Tamer Abdulradi tabdulradi

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

NOTE: a more up-to-date version of this can be found on my blog

nix-shell and Shebang Lines

A few days ago, version 1.9 of the Nix package manager was released. From the release notes:

nix-shell can now be used as a #!-interpreter. This allows you to write scripts that dynamically fetch their own dependencies.

Thread Pools

Thread pools on the JVM should usually be divided into the following three categories:

CPU-bound
Blocking IO
Non-blocking IO polling

Each of these categories has a different optimal configuration and usage pattern.

Delegating web requests in Linux to correct browser profile

A few months ago I set this up and here is the write up on it since yesterday, while talking to a fellow Linux user, they found it intriguing.

My requirements

Any URL I click in Slack, Signal desktop app, or launch via terminal actions should launch into the correct sandboxed, user-profile web browser instance (in precedence order):

https://github.com/<workorg>.* should open in the work Firefox profile

	import time
	import struct
	import socket
	import hashlib
	import sys
	from select import select
	import re
	import logging
	from threading import Thread
	import signal

	package controllers

	import lib._
	import play.api.mvc._
	import play.api.libs.json._


	object Auth extends Controller {

	val GITHUB = new OAuth2[GithubUser](OAuth2Settings(

	Latency Comparison Numbers (~2012)
	----------------------------------
	L1 cache reference 0.5 ns
	Branch mispredict 5 ns
	L2 cache reference 7 ns 14x L1 cache
	Mutex lock/unlock 25 ns
	Main memory reference 100 ns 20x L2 cache, 200x L1 cache
	Compress 1K bytes with Zippy 3,000 ns 3 us
	Send 1K bytes over 1 Gbps network 10,000 ns 10 us
	Read 4K randomly from SSD* 150,000 ns 150 us ~1GB/sec SSD