[PVE-User] Kernel Memory Leak on PVE6?

[Aaron Lauterer]

On 9/20/19 3:04 PM, Chris Hofstaedtler | Deduktiva wrote:
> * Aaron Lauterer <a.lauterer at proxmox.com> [190920 14:58]:
>> Curious, I do have a very similar case at the moment with a slab of ~155GB,
>> out of ~190GB RAM installed.
>>
>> I am not sure yet what causes it but things I plan to investigate are:
>>
>> * hanging NFS mount
> 
> Okay, to rule storage issues out, this setup has:
> - root filesystem as ext4 on GPT
> - efi system partition
> - two LVM PVs and VGs, with all VM storage in the second LVM VG
> - no NFS, no ZFS, no Ceph, no fancy userland filesystems
> 
>> * possible (PVE) service starting too many threads -> restarting each and
>> checking the memory / slab usage.
> 
> Do you have a particular service in mind?

Not at this point. I would restart all PVE services (systemctl| grep -e 
"pve.*service") one by one to see if any of it will result in memory 
being released by the kernel.

If that is not the case at least they are ruled out.
> 
> Chris
>