Re: CEPH Version choice
Hi Marc, I uploaded all scripts and a rudimentary readme to https://github.com/frans42/cephfs-bench . I hope it is sufficient to get started. I'm afraid its very much tailored to our deployment and I can't make it fully configurable anytime soon. I hope it serves a purpose though - at least I discovered a few bugs with it. We actually kept the benchmark running through an upgrade from mimic to octopus. Was quite interesting to see how certain performance properties change with that. This benchmark makes it possible to compare versions with live timings coming in. Best regards, ================= Frank Schilder AIT Risø Campus Bygning 109, rum S14 ________________________________________ From: Marc <Marc@f1-outsourcing.eu> Sent: Monday, May 15, 2023 11:28 PM To: Frank Schilder Subject: RE: [ceph-users] Re: CEPH Version choice
I planned to put it on-line. The hold-back is that the main test is un- taring a nasty archive and this archive might contain personal information, so I can't just upload it as is. I can try to put together a similar archive from public sources. Please give me a bit of time. I'm also a bit under stress right now with our users being hit by an FS meta data corruption. That's also why I'm a bit trigger happy.
Ok thanks, very nice, no hurry!!!
Hi Frank, Thanks! I have added this to my test environment todo
I uploaded all scripts and a rudimentary readme to https://github.com/frans42/cephfs-bench . I hope it is sufficient to get started. I'm afraid its very much tailored to our deployment and I can't make it fully configurable anytime soon. I hope it serves a purpose though - at least I discovered a few bugs with it.
I think I know where I should add something for creating and comparing hashes. For me this integrity of el9 + Nautilus is most important.
We actually kept the benchmark running through an upgrade from mimic to octopus. Was quite interesting to see how certain performance properties change with that.
So you have stats that show the current performance of a host having mimic and from another host that has octopus?
This benchmark makes it possible to compare versions with live timings coming in.
Do you do something with this time output like store it seperately in prometheus/influx? Or all your statistics coming from what is being reported by ceph itself? ps. my el7/el9 time does not have an option -f
Hi Marc,
We actually kept the benchmark running through an upgrade from mimic to octopus. Was quite interesting to see how certain performance properties change with that.
So you have stats that show the current performance of a host having mimic and from another host that has octopus?
I don't know what you mean by that. We have a kclient ceph fs mount to the cluster and we upgrade the ceph cluster while the benchmark is running. The kclient is on a kernel version, not a ceph version and we upgrade the ceph cluster, not the client OS.
This benchmark makes it possible to compare versions with live timings coming in.
Do you do something with this time output like store it seperately in prometheus/influx? Or all your statistics coming from what is being reported by ceph itself?
The output is tailored for grep. The script bench-grep has a list of useful expressions to search for. If you use this suite, you should aim for each benchmark taking about 30 minutes. Its not a lot of numbers per day and I just read through them. Even if you run this for a few weeks, the grep output is quite readable. If you want to do something fancy, knock yourself out :) Best regards, ================= Frank Schilder AIT Risø Campus Bygning 109, rum S14 ________________________________________ From: Marc <Marc@f1-outsourcing.eu> Sent: Wednesday, May 31, 2023 12:37 PM To: Frank Schilder Cc: ceph-users@ceph.io Subject: RE: [ceph-users] Re: CEPH Version choice Hi Frank, Thanks! I have added this to my test environment todo
I uploaded all scripts and a rudimentary readme to https://github.com/frans42/cephfs-bench . I hope it is sufficient to get started. I'm afraid its very much tailored to our deployment and I can't make it fully configurable anytime soon. I hope it serves a purpose though - at least I discovered a few bugs with it.
I think I know where I should add something for creating and comparing hashes. For me this integrity of el9 + Nautilus is most important.
We actually kept the benchmark running through an upgrade from mimic to octopus. Was quite interesting to see how certain performance properties change with that.
So you have stats that show the current performance of a host having mimic and from another host that has octopus?
This benchmark makes it possible to compare versions with live timings coming in.
Do you do something with this time output like store it seperately in prometheus/influx? Or all your statistics coming from what is being reported by ceph itself? ps. my el7/el9 time does not have an option -f
participants (2)
-
Frank Schilder
-
Marc