Age | Commit message (Collapse) | Author |
|
|
|
Too many assumptions are made in the kernel about timeout behaviour and many calls are not properly made freezer safe.
The scheduler changes should not own this issue.
|
|
|
|
|
|
|
|
|
|
|
|
call nohz idle and service them on exit from schedule.
|
|
|
|
|
|
|
|
This reverts commit ab4b15e59636f6af12136d71cc96950a9048c222.
Not relevant for 4.7 and causes build failure.
|
|
|
|
|
|
|
|
muqss since they are mandatory and low Hz is recommended.
|
|
|
|
runqueue going idle.
|
|
|
|
|
|
benefit more from turbo modes.
|
|
|
|
the existing code in cputime.c and removing it from MuQSS.c.
|
|
|
|
|
|
|
|
since we are not dependent on the timer tick at all.
|
|
highres timers to 100us to make low latency possible with low Hz values (i.e. 100Hz), retaining the benefit of the increased throughput low Hz values provide.
|
|
child.
|
|
|
|
latency/accounting bug has been fixed."
This reverts commit 04a890aaf847e7eceb65b568958379d35dc7ad3c.
Wrong again.
|
|
|
|
|
|
latency/accounting bug has been fixed.
|
|
distribution and latency outliers.
Bug tracked down with the extensive help of Serge Belyshev.
|
|
to inherit sensible values.
|
|
dependent patches.
|
|
misbehaving niced/idleprio tasks on SMT.
|
|
|
|
failures.
|
|
|
|
scheduler code, consolidating smp_send_reschedule to only be called
if the remote CPU is online.
|
|
|
|
|
|
|
|
per-runqueue except for the cpu idle map.
|
|
|
|
run for less than 100us.
|
|
forward progress without scattered use of niffy_diff.
|
|
|