The HTCondor team is pleased to announce the release of HTCondor 8.3.2. This development series release contains new features that are under development. This release contains all of the bug fixes from the 8.2.6 stable release. This new version contains: the next installment of IPv4/IPv6 mixed mode support: a submit node can simultaneously interact with an IPv4 and an IPv6 HTCondor pool; scalability improvements: a reduced memory foot-print of daemons, a reduced number of TCP connections between submit and execute machines, and an improved responsiveness from a busy condor_schedd to queries. A complete list of new features and fixed bugs can be found in the Version History. HTCondor 8.3.2 binaries and source code are available from our Downloads page.

The HTCondor Team is pleased to announce the release of HTCondor version 8.2.6. This new version contains: a bug fix to the log rotation of the condor_schedd on Linux platforms; transfer_input_files now works for directories on Windows platforms; a correction of the flags passed to the mail program on Linux platforms; a RHEL 7 platform fix of a directory permission that prevented daemons from starting. A complete list of fixed bugs can be found in the Version History. HTCondor 8.2.6 binaries and source code are available from our Downloads page.

The HTCondor Team is pleased to announce the release of HTCondor version 8.2.5. This new version contains: an updated RPM installation script that preserves a modified condor_config.local file; OpenSSL version 1.0.1j for Windows platforms. a complete list of fixed bugs and features can be found in the Version History. HTCondor 8.2.5 binaries and source code are available from our Downloads page.

The HTCondor team, together with Worldwide LHC Computing Grid Deployment Board, is offering a four-day workshop the 8th through the 11th of December at CERN in Geneva, Switzerland, for HTCondor pool administrators. Topics envisioned include pool configuration, management, theory of operation, sharing of best practices and experiences, and monitoring of individual HTCondor batch pools. Special subjects of emphasis may include: scheduling, pool policy selection, performance tuning, debugging failures, and previews of upcoming features of HTCondor. Time will be provided for question and answer sessions. Attendees should have some knowledge of Linux and network administration, but no HTCondor experience will be required. See the workshop's web site to register and for more details.

The HTCondor Team is pleased to announce the release of HTCondor version 8.2.4. This new version contains: a bug fix for an 8.2.3 condor_schedd that could not obtain a claim from an 8.0.x condor_startd; a bug fix for removed jobs that return to the queue; a workaround for a condor_schedd performance issue when handling a large number of jobs; a bug fix to prevent the condor_kbdd from crashing on Windows; a bug fix to correct the reporting of available disk on Windows. a complete list of bugs fixed and features can be found in the Version History. HTCondor 8.2.4 binaries and source code are available from our Downloads page.

The HTCondor team is pleased to announce that many videos from HTCondor Week 2014 are now available for streaming and download. These include an introduction to using HTCondor, introductory and advanced tutorials for DAGMan, and an introduction to administrating HTCondor.

The HTCondor team, together with Worldwide LHC Computing Grid Deployment Board, plans to offer a two-day workshop the 8th and 9th of December at CERN in Geneva, Switzerland. HTCondor experts will also be available at CERN on Dec 10th and 11th for less structured one-on-one interaction and problem-solving. This workshop will provide lectures and presentations aimed towards both new and experienced administrators of HTCondor pools setup to manage local compute clusters. See the workshop's web site for more details.

In this Novartis presentation at an Amazon Web Services Summit is a description of the problem and its solution, in which Cycle Computing and HTCondor enable the scheduling of 10,600 Amazon EC2 spot instances.