Almost done reallocating my drives to Ceph. Just two OSDs left...pic.twitter.com/BrhbJawIhX
-
let me know how you go with that. we had to stop using ceph for puush because it was just so unrealiable performance wise. also digitalocean had a year long struggle with stabilising it on their infrastructure (though they seem to have finally succeeded)
Been using it for my backup server for ~a year now, and also we have it in production at $work on two serving clusters. Things change fast though, e.g. CephFS (what I'm using here) wasn't usable until the past year or two.
-
-
mmm very dependent on workload i guess. high write high read with only one node in cluster was causing huge issues for us
-
Write IOPS/throughout went up by 2x with BlueStore, so that probably helps :-)
- Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.