Flexible GC workload #1277

New issue

Open

opened 2025-12-28 17:22:26 +00:00 by sami · 1 comment

sami commented

2025-12-28 17:22:26 +00:00

Owner

Originally created by @carpawell on GitHub (Oct 31, 2024).

I'm always frustrated when we delete containers with millions objects and it may last for days.

Describe the solution you'd like

Be able to tune the number of objects being deleted based on a current load. If a node does nothing, it may try harder, but if we are being benchmarked, removing objects from disks may be stopped for some time.

Describe alternatives you've considered

Originally created by @carpawell on GitHub (Oct 31, 2024). ## Is your feature request related to a problem? Please describe. I'm always frustrated when we delete containers with millions objects and it may last for days. ## Describe the solution you'd like Be able to tune the number of objects being deleted based on a current load. If a node does nothing, it may try harder, but if we are being benchmarked, removing objects from disks may be stopped for some time. ## Describe alternatives you've considered \-

sami added the

enhancement

neofs-storage

labels

2025-12-28 17:22:26 +00:00

sami commented

2025-12-28 17:22:26 +00:00

Author

Owner

@cthulhu-rider commented on GitHub (Nov 2, 2024):

when the free disk is approaching zero, the collector should increase its power. At the same time, the increased load of incoming data should not trigger its sleep as proposed

@cthulhu-rider commented on GitHub (Nov 2, 2024): when the free disk is approaching zero, the collector should increase its power. At the same time, the increased load of incoming data should not trigger its sleep as proposed