IOPS in a Very High-End NFS Environment?

Since I’m on site at a Beta customer (testing the product I work on at Oracle), this will be a quick blog entry. I’ve been meaning to direct folks to Gear6 for quite some time now. I have no stake in Gear6, so this is not a shameless plug. I think they solve interesting problems so if you are a large NFS shop, I’d recommend checking them out. They offer a plug-in NFS read-through cache and while I haven’t had first hand experience with their product, I know folks that have and they had good things to say about Gear6.

If any of you are confused about what NFS has to do with Oracle, I recommend this list of Oracle on NFS related posts.

4 Responses to “IOPS in a Very High-End NFS Environment?”

  1. 1 W.R.Welty May 8, 2008 at 2:17 am

    I am in the middle of a POC with Gear6/NetApp 6070 and a 3 node Oracle RAC RHEL4 cluster now, with early positive results.


  2. 2 kevinclosson May 9, 2008 at 1:36 am

    Hi MR Welty,

    Is this an 11g or 10g PoC? I’m very interested!

  3. 3 A. Itayemi May 31, 2008 at 10:46 pm

    Hello sir,
    – We are already started on a project implementing Oracle 11g RAC on 2 highend Solaris 10 update 4 (SPARC) servers.
    – We have no intention of using any 3rd party clustering software (either for storage management or application)
    – Oracle binaries will be installed on the local disk on each of the 2 servers
    – I had assumed all other files will go on ASM (raw devices via FCP on NetApp 6070), but the current requirement is that control files, redo logs and the archive logs stored on an actual shared filesystem (for ease of recovery for example).
    Data files will still go on the ASM disks using raw devices via FCP.
    This means we either use a cluster file system (OCFS2 would have been OK if it were available for Solaris) or as I suggested
    – NFS (Oracle DirectNFS). These files will be shared between all the instances and the filesystem will be mounted concurrently for read/write on both servers. So if one server “dies”, the other can recover it’s services since all necessary files are accessible by both nodes

    1. please what are your thoughts on this.
    2. Does it make sense?
    3. Any hints, guides available?

  4. 4 jimbo October 18, 2008 at 2:56 pm

    To the comment from MrWelty, I worked with Welty on this POC and it was an Oracle 10G RAC with three RAC servers. The caching of the Oracle database was able to off load the NetApp by 45-50%. This POC worked great, after a some bumpiness, of course! 🙂

Leave a Reply

Please log in using one of these methods to post your comment: Logo

You are commenting using your account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.


I work for Amazon Web Services. The opinions I share in this blog are my own. I'm *not* communicating as a spokesperson for Amazon. In other words, I work at Amazon, but this is my own opinion.

Enter your email address to follow this blog and receive notifications of new posts by email.

Join 744 other subscribers
Oracle ACE Program Status

Click It

website metrics

Fond Memories


All content is © Kevin Closson and "Kevin Closson's Blog: Platforms, Databases, and Storage", 2006-2015. Unauthorized use and/or duplication of this material without express and written permission from this blog’s author and/or owner is strictly prohibited. Excerpts and links may be used, provided that full and clear credit is given to Kevin Closson and Kevin Closson's Blog: Platforms, Databases, and Storage with appropriate and specific direction to the original content.

%d bloggers like this: