| clear query|facets|time |
Search criteria: .
Results from 21 to 30 from
53 (2.879s).
|
|
|
Loading phrases to help you
refine your search...
|
|
Re: a question on NameNode - MapReduce - [mail # user]
|
|
...IT sounds like you could benefit from reading the basic papers on map-reduce in general. Hadoop is a reasonable facsimile of the original Google systems. Try looking at this: htt...
|
|
|
Author: Ted Dunning,
2012-11-19, 16:37
|
|
|
Re: HDFS block size - MapReduce - [mail # user]
|
|
...Andy's points are reasonable but there are a few omissions, - modern file systems are pretty good at writing large files into contiguous blocks if they have a reasonable amount of spac...
|
|
|
Author: Ted Dunning,
2012-11-16, 20:09
|
|
|
Re: backup of hdfs data - MapReduce - [mail # user]
|
|
...Conventional enterprise backup systems are rarely scaled for hadoop needs. Both bandwidth and size are typically lacking. My employer, Mapr, offers a hadoop-derived distri...
|
|
|
Author: Ted Dunning,
2012-11-06, 00:47
|
|
|
Re: Set the number of maps - MapReduce - [mail # user]
|
|
...Is the spelling of the option correct? On Thu, Nov 1, 2012 at 6:43 AM, Cogan, Peter (Peter) wrote: ust...
|
|
|
Author: Ted Dunning,
2012-11-01, 16:50
|
|
|
Re: ClientProtocol create、mkdirs 、rename and delete methods are not Idempotent - MapReduce - [mail # user]
|
|
...Create cannot be idempotent with sequential files. Doing the same create twice creates two different files. On Sun, Oct 28, 2012 at 10:25 PM, lei liu wrote: ...
|
|
|
Author: Ted Dunning,
2012-10-29, 05:58
|
|
|
Re: Cluster wide atomic operations - MapReduce - [mail # user]
|
|
...On Sun, Oct 28, 2012 at 9:15 PM, David Parks wrote s n, Having such a limited range may require that you have a central service to generate ID's. The use of a central...
|
|
|
Author: Ted Dunning,
2012-10-29, 05:58
|
|
|
Re: ClientProtocol create、mkdirs 、rename and delete methods are not Idempotent - MapReduce - [mail # user]
|
|
...Create cannot be idempotent because of the problem of watches and sequential files. Similarly, mkdirs, rename and delete cannot generally be idempotent. In particular application...
|
|
|
Author: Ted Dunning,
2012-10-28, 18:33
|
|
|
Re: Cluster wide atomic operations - MapReduce - [mail # user]
|
|
...This is better asked on the Zookeeper lists. The first answer is that global atomic operations are a generally bad idea. The second answer is that if you an batch these operation...
|
|
|
Author: Ted Dunning,
2012-10-27, 05:22
|
|
|
Re: rules engine with Hadoop - MapReduce - [mail # user]
|
|
...That probably means that your problem is pretty easy. Just code up a standard rules engine into a mapper. You can also build a user defined function (UDF) in Pig or Hive and Hado...
|
|
|
Author: Ted Dunning,
2012-10-21, 02:07
|
|
|
Re: rules engine with Hadoop - MapReduce - [mail # user]
|
|
...Unification in a parallel cluster is a difficult problem. Writing very large scale unification programs is an even harder problem. What problem are you trying to solve? One...
|
|
|
Author: Ted Dunning,
2012-10-19, 19:45
|
|
|
|
