Checkpoint/Restart functionality for Linux processes

Overview Repositories Revisions Requests Users Attributes Meta

Checkpoint/Restart functionality for Linux processes

http://dmtcp.sourceforge.net

DMTCP (Distributed MultiThreaded Checkpointing) is a tool to transparently checkpointing the state of an arbitrary group of programs spread across many machines and connected by sockets. It runs directly on the user binary executable, without needing to modify either the user binary or the operating system.
Among the applications supported by DMTCP are OpenMPI, MATLAB, Python, Perl, and many programming languages and shell scripting languages. DMTCP also supports GNU screen sessions, including vim/cscope and emacs. With the use of TightVNC, it can also checkpoint and restart X-Windows applications, as long as they do not use extensions (e.g.: no OpenGL, no video). See the QUICK-START file for further details.

Download package
Checkout Package
osc -A https://api.opensuse.org checkout science/dmtcp && cd $_
Create Badge

Build Results
RPM Lint

Refresh

Source Files

Filename	Size	Changed
dmtcp-2.6.0.tar.gz	0001378808 1.31 MB	over 4 years ago
dmtcp.changes	0000002971 2.9 KB	over 4 years ago
dmtcp.spec	0000003018 2.95 KB	over 4 years ago

Latest Revision

Ana Guerrero (anag) accepted request 745253 from

Christian Goll (mslacken) over 4 years ago (revision 6)

- removed dmtcpaware* packages  
- updated to version 2.6.0 with following important changes, for 
  a full chnageglog see the NEWS file.
- changes for version 2.6
  * not documented upstream 
- changes for version 2.4
  * Intensive testing done for integration of MPI/SLURM
  * Support for glibc version 2.21 added
  * The environment variable DMTCP_GDB_ATTACH_ON_RESTART was added
  * DMTCP now supports InfiniBand UD
- changes for version 2.2
  * A --exit-after-ckpt flag was added for dmtcp_coordinator.
  * Scalability improvements were added.  DMTCP has now been tested
    on an MPI jobs using 2048 MPI ranks over 2048  CPU cores.
- changes for version 2.1
  * plugins have now to use "dmtcp.h" instead of "dmtcpplugin.h"
  * attempt to restore current working directory on restart
  * 'dmtcp_restart --ckptdir <DIR>' and 'dmtcp_restart_script.sh --ckptdir
    <DIR>' will change to a new directory to hold checkpoint images on restart.
  * 'dmtcp_restart --no-strict-uid-checking' or 'dmtcp_coordinator
    --no-strict-uid-checking'
  * a new internal plugin to handle 'ssh' uniformly

Places