* Re: [Xenomai] Philippe Gerum : lib/cobalt: add config switch to enable lazy setsched update mode [not found] <E1aq1Ri-0002Ry-RW@sd-51317.xenomai.org> @ 2016-04-25 15:00 ` Jan Kiszka 2016-04-25 16:05 ` Philippe Gerum 0 siblings, 1 reply; 2+ messages in thread From: Jan Kiszka @ 2016-04-25 15:00 UTC (permalink / raw) To: xenomai, Philippe Gerum On 2016-04-12 18:45, git repository hosting wrote: > Module: xenomai-3 > Branch: wip/dovetail > Commit: 867070475384652b4e3d4a25f5ad983732a59a7e > URL: http://git.xenomai.org/?p=xenomai-3.git;a=commit;h=867070475384652b4e3d4a25f5ad983732a59a7e > > Author: Philippe Gerum <rpm@xenomai.org> > Date: Sun Mar 20 17:58:33 2016 +0100 > > lib/cobalt: add config switch to enable lazy setsched update mode > > --enable-lazy-setsched should be given for enabling lazy propagation > of scheduling parameters upon calls to pthread_setschedparam*(), > sched_setscheduler(). Defaults to off. Missed this so far: Is there particular reason to keep it off by default? Regression concerns (i.e. this will be only off in the beginning) or downsides of the lazy implementation? Jan -- Siemens AG, Corporate Technology, CT RDA ITP SES-DE Corporate Competence Center Embedded Linux ^ permalink raw reply [flat|nested] 2+ messages in thread
* Re: [Xenomai] Philippe Gerum : lib/cobalt: add config switch to enable lazy setsched update mode 2016-04-25 15:00 ` [Xenomai] Philippe Gerum : lib/cobalt: add config switch to enable lazy setsched update mode Jan Kiszka @ 2016-04-25 16:05 ` Philippe Gerum 0 siblings, 0 replies; 2+ messages in thread From: Philippe Gerum @ 2016-04-25 16:05 UTC (permalink / raw) To: Jan Kiszka, xenomai On 04/25/2016 05:00 PM, Jan Kiszka wrote: > On 2016-04-12 18:45, git repository hosting wrote: >> Module: xenomai-3 >> Branch: wip/dovetail >> Commit: 867070475384652b4e3d4a25f5ad983732a59a7e >> URL: http://git.xenomai.org/?p=xenomai-3.git;a=commit;h=867070475384652b4e3d4a25f5ad983732a59a7e >> >> Author: Philippe Gerum <rpm@xenomai.org> >> Date: Sun Mar 20 17:58:33 2016 +0100 >> >> lib/cobalt: add config switch to enable lazy setsched update mode >> >> --enable-lazy-setsched should be given for enabling lazy propagation >> of scheduling parameters upon calls to pthread_setschedparam*(), >> sched_setscheduler(). Defaults to off. > > Missed this so far: Is there particular reason to keep it off by > default? Regression concerns (i.e. this will be only off in the > beginning) or downsides of the lazy implementation? Basically, this is turned off by default because of the weird effects on the regular glibc behavior due to bypassing the priority cache (e.g. standard prio protect mutexes). At any rate, people switching this on must know what they are doing, including the side-effects on the glibc, and implicitly accept them. Conversely, people who don't need this option should not have to bother about those side-effects. -- Philippe. ^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2016-04-25 16:05 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
[not found] <E1aq1Ri-0002Ry-RW@sd-51317.xenomai.org>
2016-04-25 15:00 ` [Xenomai] Philippe Gerum : lib/cobalt: add config switch to enable lazy setsched update mode Jan Kiszka
2016-04-25 16:05 ` Philippe Gerum
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.