Hello,
have problem with clearing space for RGW pool with "radosgw-admin temp
remove" command:
root@osd01:~# ceph -v
ceph version 0.56.4 (63b0f854d1cef490624de5d6cf9039735c7de5ca)
root@osd01:~# radosgw-admin temp remove --date=2014-04-26
failed to list objects
failure removing temp objects: (2) N
The temp remove is an obsolete feature that was needed before the
introduction of the garbage collector. It's not needed in that
version.
Yehuda
On Sat, Apr 27, 2013 at 6:33 AM, Igor Laskovy wrote:
> Hello,
>
> have problem with clearing space for RGW pool with "radosgw-admin temp
> remove" comm
Well, than what about used space of RGW pool? How I can trim it after
files deletion?
On Sat, Apr 27, 2013 at 6:34 PM, Yehuda Sadeh wrote:
> The temp remove is an obsolete feature that was needed before the
> introduction of the garbage collector. It's not needed in that
> version.
>
> Yehuda
>
>
I will rephrase my question.
When I upload files over s3 the ceph -s return growth in used space,
but when this files deleted there are no available space freed.
Yehuda, explain please a little bit more about how I can control this behavior ?
On Sat, Apr 27, 2013 at 7:09 PM, Igor Laskovy wrote:
>
On 04/25/2013 12:39 AM, James Harper wrote:
I'm doing some testing and wanted to see the effect of increasing journal
speed, and the fastest way to do this seemed to be to put it on a ramdisk where
latency should drop to near zero and I can see what other inefficiencies exist.
I created a tmpf
Basically you need for the relevant objects to expire, and then wait
for the garbage collector to run its course. Expiration is ~2hr from
deletion, garbage collector starts every hour, but you can run it
manually via 'radosgw-admin gc process'. There are a couple of
relevant configurables that can
Hi all,
I have 1 card raid on server, I use raid 6, then I divided into 4 partitions ,
each partitions corresponding to 1 osd. I have 2 server ==> 8 osd, but when I
run ceph services, OSD frequently down.
How can I make reasonable?
ThanksMr. Join's Pas
___
Hey folks,
I'm helping put together a new test/experimental cluster, and hit this
today when bringing the cluster up for the first time (using mkcephfs).
After doing the normal "service ceph -a start", I noticed one OSD was down,
and a lot of PGs were stuck creating. I tried restarting the down
Mark Kampe gave an excellent presentation on why Ceph may preclude the need
for RAID 6, and may provide you with better recovery advantages. Have a
look at it here: http://www.youtube.com/watch?v=La0Bxus6Fkg
On Sat, Apr 27, 2013 at 5:15 PM, ke_bac tinh
wrote:
> Hi all,
>
> I have 1 card raid on
