Commit Graph

14 Commits

Author SHA1 Message Date
Łukasz Magiera
c9a2ff4007 cleanup worker resource overrides 2021-11-30 02:06:58 +01:00
Łukasz Magiera
b961e1aab5 sched resources: Separate Parallelism defaults depending on GPU presence 2021-11-30 02:06:58 +01:00
Clint Armstrong
93e4656a27 Use a float to represent GPU utilization
Before this change workers can only be allocated one GPU task,
regardless of how much of the GPU resources that task uses, or how many
GPUs are in the system.

This makes GPUUtilization a float which can represent that a task needs
a portion, or multiple GPUs. GPUs are accounted for like RAM and CPUs so
that workers with more GPUs can be allocated more tasks.

A known issue is that PC2 cannot use multiple GPUs. And even if the
worker has multiple GPUs and is allocated multiple PC2 tasks, those
tasks will only run on the first GPU.

This could result in unexpected behavior when a worker with multiple
GPUs is assigned multiple PC2 tasks. But this should not suprise any
existing users who upgrade, as any existing users who run workers with
multiple GPUs should already know this and be running a worker per GPU
for PC2. But now those users have the freedom to customize the GPU
utilization of PC2 to be less than one and effectively run multiple PC2
processes in a single worker.

C2 is capable of utilizing multiple GPUs, and now workers can be
customized for C2 accordingly.
2021-11-30 02:06:58 +01:00
Clint Armstrong
c4f46171ae Report memory used and swap used in worker res
Attempting to report "memory used by other processes" in the MemReserved
field fails to take into account the fact that the system's memory used
includes memory used by ongoing tasks.

To properly account for this, worker should report the memory and swap
used, then the scheduler that is aware of the memory requirements for a
task can determine if there is sufficient memory available for a task.
2021-11-30 02:06:58 +01:00
Łukasz Magiera
b87142ec8e wip improve scheduling of ready work 2021-10-03 10:38:08 +02:00
Raúl Kripalani
59eab2df25 move scheduling filtering logic down. 2021-06-21 20:49:16 +01:00
Dan Shao
f3838a47c7 Format workerID as string 2020-11-23 15:07:50 +08:00
Péter Szilágyi
5f657b4333
extern/sector-storage: fix GPU usage overwrite bug 2020-10-28 20:52:33 +02:00
Łukasz Magiera
5e08d56630 sched: Allow some single-thread tasks to run in parallel with PC2/C2 2020-10-01 00:28:44 +02:00
Łukasz Magiera
e14c80360d sealing sched: Factor worker queues into utilization calc 2020-08-31 13:41:34 +02:00
Łukasz Magiera
9d0c8ae3dd sectorstorage: update sched tests for new logic 2020-08-28 21:38:21 +02:00
Raúl Kripalani
efdc428d5d keep storage-fsm (renamed to storage-sealing) and sector-storage in extern. 2020-08-17 14:26:18 +01:00
Raúl Kripalani
3c17cd655e integrate extern/sector-storage into lotus proper. 2020-08-16 11:09:58 +01:00
Łukasz Magiera
0eaf44eb31 Merge sector-storage subtree 2020-08-10 17:25:46 +02:00