Hi, On 03/09/14 10:18, Juri Lelli wrote: > Hi, > > On 03/09/14 07:49, Luca Abeni wrote: >> Hi, >> >> On 09/02/2014 11:45 PM, Henrik Austad wrote: >> [...] >>>> + On multiprocessor systems with global EDF scheduling (non partitioned >>>> + systems), a sufficient test for schedulability can not be based on the >>>> + utilisations (it can be shown that task sets with utilisations slightly >>>> + larger than 1 can miss deadlines regardless of the number of CPUs M). >>>> + However, as previously stated, enforcing that the total utilisation is smaller >>>> + than M is enough to guarantee that non real-time tasks are not starved and >>>> + that the tardiness of real-time tasks has an upper bound. >>> >>> I'd _really_ appreciate a link to a paper where all of this is presented >>> and proved! >> Well, my original plan was to add the bibliography in the next round of patches... >> Is this ok? >> >> [...] >>>> + As already stated in Section 3, a necessary condition to be respected to >>>> + correctly schedule a set of real-time tasks is that the total utilisation >>>> + is smaller than M. When talking about -deadline tasks, this requires to >>>> + impose that the sum of the ratio between runtime and period for all tasks >>>> + is smaller than M. >>> >>> "This requires to impose that .." uhm, what? Drop 'to impose'. >> Ok. I'll send an updated patch to Juri in few days >> >> >>>> [...] Notice that the ratio runtime/period is equivalent to >>>> + the utilisation of a "traditional" real-time task, and is also often >>>> + referred to as "bandwidth". >>>> + The interface used to control the CPU bandwidth that can be allocated >>>> + to -deadline tasks is similar to the one already used for -rt >>>> tasks with real-time group scheduling (a.k.a. RT-throttling - see >>>> Documentation/scheduler/sched-rt-group.txt), and is based on readable/ >>>> writable control files located in procfs (for system wide settings). >>>> @@ -232,8 +285,16 @@ CONTENTS >>>> 950000. With rt_period equal to 1000000, by default, it means that -deadline >>>> tasks can use at most 95%, multiplied by the number of CPUs that compose the >>>> root_domain, for each root_domain. >>>> - >>>> - A -deadline task cannot fork. >>>> + This means that non -deadline tasks will receive at least 5% of the CPU time, >>>> + and that -deadline tasks will receive their runtime with a guaranteed >>>> + worst-case delay respect to the "deadline" parameter. If "deadline" = "period" >>>> + and the cpuset mechanism is used to implement partitioned scheduling (see >>>> + Section 5), then this simple setting of the bandwidth management is able to >>>> + deterministically guarantee that -deadline tasks will receive their runtime >>>> + in a period. >>> >>> The whole 950000 / 1000000, is at least 50 *consecutive* ms given to non >>> rt/dl tasks every second, or is this more finegrained now? >>> >>> If the 50ms can be given in a single go, then I don't think you can >>> guarantee that deadline-tasks will receive their runtime in a period - a >>> period can be <50ms, no? >> Uhmm... Maybe there is something I am missing in how the SCHED_DEADLINE admission >> control is implemented, but I do not know about any "50 consecutive ms to non dl >> tasks" rule. I agree that if there is such a rule then deadline tasks are screwed. >> Juri? >> >> > > In SCHED_DEADLINE we use those values only at admission control time (when > the user calls sched_setattr()). Then, at runtime, we use tasks' parameters > to perform scheduling. So there is no consecutive 50ms time for !SCHED_DEADLINE > tasks. > > We could probably clarify this aspect in the previous patch with something > like this: > > [snip] > + The interface used to control the fraction of CPU bandwidth that can be > + allocated to -deadline tasks is similar to the one already used for -rt > + tasks with real-time group scheduling (a.k.a. RT-throttling - see > + Documentation/scheduler/sched-rt-group.txt), and is based on readable/ > + writable control files located in procfs (for system wide settings). > + Notice that per-group settings (controlled through cgroupfs) are still not > + defined for -deadline tasks, because more discussion is needed in order to > + figure out how we want to manage SCHED_DEADLINE bandwidth at the task group > + level. > + > + A main difference between deadline bandwidth management and RT-throttling > is that -deadline tasks have bandwidth on their own (while -rt ones don't!), > - and thus we don't need an higher level throttling mechanism to enforce the > - desired bandwidth. > + and thus we don't need a higher level throttling mechanism to enforce the > ----> > + desired bandwidth. In other words, this means that interface parameters are > + only used at admission control time (i.e., when the user calls > + sched_setattr()). Scheduling is then performed considering actual tasks' > + parameters, so that CPU bandwidth is allocated to SCHED_DEADLINE tasks > + respecting their needs in terms of granularity. Therefore, using this simple > <--- > + interface we can put a cap on total utilization of -deadline tasks (i.e., > + \Sum (runtime_i / period_i) < some_desired_value). > [snip] > > What you think? > As agreed on IRC I fixed this, and the other typos. Thanks, - Juri >>>> + Finally, notice that in order not to jeopardize this admission control a >>>> + -deadline task cannot fork. >>> >>> s/this/the >>> (there aren't any other admission controls in the kernel) >> Ok; this will go in my updated patch >> >> >> >> Thanks, >> Luca >> > > -- To unsubscribe from this list: send the line "unsubscribe linux-doc" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
