Software update: HTCondor 9.1.0 / 9.0.1

The HTCondor Team at the University of Wisconsin-Madison has released new development and stable versions of its workload management system HTCondor. The version numbers have ended up at 9.1.0 and 9.0.1. HTCondor focuses on the management of computing intensive tasks and can distribute them over several connected nodes. The user sends his task to HTCondor, after which it handles the process based on set policies and the availability of connected resources, to finally send the results back to the user. HTCondor, for example, can control a dedicated Beowulf cluster, but also ordinary desktops that have nothing to do. While SC16 Google, Fermilab and the HTCondor Team have a 160k-core cloud-based elastic compute cluster demonstrated, and last year, the National Sience Foundation selected HTCondor as part of her Partnership to Advance Throughput Computing. The announcement of these releases looks like this:

HTCondor 9.1.0 released!

The HTCondor team is pleased to announce the release of HTCondor 9.1.0. This development series release contains new features that are under development. This release contains all of the bug fixes from the 9.0.1 stable release.

Enhancements in the release include:

• Support for submitting to ARC-CE via the REST interface;
• DAGMan can put failed jobs on hold (user can correct problems and release);
• Can run gdb and ptrace within Docker containers;
• A small Docker test job is run on the execute node to verify functionality;
• The number of instructions executed is reported in the job Ad on Linux.

A complete list of new features and fixed bugs can be found in the version history. Try out our new helpful installation scripts. Further details can be found in the Development Version History and the Stable Version History. HTCondor 9.1.0 binaries and source code are available from our Downloads page.

HTCondor 9.0.1 released!

The HTCondor team is pleased to announce the release of HTCondor 9.0.1. A stable series release contains significant bug fixes.

Highlights of this release are:

• Fix problem where X.509 proxy refresh kills job when using AES encryption;
• Fix problem when jobs require a different machine after a failure;
• Fix problem where a job matched a machine it can’t use, delaying job start;
• Fix exit code and retry checking when a job exits because of a signal;
• Fix a memory leak in the job router when a job is removed via job policy;
• Fixed the back-end support for the ‘bosco_cluster –add’ command;
• An updated Windows installer that supports IDTOKEN authentication.

More details about the fixes can be found in the Version History. HTCondor 9.0.1 binaries and source code are available from our Downloads page.