Mailing-List: contact user-help@cassandra.apache.org; run by ezmlm
Precedence: bulk
Reply-To: user@cassandra.apache.org
Received-SPF: pass (nike.apache.org: domain of kohlisankalp@gmail.com
 designates 209.85.216.51 as permitted sender)
MIME-Version: 1.0
In-Reply-To: 
 <CAGPaip+P0YAhOtXHzu78q6XR7wZfCfOizCRLK3+XjDpKHR7PHw@mail.gmail.com>
References: 
 <CAGPaip+O+ZauknEeX-ixS-SHKy9n2LGs_ODXd1me=y+8JKWXbw@mail.gmail.com>
 <CAGPaip+P0YAhOtXHzu78q6XR7wZfCfOizCRLK3+XjDpKHR7PHw@mail.gmail.com>
From: sankalp kohli <kohlisankalp@gmail.com>
Date: Wed, 10 Jul 2013 12:10:13 -0700
Message-ID: 
 <CAEPxca0e94QvurOdRnvgV73C1AnTXajYF4jL-TDxkMxmHgoXfA@mail.gmail.com>
Subject: Re: Quorum reads and response time
To: user@cassandra.apache.org
Content-Type: multipart/alternative; boundary=001a11c1e2245fcb3c04e12d0969

--001a11c1e2245fcb3c04e12d0969
Content-Type: text/plain; charset=ISO-8859-1

The coordinator node has to merge the results from 2 nodes and the request
is done in parallel. I have seen lot of GC pressure with range queries
because of tombstones.
Can you see logs to see if there is lot of GC going on. Also try to have GC
log enabled.


On Wed, Jul 10, 2013 at 9:57 AM, Baskar Duraikannu <
baskar.duraikannu.db@gmail.com> wrote:

> Just adding few other details to my question.
>
> - We are using RandomPartitioner
> - 256 virtual nodes configured.
>
>
> On Wed, Jul 10, 2013 at 12:54 PM, Baskar Duraikannu <
> baskar.duraikannu.db@gmail.com> wrote:
>
>> I have a 3 node cluster with RF=3.  All nodes are running. I have a table
>> with 39 rows and ~44,000 columns evenly spread across 39 rows.
>>
>> When I do range slice query on this table with consistency of one, it
>> returns the data back in about  ~600 ms.  I tried the same from all of the
>> 3 nodes,no matter which node I ran it from, queries were answered in 600 ms
>> for consistency level of one.
>>
>> But when I run the same query with consistency level as Quorum, it is
>> taking ~2.3 seconds.  It feels as if querying of the nodes are in sequence.
>>
>>
>> Is this normal?
>>
>> --
>> Regards,
>> Baskar Duraikannu
>>
>>
>

--001a11c1e2245fcb3c04e12d0969
Content-Type: text/html; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable

<div dir=3D"ltr">The coordinator node has to merge the results from 2 nodes=
 and the request is done in parallel. I have seen lot of GC pressure with r=
ange queries because of tombstones.=A0<div style>Can you see logs to see if=
 there is lot of GC going on. Also try to have GC log enabled.=A0</div>

</div><div class=3D"gmail_extra"><br><br><div class=3D"gmail_quote">On Wed,=
 Jul 10, 2013 at 9:57 AM, Baskar Duraikannu <span dir=3D"ltr">&lt;<a href=
=3D"mailto:baskar.duraikannu.db@gmail.com" target=3D"_blank">baskar.duraika=
nnu.db@gmail.com</a>&gt;</span> wrote:<br>

<blockquote class=3D"gmail_quote" style=3D"margin:0 0 0 .8ex;border-left:1p=
x #ccc solid;padding-left:1ex"><div dir=3D"ltr">Just adding few other detai=
ls to my question.<div><br></div><div>- We are using RandomPartitioner</div=
>
<div>
- 256 virtual nodes configured.=A0</div></div><div class=3D"HOEnZb"><div cl=
ass=3D"h5"><div class=3D"gmail_extra"><br><br><div class=3D"gmail_quote">
On Wed, Jul 10, 2013 at 12:54 PM, Baskar Duraikannu <span dir=3D"ltr">&lt;<=
a href=3D"mailto:baskar.duraikannu.db@gmail.com" target=3D"_blank">baskar.d=
uraikannu.db@gmail.com</a>&gt;</span> wrote:<br><blockquote class=3D"gmail_=
quote" style=3D"margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1=
ex">


<div dir=3D"ltr">I have a 3 node cluster with RF=3D3. =A0All nodes are runn=
ing. I have a table with 39 rows and ~44,000 columns evenly spread across 3=
9 rows.=A0<div><br></div><div>When I do range slice query on this table wit=
h consistency of one, it returns the data back in about =A0~600 ms. =A0I tr=
ied the same from all of the 3 nodes,no matter which node I ran it from, qu=
eries were answered in 600 ms for consistency level of one.</div>


<div><br></div><div>But when I run the same query with consistency level as=
 Quorum, it is taking ~2.3 seconds. =A0It feels as if querying of the nodes=
 are in sequence. =A0</div><div><br></div><div>Is this normal?=A0</div>
<div><br></div><div>--</div><div>Regards,</div><div>Baskar Duraikannu</div>=
<div><br></div></div>
</blockquote></div><br></div>
</div></div></blockquote></div><br></div>

--001a11c1e2245fcb3c04e12d0969--