> The DB uses "fixed" sizes like 3,30,300G for different
levels of
> data, and when it needs to start fill a new level and it
doesn't fit,
> this level moves over to the data device.
I thought this no longer applied since the changes in
Pacific that Nathan mentioned?
Vlad
On 12/13/22 12:46, Janne Johansson wrote:
Den tis 13 dec. 2022 kl 17:47 skrev Vladimir Brik
<vladimir.brik@xxxxxxxxxxxxxxxx>:
Hello
I have a bunch of HDD OSDs with DB/WAL devices on SSD. If
the current trends continue, the DB/WAL devices will become
full before the HDDs completely fill up (e.g. a 50% full HDD
has DB/WAL device that is about 65% full).
Will anything terrible happen when DB/WAL devices fill up?
Will RocksDB just put whatever doesn't fit in DB/WAL SSD on
the HDD?
The DB uses "fixed" sizes like 3,30,300G for different levels of data,
and when it needs to start fill a new level and it doesn't fit, this
level moves over to the data device. While one can change DB sizes, at
least previously, the 3,30,300 sizes were what RocksDB used so DB
sizes in between these sizes would just leave unused space.
WAL data is more temporary in nature and will probably both be
somewhat small compared to 30-300G DB, and will probably just force
writes directly to the main device in case it runs full.
_______________________________________________
ceph-users mailing list -- ceph-users@xxxxxxx
To unsubscribe send an email to ceph-users-leave@xxxxxxx
