35,587
edits
Frequently Asked Questions/fr: Difference between revisions
Jump to navigation
Jump to search
Updating to match new version of source page
No edit summary |
(Updating to match new version of source page) |
||
| Line 125: | Line 125: | ||
*une valeur plus grande que un (1) indique que vous utilisez moins que votre juste part | *une valeur plus grande que un (1) indique que vous utilisez moins que votre juste part | ||
*une valeur plus petite que un (1) indique que vous consommez plus que votre juste part. | *une valeur plus petite que un (1) indique que vous consommez plus que votre juste part. | ||
Plus la valeur est proche de zéro, plus vous sur-utilisez les ressources et plus vos tâches en attente baissent en priorité. L’ordonnanceur «oublie» graduellement les sous-utilisations ou sur-utilisations potentielles des derniers mois. Notez également que la valeur de <tt>LevelFS</tt> est spécifique à la grappe en question. | Plus la valeur est proche de zéro, plus vous sur-utilisez les ressources et plus vos tâches en attente baissent en priorité. L’ordonnanceur «oublie» graduellement les sous-utilisations ou sur-utilisations potentielles des derniers mois. Notez également que la valeur de <tt>LevelFS</tt> est spécifique à la grappe en question. | ||
== How accurate is START_TIME in <tt>squeue</tt> output? == | |||
Start times shown by <tt>squeue</tt> are accurate but conditional. | |||
[[Running jobs|Slurm]] schedules future START_TIME for high-priority pending jobs. These expected start times are computed from current information: | |||
* what resources will be made available by running jobs that complete; and | |||
* resources needed by other, higher-priority jobs waiting to run | |||
The start times are conditional - <tt>Slurm</tt> invalidates these future plans if: | |||
* jobs end early, changing which resources become available; | |||
* prioritization is perturbed: submission of higher-priority jobs or cancellation of queued jobs | |||
On Compute Canada general purpose clusters, new jobs are submitted about every five seconds, and 30-50% of jobs end early, | |||
so <tt>Slurm</tt> often discards and recomputes its future plans. | |||
Most waiting jobs have a START_TIME of "N/A", which stands for "not available", meaning <tt>Slurm</tt> is not attempting to project a start time for that job. | |||
For jobs which are already running, the start time reported by <tt>squeue</tt> is perfectly accurate. | |||