News for hackers. Stuff that matters.

A comment on Introducing Atlas: Netflix's Primary Telemetry Platform. Parent comment

Re:Introducing Atlas: Netflix's Primary Telemetry Platform by misframer on Friday December 12, 2014 @08:05PM (#8743652)
1,000 metrics per server is quite reasonable. I work for a performance management company and we handle thousands of time series metrics per monitored server at one-second resolution.
[ Parent | on HN ]
Re:Introducing Atlas: Netflix's Primary Telemetry Platform by lifeisstillgood on Friday December 12, 2014 @08:13PM (#8743676)
What's the rough ratio for system level, process level and app level (ie total MB, MB / process and "a customer just signed up")?

How much traffic does that add up to? It seems a lot.

[ Parent | on HN ]
Re:Introducing Atlas: Netflix's Primary Telemetry Platform by CrankyFool on Saturday December 13, 2014 @01:42AM (#8744444)
above, copperlight quotes about 3%-5% of metrics being system-level. A pretty small number would be process-level, I'm guessing, with the vast majority being app-level.

At Netflix-sized, the answer to pretty much any question is "a lot." :)

[ Parent | on HN ]