My Bash-Foo is not strong. Right now I have something like

function update_project {
  for i in server-{1,2,3,4} ; do
    echo "Updating $i"
    ssh $i "git pull"
  done
}

The number of servers is growing every day, and since each update takes about 20 seconds, I'd like to do the requests concurrently. What's the best way to do this, while still being able to see the output (e.g. failed merges)?

link|improve this question

feedback

5 Answers

up vote 2 down vote accepted

Why are you trying to reinvent the wheel? Just use Capistrano to deploy your project code. It's designed for this exact purpose and runs the deploys in parallel across all of the configured machines.

link|improve this answer
feedback

func will allow you to send a command to an arbitrary number of machines, and let you watch the output.

link|improve this answer
feedback

There are several parallel ssh projects. Look for pssh.

link|improve this answer
feedback

One of the other answers is the correct thing to do, but to directly answer your question, just add an ampersand at the end of your command:

ssh $i "git pull" &
link|improve this answer
The difficulty comes when trying to work out which of the hosts the merge failed on, isn't it? – Jonathan Leffler Jun 27 '10 at 2:55
@Jonathan: Yes, the output would be a jumble. – Dennis Williamson Jun 27 '10 at 3:31
feedback

If you have GNU Parallel http://www.gnu.org/software/parallel/ installed you can do this:

parallel --slf hostfile --nonall --tag git pull

You can install GNU Parallel simply by:

wget http://git.savannah.gnu.org/cgit/parallel.git/plain/src/parallel
chmod 755 parallel
cp parallel sem

Watch the intro videos for GNU Parallel to learn more: https://www.youtube.com/playlist?list=PL284C9FF2488BC6D1

link|improve this answer
feedback

Your Answer

 
or
required, but never shown

Not the answer you're looking for? Browse other questions tagged or ask your own question.