Re: Default erasure code profile and sustaining loss of one host containing 4 OSDs

[Christian Wuerdig <christian.wuerdig@xxxxxxxxx>]

Generally the recommendation is: if your redundancy is X you should have at least X+1 entities in your failure domain to allow ceph to automatically  self-heal

Given your setup of 6 severs and failure domain host means you should select k+m=5 at most. So 3+2 should make for a good profile in your case. 

You could go to 4+2 but a loss of a host means ceph can't auto heal means of another server gets into trouble before the first one is replaced your cluster will become unavailable. 

Please note that you can't change the EC profile of an existing pool - you'll need to create a new pool and copy the data over if you want to change your current profile

Cheers

Christian

On Sat, 21 Jul 2018, 01:52 Ziggy Maes, <ziggy.maes@xxxxxxxxxxxxx> wrote:

Hello Caspar

 

That makes a great deal of sense, thank you for elaborating. Am I correct to assume that if we were to use a k=2, m=2 profile, it would be identical to a replicated pool (since there would be an equal amount of data and parity chunks)? Furthermore, how should the proper erasure profile be determined then? Are we to strive for a as high as possible data chunk value (k) and a low parity/coding value (m)?

 

Kind regards

Ziggy Maes
DevOps Engineer
CELL +32 478 644 354
SKYPE Ziggy.Maes

www.be-mobile.com

 

 

From: Caspar Smit <casparsmit@xxxxxxxxxxx>
Date: Friday, 20 July 2018 at 14:15
To: Ziggy Maes <ziggy.maes@xxxxxxxxxxxxx>
Cc: "ceph-users@xxxxxxxxxxxxxx" <ceph-users@xxxxxxxxxxxxxx>
Subject: Re: Default erasure code profile and sustaining loss of one host containing 4 OSDs

 

Ziggy,

 

For EC pools: min_size = k+1

 

So in your case (m=1) -> min_size is 3  which is the same as the number of shards. So if ANY shard goes down, IO is freezed.

 

If you choose m=2 min_size will still be 3 but you now have 4 shards (k+m = 4) so you can loose a shard and still remain availability.

 

Of course a failure domain of 'host' is required to do this but since you have 6 hosts that would be ok.

Met vriendelijke groet,

Caspar Smit
Systemengineer
SuperNAS
Dorsvlegelstraat 13
1445 PA Purmerend

t: (+31) 299 410 414
e: casparsmit@xxxxxxxxxxx
w: www.supernas.eu 

 

_______________________________________________
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