Brendan Gregg

JANUARY 17, 2018

OSes usually show you virtual memory and resident memory, shown as the "VIRT" and "RES" columns in top. Here is a MySQL database server (mysqld), PID 423, and measuring its working set size for 0.1 That's the working set size. It is used for capacity planning and scalability analysis. seconds (100 milliseconds): #./wss.pl

Cache 71

Cache Latency C++ Programming 71

Brendan Gregg

JANUARY 16, 2018

OSes usually show you virtual memory and resident memory, shown as the "VIRT" and "RES" columns in top. Here is a MySQL database server (mysqld), PID 423, and measuring its working set size for 0.1 That's the working set size. It is used for capacity planning and scalability analysis. seconds (100 milliseconds): #./wss.pl

Cache 40

Cache Latency C++ Programming 40

O'Reilly Software

MARCH 7, 2018

WebServices, unfortunately, failed to deliver on the distributed systems front by having virtually all implementations using synchronous/blocking calls—which we all know is a recipe for scaling disaster. Schema evolution practices were rarely in place. Furthermore, the deployment tooling was not ready for SOA.

Transportation 72

Transportation Java Programming Architecture 72

All Things Distributed

OCTOBER 2, 2017

The success of our early results with the Dynamo database encouraged us to write Amazon's Dynamo whitepaper and share it at the 2007 ACM Symposium on Operating Systems Principles (SOSP conference), so that others in the industry could benefit. This was the genesis of the Amazon Dynamo database.

Internet 128

Internet Internet AWS Performance 128