summaryrefslogtreecommitdiff
path: root/tools/perf/scripts/python/task-analyzer.py
diff options
context:
space:
mode:
authorTejun Heo <tj@kernel.org>2025-01-24 23:48:25 +0300
committerTejun Heo <tj@kernel.org>2025-01-24 23:48:25 +0300
commite9fe182772dcb2630964724fd93e9c90b68ea0fd (patch)
tree190d0cfd51c1eee4830f0f4bc0095f34796d6234 /tools/perf/scripts/python/task-analyzer.py
parent74ca334338a4489173d9e50775b13fa20cbd5958 (diff)
downloadlinux-e9fe182772dcb2630964724fd93e9c90b68ea0fd.tar.xz
sched_ext: selftests/dsp_local_on: Fix sporadic failures
dsp_local_on has several incorrect assumptions, one of which is that p->nr_cpus_allowed always tracks p->cpus_ptr. This is not true when a task is scheduled out while migration is disabled - p->cpus_ptr is temporarily overridden to the previous CPU while p->nr_cpus_allowed remains unchanged. This led to sporadic test faliures when dsp_local_on_dispatch() tries to put a migration disabled task to a different CPU. Fix it by keeping the previous CPU when migration is disabled. There are SCX schedulers that make use of p->nr_cpus_allowed. They should also implement explicit handling for p->migration_disabled. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Ihor Solodrai <ihor.solodrai@pm.me> Cc: Andrea Righi <arighi@nvidia.com> Cc: Changwoo Min <changwoo@igalia.com>
Diffstat (limited to 'tools/perf/scripts/python/task-analyzer.py')
0 files changed, 0 insertions, 0 deletions