You are viewing a plain text version of this content. The canonical link for it is here.
Posted to user@cassandra.apache.org by Jonathan Colby <jo...@gmail.com> on 2010/12/20 15:25:36 UTC
Virtual IP / hardware load balancing for cassandra nodes
I was unable to find example or documentation on my question. I'd like to know what the best way to group a cluster of cassandra nodes behind a virtual ip.
For example, can cassandra nodes be placed behind a Citrix Netscaler hardware load balancer?
I can't imagine it being a problem, but in doing so would you break any cassandra functionality?
The goal is to have the application talk to a single virtual ip and be directed to a random node in the cluster.
I heard a little about adding the node addresses to Hector's load-balancing mechanism, but this doesn't seem too robust or easy to maintain.
Thanks in advance.
Re: Virtual IP / hardware load balancing for cassandra nodes
Posted by Nate McCall <na...@riptano.com>.
Current versions of Hector will mark the host as temporarily down if a
connection times out (retrying N seconds later; defaults to 10). If
you only have one host in your list, this will be an issue. It would
be a good idea to use more than one VIP for this reason.
Managing configurations on the app server does not have to be
difficult. I have used puppet previously to keep an
/etc/hector/hector.properties file up to date with my list of servers
(using SpringFramework's excellent configuration parameter replacement
plumbing to pull this in at startup). You can also add/remove hosts
via JMX at this point as well.
If there are any Hector-specific things that come up, feel free to
send us an email on hector-users@googlegroups.com.
On Mon, Dec 20, 2010 at 11:28 AM, Jonathan Colby
<jo...@gmail.com> wrote:
> Thanks guys.
> On Dec 20, 2010, at 5:44 PM, Dave Viner wrote:
>
> You can put a Cassandra cluster behind a load balancer. One thing to be
> cautious of is the health check. Just because the node is listening on port
> 9160 doesn't mean that it's healthy to serve requests. It is required, but
> not sufficient.
> The real test is the JMX values.
> Dave Viner
>
> On Mon, Dec 20, 2010 at 6:25 AM, Jonathan Colby <jo...@gmail.com>
> wrote:
>>
>> I was unable to find example or documentation on my question. I'd like to
>> know what the best way to group a cluster of cassandra nodes behind a
>> virtual ip.
>>
>> For example, can cassandra nodes be placed behind a Citrix Netscaler
>> hardware load balancer?
>>
>> I can't imagine it being a problem, but in doing so would you break any
>> cassandra functionality?
>>
>> The goal is to have the application talk to a single virtual ip and be
>> directed to a random node in the cluster.
>>
>> I heard a little about adding the node addresses to Hector's
>> load-balancing mechanism, but this doesn't seem too robust or easy to
>> maintain.
>>
>> Thanks in advance.
>
>
Re: Virtual IP / hardware load balancing for cassandra nodes
Posted by Jonathan Colby <jo...@gmail.com>.
Thanks guys.
On Dec 20, 2010, at 5:44 PM, Dave Viner wrote:
> You can put a Cassandra cluster behind a load balancer. One thing to be cautious of is the health check. Just because the node is listening on port 9160 doesn't mean that it's healthy to serve requests. It is required, but not sufficient.
>
> The real test is the JMX values.
>
> Dave Viner
>
>
> On Mon, Dec 20, 2010 at 6:25 AM, Jonathan Colby <jo...@gmail.com> wrote:
> I was unable to find example or documentation on my question. I'd like to know what the best way to group a cluster of cassandra nodes behind a virtual ip.
>
> For example, can cassandra nodes be placed behind a Citrix Netscaler hardware load balancer?
>
> I can't imagine it being a problem, but in doing so would you break any cassandra functionality?
>
> The goal is to have the application talk to a single virtual ip and be directed to a random node in the cluster.
>
> I heard a little about adding the node addresses to Hector's load-balancing mechanism, but this doesn't seem too robust or easy to maintain.
>
> Thanks in advance.
>
Re: Virtual IP / hardware load balancing for cassandra nodes
Posted by Dave Viner <da...@gmail.com>.
You can put a Cassandra cluster behind a load balancer. One thing to be
cautious of is the health check. Just because the node is listening on port
9160 doesn't mean that it's healthy to serve requests. It is required, but
not sufficient.
The real test is the JMX values.
Dave Viner
On Mon, Dec 20, 2010 at 6:25 AM, Jonathan Colby <jo...@gmail.com>wrote:
> I was unable to find example or documentation on my question. I'd like to
> know what the best way to group a cluster of cassandra nodes behind a
> virtual ip.
>
> For example, can cassandra nodes be placed behind a Citrix Netscaler
> hardware load balancer?
>
> I can't imagine it being a problem, but in doing so would you break any
> cassandra functionality?
>
> The goal is to have the application talk to a single virtual ip and be
> directed to a random node in the cluster.
>
> I heard a little about adding the node addresses to Hector's load-balancing
> mechanism, but this doesn't seem too robust or easy to maintain.
>
> Thanks in advance.
Re: Virtual IP / hardware load balancing for cassandra nodes
Posted by Daniel Doubleday <da...@gmx.net>.
You will loose part of the retry / fallback functionality offered by hector.
The job of the client lib is not only load-balancing. I.e. if a node is bootstrapping it will accept TCP connections but throw an exception which will be communicated via thrift. The client lib is supposed to handle that.
On Dec 20, 2010, at 3:25 PM, Jonathan Colby wrote:
> I was unable to find example or documentation on my question. I'd like to know what the best way to group a cluster of cassandra nodes behind a virtual ip.
>
> For example, can cassandra nodes be placed behind a Citrix Netscaler hardware load balancer?
>
> I can't imagine it being a problem, but in doing so would you break any cassandra functionality?
>
> The goal is to have the application talk to a single virtual ip and be directed to a random node in the cluster.
>
> I heard a little about adding the node addresses to Hector's load-balancing mechanism, but this doesn't seem too robust or easy to maintain.
>
> Thanks in advance.