I may be wrong but CEPH won’t split it into % based on disk size.
A block is wrote of 4MB to each PG that CEPH decided to use for that I/O and replication. Yes the 8TB ones would be used more as the size / crush algorithm will put them higher in the “chance” list but every write will be the same size no matter the size of the disk.
So to your answer I Guess, yes the 8TB would hold more data and do more reading. But when it comes to a write each disk will get the same amount of data on a write. And not 25/75 or another variation.
,Ash
On Wed, 13 Mar 2019 at 11:05 PM, tim taler <robur314@xxxxxxxxx> wrote:
Hi all,
how are your experiences with different disk sizes in one pool
regarding the overall performance?
I hope someone could shed some light on the following scenario:
Let's say I mix an equal amount of 2TB and 8TB disks in one pool,
with a crush map that tries to fill all disks to the same percentage.
Assuming that all disks have roughly the same speed of let's say 100MB/s,
wouldn't that hurt the performance?
As a thought experiment let's say the pool consists of only two disks,
one 2GB, one 8GB disk - both at 100MB/s
If I put a 1GB file onto it that would would write
250MB to the small disk and
750MB to the big disk.
leading to an overall write time of 7,5 sec.
If my pool would consist of disks with the same size,
than on both disks 500MB would be written,
leading to an estimated time of only 5sec.
Am I right here - in principle, not in exact numbers - or am I missing some
hidden magic ('cause even the cache operations would take different
times for different disk sizes, right?)
TIA
and best regards
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
_______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
