Re: CephFS: mds client failing to respond to cache pressure

Elias Abacioglu <elias.abacioglu@xxxxxxxxxxxxxxxxx> · Thu, 9 Jun 2016 13:18:14 +0200

Hi Sean,

Isn't there any downsides to increasing the mds cache size?
My colleague mentioned that he tested it previously and then the cluster didn't recover during a failover..

On Thu, Jun 9, 2016 at 12:41 PM, Sean Crosby <richardnixonshead@xxxxxxxxx> wrote:
Hi Elias,
When we have received the same warning, our solution has been to increase the inode cache on the MDS.

We have added

mds cache size = 2000000

to the [global] section of ceph.conf on the MDS server. We have to restart MDS for the changes to be applied.

Sean

On 9 June 2016 at 19:55, Elias Abacioglu <elias.abacioglu@xxxxxxxxxxxxxxxxx> wrote:
Hi,

I know this have been asked here a couple of times, but couldn't find anything concrete.

I have the following warning in our ceph cluster.
mds0: Client web01:cephfs.web01 failing to respond to cache pressure

In previous Ceph versions this might have been a bug. But now we are running Jewel.
So is there a way to fix this warning?
Do I need to tune some values? Boost the cluster? Boost the client?

Here are some details:
Client kernel is 4.4.0.
Ceph 10.2.1

# ceph mds dump
dumped fsmap epoch 5755
fs_name    cephfs
epoch    5755
flags    0
created    2015-12-03 11:21:28.128193
modified    2016-05-16 06:48:47.969430
tableserver    0
root    0
session_timeout    60
session_autoclose    300
max_file_size    1099511627776
last_failure    4900
last_failure_osd_epoch    5884
compat    compat={},rocompat={},incompat={1=base v0.20,2=client writeable ranges,3=default file layouts on dirs,4=dir inode in separate object,5=mds uses versioned encoding,6=dirfrag is stored in omap,8=no anchor table}
max_mds    1
in    0
up    {0=574261}
failed
damaged
stopped
data_pools    2
metadata_pool    3
inline_data    disabled
574261:    10.3.215.5:6801/62035 'ceph-mds03' mds.0.5609 up:active seq 515014
594257:    10.3.215.10:6800/1386 'ceph-mds04' mds.0.0 up:standby-replay seq 1

Thanks,
Elias

_______________________________________________

ceph-users mailing list

ceph-users@xxxxxxxxxxxxxx

http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com

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