Dmtcp Checkpointing - Revision history

Wwarr@uab.edu: Overhaul of page to include new information and more details

2021-06-17T19:20:20Z

Overhaul of page to include new information and more details

@@ Line 1: / Line 1: @@
-'''DMTCP: Distributed MultiThreaded CheckPointing'''
+= Introduction =
-Search keywords: checkpoint check point
+== How it Works ==
-http://dmtcp.sourceforge.net/FAQ.html
+When a checkpoint is requested by the server, the client halts execution of the wrapped software. Any data in system memory associated with the wrapped software is dumped to disk as a binary data file. The client also creates a restart shell script for restarting from the most recent checkpoint.
-Available on Cheaha.RC
+If execution of the job is interrupted for any reason before completion, the restart shell script can be executed
-example [[Slurm|SLURM]] Job: https://github.com/dmtcp/dmtcp/tree/master/plugin/batch-queue/job_examples
+= Advantages and Considerations =
-* to use "srun" or not?  - just for better reporting via sacct -j ### / sstat -j ###
+There are multiple advantages to using checkpointing:

Curtish@uab.edu: add keyword checkpoint

2017-09-14T19:21:10Z

add keyword checkpoint

← Older revision		Revision as of 19:21, 14 September 2017
Line 1:		Line 1:
	'''DMTCP: Distributed MultiThreaded CheckPointing'''		'''DMTCP: Distributed MultiThreaded CheckPointing'''

			Search keywords: checkpoint check point

	http://dmtcp.sourceforge.net/FAQ.html		http://dmtcp.sourceforge.net/FAQ.html

Curtish@uab.edu: Curtish@uab.edu moved page Dmtcp to Dmtcp Checkpointing: make this page searchable under the keyword checkpoint

2017-09-14T19:17:33Z

Curtish@uab.edu moved page Dmtcp to Dmtcp Checkpointing: make this page searchable under the keyword checkpoint

← Older revision	Revision as of 19:17, 14 September 2017
(No difference)

Curtish@uab.edu: add module load

2017-02-17T20:11:08Z

add module load

← Older revision		Revision as of 20:11, 17 February 2017
Line 1:		Line 1:
	'''DMTCP: Distributed MultiThreaded CheckPointing'''		'''DMTCP: Distributed MultiThreaded CheckPointing'''

	~~Coming soon to Cheaha.RC as a module:~~ http://dmtcp.sourceforge.net/FAQ.html		http://dmtcp.sourceforge.net/FAQ.html

			Available on Cheaha.RC
			* module load DMTCP/2.4.5
			* module load DMTCP/2.5.0

	example [[Slurm\|SLURM]] Job: https://github.com/dmtcp/dmtcp/tree/master/plugin/batch-queue/job_examples		example [[Slurm\|SLURM]] Job: https://github.com/dmtcp/dmtcp/tree/master/plugin/batch-queue/job_examples
	* to use "srun" or not? - just for better reporting via sacct -j ### / sstat -j ###		* to use "srun" or not? - just for better reporting via sacct -j ### / sstat -j ###

Curtish@uab.edu at 16:56, 7 February 2017

2017-02-07T16:56:33Z

← Older revision		Revision as of 16:56, 7 February 2017
Line 4:		Line 4:

	example [[Slurm\|SLURM]] Job: https://github.com/dmtcp/dmtcp/tree/master/plugin/batch-queue/job_examples		example [[Slurm\|SLURM]] Job: https://github.com/dmtcp/dmtcp/tree/master/plugin/batch-queue/job_examples
			* to use "srun" or not? - just for better reporting via sacct -j ### / sstat -j ###

Curtish@uab.edu: add link to slurm page

2017-02-07T16:46:45Z

add link to slurm page

← Older revision		Revision as of 16:46, 7 February 2017
Line 3:		Line 3:
	Coming soon to Cheaha.RC as a module: http://dmtcp.sourceforge.net/FAQ.html		Coming soon to Cheaha.RC as a module: http://dmtcp.sourceforge.net/FAQ.html

	example SLURM Job: https://github.com/dmtcp/dmtcp/tree/master/plugin/batch-queue/job_examples		example [[Slurm\|SLURM]] Job: https://github.com/dmtcp/dmtcp/tree/master/plugin/batch-queue/job_examples

Curtish@uab.edu: created based on discussion with Thomas Anthony

2017-02-07T16:43:15Z

created based on discussion with Thomas Anthony

New page

'''DMTCP: Distributed MultiThreaded CheckPointing'''

Coming soon to Cheaha.RC as a module: http://dmtcp.sourceforge.net/FAQ.html

example SLURM Job: https://github.com/dmtcp/dmtcp/tree/master/plugin/batch-queue/job_examples