On Sun, 25 May 2008, Marc Bevand wrote: > > Primarily cost, reliability (less complex hw = less hw that can fail), > and serviceability (no need to rebuy the exact same raid card model > when it fails, any SATA controller will do).
As long as the RAID is self-contained on the card, and the disks are exported as JBOD, then you should be able to replace the card with any adaptor supporting at least as many ports. > If you want good write performance, instead of adding N GB of cache memory > to a disk controller, add N*5 or N*10 GB of system memory (DDR2 is maybe > 1/5th or 1/10th cheaper per GB, and the OS already uses main memory to > cache disk writes). Something tells me that Kyle may know what he is talking about. More system RAM does not help synchronous writes go much faster. It does help with asynchronous writes, but only for intermittent or relatively slow write loads. What makes the synchronous writes go faster is for the data to be queued as fast as possible to non-volatile media (e.g. NV write cache) so that the ZFS write operation can return right away. ZFS loads up the drives according to the current amount of I/O wait for the device. If the device accepts data faster, then ZFS returns faster, and the client application (e.g. NFS or database) can run again. Bob ====================================== Bob Friesenhahn [EMAIL PROTECTED], http://www.simplesystems.org/users/bfriesen/ GraphicsMagick Maintainer, http://www.GraphicsMagick.org/ _______________________________________________ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
