You are viewing a plain text version of this content. The canonical link for it is here.
Posted to common-user@hadoop.apache.org by Stas Oskin <st...@gmail.com> on 2009/04/11 11:43:47 UTC

NameNode resilency

Hi.

I wonder, what Hadoop community uses in order to make NameNode resilient to
failures?

I mean, what High-Availability measures are taken to keep the HDFS available
even in case of NameNode failure?

So far I read a possible solution using DRBD, and another one using carp.
Both of them had the downside of keeping a passive machine aside taking the
IP of the NameNode.

Perhaps there is a way to keep only a passive NameNode service on another
machine (which does other tasks), taking the IP only when the main has
failed?

That of course until the human operator restores the main node to action.\

Regards.

Re: NameNode resilency

Posted by Stas Oskin <st...@gmail.com>.
Hi.
Any tutorial about using Zookeeper with NameNode?

Thanks!

2009/4/12 Billy Pearson <sa...@pearsonwholesale.com>

> Not 100% sure but I thank they plan on using zookeeper to help with
> namenode fail over but that may have changed.
>
> Billy
>
> "Stas Oskin" <st...@gmail.com> wrote in message
> news:77938bc20904110243u7a2baa6dw6d710e4e51ae0dfa@mail.gmail.com...
>
>  Hi.
>>
>> I wonder, what Hadoop community uses in order to make NameNode resilient
>> to
>> failures?
>>
>> I mean, what High-Availability measures are taken to keep the HDFS
>> available
>> even in case of NameNode failure?
>>
>> So far I read a possible solution using DRBD, and another one using carp.
>> Both of them had the downside of keeping a passive machine aside taking
>> the
>> IP of the NameNode.
>>
>> Perhaps there is a way to keep only a passive NameNode service on another
>> machine (which does other tasks), taking the IP only when the main has
>> failed?
>>
>> That of course until the human operator restores the main node to action.\
>>
>> Regards.
>>
>>
>
>

Re: NameNode resilency

Posted by Billy Pearson <sa...@pearsonwholesale.com>.
Not 100% sure but I thank they plan on using zookeeper to help with namenode 
fail over but that may have changed.

Billy

"Stas Oskin" <st...@gmail.com> wrote in 
message news:77938bc20904110243u7a2baa6dw6d710e4e51ae0dfa@mail.gmail.com...
> Hi.
>
> I wonder, what Hadoop community uses in order to make NameNode resilient 
> to
> failures?
>
> I mean, what High-Availability measures are taken to keep the HDFS 
> available
> even in case of NameNode failure?
>
> So far I read a possible solution using DRBD, and another one using carp.
> Both of them had the downside of keeping a passive machine aside taking 
> the
> IP of the NameNode.
>
> Perhaps there is a way to keep only a passive NameNode service on another
> machine (which does other tasks), taking the IP only when the main has
> failed?
>
> That of course until the human operator restores the main node to action.\
>
> Regards.
>