> > Alright, just a sec, as I'm running another benchmark with write-back's > aggregate-size set to 4MB (which seems to be the maximum)... Alright, > that made a bit of an improvement, but it's still slower than 1.3.10 > with aggregate-size set to 1MB on the server side, and also still a > *lot* slower than the write speeds of the systems involved (~70MB/sec on > server1, ~35MB/sec on server2): > Please load write-behind and read-ahead on top of AFR (just one instances of each perf xlator). write-behind with high aggregate-size is effective when used on top of AFR. Currently there is some code cleanup happening in AFR in 1.4, so please await the next pre-release to use AFR. avati -------------- next part -------------- An HTML attachment was scrubbed... URL: http://zresearch.com/pipermail/gluster-users/attachments/20080920/033dce7e/attachment.htm
