Filed in archive
Scalability stories
by Mateusz Berezecki on December 24, 2008

Two deployments:
- 130 node cluster hosting log data
- ~2M files; 70TB of data; WORM system
- Metaserver uses ~2GB RAM
- ~1TB of data copied in during a week
- Used for daily jobs in read mode
Plan is to use both KFS and HDFS
- For job output, backup from KFS to HDFS using Hadoop's distcp
For some more insight and technical details about moving petabyte data centers, hadoop and KFS and they uses in practice please see these:
- Kosmos FS - presentation slides
- Hadoop User Group video lecture with Sriram Rao
Permalink: KFS at Quantcast
Tags:
KosmosFS
CloudStore
Hadoop
quantcast
hadoop
source+alternatives
open+source
scalability+stories
Trackback: http://publish.creative-weblogging.com/publish/mt-tb.pl/140125
Mr Wong
Vote for KFS at Quantcast:
|
Rating: 9.00 out of 5 vote(s) cast.
|
Response from:
neon tabela
(10/07/09 11:57am)
Your site is very easy in terms of expression and open. I think everyone who enters your site is very gratifying, but also sharing a very nice opportunity to give
Response from:
lisa
(10/23/09 7:38am)
You can also try http://www.estimix.com
a free tool that provides a nice summary of the website performance. The estimation provided by estimix is the result of a complex analysis based on factors like: the age of the website, the demographic structure of the traffic, the countries where the website is popular and sources of the traffic
a free tool that provides a nice summary of the website performance. The estimation provided by estimix is the result of a complex analysis based on factors like: the age of the website, the demographic structure of the traffic, the countries where the website is popular and sources of the traffic
Subscribe
Use the search to look for other interesting posts
| RSS | See all blog subscribe options |
|
What is RSS? | |
| Yahoo! |
|
| Addthis |
|
| Bloglines |
|
| Newsletter | |
| Follow us on Twitter! |










