SystemImager and BitT orrent: a p2p approach to large scale OS - - PowerPoint PPT Presentation

systemimager and bitt orrent a p2p approach to large
SMART_READER_LITE
LIVE PREVIEW

SystemImager and BitT orrent: a p2p approach to large scale OS - - PowerPoint PPT Presentation

SystemImager and BitT orrent: a p2p approach to large scale OS deployment Andrea Righi <a.righi@cineca.it> Bernard Li <bli@bcgsc.ca> Brian Elliott Finley <brian@thefinleys.com> Erich Focht <efocht@hpce.nec.com> LinuxT


slide-1
SLIDE 1

LinuxT ag 2007 (May 29 – Jun 2)

SystemImager and BitT

  • rrent:

a p2p approach to large scale OS deployment

Andrea Righi <a.righi@cineca.it> Bernard Li <bli@bcgsc.ca> Brian Elliott Finley <brian@thefinleys.com> Erich Focht <efocht@hpce.nec.com>

slide-2
SLIDE 2

LinuxT ag 2007 (May 29 – Jun 2)

The problem

You have to install a lot of computers

✔ PC labs, ✔ Server farms, ✔ HPC clusters, ✔ Complex grid-computing environments, ✔ Etc.

But you don't have enough time!

slide-3
SLIDE 3

LinuxT ag 2007 (May 29 – Jun 2)

A practical example

slide-4
SLIDE 4

LinuxT ag 2007 (May 29 – Jun 2)

The tool

SystemImager is a software which automates GNU/Linux installs, software distributions and production deployment

slide-5
SLIDE 5

LinuxT ag 2007 (May 29 – Jun 2)

Major Goals

Support all Linux distributions Support a large number of architectures Make it easy to add support for new distro and architectures Make it solve massive installation problems Create a centralized point of installation and maintenance

slide-6
SLIDE 6

LinuxT ag 2007 (May 29 – Jun 2)

What does it do for me?

System Installation System Updates Build replicants of machines File system or block device migration

slide-7
SLIDE 7

LinuxT ag 2007 (May 29 – Jun 2)

Advantage of SystemImager

File-oriented approach

✔ Distribution agnostic ✔ Hardware independence ✔ Filesystem independence ✔ Plain filesystem dump: exclude swap space or

unused partitions

✔ Block device independence ✔ Live customization (manipulate cloned

filesystems directly)

slide-8
SLIDE 8

LinuxT ag 2007 (May 29 – Jun 2)

Basic concepts

slide-9
SLIDE 9

LinuxT ag 2007 (May 29 – Jun 2)

Basic concept: image

Image:

✔ Live snapshot of a machine containing files and

directories from the root of that machine's filesystem

✔ chroot-able filesystem stored in

/var/lib/systemimager/images/$NAME

✔ Examples:

✔ /var/lib/systemimager/images/RHEL4 ✔ /var/lib/systemimager/images/Debian_Etch ✔ /var/lib/systemimager/images/HPC_1.0 ✔ ...

slide-10
SLIDE 10

LinuxT ag 2007 (May 29 – Jun 2)

Basic concept: image server

Image Server:

✔ a server that has all the images available for the

installation

✔ “Jukebox” of images

slide-11
SLIDE 11

LinuxT ag 2007 (May 29 – Jun 2)

Basic concept: client

Client:

✔ a machine to be auto-installed with a (single)

selected image

✔ Example: the dancing penguins are the clients :-)

slide-12
SLIDE 12

LinuxT ag 2007 (May 29 – Jun 2)

Basic concept: transport

Transport:

✔ the protocol used to distribute images from the

image server to the clients

✔ push/pull/p2p approach ✔ Examples:

✔ rsync, multicast, SSL, BitT

  • rrent, ...
slide-13
SLIDE 13

LinuxT ag 2007 (May 29 – Jun 2)

Application stack (SIS)

Image Server (SystemImager)

Golden client

HPC clusters HA-clusters Web farms PC labs SystemImager transports + SystemConfigurator

Software

(Debootstrap, YaST, yum, SystemInstaller, ...)

RHEL4 HPC-1.0 SUSE10 Debian4

slide-14
SLIDE 14

LinuxT ag 2007 (May 29 – Jun 2)

Transports

slide-15
SLIDE 15

LinuxT ag 2007 (May 29 – Jun 2)

rsync transport

rsync (plain / SSL encrypted):

✔ Client-server approach

✔ Limited in scalability ✔ Limited in reliability with a lot of clients

✔ Max Theoretical Bandwidth: Us / N

slide-16
SLIDE 16

LinuxT ag 2007 (May 29 – Jun 2)

rsync diagram

Image server

Client1 Client2 ClientN ... Upload bandwidth = Us Download bandwidth = Us / N

slide-17
SLIDE 17

LinuxT ag 2007 (May 29 – Jun 2)

Multicast (Flamethrower) transport

Flamethrower:

✔ Multicast approach:

✔ Perfect scalability ✔ But limited in reliability

✔ Max Theoretical Bandwidth: Us

slide-18
SLIDE 18

LinuxT ag 2007 (May 29 – Jun 2)

Multicast (Flamethrower) diagram

Image server

Client1 Client2 ClientN ... Upload bandwidth = Us Download bandwidth = Us

slide-19
SLIDE 19

LinuxT ag 2007 (May 29 – Jun 2)

BitTorrent overview

BitT

  • rrent is a TCP/IP p2p oriented protocol

designed for transferring files Peers connect to each other directly to send and receive chunks of data There is a central server (tracker) which coordinates the action of all such peers The tracker does not have any knowledge of the contents of the files being distributed Users upload (transmit outbound) at the same time they are downloading (receiving inbound)

slide-20
SLIDE 20

LinuxT ag 2007 (May 29 – Jun 2)

BitTorrent transport

BitT

  • rrent:

✔ p2p approach: scalability && reliability ✔ Qiu and Srikant model

✔ T

  • tal upload rate:

✔ Steady state:

✔ x(t) downloaders => ✔ y(t) uploaders =>

✔ Max Theoretical Bandwidth:

✔ Us (steady state)

d xt d t =0 d xt d t =0

 xt yt

slide-21
SLIDE 21

LinuxT ag 2007 (May 29 – Jun 2)

BitTorrent diagram

Image server (+tracker)

Client1 Client2 ClientN ... Upload bandwidth = Us Download bandwidth = Us (in steady state)

slide-22
SLIDE 22

LinuxT ag 2007 (May 29 – Jun 2)

BitTorrent fun!

Image server

slide-23
SLIDE 23

LinuxT ag 2007 (May 29 – Jun 2)

T estbed environment

slide-24
SLIDE 24

LinuxT ag 2007 (May 29 – Jun 2)

BCX/5120 cluster @

IBM BCX/5120, with 5120 cores, is the largest computer in Italy for Scientific Computing 2 dual-core AMD Opteron(tm) 2.4GHz, 8GB RAM per node It is the 44th most powerful computer in the world (TOP500).

slide-25
SLIDE 25

LinuxT ag 2007 (May 29 – Jun 2)

BCX network topology

Cisco Catalyst 6513 IBM Bladecenter H (from 1 up to 11) IBM LS21 switch IBM Blade LS21 (x 14) BladeCenter H internal bus (1Gb/s) 1 14 ... 1 Gb/s x 4 uplinks IBM e326m (image server) 1 Gb/s link

slide-26
SLIDE 26

LinuxT ag 2007 (May 29 – Jun 2)

Experimental results

slide-27
SLIDE 27

LinuxT ag 2007 (May 29 – Jun 2)

Deployment time

slide-28
SLIDE 28

LinuxT ag 2007 (May 29 – Jun 2)

Rsync: 50 clients (download rate)

slide-29
SLIDE 29

LinuxT ag 2007 (May 29 – Jun 2)

Multicast: 50 clients (download rate)

slide-30
SLIDE 30

LinuxT ag 2007 (May 29 – Jun 2)

BitTorrent: 50 clients (download rate)

slide-31
SLIDE 31

LinuxT ag 2007 (May 29 – Jun 2)

Rsync: 50 clients (aggregated bandwidth)

slide-32
SLIDE 32

LinuxT ag 2007 (May 29 – Jun 2)

Multicast: 50 clients (aggregated bandwidth)

slide-33
SLIDE 33

LinuxT ag 2007 (May 29 – Jun 2)

BitTorrent: 50 clients (aggregated bandwidth)

slide-34
SLIDE 34

LinuxT ag 2007 (May 29 – Jun 2)

Conclusion

slide-35
SLIDE 35

LinuxT ag 2007 (May 29 – Jun 2)

Advantages

Quicker deployment of images Safer deployment (better error handling) Less load on the image server

✔ no need to buy a powerful machine

slide-36
SLIDE 36

LinuxT ag 2007 (May 29 – Jun 2)

Disadvantages

No time to have a coffee while the clients are imaging More disk space consumption!

✔ tarballs of images

Images and tarballs must be kept in-sync

✔ Re-generate tarball and .torrent at each image

change

slide-37
SLIDE 37

LinuxT ag 2007 (May 29 – Jun 2)

Future work

Optimize performance in LAN environments and dedicated HPC networks Improve security (encryption of BT tarballs) Virtual cluster deployment (re-imaging using the same physical resource pool) Exploit the p2p approach to create distributed and redundant repositories of custom image Use BT transport also for updates (pushing changes/differences of images) => a path to image version management

slide-38
SLIDE 38

LinuxT ag 2007 (May 29 – Jun 2)

References

Web:

✔ http://www.systemimager.org

Mailing list:

✔ sisuite-users@lists.sourceforge.net ✔ sisuite-devel@lists.sourceforge.net

IRC:

✔ #sisuite (irc.freenode.net)

slide-39
SLIDE 39

LinuxT ag 2007 (May 29 – Jun 2)

T ank you for attending!!!