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 <bdeetz@xxxxxxxxx> Sent: Tuesday, July 20, 2021 11:32 AM To: huxiaoyu@xxxxxxxxxxxx <huxiaoyu@xxxxxxxxxxxx> Cc: ceph-users <ceph-users@xxxxxxx> Subject: 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 huxiaoyu@xxxxxxxxxxxx <huxiaoyu@xxxxxxxxxxxx> 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 > > > > huxiaoyu@xxxxxxxxxxxx > _______________________________________________ > ceph-users mailing list -- ceph-users@xxxxxxx > To unsubscribe send an email to ceph-users-leave@xxxxxxx > _______________________________________________ ceph-users mailing list -- ceph-users@xxxxxxx To unsubscribe send an email to ceph-users-leave@xxxxxxx _______________________________________________ ceph-users mailing list -- ceph-users@xxxxxxx To unsubscribe send an email to ceph-users-leave@xxxxxxx
 |