Re: [ceph-users] cephfs file block size: must it be so big?

> I tested fread on Fedora 28. fread does 8k read on even block size is 4M. So maybe I should be looking at changing my GNU Libc instead of my Ceph. But I can't confirm that reading 8K regardless of blocksize is normal anywhere. My test on Debian 9 (about 3 years old) with glibc 2.24 shows fread

Re: [ceph-users] cephfs file block size: must it be so big?

> Going back through the logs though it looks like the main reason we do a > 4MiB block size is so that we have a chance of reporting actual cluster > sizes to 32-bit systems, I believe you're talking about a different block size (there are so many of them). The 'statvfs' system call (the essence

Re: [ceph-users] Correlate Ceph kernel module version with Ceph version

CRUSH map tunables support within the kernel is documented here [1] and RBD feature support within the kernel is documented here [2]. [1] http://docs.ceph.com/docs/master/rados/operations/crush-map/?highlight=tunables#tunables [2] http://docs.ceph.com/docs/master/rbd/rbd-config-ref/#rbd-features

[ceph-users] mirroring global id mismatch

Hi there, We are replicating a RBD image from Primary to DR site using RBD mirroring. We were using 10.2.10. We decided to upgrade the DR site to luminous and upgrade went fine and mirroring status also was good. We then promoted the DR copy to test the failure. Everything checked out good. The

Re: [ceph-users] Scheduling deep-scrub operations

Have you tried adjusting osd_scrub_sleep? This together with increasing the time for deep scrubs is usually the solution for performance problems during scrubbing. (Only increase time between scrubs if using Bluestore) Paul -- Paul Emmerich Looking for help with your Ceph cluster? Contact us at

Re: [ceph-users] Correlate Ceph kernel module version with Ceph version

It's unfortunately not as easy as mapping the kernel version to a specific Ceph release. The kernel implementation is completely separate from the normal user space implementation, so you have to check for individual features and check when they have been implemented. Paul Paul -- Paul Emmer

[ceph-users] deleting a file

Hello. I am deleting files via S3CMD and for the most part have no issue. Every once in a while though, I get a positive response that a file has been deleted but when I check back the next day, the file is still there. I was wondering if there is a way to delete a file from within CEPH? I don'

Re: [ceph-users] Scheduling deep-scrub operations

Thanks Dan! This seems to be added by the following commit: https://github.com/ceph/ceph/commit/87be7c70a17492c9e5f06e01722690acec7a2c51 It contains a brief instruction on how to use it. PS. I agree with the other comments that the cluster needs to be able to handle deep-scrub during normal ope

Re: [ceph-users] Scheduling deep-scrub operations

On 14/12/2018 13:42, Alexandru Cucu wrote: Hi, Unfortunately there is no way of doing this from the Ceph configuration but you could create some cron jobs to add and remove the nodeep-scrub flag. The only problem would be that your cluster status will show HEALTH_WARN but i think you could set/u

Re: [ceph-users] Scheduling deep-scrub operations

Luminous has: osd_scrub_begin_week_day osd_scrub_end_week_day Maybe these aren't documented. I usually check here for available option: https://github.com/ceph/ceph/blob/luminous/src/common/options.cc#L2533 -- Dan On Fri, Dec 14, 2018 at 12:25 PM Caspar Smit wrote: > > Hi all, > > We have op

Re: [ceph-users] Scheduling deep-scrub operations

Hi, Unfortunately there is no way of doing this from the Ceph configuration but you could create some cron jobs to add and remove the nodeep-scrub flag. The only problem would be that your cluster status will show HEALTH_WARN but i think you could set/unset the flags per pool to avoid this. On Fr

Re: [ceph-users] Scheduling deep-scrub operations

Den fre 14 dec. 2018 kl 12:25 skrev Caspar Smit : > We have operating hours from 4 pm until 7 am each weekday and 24 hour days in > the weekend. > I was wondering if it's possible to allow deep-scrubbing from 7 am until 15 > pm only on weekdays and prevent any deep-scrubbing in the weekend. > I'v

Re: [ceph-users] disk controller failure

On 12/14/18 1:44 AM, Christian Balzer wrote: > On Thu, 13 Dec 2018 19:44:30 +0100 Ronny Aasen wrote: > >> On 13.12.2018 18:19, Alex Gorbachev wrote: >>> On Thu, Dec 13, 2018 at 10:48 AM Dietmar Rieder >>> wrote: Hi Cephers, one of our OSD nodes is experiencing a Disk controller p

[ceph-users] Scheduling deep-scrub operations

Hi all, We have operating hours from 4 pm until 7 am each weekday and 24 hour days in the weekend. I was wondering if it's possible to allow deep-scrubbing from 7 am until 15 pm only on weekdays and prevent any deep-scrubbing in the weekend. I've seen the osd scrub begin/end hour settings but th

[ceph-users] Correlate Ceph kernel module version with Ceph version

Hello, maybe a dump question but is there a way to correlate the ceph kernel module version with a ceph specific version? For example can I figure this out using "modinfo ceph"? Whats the best way to check if a specific client is running at least at Luminous? Best, Martin ___

Re: [ceph-users] cephfs file block size: must it be so big?

On Fri, Dec 14, 2018 at 7:50 AM Bryan Henderson wrote: > > I've searched the ceph-users archives and found no discussion to speak of of > Cephfs block sizes, and I wonder how much people have thought about it. > > The POSIX 'stat' system call reports for each file a block size, which is > usually