Brendan Gregg

JANUARY 17, 2018

It is used for capacity planning and scalability analysis. My tool does this using /proc/PID/clear_refs and the Referenced value from /proc/PID/smaps, which were added in 2007 by David Rientjes (thanks). Your app may have populated 100 Gbytes of main memory, but only uses 50 Mbytes each second to do its job. Consider these overheads.

Cache 71

Cache Latency C++ Programming 71

O'Reilly Software

MARCH 7, 2018

Build a more scalable, composable, and functional architecture for interconnecting systems and applications. Software today is not typically a single program—something that is executed by an operator or user, producing a result to that person—but rather a service : something that runs for the benefit of its consumers, a provider of value.

Transportation 72

Transportation Java Programming Architecture 72

Brendan Gregg

JANUARY 16, 2018

It is used for capacity planning and scalability analysis. My tool does this using /proc/PID/clear_refs and the Referenced value from /proc/PID/smaps, which were added in 2007 by David Rientjes (thanks). Your app may have populated 100 Gbytes of main memory, but only uses 50 Mbytes each second to do its job. Consider these overheads.

Cache 40

Cache Latency C++ Programming 40

The Netflix TechBlog

MARCH 1, 2021

It supports both high throughput services that consume hundreds of thousands of CPUs at a time, and latency-sensitive workloads where humans are waiting for the results of a computation. The first generation of this system went live with the streaming launch in 2007.

Serverless 228

Serverless Media Latency Social Media 228