Replies: 1 comment
-
see also: https://docs.google.com/document/d/1aoBhcosW4iIoZyMhTGjoMVkSOp5A_uDy9fDg7JuNxUE/edit#heading=h.p9zl29k6d3l0 |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Automatically gathering metrics about the ldmsd itself, particularly for aggregators, is key to monitoring center-wide ldmsd hierarchy performance.
As daemon features have grown, there are other quantities of interest available at varying costs. Costs (counts) driven by user behaviors are particularly of interest, such as unique stream tags received, stream message counts, stream byte totals, and failed connections.
What other statistics are of interest, now that we have so many interactive status commands from which we might derive metrics?
The currently supported dstat metrics groups are:
Beta Was this translation helpful? Give feedback.
All reactions