[Gluster-users] performance/writebehind behavior

Richard van der Hoff richard at swiftserve.com
Thu Jul 10 18:29:12 UTC 2014

Hi folks,

Just wondering if anyone could clear up a question about expected 
behavior for the performance/writebehind translator.

I'm using Gluster 3.3, with a single volume which is distributed to two 
bricks on a pair of servers. I have performance.flush-behind=off; the 
documentation [1] leads me to expect (but doesn't say explicitly) that 
this will make close() block until the write has been flushed - but that 
isn't consistent with the behaviour I'm seeing:

$ dd if=/dev/zero of=/shared/vod/zero bs=1024 count=1000; wc -c 
1000+0 records in
1000+0 records out
1024000 bytes (1.0 MB) copied, 0.133975 s, 7.6 MB/s
1016832 /shared/vod/zero

As you can see, the wc doesn't see all of the data which has been 
written by dd.

If anyone could clear up whether or not this is expected, I'd be grateful.




More information about the Gluster-users mailing list