One of the most common requests to the trending of data is "How do I make the charts graph data samples which are smaller than 300 seconds?" And the answer has been, you have the source, have fun.
The original design decision that Henrik inherited was larrd should only be for capacity planning and NOT real-time performance analysis. Do one thing and do it well.
I had a thought the other day, and I think we could possibly get the "best of both worlds."
Instead of
$ vmstat 300 2 (resulting in one 300 second sample)
why not
$ vmstat 5 61 (resulting in sixty 5 second samples)
The data would still only be transported every five minutes, but contain more granular samples.
This could not be done for all metrics, but many. This would also require the RRAs of the all the RRDs be re-made (export, re-create, import). But I've that's been on my mind anyway cause the original RRA structure was based on screen sizes for 800x600, instead of business requirements.
Henrik, do you follow my thinking? It's kinda hard for me to believe it's taken me over five years to think of this!
My biggest concern is not the technical details of the collectors and RRD/RRA restructuring, but inflicting resource usage on servers measuring themselves.
$ vmstat 1 301 would definitely be a bad idea.
Scott Walters -PacketPusher