High Scalability Building bigger, faster, more reliable websites.

Is there any type of server technology that allows visitors to a website to become part of the server? Like with bittorrent, users share some of their bandwidth, so would this be possible with web servers where a person goes to a website, downloads and runs the software which makes their internet connection and cpu and hdd become part of the web server?

IBM WebSphere eXtreme Scale is IBMs in memory data grid product (IMDG). It can be used as a key-value store which partitions the keys (using a form of consistent hashing) over a set of servers such that each server is responsible for a subset of the keys. It automatically handles replication which can be either synchronous of asynchronous and handles advanced placement so that replicas can be placed in different physical zones when compared to the placement of the primary. Think buildings, racks, floor, data centers.

It is fully elastic in that servers can be added and removed and it automatically redistributes the partition primaries and backups. It can be scaled from one server to hundreds if not thousands of JVMs in a single grid. Each additional server provides more CPU, memory capacity and network and it scales linearly with grid growth.

It also has a key-graph mode where a graph of objects can be associated with a single key and it allows fine grained modification of that graph. The object graph and key is stored in tuple form in this mode. This allows clients using different object representations of some subset of the IMDG schema to share data stored in the IMDG.

It comes with automatic integration with databases so that values are automatically pulled from a database if not present and are written to the database when they change. Write behind logic allows writes to the database to be much more efficient and allows the grid to run with the database down.

It comes with a HTTP Session filter to provide HTTP Session management for servlet containers. It have a flexible deployment model allowing a lot of customization by customers.

We do a weekly video podcast on iTunes (search for extreme scale in iTunes) and make it available on YouTube also for customer education. We answer customer questions and forum topics from the week in a casual two person chat forum.

I found the discussion of the available bandwidth of tree vs higher dimensional virtual networks topologies quite, to quote Spock, fascinating:

A mathematical analysis by Ritter (2002) (one of the original developers
of Napster) presented a detailed numerical argument demonstrating that the
Gnutella network could not scale to the capacity of its competitor, the
Napster network. Essentially, that model showed that the Gnutella network is
severely bandwidth-limited long before the P2P population reaches a million
peers. In each of these previous studies, the conclusions have overlooked the
intrinsic bandwidth limits of the underlying topology in the Gnutella network:
a Cayley tree (Rains and Sloane 1999) (see Sect. 9.4 for the definition).

In this chapter, we analyze the scalability of several alternative topologies
and compare their throughput up to 2–3 million peers. The virtual hypercube
and the virtual hypertorus offer near-linear scalable bandwidth subject to
the number of peer TCP/IP connections that can be simultaneously kept
open.

How do you design a reliable distributed file system when the expected availability of the individual nodes are only ~1/5? That is the case for P2P systems. Dominik Grolimund, the founder of a Swiss startup Caleido will show you how! They have launched Wuala, the social online storage service which scales as new nodes join the P2P network.

The goal of Wua.la is to provide distributed online storage that is:

• large
• scalable
• reliable
• secure

by harnessing the idle resources of participating computers.

This challenge is an old dream of computer science. In fact as Andrew Tanenbaum wrote in 1995:
"The design of a world-wide, fully transparent distributed filesystem fot simultaneous use by millions of mobile and frequently disconnected users is left as an exercise for the reader"

After three years of research and development at at ETH Zurich, the Swiss Federal Institute of Technology on a distributed storage system, Caleido is ready to unveil the result: Wuala. Wuala is a new way of storing, sharing, and publishing files on the internet. It enables its users to trade parts of their local storage for online storage and it allows us to provide a better service for free. In this Google Tech Talk, Dominik will explain what Wuala is and how it works, and he will also show a demo.

Consistent hashing is one of those ideas that really puts the science in computer science and reminds us why all those really smart people spend years slaving over algorithms. Consistent hashing is "a scheme that provides hash table functionality in a way that the addition or removal of one slot does not significantly change the mapping of keys to slots" and was originally a way of distributing requests among a changing population of web servers. My first reaction to the idea was "wow, that's really smart" and I sadly realized I would never come up with something so elegant. I then immediately saw applications for it everywhere. And consistent hashing is used everywhere: distributed hash tables, overlay networks, P2P, IM, caching, and CDNs. Here's the abstract from the original paper and after the abstract are some links to a few very good articles with accessible explanations of consistent hashing and its applications in the real world.

Colm MacCarthaigh, Network Architect at Joost, gave this presentation at the UK Network Operators' Forum Meeting in Manchester on April 3rd, 2007.

Skype's 220 millions users lost service for a stunning two days. The primary cause for Skype's nightmare (can you imagine the beeper storm that went off?) was a massive global roll-out of a Window's patch triggering the simultaneous reboot of millions of machines across the globe. The secondary cause was a bug in Skype's software that prevented "self-healing" in the face of such attacks. The flood of log-in requests and a lack of "peer-to-peer resources" melted their system.

Who's fault is it? Is Skype to blame? Is Microsoft to blame? Or is the peer-to-peer model itself fundamentally flawed in some way?