[Moosefs-users] Non-journaling file system as underlying FS

[Florent B. <fl...@co...>]

Hi all,

Today i'm having some benchmark tests on a 2 chunkservers MFS installation.
It consists on a lot of read/write operations.

Both are using ext4 as underlying file system.

I see that "jbd2" process (Journaling Block Device, from Linux kernel) 
is taking around 50% of CPU time !! When mfschunkserver process, less 
dans 10%...

So i wonder if we just could use a non-journaling file system for 
chunkservers, assuming that data consistency is managed by the overlying 
FS (MFS and mfsmaster). If some problems occurs on chunkservers, and 
data is lost or corrupted, it will automatically be corrected by 
distributing chunk files over servers.

Am I wrong ? What do you think about it ?

Flo