Software-update: HTCondor 24.3.0 / 24.0.3
HTCondor richt zich op het beheer van rekenintensieve taken en kan deze over verschillende aangesloten nodes verdelen. De gebruiker stuurt zijn taak naar HTCondor, waarna dit het proces afhandelt op basis van ingestelde policies en de beschikbaarheid van aangesloten resources, om tot slot de resultaten naar de gebruiker terug te sturen. HTCondor kan bijvoorbeeld een dedicated Beowulf-cluster aansturen, maar ook gewone desktops die even niets te doen hebben.Tijdens SC16 hebben Google, Fermilab en het HTCondor Team een 160k-core cloud-based elastic compute cluster gedemonstreerd, en in 2020 heeft de National Science Foundation gekozen voor HTCondor als onderdeel van haar Partnership to Advance Throughput Computing.Het HTCondor Team van de Universiteit van Wisconsin-Madison heeft enkele dagen geleden twee nieuwe versies uitgebracht. De versienummer zijn beland bij 24.3.0 en 24.0.3. De beknopte lijst van aanpassingen van deze uitgaven ziet er als volgt uit:
Version 24.3.0Allow local issuer credmon and Vault credmon to coexistAdd Singularity launcher to distinguish runtime failure from job failureAdvertises when the EP is enforcing disk usage via LVMBy default, LVM disk enforcement hides mounts when possibleContainer Universe jobs can now mount a writable directory under scratchPass PELICAN_* job environment variables to pelican file transfer pluginFix HTCondor startup when network interface has no IPv6 addressVacateReason is set in the job ad under more circumstances‘htcondor job submit’ now issues credentials like ‘condor_submit’ doesNumerous updates in memory tracking with cgroupsFix bug in reporting peak memoryMade cgroup v1 and v2 memory tracking consistent with each otherFix bug where cgroup v1 usage included disk cache pagesFix bug where cgroup v1 jobs killed by OOM were not heldPolls cgroups for memory usage more oftenCan configure to always hold jobs killed by OOMMake condor_adstash work with OpenSearch Python Client v2.xRestore case insensitivity to ‘condor_status -subsystem’Fix bug where jobs would match but not start when using KeyboardIdleFix bug when trying to avoid IPv6 link local addressesEPs spawned by ‘htcondor annex’ no longer crash on startup
Allow local issuer credmon and Vault credmon to coexistAdd Singularity launcher to distinguish runtime failure from job failureAdvertises when the EP is enforcing disk usage via LVMBy default, LVM disk enforcement hides mounts when possibleContainer Universe jobs can now mount a writable directory under scratchPass PELICAN_* job environment variables to pelican file transfer pluginFix HTCondor startup when network interface has no IPv6 addressVacateReason is set in the job ad under more circumstances‘htcondor job submit’ now issues credentials like ‘condor_submit’ doesNumerous updates in memory tracking with cgroupsFix bug in reporting peak memoryMade cgroup v1 and v2 memory tracking consistent with each otherFix bug where cgroup v1 usage included disk cache pagesFix bug where cgroup v1 jobs killed by OOM were not heldPolls cgroups for memory usage more oftenCan configure to always hold jobs killed by OOMFix bug in reporting peak memoryMade cgroup v1 and v2 memory tracking consistent with each otherFix bug where cgroup v1 usage included disk cache pagesFix bug where cgroup v1 jobs killed by OOM were not heldPolls cgroups for memory usage more oftenCan configure to always hold jobs killed by OOM
Fix bug in reporting peak memoryMade cgroup v1 and v2 memory tracking consistent with each otherFix bug where cgroup v1 usage included disk cache pagesFix bug where cgroup v1 jobs killed by OOM were not heldPolls cgroups for memory usage more oftenCan configure to always hold jobs killed by OOMMake condor_adstash work with OpenSearch Python Client v2.xRestore case insensitivity to ‘condor_status -subsystem’Fix bug where jobs would match but not start when using KeyboardIdleFix bug when trying to avoid IPv6 link local addressesEPs spawned by ‘htcondor annex’ no longer crash on startupVersion 24.0.3Numerous updates in memory tracking with cgroupsFix bug in reporting peak memoryMade cgroup v1 and v2 memory tracking consistent with each otherFix bug where cgroup v1 usage included disk cache pagesFix bug where cgroup v1 jobs killed by OOM were not heldPolls cgroups for memory usage more oftenCan configure to always hold jobs killed by OOMMake condor_adstash work with OpenSearch Python Client v2.xRestore case insensitivity to ‘condor_status -subsystem’Fix bug where jobs would match but not start when using KeyboardIdleFix bug when trying to avoid IPv6 link local addressesEPs spawned by ‘htcondor annex’ no longer crash on startup
Numerous updates in memory tracking with cgroupsFix bug in reporting peak memoryMade cgroup v1 and v2 memory tracking consistent with each otherFix bug where cgroup v1 usage included disk cache pagesFix bug where cgroup v1 jobs killed by OOM were not heldPolls cgroups for memory usage more oftenCan configure to always hold jobs killed by OOMFix bug in reporting peak memoryMade cgroup v1 and v2 memory tracking consistent with each otherFix bug where cgroup v1 usage included disk cache pagesFix bug where cgroup v1 jobs killed by OOM were not heldPolls cgroups for memory usage more oftenCan configure to always hold jobs killed by OOM
Fix bug in reporting peak memoryMade cgroup v1 and v2 memory tracking consistent with each otherFix bug where cgroup v1 usage included disk cache pagesFix bug where cgroup v1 jobs killed by OOM were not heldPolls cgroups for memory usage more oftenCan configure to always hold jobs killed by OOMMake condor_adstash work with OpenSearch Python Client v2.xRestore case insensitivity to ‘condor_status -subsystem’Fix bug where jobs would match but not start when using KeyboardIdleFix bug when trying to avoid IPv6 link local addressesEPs spawned by ‘htcondor annex’ no longer crash on startup
Source:
Tweakers.net