[ceph-users] Re: RGW listing slower on nominally faster setup

Hi, I’m experiencing the same symptoms as OP. We’re running Ceph Octopus 15.2.1 with RGW, and have seen on multiple occasions the bucket index pool go up to 500MB/s read throughput / 100K read IOPS. Our logs during this time are flooded with these entries: 2020-06-09T07:11:18.070+0200 7f2676efd

[ceph-users] Upload speed slow for 7MB file cephfs+Samaba

Hi, I have Ceph Octopus 4 Node, each node has 12 disk cluster, which is configured with cephfs (replica 2) + exposed via samba for windows 10G client. When a user copies a folder containing 1000's of 7MB files from windows 10 client getting only a speed of 40MB/s. Client and Ceph nodes all connec

[ceph-users] Re: dealing with spillovers

Hi Reed, thanks for the log. Nothing much of interest there though. Just a regular SST file that RocksDB instructed to put at "slow" device. Presumably it belongs to a higher level hence the desire to put it that "far". Or (which is less likely) RocksDB lacked free space when doing compaction

[ceph-users] Re: Poor Windows performance on ceph RBD.

Hi, I think you are hit by two different problems at the same time. The second problem might be the same that we also experience, namely that Windows VMs have very strange performance characteristics with libvirt, vd driver and RBD. With copy operations on very large files (>2GB) we see a sharp

[ceph-users] ceph grafana dashboards on git

I was wondering if I can fork and do pull request on the grafana dashboards at git[1] Clean up a bit inconsistent naming use of labels etc. [1] https://github.com/ceph/ceph/tree/master/monitoring/grafana/dashboards ___ ceph-users mailing list -- ceph

[ceph-users] Re: dealing with spillovers

Thanks for sticking with me Igor.Attached is the ceph-kvstore-tool stats output.Hopefully something interesting in here.Thanks,Reed kvstoretool.log Description: Binary data On Jun 12, 2020, at 6:56 AM, Igor Fedotov wrote: Hi Reed,thanks for the log.Nothing much of i

[ceph-users] ceph grafana dashboards: rbd overview empty

The grafana dashboard 'rbd overview' is empty. Queries have measurements 'ceph_rbd_write_ops' that do not exist in prometheus (I think). Should I enable something more than just 'ceph mgr module enable prometheus' I am on Nautilus ___ ceph-users m

[ceph-users] ceph grafana dashboards: osd device details keeps loading.

I have sometimes that the dashboard keeps loading when switching to 3 hours range. However I do not see any load on the prometheus server. Anyone having something similar? ___ ceph-users mailing list -- ceph-users@ceph.io To unsubscribe send an em

[ceph-users] Re: dealing with spillovers

hmm, RocksDB reports 13GB at L4:  "": "Level    Files   Size Score Read(GB)  Rn(GB) Rnp1(GB) Write(GB) Wnew(GB) Moved(GB) W-Amp Rd(MB/s) Wr(MB/s) Comp(sec) CompMergeCPU(sec) Comp(cnt) Avg(sec) KeyIn KeyDrop",     "": "

[ceph-users] ceph on rhel7 / centos7 till eol?

Will there be a ceph release available on rhel7 until the eol of rhel7? ___ ceph-users mailing list -- ceph-users@ceph.io To unsubscribe send an email to ceph-users-le...@ceph.io

[ceph-users] Re: ceph on rhel7 / centos7 till eol?

On 2020-06-12 16:35, Marc Roos wrote: > > Will there be a ceph release available on rhel7 until the eol of rhel7? much needed here as well +1 Would be really great, Thanks a lot. Dietmar -- _ D i e t m a r R i e d e r, Mag.Dr. Innsbruck Medical Univers

[ceph-users] Re: RGW listing slower on nominally faster setup

On 6/12/20, 5:40 AM, "James, GleSYS" wrote: > When I set the debug_rgw logs to "20/1", the issue disappears immediately, > and the throughput for the index pool goes back down to normal levels. I can – somewhat happily – confirm that setting debug_rgw to "20/1" makes the issue disappear instan

[ceph-users] Re: dealing with spillovers

Thanks Igor, I did see that L4 sizing and thought it seemed auspicious. Though after looking at a couple other OSD's with this, I saw that I think the sum of L0-L4 appears to match a rounded off version of the metadata size reported in ceph osd df tree. So I'm not sure if thats actually showing

[ceph-users] Re: help with failed osds after reboot

Hi, which ceph release are you using? You mention ceph-disk so your OSDs are not LVM based, I assume? I've seen these messages a lot when testing in my virtual lab environment although I don't believe it's the cluster's fsid but the OSD's fsid that's in the error message (the OSDs have th

[ceph-users] Re: help with failed osds after reboot

Maybe you have the same issue? https://tracker.ceph.com/issues/44102#change-167531 In my case an update(?) disabled osd runlevels. systemctl is-enabled ceph-osd@0 -Original Message- To: ceph-users@ceph.io Subject: [ceph-users] Re: help with failed osds after reboot Hi, which ceph

[ceph-users] Re: Is there a way froce sync metadata in a multisite cluster

黄明友 wrote: > Hi,all: > > the slave zone show metadata is caught up with master ; but use > radosgw-admin bucket list|wc diff master and the slave zone , is not equal. > how can I force sync it? I too face the same problem. I see new buckets getting created in the master zone howe

[ceph-users] radosgw - how to grant read-only access to another user by default

Hi, I'm new to radosgw (learned more about the MDS than I care to...), and it seems like the buckets and objects created by one user cannot be accessed by another user. Is there a way to make any content created by User A accessible (read-only) by User B? >From the documentation it looks like thi

[ceph-users] Re: radosgw - how to grant read-only access to another user by default

Yes best via bucket policies https://docs.ceph.com/docs/mimic/radosgw/bucketpolicy/ -Original Message- To: ceph-users@ceph.io Subject: [ceph-users] radosgw - how to grant read-only access to another user by default Hi, I'm new to radosgw (learned more about the MDS than I care t