idle_page_tracking[1] is a simple, stupid toolbox for idle pages tracking. It can be used to get real working set size of a process. Tools This section describes two tools in the box though more tools exists. You can get more description about each tool from the README in the repository[1]. userprog userprog is a sample synthetic workload for test of other tools. It interactively allocates and access specified pages in the allocated pages....
Benchmarks for Database can be roughly divided into two kinds, OLTP and OLAP[1]. One of the most popular OLTP benchamrks is TPC-C, while that of OLAP is TPC-H[2]. This post describes how you can run TPC-H against MariaDB. Environment Setup The versions of the OS and programs I used for writeup of this post are as below. Ubuntu 16.04.2 Server MariaDB 10.2.8 TPC-H toolkit 2.17.2 Automated Scripts I automated whole things I will describe below using scripts and uploaded the scripts to the Github: https://github....
최근 커널은 stakc dump 에서 콜 트레이스(Call Trace) 에 각 코드의 메모리 어드레스를 찍어주지 않습니다. 이에 대해 포스팅을 해봅니다. Call Trace 커널은 문제가 발생하거나 하면 문제의 원인을 찾을 수 있는 다양한 정보를 담고 있는 stack dump 를 로그로 뿌려 줍니다. 문제의 원인을 찾는데 매우 소중한 정보입니다. 그 정보 중에서도 중요한 것 중 하나가 콜 트레이스로, 이 문제의 순간에 오기까지 어느 함수의 어느 지점에서 어느 함수를 호출해서 여기까지 왔는가를 담는 정보입니다....
I wrote a simple, stupid program[1] that showing LKML[2] mails in terminal briefly like twitter livestream in Go language. It is just an early version and so many things to be complemented exists, though. Nevertheless, now it just works as I wanted at first. References [1] https://github.com/sjp38/lkml [2] https://en.wikipedia.org/wiki/Linux_kernel_mailing_list
SPEC, which is a standard corporation for the benchmark[1], makes and shares various benchmark suites. SPEC CPU 2006[1] is one of those benchmark suites. It has made to measure performance of computation intensive workload and widely being used now. It has released v1.0 in 2006, 1.1 in 2008, and 1.2 in 2011. This post briefly describes the way to install and execute the SPEC CPU 2006 v1.1 on Ubuntu 16.04 servers....