Messages in this thread | | | From | Joel Fernandes <> | Subject | Re: [RFC PATCH 07/11] sched: Add proxy execution | Date | Mon, 17 Oct 2022 00:03:09 -0400 |
| |
> On Oct 16, 2022, at 4:48 PM, Steven Rostedt <rostedt@goodmis.org> wrote: > > On Sat, 15 Oct 2022 15:53:19 +0200 > Peter Zijlstra <peterz@infradead.org> wrote: > >>> From this it is easy to see that the critical secion executes with the >> direct sum of the blockchain as a whole (all of them will have donated >> their relative time to make the owner elegible again) -- provided the >> critical section is of course long enough for this to matter (or it's >> owner's weight small enough etc..). > > Does this mean that a lower priority task could do a sort of DOS attack > on a high priority task, if it creates a bunch of threads that > constantly grabs a shared lock from the higher priority task? That is, > the higher priority task could possibly lose a lot of its quota due to > other tasks running on its behalf in the critical section?
Just my opinion: I can see that as a problem, but on the other hand, if a bunch of threads are acquiring a shared lock to block a high priority task, then they are probably causing a DOS-type of issue anyway whether PE is enabled or not. Even if a prio inheritance mechanism boosts them, they’re still making the progress of the blocking high priority tasks slower. Or, did I miss something in this use case?
Thanks.
| |