On Wed, Mar 18, 2015 at 12:58 PM, Steven Jones <steven.jones1201@xxxxxxxxxxx> wrote: > Yes BBU is on the controller; 1024Mb. It is a HP P410i controller, with write caching turned on the controller; off on disk level. vm.dirty_background_bytes=67108864 and vm.dirty_bytes=536870912 looks resonable for 512MB BBU, you can calculate them for 1024 or recalculate them for dirty_background_ratio By the way, which kernel do you use? > We don't at this stage have any graphs, but we will set it up over the next 24hrs at least. Do not forget to have iostat statistics on them, at least latency, %iowait and %util, such parameters are very helpful. And I am always suspicious about zfs under heavy writes. It is reliable and quite comfortable in terms of configuration, but for speed ext4 or xfs with disabled barrier looks more reasonable >> >> -- >> Ilya Kosmodemiansky, >> >> PostgreSQL-Consulting.com >> tel. +14084142500 >> cell. +4915144336040 >> ik@xxxxxxxxxxxxxxxxxxxxxxxxx >> >> >> -- >> Sent via pgsql-performance mailing list (pgsql-performance@xxxxxxxxxxxxxx) >> To make changes to your subscription: >> http://www.postgresql.org/mailpref/pgsql-performance > -- Ilya Kosmodemiansky, PostgreSQL-Consulting.com tel. +14084142500 cell. +4915144336040 ik@xxxxxxxxxxxxxxxxxxxxxxxxx -- Sent via pgsql-performance mailing list (pgsql-performance@xxxxxxxxxxxxxx) To make changes to your subscription: http://www.postgresql.org/mailpref/pgsql-performance
