I start 2 processes because I only have 2 gpus but it starts 4 and then gives me a Exception: process 0 terminated with signal SIGSEGV, why is that? How can I stop it? (I am assuming that is the source of my bug btw)
Error msg:
$ python playground/multiprocessing_playground/ddp_basic_example.py
starting __main__
running main()
current process: <_MainProcess name='MainProcess' parent=None started>
pid: 30735
world_size=2
Start running DDP with model parallel example on rank: 0.
Start running DDP with model parallel example on rank: 1.
current process: <SpawnProcess name='SpawnProcess-1' parent=30735 started>
pid: 30753
current process: <SpawnProcess name='SpawnProcess-2' parent=30735 started>
pid: 30754
Start running DDP with model parallel example on rank: 1.
current process: <SpawnProcess name='SpawnProcess-2' parent=30735 started>
pid: 30754
Start running DDP with model parallel example on rank: 0.
current process: <SpawnProcess name='SpawnProcess-1' parent=30735 started>
pid: 30753
Traceback (most recent call last):
File "playground/multiprocessing_playground/ddp_basic_example.py", line 152, in <module>
main()
File "playground/multiprocessing_playground/ddp_basic_example.py", line 147, in main
mp.spawn(run_parallel_training_loop, args=(world_size,), nprocs=world_size)
File "/home/miranda9/miniconda3/envs/automl-meta-learning/lib/python3.8/site-packages/torch/multiprocessing/spawn.py", line 199, in spawn
return start_processes(fn, args, nprocs, join, daemon, start_method='spawn')
File "/home/miranda9/miniconda3/envs/automl-meta-learning/lib/python3.8/site-packages/torch/multiprocessing/spawn.py", line 157, in start_processes
while not context.join():
File "/home/miranda9/miniconda3/envs/automl-meta-learning/lib/python3.8/site-packages/torch/multiprocessing/spawn.py", line 105, in join
raise Exception(
Exception: process 0 terminated with signal SIGSEGV
completely self-contained example:
import os
import torch
import torch.distributed as dist
import torch.multiprocessing as mp
import torch.nn as nn
import torch.optim as optim
from torch.nn.parallel import DistributedDataParallel as DDP
def example(rank, world_size):
# create default process group
os.environ['MASTER_ADDR'] = 'localhost'
os.environ['MASTER_PORT'] = '8888'
dist.init_process_group("gloo", rank=rank, world_size=world_size)
# create local model
model = nn.Linear(10, 10).to(rank)
# construct DDP model
ddp_model = DDP(model, device_ids=[rank])
# define loss function and optimizer
loss_fn = nn.MSELoss()
optimizer = optim.SGD(ddp_model.parameters(), lr=0.001)
# forward pass
outputs = ddp_model(torch.randn(20, 10).to(rank))
labels = torch.randn(20, 10).to(rank)
# backward pass
loss_fn(outputs, labels).backward()
# update parameters
optimizer.step()
def main():
# world_size = 2
world_size = torch.cuda.device_count()
mp.spawn(example,
args=(world_size,),
nprocs=world_size,
join=True)
if __name__=="__main__":
main()
print('Done\n\a')
crossposted: https://stackoverflow.com/questions/66268131/why-is-mp-spawn-spawning-4-processes-when-i-only-want-2