In some circumstances you may encounter sluggishness after downtime. This is mainly when you request large amounts of data from the database. The reason for this is that we are adding two 36GB 15KRPM FibreChannel disks in each downtime to the Data array of the Squidwolf SQL and the array gets a bit sluggish when the are synchronzing in. We have also added disks to the tempdb/master/msdb and the transaction log array (for those of you that know what that is).
We’ll keep on adding to the array until we have all 56 disks running on the FAStT600 array. We are adding these disks to increase perfomance, not to hold more data. I estimate we’ll only use 10% of available storage cause it’s all about the speed (SPIFFEH). Too bad the client performance isn’t allowing the cluster performance to blossom … but as you know, we are working hard on project Lagfest. Oh, and useless trivia of the day, February is now roughly 1 ton 🙂