[ceph-users] Re: cephadm automatic sizing of WAL/DB on SSD
I think that the backported fix for this issue made it into ceph v16.2.11. https://ceph.io/en/news/blog/2023/v16-2-11-pacific-released/ "ceph-volume: Pacific backports (pr#47413, Guillaume Abrioux, Zack Cerza, Arthur Outhenin-Chalandre)" https://github.com/ceph/ceph/pull/47413/commits/4252cc44211f0ccebf388374744eaa26b32854d3 -Patrick ___ ceph-users mailing list -- ceph-users@ceph.io To unsubscribe send an email to ceph-users-le...@ceph.io
[ceph-users] Re: How to make CephFS a tiered file system?
At a glance, it looks to me like cache-pools ( https://docs.ceph.com/en/latest/dev/cache-pool/ ) can be somewhat HSM-like, but on an object level rather than a file level. Side-question: Is that cache pool approach different from the seldom-recommended cache-tiering ( https://docs.ceph.com/en/latest/rados/operations/cache-tiering/ ), with respect to the "words of caution" and limited number of known-good workloads? -Patrick From: Brady Deetz Sent: Tuesday, July 20, 2021 11:32 AM To: huxia...@horebdata.cn Cc: ceph-users Subject: [ceph-users] Re: How to make CephFS a tiered file system? What you are proposing is called a hierarchical storage manager (HSM). Cephfs does not have a built in HSM. Would be amazing if it did though. On Mon, Jul 19, 2021, 4:28 PM huxia...@horebdata.cn wrote: > Dear Cepher, > > I have a requirement to use CephFS as a tiered file system, i.e. the data > will be first stored onto an all-flash pool (using SSD OSDs), and then > automatically moved to an EC coded pool (using HDD OSDs) according to > threshold on file creation time (or access time). The reason for such a > file system is due to the fact that, files are created and most likely > accessed within the first 6 months or 1 year, and after that period, those > files have much less chance to be accessed and thus could be moved to a > slower and cheap pool. > > Does CephFS already support such a tiered feature? and if yes, how to > implement such feature with a pool of all SSD pool and a pool of EC-coded > HDD pool? > > Any suggestion, ideas, comments are highly appreciated, > > best regards, > > samuel > > > > huxia...@horebdata.cn > ___ > ceph-users mailing list -- ceph-users@ceph.io > To unsubscribe send an email to ceph-users-le...@ceph.io > ___ ceph-users mailing list -- ceph-users@ceph.io To unsubscribe send an email to ceph-users-le...@ceph.io ___ ceph-users mailing list -- ceph-users@ceph.io To unsubscribe send an email to ceph-users-le...@ceph.io
[ceph-users] Re: How to make CephFS a tiered file system?
Do I understand correctly that to relocate a single file to a different pool, the process would be: setfattr -n ceph.dir.layout.pool -v NewPool original_file_name cp -a original_file_name .hidden_file_name && mv -f .hidden_file_name original_file_name -Patrick From: Patrick Donnelly Sent: Thursday, July 22, 2021 5:03 PM To: huxia...@horebdata.cn Cc: ceph-users Subject: [ceph-users] Re: How to make CephFS a tiered file system? On Wed, Jul 21, 2021 at 1:49 PM huxia...@horebdata.cn wrote: > > Dear Patrick, > > Thanks a lot for pointing out the HSM ticket. We will see whether we have the > resource to do something with the ticket. > > I am thinking of a temporary solution for HSM using cephfs client commands. > The following command >'setfattr -n ceph.dir.layout.pool -v NewPool Folder' > will set the specified folder Folder to be written to NewPool. > > If i understand correctly, the new file written to Folder will be directed to > NewPool, but how about the old files that already exist in FOLDER before > executing the above command? Correct. > Should i mannually migrate those old files, and how? Copy them. -- Patrick Donnelly, Ph.D. He / Him / His Principal Software Engineer Red Hat Sunnyvale, CA GPG: 19F28A586F808C2402351B93C3301A3E258DD79D ___ ceph-users mailing list -- ceph-users@ceph.io To unsubscribe send an email to ceph-users-le...@ceph.io ___ ceph-users mailing list -- ceph-users@ceph.io To unsubscribe send an email to ceph-users-le...@ceph.io
[ceph-users] cephadm automatic sizing of WAL/DB on SSD
Hi, I'd like to understand if the following behaviour is a bug. I'm running ceph 16.2.9. In a new OSD node with 24 hdd (16 TB each) and 2 ssd (1.44 TB each), I'd like to have "ceph orch" allocate WAL and DB on the ssd devices. I use the following service spec: spec: data_devices: rotational: 1 size: '14T:' db_devices: rotational: 0 size: '1T:' db_slots: 12 This results in each OSD having a 60GB volume for WAL/DB, which equates to 50% total usage in the VG on each ssd, and 50% free. I honestly don't know what size to expect, but exactly 50% of capacity makes me suspect this is due to a bug: https://tracker.ceph.com/issues/54541 (In fact, I had run into this bug when specifying block_db_size rather than db_slots) Questions: Am I being bit by that bug? Is there a better approach, in general, to my situation? Are DB sizes still governed by the rocksdb tiering? (I thought that this was mostly resolved by https://github.com/ceph/ceph/pull/29687 ) If I provision a DB/WAL logical volume size to 61GB, is that effectively a 30GB database, and 30GB of extra room for compaction? Thanks, Patrick ___ ceph-users mailing list -- ceph-users@ceph.io To unsubscribe send an email to ceph-users-le...@ceph.io
[ceph-users] Re: cephadm automatic sizing of WAL/DB on SSD
Thanks, Arthur, I think you are right about that bug looking very similar to what I've observed. I'll try to remember to update the list once the fix is merged and released and I get a chance to test it. I'm hoping somebody can comment on what are ceph's current best practices for sizing WAL/DB volumes, considering rocksdb levels and compaction. -Patrick From: Arthur Outhenin-Chalandre Sent: Friday, July 29, 2022 2:11 AM To: ceph-users@ceph.io Subject: [ceph-users] Re: cephadm automatic sizing of WAL/DB on SSD Hi Patrick, On 7/28/22 16:22, Calhoun, Patrick wrote: > In a new OSD node with 24 hdd (16 TB each) and 2 ssd (1.44 TB each), I'd like > to have "ceph orch" allocate WAL and DB on the ssd devices. > > I use the following service spec: > spec: > data_devices: > rotational: 1 > size: '14T:' > db_devices: > rotational: 0 > size: '1T:' > db_slots: 12 > > This results in each OSD having a 60GB volume for WAL/DB, which equates to > 50% total usage in the VG on each ssd, and 50% free. > I honestly don't know what size to expect, but exactly 50% of capacity makes > me suspect this is due to a bug: > https://tracker.ceph.com/issues/54541 > (In fact, I had run into this bug when specifying block_db_size rather than > db_slots) > > Questions: > Am I being bit by that bug? > Is there a better approach, in general, to my situation? > Are DB sizes still governed by the rocksdb tiering? (I thought that this > was mostly resolved by https://github.com/ceph/ceph/pull/29687 ) > If I provision a DB/WAL logical volume size to 61GB, is that effectively a > 30GB database, and 30GB of extra room for compaction? I don't use cephadm, but it's maybe related to this regression: https://tracker.ceph.com/issues/56031. At list the symptoms looks very similar... Cheers, -- Arthur Outhenin-Chalandre ___ ceph-users mailing list -- ceph-users@ceph.io To unsubscribe send an email to ceph-users-le...@ceph.io ___ ceph-users mailing list -- ceph-users@ceph.io To unsubscribe send an email to ceph-users-le...@ceph.io