mainframe

#!/usr/bin/env python

'''
Simple Python script which endlessly keeps writing 100MB to a temp file.

Used to demonstrate a Ceph cluster. This script runs inside a Virtual Machine (KVM)
running on a RBD image on a Ceph cluster.

The demo is to randomly pull out machines and show that the script can still write
and read data.

mainframe

#!/usr/bin/env python

'''
This script writes X MegaByte random data to 10 RADOS objects and read the data again afterwards

It writes these statistics towards a Graphite server so you can see what the latency
inside your cluster is for both Read and Write

Author: Wido den Hollander <[email protected]>
'''

mainframe

#!/bin/bash

# Generates a CRUSH location based on the machine's hostname.
# This Gist was written for a customer who has mixed SSDs and HDDs in a a chassis.
# Hostname example in this case: dc2-rk01-ceph01 (Datacenter 2, rack 01, Ceph machine 01)
# It checks if the backing disk is a SSD or not and then comes up with the CRUSH location

while :; do
    case $1 in
        --cluster)

mainframe

# udev rule to set disk schedulers for Ceph
# For spinning disks we want the CFQ scheduler so that we can set
# priorities on client and recovery I/O threads
#
# Author: Wido den Hollander <[email protected]>
# Date: July 2015

# Use deadline for SSDs
ACTION=="add|change", KERNEL=="sd[a-z]*", ATTR{queue/rotational}=="0", ATTR{queue/scheduler}="deadline"

mainframe

#!/usr/bin/env python
'''
Script to send Zabbix Agent active data to the Zabbix Server.

It runs the ceph command locally to get information from the running
OSDs and send the aggegrated data back to Zabbix.
'''

import sys
import subprocess

mainframe

#!/bin/bash
#
# Script for updating a running Ceph Hammer cluster to Jewel
#
# This has to be run on the OSD node(s) as root
#
# Written for and tested on CentOS 7
#
# Used to upgrade Ceph at ODC-Noord in the Netherlands
#

mainframe

#!/usr/bin/env python
"""
Python script to multi-threaded copy a RBD image from one cluster to another

This script requires a configuration file and a RBD image to copy.

It will copy the RBD image from the source pool to destination pool as
specified in the configuration file.

It assumes the destination image already exists and is at least the size of the

mainframe

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
    <dict>
        <key>Protocol</key>
        <string>s3</string>
        <key>Vendor</key>
        <string>NodeFabric</string>
        <key>Scheme</key>
        <string>http</string>

mainframe

#!/bin/bash
# Copyright (C) 2013, OpenNode LLC. All rights reserved.
# Email: [email protected]
#
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License
# as published by the Free Software Foundation; either version 2
# of the License, or (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,

mainframe

#!/bin/bash
# Copyright (C) 2013, OpenNode LLC. All rights reserved.
# Email: [email protected]
#
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License
# as published by the Free Software Foundation; either version 2
# of the License, or (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,