Moving to flash storage

From: Matt Adams <>
Date: Thu, 17 May 2018 14:15:46 +0000
Message-ID: <>

It looks like we might be migrating the big production databases (2 of them for a combined 40 Tb or so) to a NetApp 8080 Flash storage device. These database have thousands of concurrent connections and turn over between 10 G and 30 G of redo per hour.

I seem to vaguely recall a message or two here on the list over the last couple of years regarding things to watch out for when migrating to flash storage.

I've already considered that fact that if our queries/process are bound by either CPU or I/O transfer bottlenecks, then we will see little performance gain. I've also been reading that some flash storage system suffer from write performance penalties if the writes are not on 4K boundaries, which means that writes to the online redo logs may (or may not) suffer and that careful testing should be done before moving online redo to flash (not sure if the 8080 has this issue or not). (We use ZFS which normally bundles writes together which may mitigate this problem).

Any other 'gotchas' I should be aware of?

We're on RDBMS EE and on Sun Solaris (sparc) **** This communication may contain privileged and/or confidential information. If you are not the intended recipient, you are hereby notified that disclosing, copying, or distributing of the contents is strictly prohibited. If you have received this message in error, please contact the sender immediately and destroy any copies of this document. ****

Received on Thu May 17 2018 - 16:15:46 CEST

Original text of this message