diff options
| author | Nirmoy Das <nirmoy.das@amd.com> | 2020-01-15 15:06:04 +0100 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2020-01-16 13:37:54 -0500 |
| commit | 56822db194232c089601728d68ed078dccb97f8b (patch) | |
| tree | c90d40644880a4ba8e6e5166f99bd2d0e76ae05f /include/drm | |
| parent | 0c0dab86d9792576301444af211eb2b2c9131bcc (diff) | |
| download | linux-56822db194232c089601728d68ed078dccb97f8b.tar.bz2 | |
drm/scheduler: improve job distribution with multiple queues
This patch uses score based logic to select a new rq for better
loadbalance between multiple rq/scheds instead of num_jobs.
Below are test results after running amdgpu_test from mesa drm
Before this patch:
sched_name num of many times it got scheduled
========= ==================================
sdma0 314
sdma1 32
comp_1.0.0 56
comp_1.0.1 0
comp_1.1.0 0
comp_1.1.1 0
comp_1.2.0 0
comp_1.2.1 0
comp_1.3.0 0
comp_1.3.1 0
After this patch:
sched_name num of many times it got scheduled
========= ==================================
sdma0 216
sdma1 185
comp_1.0.0 39
comp_1.0.1 9
comp_1.1.0 12
comp_1.1.1 0
comp_1.2.0 12
comp_1.2.1 0
comp_1.3.0 12
comp_1.3.1 0
Signed-off-by: Nirmoy Das <nirmoy.das@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'include/drm')
| -rw-r--r-- | include/drm/gpu_scheduler.h | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 96a1a1b7526e..537f7a4655a5 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -261,7 +261,7 @@ struct drm_sched_backend_ops { * @job_list_lock: lock to protect the ring_mirror_list. * @hang_limit: once the hangs by a job crosses this limit then it is marked * guilty and it will be considered for scheduling further. - * @num_jobs: the number of jobs in queue in the scheduler + * @score: score to help loadbalancer pick a idle sched * @ready: marks if the underlying HW is ready to work * @free_guilty: A hit to time out handler to free the guilty job. * @@ -282,8 +282,8 @@ struct drm_gpu_scheduler { struct list_head ring_mirror_list; spinlock_t job_list_lock; int hang_limit; - atomic_t num_jobs; - bool ready; + atomic_t score; + bool ready; bool free_guilty; }; |