On Tue, Jun 3, 2008 at 7:39 PM, Bob Friesenhahn <[EMAIL PROTECTED]> wrote:
> See the writeup for my own experiences which may be found at > "http://www.simplesystems.org/users/bfriesen/zfs-discuss/2540-zfs-performance.pdf";. Thanks for your fast reply. I've read your white paper (as well as the email thread that it originated from) at I must say it is very good, nice work! A few questions: 1. Is there a difference between disabling the cache nvsync and run ZFS with nocacheflush? 2. Why do you have separate storage pools for each disk? Would you get the same result of having 12 different virtual disks and share the same pool? > Note that this is with fast SAS drives. While the available IOPS would be > less with SATA drives, it seems that sequential write speed should not be > terribly less since from what I have seen, the bottleneck for sequential > writes is in the 2540's RAID controller and not the drives themselves. SATA > drive latency is a lot higher than SAS so that is surely a factor and may > put additional load on the RAID controller. You're absolutely right but 12MB/s is a very low number IMHO. cheers, Nickus _______________________________________________ storage-discuss mailing list [email protected] http://mail.opensolaris.org/mailman/listinfo/storage-discuss
