Created
January 18, 2013 10:59
-
-
Save stephenroller/4563890 to your computer and use it in GitHub Desktop.
madcow: A simple tool for parallelizing bash commands across many Longhorn servers.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
import os, errno, os.path | |
import argparse | |
JOB_TEMPLATE = """ | |
#!/bin/sh | |
#----------------------------------------------------------------------------- | |
#$ -V | |
#$ -cwd | |
#$ -N %(name)s%(i)02d | |
#$ -j y | |
#$ -o %(base_dir)s/%(name)s/logs/command.%(i)02d.log | |
#$ -pe 1way 8 | |
#$ -q %(queue)s | |
#$ -P data | |
#$ -l h_rt=%(hours)d:00:00 | |
#$ -A %(project)s | |
#----------------------------------------------------------------------------- | |
parallel < %(base_dir)s/%(name)s/commands/command.%(i)02d | |
""" | |
queue = "long" | |
project = "isogram" | |
num_hosts = 20 | |
base_dir = "/home/01813/roller/parallel" | |
hours = 24 | |
name = "redo" | |
def argmin(w): | |
return min(enumerate(w), key=lambda x: x[1])[0] | |
def mkdir_p(path): | |
try: | |
os.makedirs(path) | |
except OSError as exc: # Python >2.5 | |
if exc.errno == errno.EEXIST and os.path.isdir(path): | |
pass | |
else: raise | |
parser = argparse.ArgumentParser( | |
description='MadCow: a system for distributing bash commands across Longhorn') | |
parser.add_argument("--input", "-i", default="-", metavar="FILE", | |
help="The input of commands to run, one per line.") | |
parser.add_argument("--hours", "-t", default=24, type=int, metavar="HOURS", | |
help="The maximum number of hours to allow one computer to use.") | |
parser.add_argument("--name", "-n", metavar="NAME", | |
help="The name of the job.") | |
parser.add_argument("--num-hosts", "-k", metavar="#", type=int, default=num_hosts, | |
help="The number of hosts/jobs to create.") | |
parser.add_argument("--base-dir", "-d", metavar="DIR", default=base_dir, | |
help="The path to output job files, logs, etc.") | |
parser.add_argument("--project", "-p", metavar="PROJECT", default=project, | |
help="The TACC project to dock compute hours from.") | |
parser.add_argument("--queue", "-q", metavar="QUEUE", default=queue, | |
help="The queue to place the jobs in.") | |
args = parser.parse_args() | |
queue = args.queue | |
project = args.project | |
num_hosts = args.num_hosts | |
base_dir = args.base_dir | |
hours = args.hours | |
name = args.name | |
if args.input == "-": | |
commandfile = sys.stdin | |
else: | |
commandfile = open(args.input) | |
mkdir_p(base_dir) | |
mkdir_p(os.path.join(base_dir, name)) | |
for d in ("commands", "jobs", "logs"): | |
mkdir_p(os.path.join(base_dir, name, d)) | |
# split up the computations | |
weights = [0] * num_hosts | |
bins = [list() for k in range(num_hosts)] | |
lst = commandfile.read().split("\n") | |
for inpt in reversed(lst): | |
inpt = inpt.strip() | |
if not inpt: continue | |
try: | |
size, cmd = inpt.split("\t") | |
size = int(size) | |
except ValueError: | |
size, cmd = 1, inpt | |
bin = argmin(weights) | |
weights[bin] += size | |
bins[bin].append(cmd) | |
for i, bin in enumerate(bins): | |
f = open("%s/%s/commands/command.%02d" % (base_dir, name, i), "w") | |
for command in bin: | |
f.write(command + "\n") | |
f.close() | |
f = open("%s/%s/jobs/job.%02d" % (base_dir, name, i), "w") | |
template = JOB_TEMPLATE % { | |
'base_dir': base_dir, | |
'project': project, | |
'hours': hours, | |
'name': name, | |
'i': i, | |
'queue': queue, | |
} | |
f.write(template) | |
f.close() | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment