: Switch clocksource to hrtimers

Am 02.11.2015 um 09:57 schrieb Anton Ivanov: > On 02/11/15 08:52, Richard Weinberger wrote: >> Am 02.11.2015 um 09:41 schrieb Anton Ivanov: >>> On 02/11/15 08:37, Richard Weinberger wrote: Hi! Am 02.11.2015 um 09:14 schrieb Anton Ivanov: > I was testing under similar conditions

Re: [uml-devel] [PATCH v3] um: Switch clocksource to hrtimers

On 02/11/15 10:59, Anton Ivanov wrote: > On 02/11/15 10:01, Richard Weinberger wrote: >> Am 02.11.2015 um 10:53 schrieb Anton Ivanov: >>> [snip] >>> >> I'm pretty sure that you don't see the issue as your Jessy >> userspace uses nanosleep periodically. > There are quite a few things

Re: [uml-devel] [PATCH v3] um: Switch clocksource to hrtimers

On 02/11/15 10:01, Richard Weinberger wrote: > Am 02.11.2015 um 10:53 schrieb Anton Ivanov: >> [snip] >> > I'm pretty sure that you don't see the issue as your Jessy userspace uses > nanosleep periodically. There are quite a few things running so this may indeed be the case.

Re: [uml-devel] [PATCH v3] um: Switch clocksource to hrtimers

Am 31.10.2015 um 16:24 schrieb Thomas Meyer: > Am Samstag, den 31.10.2015, 16:21 +0100 schrieb Richard Weinberger: >> Am 31.10.2015 um 16:16 schrieb Thomas Meyer: >>> mhh. strange. I didn't see this behaviour on my machine, but my >>> machine >>> is a rare single core system so, likely a race

Re: [uml-devel] [PATCH v3] um: Switch clocksource to hrtimers

Am 31.10.2015 um 17:22 schrieb Anton Ivanov: > Richard, can you send me your config. Sure. It is basically a defconfig. > I have had it running for a couple of days before submission both under load > and idle it was doing OK. Well, what userspace did you try? I did some more tests, if

Re: [uml-devel] [PATCH v3] um: Switch clocksource to hrtimers

Am 31.10.2015 um 16:44 schrieb Thomas Meyer: > Am Samstag, den 31.10.2015, 16:30 +0100 schrieb Richard Weinberger: >> Am 31.10.2015 um 16:24 schrieb Thomas Meyer: >>> Am Samstag, den 31.10.2015, 16:21 +0100 schrieb Richard Weinberger: Am 31.10.2015 um 16:16 schrieb Thomas Meyer: > mhh.

Re: [uml-devel] [PATCH v3] um: Switch clocksource to hrtimers

On 31/10/15 19:08, Richard Weinberger wrote: > Am 31.10.2015 um 17:22 schrieb Anton Ivanov: >> Richard, can you send me your config. > Sure. It is basically a defconfig. I am dragging an old config from some work I did a while back. I will scrap it and do a defconfig build one I get back home (I

Re: [uml-devel] [PATCH v3] um: Switch clocksource to hrtimers

On Thu, Oct 29, 2015 at 7:23 AM, Anton Ivanov wrote: > I got the first patchset to build, it works very well on a single core > host or with CPU pinning of the UML - the performance gain is > 25%. > > However, I introduced a race somewhere along the way - it

Re: [uml-devel] [PATCH v3] um: Switch clocksource to hrtimers

Am Samstag, den 31.10.2015, 16:13 +0100 schrieb Richard Weinberger: > Am 31.10.2015 um 16:10 schrieb Thomas Meyer: > > Am Samstag, den 31.10.2015, 14:54 +0100 schrieb Richard Weinberger: > > > On Thu, Oct 29, 2015 at 7:23 AM, Anton Ivanov > > > wrote: > > > > I got

Re: [uml-devel] [PATCH v3] um: Switch clocksource to hrtimers

Am Samstag, den 31.10.2015, 16:21 +0100 schrieb Richard Weinberger: > Am 31.10.2015 um 16:16 schrieb Thomas Meyer: > > mhh. strange. I didn't see this behaviour on my machine, but my > > machine > > is a rare single core system so, likely a race condition while > > relaying > > the timer interrupt

Re: [uml-devel] [PATCH v3] um: Switch clocksource to hrtimers

Am Samstag, den 31.10.2015, 16:30 +0100 schrieb Richard Weinberger: > Am 31.10.2015 um 16:24 schrieb Thomas Meyer: > > Am Samstag, den 31.10.2015, 16:21 +0100 schrieb Richard Weinberger: > > > Am 31.10.2015 um 16:16 schrieb Thomas Meyer: > > > > mhh. strange. I didn't see this behaviour on my

Re: [uml-devel] [PATCH v3] um: Switch clocksource to hrtimers

Am 31.10.2015 um 16:10 schrieb Thomas Meyer: > Am Samstag, den 31.10.2015, 14:54 +0100 schrieb Richard Weinberger: >> On Thu, Oct 29, 2015 at 7:23 AM, Anton Ivanov >> wrote: >>> I got the first patchset to build, it works very well on a single >>> core >>> host or

Re: [uml-devel] [PATCH v3] um: Switch clocksource to hrtimers

Am 31.10.2015 um 16:16 schrieb Thomas Meyer: > mhh. strange. I didn't see this behaviour on my machine, but my machine > is a rare single core system so, likely a race condition while relaying > the timer interrupt to the userspace process. Here I can trigger it by starting UML, logging in and

Re: [uml-devel] [PATCH v3] um: Switch clocksource to hrtimers

Am Samstag, den 31.10.2015, 14:54 +0100 schrieb Richard Weinberger: > On Thu, Oct 29, 2015 at 7:23 AM, Anton Ivanov > wrote: > > I got the first patchset to build, it works very well on a single > > core > > host or with CPU pinning of the UML - the performance

Re: [uml-devel] [PATCH v3] um: Switch clocksource to hrtimers

Richard, can you send me your config. I have had it running for a couple of days before submission both under load and idle it was doing OK. A On 31/10/15 15:44, Thomas Meyer wrote: > Am Samstag, den 31.10.2015, 16:30 +0100 schrieb Richard Weinberger: >> Am 31.10.2015 um 16:24 schrieb Thomas

Re: [uml-devel] [PATCH v3] um: Switch clocksource to hrtimers

I got the first patchset to build, it works very well on a single core host or with CPU pinning of the UML - the performance gain is > 25%. However, I introduced a race somewhere along the way - it crashes UML reliably if you do not pin CPUs. I will debug it, fix it and submit. I am guessing a

Re: [uml-devel] [PATCH v3] um: Switch clocksource to hrtimers

Hi! Am 25.10.2015 um 19:46 schrieb Anton Ivanov: > Hi List, hi Richard, > > I am going to sort out the UBD patchset next as that has no dependencies on > timer and the other stuff which is waiting in the queue behind the timers. > > That should give UML a significant boost. It is nothing

Re: [uml-devel] [PATCH v3] um: Switch clocksource to hrtimers

Hi List, hi Richard, I am going to sort out the UBD patchset next as that has no dependencies on timer and the other stuff which is waiting in the queue behind the timers. That should give UML a significant boost. It is nothing particularly revolutionary (qemu has been using some of that for

[uml-devel] [PATCH v3] um: Switch clocksource to hrtimers

Background: UML is using an obsolete itimer call for all timers and "polls" for kernel space timer firing in its userspace portion resulting in a long list of bugs and incorrect behaviour(s). It also uses ITIMER_VIRTUAL for its timer which results in the timer being dependent on it running and the