Thank you Andreas.
Then I understand that it doesn't make sense configure the ZIL...I will
try to use the ZIL SSDs disks for the MDT instead of our current SAS
disks ;)
Regards.
=============================================
Fernando Pérez
Institut de Ciències del Mar (CMIMA-CSIC)
Departament Oceanografía Física i Tecnològica
Passeig Marítim de la Barceloneta,37-49
08003 Barcelona
Phone: (+34) 93 230 96 35
=============================================
On 09/07/2015 08:04 PM, Dilger, Andreas wrote:
The ZIL is not currently used by Lustre OSTs or MDTs since it needs specific
support in the filesystem. It will be used at some point in the future.
The L2ARC usage is transparent to the filesystem so it works with Lustre today.
Cheers, Andreas
On Sep 7, 2015, at 06:14, Fernando Perez <fpe...@icm.csic.es> wrote:
Dear Lustre experts,
I have some questions about migrate OSTs to ZFS backend.
We have a Lustre filesystem with 200 TB and ten OSTs with lustre 2.4.1. Due to
hardware problems in some OSTs disks we are planning to change these disks and
configure the new ones (server + JBOD) with ZFS backend.
I have some questions about this:
- I have seen LU-4009 about ZFS ZIL. Does it mean that we should configure the
zfs filesystem osts without ZIL dedicated ssds?
- Is L2ARC cache supported in Lustre?
Regards.
--
=============================================
Fernando Pérez
Institut de Ciències del Mar (CMIMA-CSIC)
Departament Oceanografía Física i Tecnològica
Passeig Marítim de la Barceloneta,37-49
08003 Barcelona
Phone: (+34) 93 230 96 35
=============================================
_______________________________________________
lustre-discuss mailing list
lustre-discuss@lists.lustre.org
http://lists.lustre.org/listinfo.cgi/lustre-discuss-lustre.org
_______________________________________________
lustre-discuss mailing list
lustre-discuss@lists.lustre.org
http://lists.lustre.org/listinfo.cgi/lustre-discuss-lustre.org