hadoop-common-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Otis Gospodnetic <otis_gospodne...@yahoo.com>
Subject Re: Why Hadoop uses HTTP for file transmission between Map and Reduce?
Date Sun, 16 Jan 2011 07:21:03 GMT

----- Original Message ----
> From: Owen O'Malley <omalley@apache.org>
> At some point, we'll replace Jetty in the shuffle, because it imposes  too
> much overhead and go to Netty or some other lower level library. I  don't
> think that using HTTP adds that much overhead although it would  be
> interesting to measure that.

I use Jetty in a lot of places, so I'm curious about this Jetty + overhead 
comment.  Could you please share more info about what sort of overhead you are 
referring to? (also, does it apply to all recent versions of Jetty - 6, 7, and 

Sematext :: http://sematext.com/ :: Solr - Lucene - Nutch
Hadoop ecosystem search :: http://search-hadoop.com/

View raw message