Re: ceph nautilus deep-scrub health error

[nokia ceph <nokiacephusers@xxxxxxxxx>]

Hi Manuel.

Thanks for your response. We will consider this settings when we enable deep-scrubbing. For now i saw this write up from Nautilus release notes,

Configuration values mon_warn_not_scrubbed and
mon_warn_not_deep_scrubbed have been renamed. They are now
mon_warn_pg_not_scrubbed_ratio and mon_warn_pg_not_deep_scrubbed_ratio
respectively. This is to clarify that these warnings are related to
pg scrubbing and are a ratio of the related interval. These options
are now enabled by default.  

So, we made mon_warn_pg_not_deep_scrubbed_ratio = 0  and after that cluster not moving to warning state for not deep scrubbing.

Thanks,

Muthu 

On Tue, May 14, 2019 at 4:30 PM EDH - Manuel Rios Fernandez <mriosfer@xxxxxxxxxxxxxxxx> wrote:

Hi Muthu

 

We found the same issue near 2000 pgs not deep-scrubbed in time.

 

We’re manually force scrubbing with :

 

ceph health detail | grep -i not | awk '{print $2}' | while read i; do ceph pg deep-scrub ${i}; done

 

It launch near 20-30 pgs to be deep-scrubbed. I think you can improve  with a sleep of 120 secs between scrub to prevent overload your osd.

 

For disable deep-scrub you can use “ceph osd set nodeep-scrub” , Also you can setup deep-scrub with threshold .

#Start Scrub 22:00

osd scrub begin hour = 22

#Stop Scrub 8

osd scrub end hour = 8

#Scrub Load 0.5

osd scrub load threshold = 0.5

 

Regards,

 

Manuel

 

 

 

 

De: ceph-users <ceph-users-bounces@xxxxxxxxxxxxxx> En nombre de nokia ceph
Enviado el: martes, 14 de mayo de 2019 11:44
Para: Ceph Users <ceph-users@xxxxxxxxxxxxxx>
Asunto: ceph nautilus deep-scrub health error

 

Hi Team,

 

After upgrading from Luminous to Nautilus , we see 654 pgs not deep-scrubbed in time error in ceph status . How can we disable this flag? . In our setup we disable deep-scrubbing for performance issues.

 

Thanks,

Muthu

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