incubator-cassandra-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From aaron morton <aa...@thelastpickle.com>
Subject Re: how to test our transfer speeds
Date Thu, 04 Apr 2013 00:42:29 GMT
JBOD as talked about here http://www.datastax.com/wp-content/uploads/2012/08/C2012-StateofCassandra-JonathanEllis.pdf
and defined by disk_failure_policy

So that when you have very large nodes disk failed does not require a full replacement. But
if you are using a high level raid guess that's not necessary. 

Cheers

-----------------
Aaron Morton
Freelance Cassandra Consultant
New Zealand

@aaronmorton
http://www.thelastpickle.com

On 2/04/2013, at 6:35 PM, "Hiller, Dean" <Dean.Hiller@nrel.gov> wrote:

> Oh, JBOD, not JBOB.
> 
> no, we were using RAID 5 and RAID 6 from what I understand.  I am trying to get a test
run with just one disk to make sure the test is correct as one disk should have much less
performance than 20 in the case of random access.  In sequential, I think performance would
be the same(ie. Both would be 250MB/sec in throughput is my guess)
> Thanks,
> Dean
> 
> From: <Hiller>, Nrel <Dean.Hiller@nrel.gov<mailto:Dean.Hiller@nrel.gov>>
> Date: Tuesday, April 2, 2013 6:40 AM
> To: "user@cassandra.apache.org<mailto:user@cassandra.apache.org>" <user@cassandra.apache.org<mailto:user@cassandra.apache.org>>
> Subject: Re: how to test our transfer speeds
> 
> Is 1.2 JBOB and april fools joke?  Heh, seriously though, I have no idea what you are
talking about there.  I am trying to get raw disk performance with no cassandra involved before
involving cassandra…..which is the next step.
> 
> Thanks,
> Dean
> 
> From: aaron morton <aaron@thelastpickle.com<mailto:aaron@thelastpickle.com>>
> Reply-To: "user@cassandra.apache.org<mailto:user@cassandra.apache.org>" <user@cassandra.apache.org<mailto:user@cassandra.apache.org>>
> Date: Monday, April 1, 2013 11:01 PM
> To: "user@cassandra.apache.org<mailto:user@cassandra.apache.org>" <user@cassandra.apache.org<mailto:user@cassandra.apache.org>>
> Subject: Re: how to test our transfer speeds
> 
> If not, maybe I just generate the same 1,000,000 files on each machine, then randomly
delete 1/2 the files and stream them from the other machine as writing those files would all
be in random locations again forcing a much worse measurement of MB/sec I would think.
> Not sure I understand the question. But you could just scrub the data off a node and
rebuild it.
> 
> Note that streaming is throttled, and it will also generate compaction.
> 
> He has twenty 1T drives on each machine and I think he also tried with one 1T drive seeing
the same performance which makes sense if writing sequentially
> Are you using the 1.2 JBOB configuration?
> 
> Cheers
> 
> -----------------
> Aaron Morton
> Freelance Cassandra Consultant
> New Zealand
> 
> @aaronmorton
> http://www.thelastpickle.com
> 
> On 1/04/2013, at 11:01 PM, "Hiller, Dean" <Dean.Hiller@nrel.gov<mailto:Dean.Hiller@nrel.gov>>
wrote:
> 
> (we plan on running similar performance tests on cassandra but wanted to understand the
raw foot print first)…..
> 
> Someone in ops was doing a test transferring 1T of data from one node to another.  I
had a huge concern I emailed him that this could end up being a completely sequential write
not testing random access speeds.  He has twenty 1T drives on each machine and I think he
also tried with one 1T drive seeing the same performance which makes sense if writing sequentially.
 Does anyone know of something that could generate a random access pattern such that we could
time that?  Right now, he was measuring 253MB / second from the time it took and the 1T of
data.  I would like to find the much worse case of course.
> 
> If not, maybe I just generate the same 1,000,000 files on each machine, then randomly
delete 1/2 the files and stream them from the other machine as writing those files would all
be in random locations again forcing a much worse measurement of MB/sec I would think.
> 
> Thoughts?
> 
> Thanks,
> Dean
> 


Mime
View raw message