hadoop-hdfs-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Cosmin Lehene <cleh...@adobe.com>
Subject Re: [VOTE -- Round 2] Commit hdfs-630 to 0.21?
Date Fri, 22 Jan 2010 20:30:38 GMT
Steve, 

A DoS could not be done using excludedNodes.

The blacklisting takes place only at DFSClientLevel. The NN will return a
list of block locations that excludes the nodes the client decided. This
list isn't persisted anywhere on the server. So if a client excludes the
entire set of DNs other clients won't be affected.

Cosmin 


On 1/22/10 5:32 PM, "Steve Loughran" <stevel@apache.org> wrote:

> Stack wrote:
> 
> I'm being 0 on this
> 
> -I would worry if the exclusion list was used by the NN to do its
> blacklisting, I'm glad to see this isn't happening. Yes, you could pick
> up datanode failure faster, but you would also be vulnerable to a user
> doing a DoS against the cluster by reporting every DN as failing
> 
> -Russ Perry's work on high-speed Hadoop rendering [1] tweaked Hadoop to
> allow the datanodes to get the entire list of nodes holding the data,
> and allowed them to make their own decision about where to get the data
> from. This
>   1. pushed the policy of handling failure down to the clients, less
> need to talk to the NN about it.
>   2. lets you do something very fancy where you deliberately choose data
> from different DNs, so that you can then pull data off the cluster at
> the full bandwidth of every disk
> 
> Long term, I would like to see Russ's addition go in, so worry if the
> HDFS-630 patch would be useful long term. Maybe its a more fundamental
> issue: where does the decision making go, into the clients or into the NN?
> 
> -steve
> 
> 
> 
> [1] http://www.hpl.hp.com/techreports/2009/HPL-2009-345.html


Mime
View raw message