Seattle Conference on Scalability: Scalable Wikipedia with E

Back


Google Tech Talks
June 14, 2008

ABSTRACT

IGlobal online services at Amazon, eBay, Myspace, YouTube, or Google serve millions of customers with tens of thousands of servers located throughout the world. At this scale, components fail continuously and it is difficult to maintain a consistent state while hiding failures from the application. Peer-to-peer protocols provide availability by replicating services among peers, but they are mostly limited to write-once/read-many data sharing. To extend them beyond the typical file sharing, the support of fast transactions on distributed hash tables (DHTs) is an important yet missing feature.

We will present a distributed key/value store based on a DHT that supports consistent writes. Our system comprises three layers:

- a DHT layer for scalable, reliable access to replicated data,
- a transaction layer to ensure data consistency in the face of concurrent write operations,
- an application layer with an extremely high access rate.
For the application layer, we selected a distributed, scalable Wiki with full transaction support. We will show that our Wiki outperforms the public Wikipedia in terms of served page requests per second and
we will discuss how the development of the distributed code benefited from the use of Erlang.

This is joint work of Zuse Institute Berlin and onScale solutions GmbH.

Speaker: Thorsten Schuett, Zuse Institute Berlin
Thorsten Schütt is a senior researcher with the Zuse Institute Berlin (ZIB) and a co-founder of onScale solutions GmbH. He received a CS diploma with distinction in 2002 from the Technical University Berlin. Since then he works as a research staff member in the Computer Science Research Department at ZIB and participates in several EU projects like GridLab, XtreemOS and Selfman. He is the principal system architect of the scalable, transactional key/value store at ZIB. His research interests include distributed data management, scalable grid systems, p2p algorithms and self-managing transactional
storage systems.

Slides for this talk are available at

Channel: Science & Technology
Uploaded: June 19, 2008 at 2:12 am
Author: googletechtalks

Length: 00:26:31
Rating: 4.33
Views: 8803

Tags: google techtalks techtalk engedu talk talks googletechtalks education

Video Comments:
DeletedaccountOx (November 17, 2008 at 9:57 am)
Awake you of Israel, come learn the truth! This white man is nothing but wicked! GMS is rousing the House of Jacob come and sing with us! youtube Lastdaysofedom and set yourself free, you so-called blacks, native americans and latins!
scalability (October 2, 2008 at 12:26 am)
The slides can be found on the onscale de website.
mux4fun (September 14, 2008 at 3:36 pm)
User marstein said it already. This talk is nearly worthless without the slides... but it's so interesting! Please could anybody fix that? Is there someone out there who has the slides and can load them up/make a youtube presentation -- one could view this flv and the new one side by side... thanks in advance!
marstein (September 11, 2008 at 4:25 pm)
The slides are overexposed unfortunately. And they are essential to understanding the subject. dang.
Jack9C (August 21, 2008 at 7:02 am)
Where can we get the slides? These are too distorted for me to understand.
alexandredulaunoy (June 23, 2008 at 8:21 am)
Chord seems nice on paper... but I'm always wondering why git cannot be used. Chord is storing the change sets that needs to be propagated (in a very simplified way). Why not using git where only blobs are exchanged while commits are just ref to blobs and trees.. Git merging/rebasing must be accommodated but that's also the case for Chord. Git has a major advantage the space efficiency of the date store.