I don't specifically, Mike, but I'll point out a few things: 1) There's more to life than performance. Simplicity, cost savings, and additional features/enhancements all need to be considered. 2) It used to be the case that 1Gb Ethernet, even using LACP or other aggregation protocols, couldn't keep up with FC. FC is a more efficient protocol than NFS. However, now that we have 10Gb Ethernet, it's really no longer an issue. 3) The performance of the backend storage array and architecture are even more important than simply the line speed and efficiency of the line protocol.
-Adam On Wed, Apr 2, 2014 at 8:53 AM, Michael Ryder <[email protected]> wrote: > > On Tue, Apr 1, 2014 at 11:31 AM, Adam Levin <[email protected]> wrote: > >> Unfortunately, trying to convince Oracle DBAs to try something new and >> better than the way they've been doing things for decades is very, very >> difficult. >> >> If you can, I suggest creating an eval environment or POC using NFS for >> Oracle. Oracle as a company ran petabytes of databases on NetApp NFS for >> many years until they purchased Exadata and have been migrating. Oracle on >> NetApp NFS works beautifully. It would really benefit the DBAs at your >> organization to explore the possibility. >> >> > Adam, I must confess I am in the school that doubts NFS can provide the > same level of performance as block storage. Unfortunately, I don't have > the resources to do a proof of concept -- can you direct me to a good study > I can read? > > Thanks > > Mike >
_______________________________________________ Discuss mailing list [email protected] https://lists.lopsa.org/cgi-bin/mailman/listinfo/discuss This list provided by the League of Professional System Administrators http://lopsa.org/
