For every single access to "data" at least one write to metadata is required. So the IOPS for the Special Device is really relevant.
Correct. Bandwidth is not the point here.
Maybe. I can not confirm that, but the suspicion is plausible...
Disclaimer first: I have never done that and I am not a Ceph specialist.
Ceph is using an authentication mechanism with some "keyrings" involved. I really hope that adding a foreign OSD (with content) to a freshly setup cluster does not work...
That's surprising. Some weeks ago I tested a VM with many more virtual CPUs than the host has. (As a proof-of-concept, not to be used in production.)
Try to setup that VM with only two CPUs. You can increase the number of cores (and modify...
You probably know the answer, technically yes. But no one will recommend that...
If you need to use consumer grade SSDs: 1) use different brands. 2) use "too large ones" intentionally. 3) run a mirror vdev consisting of three devices instead of...
Hello folks! I've cleaned up my plugin and it's now mostly ready for consumption.
Check it out here - https://github.com/Zorlin/pve-moosefs
Please open an issue on https://github.com/Zorlin/pve-moosefs if you have any issues.
Personally, I prefer AMD CPUs these days. They seem to work a little better than recent Intel models. But realistically, the difference will be subtle and probably don't matter all that much.
Either one of these devices should be good enough to...
Man wächst mit seinen Aufgaben. ;)
zpool = hierarchisch über dem zfs/dataset
zpool list <- zeigt die Bruttokapazität
zpool get all rpool <- nachgucken, welche Flags und Features aka properties es auf dem pool gibt und was eingestellt ist
zpool...
There is no physical connection. Both "eno" and "vmbr0" are reporting "state DOWN"! (It must be "state UP" for both.)
Check your cable, replace it; look at the "link"-LED - it should signal a connection.
Remove the cable and plug it in again...
Usually backups are encrypted. By the source! The destination-PBS shall not be able to decrypt this data = only the source-PVE knows the secret key.
Encrypted data is NOT compressible. (Perhaps a few percent, but that does not count here.) By...
ich hab blissos 14 als VM am laufen (damit whatsapp online is und ich die matrix bride verwenden kann), somit sind die anforderungen sehr gering ... läuft soweit, außer das automatische herunterfahren, wenn der host herunter gefahren wird...
Bin jetzt auf der neuen Node auf die DC600M umgestiegen, und hab mich doch wieder für ZFS entschieden. Da die Anwendung stark datenbanklastig ist
(bbolt) hab ich die recordsize auf 32K gesenkt, xattr auf sa gesetzt und atime wie von @news...
SCP or SFTP is a well defined protocol, however that is single stream, single thread and commands shouldn’t return until all the data has been written. So you can use SFTP or other streams to transfer data over SSH, SSHFS is a different beast...
That's what I do :)
ZFS replication works fine for me. But you need to accept data loss of data written to the original (virtual) disk after the last successful replication. In some businesses this is a hard show stopper. In some (my) Homelab I...
For a backup only modified data is transferred to the PBS and written to disk. Usually that's only a small portion of the whole disk.
For a restore each and every "chunk" of the image has to be read on the PBS. (And all bytes have to be...
"Replication" is a term used for ZFS.
For Ceph you have (by default) three OSDs (Object Storage Daemon, usually = one disk) storing a copy of each block. Each one being on a different host.
There are some more aspects to consider...
When you say upgrade, did you add a new PCI device?
If so, then upon doing so your network ID have changed.
Compare the results returned with the new NIC installed and without the new NIC as shown from ip a
The config file found at...