devdazed

"""
Simple Linear Probabilistic Counters

Credit for idea goes to:
http://highscalability.com/blog/2012/4/5/big-data-counting-how-to-count-a-billion-distinct-objects-us.html
http://highlyscalable.wordpress.com/2012/05/01/probabilistic-structures-web-analytics-data-mining/

Installation:
    pip install smhasher
    pip install bitarray

devdazed

import json
from pycassa.pool import ConnectionPool
from pycassa.columnfamily import ColumnFamily
from pycassa.cassandra.ttypes import ConsistencyLevel, NotFoundException

HOSTS = ['localhost']

pool = ConnectionPool('my_keyspace', HOSTS)
my_cf = ColumnFamily(pool, 'my_cf')

devdazed

for ks in SYSTEM_MANAGER.list_keyspaces():
    describe_keyspace(ks)
    for cf in SYSTEM_MANAGER.get_keyspace_column_families(ks):
        describe_column_family(ks, cf)

devdazed

        for args in tables_for_load:
            thread = FileLoaderWorker(*args)
            thread.start()

        completed = 0
        while completed < len(tables_for_load):
            try:
                response, exception = response_queue.get(block=False, timeout=0.1)

                if exception:

devdazed

class Result(threading.Event):
    exception = None


def execute():
    cql = 'select * from events limit 10'
    response = Result()
    
    def _on_error(error):
        response.exception = error

devdazed

ui: mocha-qunit
browsers:
  - name:chrome
  - version: latest

scripts:
  - "http://d8rk54i4mohrb.cloudfront.net/js/reach.js"

server: ./server.js

devdazed

class TunableRetryPolicy(RetryPolicy):
    """ A retry policy that allows you to decide if you want to downgrade consistency before
    attempting to retry, additionally, you can specify the number of retries to try
    """

    def __init__(self, read_retries=3, write_retries=3, downgrade_consistency=True):
        self._read_retries = read_retries
        self._write_retries = write_retries
        self._downgrade_consistency = downgrade_consistency

devdazed

#!/usr/bin/env python

"""
Counts the number of tombstones in a keyspace.table and reports the top N highest counts

tombstone_count.py
    [-h]                   This help screen
    [--data-dir DATA_DIR]  The C* data directory (/var/lib/cassandra/data)
    [--top-k TOP_K]        The top number of keys with highest tombstone counts to display.
    keyspace               The keyspace that contains the table

devdazed

import fileinput, re, operator
from collections import Counter

def sizeof_fmt(num, suffix='B'):
    for unit in ['', 'Ki', 'Mi', 'Gi', 'Ti', 'Pi', 'Ei', 'Zi']:
        if abs(num) < 1024.0:
            return "%3.1f%s%s" % (num, unit, suffix)
        num /= 1024.0
    return "%.1f%s%s" % (num, 'Yi', suffix)

devdazed

#!/usr/bin/env python

from __future__ import print_function

import json
import logging
import re

from base64 import b64decode, b64encode
from urllib2 import Request, urlopen, URLError, HTTPError