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 yulinyen@gmail.com designates
 209.85.215.44 as permitted sender)
MIME-Version: 1.0
In-Reply-To: 
 <CAHwsXY=XCbcBM7Zhx3z-ww2UHBHJHwEzXRC0d1fNjrEDNk0WHQ@mail.gmail.com>
References: 
 <CAHwsXY=SJuX94k9wdzkq4DBNTQPnPka77Y4uNrH_GdjajzHHSg@mail.gmail.com>
	<CAHwsXY=XCbcBM7Zhx3z-ww2UHBHJHwEzXRC0d1fNjrEDNk0WHQ@mail.gmail.com>
Date: Mon, 8 Aug 2011 10:51:27 +0800
Message-ID: 
 <CAAaMp50A70KjMKUa6bMrncxPztKpU-_j9-4LQCgAH58O95-12Q@mail.gmail.com>
Subject: Re: batch mutates & throughput
From: Boris Yen <yulinyen@gmail.com>
To: user@cassandra.apache.org
Content-Type: multipart/alternative; boundary=bcaec52be7ad03cf1b04a9f5864e

--bcaec52be7ad03cf1b04a9f5864e
Content-Type: text/plain; charset=ISO-8859-1

Maybe you could try to adjust the setting "cassandraThriftSocketTimeout" of
hector. https://github.com/rantav/hector/wiki/User-Guide


On Mon, Aug 8, 2011 at 6:54 AM, Philippe <watcherfr@gmail.com> wrote:

> Quick followup.
> I have pushed the RPC timeout to 30s. Using Hector, I'm doing 1 thread
> doing batches of 10 mutates at a time so that's even slower than when I was
> doing 16 threads in parallel doing non-batched mutations.
> After a couple hundred execute() calls, I get a timeout for every node; I
> have a 15 second grace period between retries. tpstats indicate no pendings
> on any of the nodes. I never recover from that
>
> I then set the batch size to one and it seems to work a lot better. The
> only difference I note is that the Mutator.execute() method returns a result
> than sometimes has a null host and 0 microsecond time in the batch sizes of
> ten but never in batch sizes of 1.
>
>
> I'm stumped ! Any ideas ?
>
> Thanks
>

--bcaec52be7ad03cf1b04a9f5864e
Content-Type: text/html; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable

Maybe you could try to adjust the setting &quot;<meta http-equiv=3D"content=
-type" content=3D"text/html; charset=3Dutf-8"><span class=3D"Apple-style-sp=
an" style=3D"border-collapse: collapse; font-family: helvetica, arial, free=
sans, clean, sans-serif; font-size: 14px; line-height: 19px; ">cassandraThr=
iftSocketTimeout</span>&quot; of hector.=A0<meta http-equiv=3D"content-type=
" content=3D"text/html; charset=3Dutf-8"><a href=3D"https://github.com/rant=
av/hector/wiki/User-Guide">https://github.com/rantav/hector/wiki/User-Guide=
</a><div>
<div><br></div><div><br><div class=3D"gmail_quote">On Mon, Aug 8, 2011 at 6=
:54 AM, Philippe <span dir=3D"ltr">&lt;<a href=3D"mailto:watcherfr@gmail.co=
m">watcherfr@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;">
Quick followup.<div>I have pushed the RPC timeout to 30s.=A0Using Hector, I=
&#39;m doing 1 thread doing batches of 10 mutates at a time so that&#39;s e=
ven slower than when I was doing 16 threads in parallel doing non-batched m=
utations.<div>

After a couple hundred execute() calls, I get a timeout for every node; I h=
ave a 15 second grace period between retries. tpstats indicate no pendings =
on any of the nodes. I never recover from that</div><div><br></div><div>

I then set the batch size to one and it seems to work a lot better. The onl=
y difference I note is that the Mutator.execute() method returns a result t=
han sometimes has a null host and 0 microsecond time in the batch sizes of =
ten but never in batch sizes of 1.</div>

<div><br></div><div><br></div><div>I&#39;m stumped ! Any ideas ?</div><div>=
<br></div><div>Thanks<br></div></div>
</blockquote></div><br></div></div>

--bcaec52be7ad03cf1b04a9f5864e--