[DRBD-user] umount /drbdpart takes >50 seconds

Harald Dunkel harald.dunkel at aixigo.de
Fri Dec 14 14:13:50 CET 2018


Hi Lars,

On 12/14/18 1:27 PM, Lars Ellenberg wrote:
> 
> There was nothing dirty (~ 7  MB; nothing worth to mention).
> So nothing to sync.
> 
> But it takes some time to invalidate and shrink 20 million dentries
> and inodes and 13 million buffer heads and associated caches.
> Also, cpu bound now makes more sense.

Would you suggest to set cpu-mask? The host has 24 cores (no HT) and
is supposed to run LXContainers. How many cores should I reserve for
drbd? https://docs.linbit.com/docs/users-guide-8.4/#s-latency-tuning
doesn't give any recommendations, unfortunately.

> Apparently no (or negligible) IO happening.
> (you have 20 Gig in ext4_inode_cache alone...
> I'm not surprised that umount takes "a while").
> 
>> Is sync broken for drbd?
> 
> Well, I don't think so.
> But thank you for considering that ;-)
> 

No offense, of course. It was just weird.


Thanx for you help
Harri


More information about the drbd-user mailing list