BA. Available in San Jose area or remote.
From: Robert Coli
To: "user@cassandra.apache.org"
Sent: Tuesday, September 9, 2014 2:44 PM
Subject: Re: hardware sizing for cassandra
On Tue, Sep 9, 2014 at 2:16 PM, Russell Bradberry wrote:
Because R
On Tue, Sep 9, 2014 at 2:16 PM, Russell Bradberry
wrote:
> Because RAM is expensive and the JVM heap is limited to 8gb. While you do
>> get benefit out of using extra RAM as page cache, it's often not cost
>> efficient to do so
>
>
> Again, this is so use-case dependent. I have met several people
>
> Because RAM is expensive and the JVM heap is limited to 8gb. While you do
> get benefit out of using extra RAM as page cache, it's often not cost
> efficient to do so
Again, this is so use-case dependent. I have met several people that run
small nodes with fat ram to get it all in memory to s
Paolo
>
>
>
>
> Paolo Crosato
> Software engineer/Custom Solutions
>
>
> ____________
> Da: Chris Lohfink
> Inviato: martedì 9 settembre 2014 21.26
On Tue, Sep 9, 2014 at 1:07 PM, Rahul Neelakantan wrote:
> Why not more than 32gb of RAM/node?
>
Because RAM is expensive and the JVM heap is limited to 8gb. While you do
get benefit out of using extra RAM as page cache, it's often not cost
efficient to do so.
=Rob
12:53 PM
To: user@cassandra.apache.org
Subject: RE: hardware sizing for cassandra
Every node should have at least 4 cores, with a maximum of 8. Memory shouldn't
be higher than 32g, 16gb is good for a start. Every node should be a phisical
machine, not a virtual one, or at least a virtual mac
ohfink
> Inviato: martedì 9 settembre 2014 21.26
> A: user@cassandra.apache.org
> Oggetto: Re: hardware sizing for cassandra
>
> It depends. Ultimately your load is low enough a single node can probably
> handle it so you kinda want a "minimum" cluster. Different pe
tions
Da: Chris Lohfink
Inviato: martedì 9 settembre 2014 21.26
A: user@cassandra.apache.org
Oggetto: Re: hardware sizing for cassandra
It depends. Ultimately your load is low enough a single node can probably
handle it so you kinda want a "minimum" cluster. Different people
It depends. Ultimately your load is low enough a single node can probably
handle it so you kinda want a "minimum" cluster. Different people have
different thoughts on what this means - I would recommend 5-6 nodes with a 3
replication factor. (say m1.xlarge, or c3.2xlarge striped ephemerals, I
I would also love to see any resources that are shared describing best
practices. If you find something Oleg, or others have some very useful
resources outside of what I have found by searching online, I would be very
grateful if these were shared in my direction. Cheers.
Nate
On Tue, Sep 9, 2014
10 matches
Mail list logo
