X-Git-Url: https://git.arvados.org/arvados.git/blobdiff_plain/e4f96fc61cd9c85f91bdb0020bc365f2f4825ffb..c7399ec7afdf0cfdd0f3177f410f102083a26e15:/doc/user/topics/tutorial-parallel.html.textile.liquid?ds=inline
diff --git a/doc/user/topics/tutorial-parallel.html.textile.liquid b/doc/user/topics/tutorial-parallel.html.textile.liquid
index 9d08b6988b..4ff402ea7f 100644
--- a/doc/user/topics/tutorial-parallel.html.textile.liquid
+++ b/doc/user/topics/tutorial-parallel.html.textile.liquid
@@ -1,59 +1,67 @@
---
layout: default
navsection: userguide
-title: "Parallel Crunch tasks"
+title: "Concurrent Crunch tasks"
...
+{% comment %}
+Copyright (C) The Arvados Authors. All rights reserved.
-In the previous tutorials, we used @arvados.job_setup.one_task_per_input_file()@ to automatically parallelize our jobs by creating a separate task per file. For some types of jobs, you may need to split the work up differently, for example creating tasks to process different segments of a single large file. In this this tutorial will demonstrate how to create Crunch tasks directly.
+SPDX-License-Identifier: CC-BY-SA-3.0
+{% endcomment %}
-Start by entering the @crunch_scripts@ directory of your git repository:
+{% include 'pipeline_deprecation_notice' %}
+
+In the previous tutorials, we used @arvados.job_setup.one_task_per_input_file()@ to automatically create concurrent jobs by creating a separate task per file. For some types of jobs, you may need to split the work up differently, for example creating tasks to process different segments of a single large file. This tutorial will demonstrate how to create Crunch tasks directly.
+
+Start by entering the @crunch_scripts@ directory of your Git repository:
~$ cd you/crunch_scripts
+
~$ cd $USER/crunch_scripts
~/you/crunch_scripts$ nano parallel-hash.py
+notextile. ~/$USER/crunch_scripts$ nano concurrent-hash.py
-Add the following code to compute the md5 hash of each file in a
+Add the following code to compute the MD5 hash of each file in a collection:
-~/you/crunch_scripts$ chmod +x parallel-hash.py
+notextile. ~/$USER/crunch_scripts$ chmod +x concurrent-hash.py
-Next, add the file to @git@ staging, commit and push:
+Add the file to the Git staging area, commit, and push:
~/you/crunch_scripts$ git add parallel-hash.py
-~/you/crunch_scripts$ git commit -m"parallel hash"
-~/you/crunch_scripts$ git push origin master
+~/$USER/crunch_scripts$ git add concurrent-hash.py
+~/$USER/crunch_scripts$ git commit -m"concurrent hash"
+~/$USER/crunch_scripts$ git push origin master
~/you/crunch_scripts$ cat >~/the_job <<EOF
+~/$USER/crunch_scripts$ cat >~/the_job <<EOF
{
- "script": "parallel-hash.py",
- "script_version": "you:master",
+ "script": "concurrent-hash.py",
+ "repository": "$USER/$USER",
+ "script_version": "master",
"script_parameters":
{
"input": "887cd41e9c613463eab2f0d885c6dd96+83"
}
}
EOF
-~/you/crunch_scripts$ arv job create --job "$(cat ~/the_job)"
+~/$USER/crunch_scripts$ arv job create --job "$(cat ~/the_job)"
{
...
"uuid":"qr1hi-xxxxx-xxxxxxxxxxxxxxx"
...
}
-~/you/crunch_scripts$ arv job get --uuid qr1hi-xxxxx-xxxxxxxxxxxxxxx
+~/$USER/crunch_scripts$ arv job get --uuid qr1hi-xxxxx-xxxxxxxxxxxxxxx
{
...
"output":"e2ccd204bca37c77c0ba59fc470cd0f7+162",
@@ -62,18 +70,16 @@ EOF
~/you/crunch_scripts$ arv keep ls e2ccd204bca37c77c0ba59fc470cd0f7+162
-md5sum.txt
-md5sum.txt
-md5sum.txt
-~/you/crunch_scripts$ arv keep get e2ccd204bca37c77c0ba59fc470cd0f7+162/md5sum.txt
+~/$USER/crunch_scripts$ arv keep ls e2ccd204bca37c77c0ba59fc470cd0f7+162
+./md5sum.txt
+~/$USER/crunch_scripts$ arv keep get e2ccd204bca37c77c0ba59fc470cd0f7+162/md5sum.txt
0f1d6bcf55c34bed7f92a805d2d89bbf alice.txt
504938460ef369cd275e4ef58994cffe bob.txt
8f3b36aff310e06f3c5b9e95678ff77a carol.txt