Hi,
are any of those old disks SMR ones? Because they will absolutely
destroy any kind of performance (ceph does not use writecaches due to
powerloss concerns, so they kinda do their whole magic for each
writerequest).
Greetings
On 9/6/21 10:47 AM, Simon Sutter wrote:
Hello everyone!
I ha
>
>
> At the moment, the nodes look like this:
> 8 Nodes
> Worst CPU: i7-3930K (up to i7-6850K)
> Worst ammount of RAM: 24GB (up to 64GB)
> HDD Layout:
> 1x 1TB
> 4x 2TB
> 1x 6TB
> all sata, some just 5400rpm
>
> I had to put the OS on the 6TB HDDs, because there are no more sata
> connections
do you think about having the os on one of the disks, used by ceph?
Thanks in advance,
Simon
Von: Kai Börnert
Gesendet: Montag, 6. September 2021 10:54:24
An: ceph-users@ceph.io
Betreff: [ceph-users] Re: Performance optimization
Hi,
are any of those old disks
Am 06.09.21 um 11:54 schrieb Marc:
- The one 6TB disk, per node?
You get bad distribution of data, why not move drives around between these to
clusters, so you have more the same in each.
I would assume that this behaves exactly the other way around. As long
as you have the same number of
>
> >> - The one 6TB disk, per node?
> >
> > You get bad distribution of data, why not move drives around between
> these to clusters, so you have more the same in each.
> >
>
> I would assume that this behaves exactly the other way around. As long
> as you have the same number of block devices w
Because replicated uses so much more storage, it wasn't really an option until
now.
We didn't have any problems with CPU utilization and I can go to 32GB for every
node, and 64 for MDS nodes.
Thanks
____________
Von: Marc
Gesendet: Montag, 6. September 2021 1
Am 06.09.21 um 16:44 schrieb Simon Sutter:
|node1|node2|node3|node4|node5|node6|node7|node8|
|1x1TB|1x1TB|1x1TB|1x1TB|1x1TB|1x1TB|1x1TB|1x1TB|
|4x2TB|4x2TB|4x2TB|4x2TB|4x2TB|4x2TB|4x2TB|4x2TB|
|1x6TB|1x6TB|1x6TB|1x6TB|1x6TB|1x6TB|1x6TB|1x6TB|
"ceph osd df tree" should show the data distributio
stead of writing it
to the disk directly.
Tahnks,
Simon
Von: Robert Sander
Gesendet: Montag, 6. September 2021 16:48:52
An: Simon Sutter; Marc; ceph-users@ceph.io
Betreff: Re: [ceph-users] Re: Performance optimization
Am 06.09.21 um 16:44 schrieb Simon Sutter:
>
Am 07.09.21 um 11:49 schrieb Simon Sutter:
I never looked into RocksDB, because I thought writing data 24/7 does
not benefit from caching.
But this is metadata storage, so I might profit from it.
Due to lack of sata ports, is it possible to save all RocksDB's on one ssd?
It should still be f