Hi Dan,

thanks for quick reply!
Didnt read in detail yet but here are my first comments:

3.b BTW, our old friend updatedb seems to trigger the same problem..
grabbing caps very quickly as it indexes CephFS. updatedb.conf is
configured to PRUNEFS="... fuse ...", but CephFS has type
fuse.ceph-fuse. We'll need to add "ceph" to that list too.
This was my first thought and I add CEPH paths to PRUNEPATH. But as you said maybe I have to add FS type too..?! >> PRUNEPATHS="/tmp /var/spool /media /home/.ecryptfs /*var/lib/ceph/osd **/mnt/ceph*" NEVERTHLESS since that I didnt see the mlocate process in 'D' state anymore. Plus the fact that the high load comes up with MDS / client problem I dont really think that updatedb ist still the problem....but just a assumption
4. "mds cache size = 5000000" is going to use a lot of memory! We have
an MDS with just 8GB of RAM and it goes OOM after delegating  around 1
million caps. (this is with mds cache size = 100000, btw)
At least I never saw on 'htop' that much memory used or any other resources are high...just the load raises


Best regards,

Mathias


Attachment: smime.p7s
Description: S/MIME Cryptographic Signature

_______________________________________________
ceph-users mailing list
ceph-users@lists.ceph.com
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com

Reply via email to