iceqp

Sample config for 2 million web socket connection

    sysctl -w fs.file-max=12000500
    sysctl -w fs.nr_open=20000500
    # Set the maximum number of open file descriptors
    ulimit -n 20000000

    # Set the memory size for TCP with minimum, default and maximum thresholds 
 sysctl -w net.ipv4.tcp_mem='10000000 10000000 10000000'

iceqp

linux查看httpd进程数

ps -ef | grep httpd | wc -l

查看Apache的并发请求数及其TCP连接状态

netstat -n | awk '/^tcp/ {++S[$NF]} END {for(a in S) print a, S[a]}'

iceqp

Tmux layouts with tmuxinator

Finally this time, I'm sold on tmux after I used tmuxinator to configure tmux layouts. The default layout didn't work for me, I wanted more control on the split panes. Here's how you can fine tune your tmux layout:

1. Add this to your ~/.tmux.conf -> set -g mouse-resize-pane on
2. Start tmux, split panes, resize panes with mouse to your liking
3. On your shell, run tmux list-windows to list active tmux windows and their layouts
4. Copy paste the layout in tmuxinator project file

iceqp

# connect to tty on Docker for Mac VM
screen ~/Library/Containers/com.docker.docker/Data/com.docker.driver.amd64-linux/tty

# disconnect that session but leave it open in background
Ctrl-a d

# list that session that's still running in background
screen -ls

# reconnect to that session (don't open a new one, that won't work and 2nd tty will give you garbled screen)

iceqp

Latency numbers every programmer should know

L1 cache reference ......................... 0.5 ns
Branch mispredict ............................ 5 ns
L2 cache reference ........................... 7 ns
Mutex lock/unlock ........................... 25 ns
Main memory reference ...................... 100 ns             
Compress 1K bytes with Zippy ............. 3,000 ns  =   3 µs
Send 2K bytes over 1 Gbps network ....... 20,000 ns  =  20 µs
SSD random read ........................ 150,000 ns  = 150 µs

Read 1 MB sequentially from memory ..... 250,000 ns = 250 µs

iceqp

Codes for Machine Learning Foundations(NTU)
台湾国立大学《机器学习基石》（Coursera版）相关的代码、编程作业等。

课程地址：https://class.coursera.org/ntumlone-001/