June 12, 2013 at 1:21 pm
Hi,
I wanted to start a short discussion about Lock Pages in Memory (LPIM) and any possible impact (positive one) on disk's latency.
Recently, I contacted MS to get some help on a Cluster's issue. Long history short, the case is still open but it looks it has been resolved. However, they did recommend the use of LPIM on my SQL box.
Now, I am running a standard version of SQL 2012 on a two node Cluster. The Cluster does not lack of RAM (96GB per node, with 64GB assigned to SQL, dedicated box) But just today and after a few days of that change, I noticed on my RedGate Monitoring tool, that read and writes (latency) on my Data LUN went down to zero!
Could be that such action put most of my data into RAM, improving latency in such a dramatic way? Or ... should I look for any RedGate patch / issue? It's just hard to believe that a simple change, made such a huge improvement.
I know how LPIM works, and that LPIM will avoid the Os to trim any memory from SQL server, etc, but I find these results really outstanding and dramatic, especially on a dedicated box.
Viewing 0 posts
You must be logged in to reply to this topic. Login to reply
This website stores cookies on your computer.
These cookies are used to improve your website experience and provide more personalized services to you, both on this website and through other media.
To find out more about the cookies we use, see our Privacy Policy