Commit bced76aeaca03b45e3b4bdb868cada328e497847
Committed by
Ingo Molnar
1 parent
6db9dc150e
Exists in
master
and in
6 other branches
sched: Fix lockup by limiting load-balance retries on lock-break
Eric and David reported dead machines and traced it to commit a195f004 ("sched: Fix load-balance lock-breaking"), it turns out there's still a scenario where we can end up re-trying forever. Since there is no strict forward progress guarantee in the load-balance iteration we can get stuck re-retrying the same task-set over and over. Creating a forward progress guarantee with the existing structure is somewhat non-trivial, for now simply terminate the retry loop after a few tries. Reported-by: Eric Dumazet <eric.dumazet@gmail.com> Tested-by: Eric Dumazet <eric.dumazet@gmail.com> Reported-by: David Ahern <dsahern@gmail.com> [ logic cleanup as suggested by Eric ] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Suresh Siddha <suresh.b.siddha@intel.com> Link: http://lkml.kernel.org/r/1326297936.2442.157.camel@twins Signed-off-by: Ingo Molnar <mingo@elte.hu>
Showing 1 changed file with 7 additions and 3 deletions Side-by-side Diff
kernel/sched/fair.c
... | ... | @@ -3130,8 +3130,10 @@ |
3130 | 3130 | } |
3131 | 3131 | |
3132 | 3132 | #define LBF_ALL_PINNED 0x01 |
3133 | -#define LBF_NEED_BREAK 0x02 | |
3134 | -#define LBF_ABORT 0x04 | |
3133 | +#define LBF_NEED_BREAK 0x02 /* clears into HAD_BREAK */ | |
3134 | +#define LBF_HAD_BREAK 0x04 | |
3135 | +#define LBF_HAD_BREAKS 0x0C /* count HAD_BREAKs overflows into ABORT */ | |
3136 | +#define LBF_ABORT 0x10 | |
3135 | 3137 | |
3136 | 3138 | /* |
3137 | 3139 | * can_migrate_task - may task p from runqueue rq be migrated to this_cpu? |
... | ... | @@ -4508,7 +4510,9 @@ |
4508 | 4510 | goto out_balanced; |
4509 | 4511 | |
4510 | 4512 | if (lb_flags & LBF_NEED_BREAK) { |
4511 | - lb_flags &= ~LBF_NEED_BREAK; | |
4513 | + lb_flags += LBF_HAD_BREAK - LBF_NEED_BREAK; | |
4514 | + if (lb_flags & LBF_ABORT) | |
4515 | + goto out_balanced; | |
4512 | 4516 | goto redo; |
4513 | 4517 | } |
4514 | 4518 |