Timeout OSError while running dask on local cluster

Question

I am trying to run the following code on a Power PC with config:

Operating System: Red Hat Enterprise Linux Server 7.6 (Maipo)
CPE OS Name: cpe:/o:redhat:enterprise_linux:7.6:GA:server
          Kernel: Linux 3.10.0-957.21.3.el7.ppc64le
    Architecture: ppc64-le

single node localcluster with 20 cores.

import os, subprocess
from timeit import default_timer as timer
from dask.distributed import Client, LocalCluster, fire_and_forget, as_completed

def run_client(n_workers):
    files = []
    for dirpaths, dirnames, filenames in os.walk('cap_logs/'):
        if not dirnames:
            files.extend([os.path.join(dirpaths, file) for file in filenames])

    def parser(file):
        val = subprocess.run(['./test.sh', file], stdout=subprocess.PIPE)
        return val.stdout.decode()

    cluster = LocalCluster(n_workers=n_workers, dashboard_address=None)
    with Client(cluster) as client:
        futures = []
        files = client.scatter(files)
        futures = client.map(parser, files)
        results = [future.result() for future in as_completed(futures)]
        del futures
        cluster.close()

workers = [20, 18, 16, 14, 12, 10, 8, 7, 6, 5, 4, 3, 2, 1]
times = {}
for n_workers in workers:
    tic = timer()
    run_client(n_workers)
    toc = timer()
    time = toc - tic
    times[n_workers] = round(time, 2)

It works fine if n_workers is relatively smaller (<15) than the total num of cores i.e. 20 but as soon as I set n_workers to be >15 it gives the following error:

OSError: Timed out trying to connect to 'tcp://127.0.0.1:34487' after 10 s: connect() didn't finish in time

Are there any other errors before `OSError` ? Does the single node cluster start cleanly ? — quasiben, May 16 '20 at 02:41

score 3 · Answer 1 · answered May 16 '20 at 04:03

I'm surprised you're seeing timeouts like that with so few workers. But even so, you might want to try supplying a longer connect timeout to the distributed.timeouts section of your dask config:

distributed:
  comm:
    timeouts:
      connect: 10s          # time before connecting fails
      tcp: 30s              # time before calling an unresponsive connection dead

The full default config can be found in the source code.

Timeout OSError while running dask on local cluster

1 Answers1