hadoop-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Vishnu Viswanath <vishnu.viswanat...@gmail.com>
Subject Re: how does hdfs client write a file .
Date Mon, 24 Mar 2014 13:05:01 GMT
Does that mean that the writes are no longer cached?

Vishnu Viswanath

> On 24-Mar-2014, at 15:56, Azuryy Yu <azuryyyu@gmail.com> wrote:
> 
> Thanks, I think this was deperecated. I'll file a JIRA for this.
> 
> 
>> On Mon, Mar 24, 2014 at 5:46 PM, 张建伟 <connerlyzhang@gmail.com> wrote:
>> http://hadoop.apache.org/docs/r1.2.1/hdfs_design.html
>> 
>> 
>> Staging
>> 
>> A client request to create a file does not reach the NameNode immediately. In fact,
initially the HDFS client caches the file data into a temporary local file. Application writes
are transparently redirected to this temporary local file. 
>> 
>> 
>>  
>> 
>> 
>> 2014-03-24 17:01 GMT+08:00 Azuryy Yu <azuryyyu@gmail.com>:
>> 
>>> Can you give the URL where you looked at?
>>> 
>>> 
>>>> On Mon, Mar 24, 2014 at 4:49 PM, 张建伟 <connerlyzhang@gmail.com>
wrote:
>>>> hi,
>>>> 
>>>> In the apache site,I find a document said :
>>>> 
>>>> "A client request to create a file does not reach the NameNode immediately.
In fact, initially the HDFS client caches the file data into a temporary local file. Application
writes are transparently redirected to this temporary local file. When the local file accumulates
data worth over one HDFS block size, the client contacts the NameNode. "
>>>> 
>>>> does it still right in 2.2.0 and 1.2.1 version? why write a file like this?
> 

Mime
View raw message