jboner

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

mikeal

var portrange = 45032

function getPort (cb) {
  var port = portrange
  portrange += 1

  var server = net.createServer()
  server.listen(port, function (err) {
    server.once('close', function () {
      cb(port)

dcramer

from django.db.models.signals import post_init

def track_data(*fields):
    """
    Tracks property changes on a model instance.
    
    The changed list of properties is refreshed on model initialization
    and save.
    
    >>> @track_data('name')

tkaemming

#!/usr/bin/env python
"""
Self-versioning and argument-hashing cache decorator for deterministic functions.
Designed to be extensible and API-compliant with Django and Flask cache backends.

For examples and caveats, see the bottom of the file.

Ted Kaemming: https://github.com/tkaemming
Mike Tigas: https://github.com/mtigas
"""

tkaemming

#!/usr/bin/env python
from collections import namedtuple
from struct import Struct


class NamedStruct(Struct):
    def __init__(self, name, fields, byteorder=None):
        fmt = (byteorder or '') + ''.join(field[0] for field in fields)
        super(NamedStruct, self).__init__(fmt)
        self.namedtuple = namedtuple(name, (field[1] for field in fields))

tkaemming

import logging, time
from timer import timed

logger = logging.getLogger()
logger.setLevel(logging.DEBUG)

handler = logging.StreamHandler()
handler.setLevel(logging.DEBUG)
logger.addHandler(handler)

rbranson

The point of this is to use cheap machines with small/slow storage to coordinate client requests while dedicating the machines with the big and fast storage to doing what they do best. I found that request coordination was contributing to about half the CPU usage on our Cassandra nodes, on average. Solid state storage is quite expensive, nearly doubling the cost of typical hardware. It also means that if people have control over hardware placement within the network, they can place proxy nodes closer to the client without impacting their storage footprint or fault tolerance characteristics.

This is accomplished in Cassandra by passing the -Dcassandra.join_ring=false option when the process is started. These nodes will connect to the seeds, cache the gossip data, load the schema, and begin listening for client requests. Messages like "/x.x.x.x is now UP!" will appear on the other nodes.

There are also some more practical benefits to this. Handling client requests caused us to push the NewSize of the heap up

mitsuhiko

import uuid


alphabet = (
    '!"#$%&\'()*+,-./0123456789:;<=>?@'
    'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
    '[\\]^_`'
    'abcdefghijklmnopqrstuvwxyz{|}~'
)

tkaemming

"""
makes text read like it was written by a drunk person

er, makes txet rea dlike i twas rwitten by a durnk persob
"""
import random
import sys


drinks = float(sys.argv[1])

tkaemming

import os
import signal
import subprocess
import sys
import tempfile
import time


processes = set()