cassandra-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Kent Tong <>
Subject Re: read performance problem
Date Mon, 21 Nov 2011 08:41:59 GMT
Dear all,

Sorry, I was running the wrong test. Yes, the query performance is 2,300 QPS which is
pretty good.

Author of books for learning CXF, Axis2, Wicket, JSF (

 From: Jahangir Mohammed <>
To:; Kent Tong <> 
Sent: Monday, November 21, 2011 5:22 AM
Subject: Re: read performance problem

There is something wrong with the system. Your benchmarks are way off. How are you benchmarking?
Are you using the stress lib included?
On Nov 19, 2011 8:58 PM, "Kent Tong" <> wrote:

>On my computer with 2G RAM and a core 2 duo CPU E4600 @ 2.40GHz, I am testing the 
>performance of Cassandra. The write performance is good: It can write a million records 
>in 10 minutes. However, the query performance is poor and it takes 10 minutes to read 
>10K records with sequential keys from 0 to 9999 (about 100 QPS). This is far away from 
>the 3,xxx QPS found on the net.
>Cassandra decided to use 1G as the Java heap size which seems to be fine as at the end
>of the benchmark the swap was barely used (only 1M used).
>I understand that my computer may be not as powerful as those used in the other benchmarks, 
>but it shouldn't be that far off (1:30), right?
>Any suggestion? Thanks in advance!
View raw message