-
Notifications
You must be signed in to change notification settings - Fork 1
Open
Description
We are seeing syncstorage pods killed/evicted in production due to consuming too much memory and starving the host. It has been difficult to pin down when/why this is happening, as the memory utilization reported by monitoring stats is always below 75%. The application must be allocating a large amount of memory in a very short period of time, otherwise, we would see the 100% memory utilization in monitoring stats.
Is it possible to bound the memory footprint of rust applications?
Are there metrics available from the application concerning memory allocation?
Reactions are currently unavailable
Metadata
Metadata
Assignees
Labels
No labels