Mailing-List: contact cassandra-dev-help@incubator.apache.org; run by ezmlm
Precedence: bulk
Reply-To: cassandra-dev@incubator.apache.org
Received-SPF: pass (athena.apache.org: domain of masoodmortazavi@gmail.com
 designates 209.85.222.185 as permitted sender)
DomainKey-Signature: a=rsa-sha1; c=nofws;
        d=gmail.com; s=gamma;
        h=mime-version:in-reply-to:references:date:message-id:subject:from:to
         :content-type;
        b=b6GZwfjuVb6RPMx/Rp3C+nYwiG2+pehLFXiGTIUFIUmOQ9nsmruJqNvYyeXpMtgZi5
         IbgAnqiDcs4E95FvV9r7EmXrrC0UfpGW/gkSJnZZ3U/RMIJ5tDmMPo2CMe60k+suaawG
         0Tc02Fl4Zz8cKGu897u0ST8tEPO2rMNd0TDL4=
MIME-Version: 1.0
In-Reply-To: <201003121336073026052@gmail.com>
References: <201003121336073026052@gmail.com>
Date: Fri, 12 Mar 2010 15:57:18 +0800
Message-ID: <b3e0f7631003112357x78b27ad8w8ca83319d8201c02@mail.gmail.com>
Subject: Re: wo did some test on cassandra ,but the result puzzled us
From: Masood Mortazavi <masoodmortazavi@gmail.com>
To: cassandra-dev@incubator.apache.org
Content-Type: multipart/alternative; boundary=000e0cd17fa672368b048195e1af

--000e0cd17fa672368b048195e1af
Content-Type: text/plain; charset=windows-1252
Content-Transfer-Encoding: quoted-printable

Bingbing Liu,

On Fri, Mar 12, 2010 at 1:36 PM, Bingbing Liu <rucbing@gmail.com> wrote:

> We did some test on on Cassandra, and the benchmark is from Section 7 of
> the BigTable paper =93Bigtable: A Distributed Storage System for Structur=
ed
> Data=94, the benchmark task includes: random write, random read, sequenti=
al
> write, and sequential read. The test results made us puzzled. We use a
> cluster of 5 nodes (each node has a 4 cores cpu , 4G memory).The data for
> test is a table with 4,000,000  records each of which is 1000 bytes. The
> test results are as follows:
> Sequential write:  875124 ms
> Sequential read:  1972588 ms
> Random read:  43331738 ms
> Random write:  20193484 ms
> We wondered why the speed of sequential write are so faster than the spee=
d
> of sequential read, and why the speed of sequential write are so faster t=
han
> that of random write? We think that the speed of read should be faster th=
an
> that of data write, but the results are just the opposite, would you plea=
se
> give us some explanations, thanks a lot!
>


Please read the BigTable paper, carefully, again.

They have similar characteristics and describe why this is the case. I thin=
k
you'll find that behavior you observed is quite consistent with the theory
of it all (and reading the text to which Jonathan has pointed you, will
essentially give you the same reasons).

It is part and parcel of the storage architecture of "BigTable" type
systems.

- m.

--000e0cd17fa672368b048195e1af--