Mailing-List: contact user-help@hadoop.apache.org; run by ezmlm
Precedence: bulk
Reply-To: user@hadoop.apache.org
Received-SPF: pass (athena.apache.org: domain of linlma@gmail.com designates
 209.85.220.179 as permitted sender)
MIME-Version: 1.0
In-Reply-To: 
 <CAAE8jdeEOJUX_n7z81tioQTUhqHMmmtwvDb8jR0w4pAdkQxBnA@mail.gmail.com>
References: 
 <CAK_MoSv+kWzmJuuFY=uM1Vu1wXdwUrv6sn5=Zwicz5Sk3319=g@mail.gmail.com>
	<CAAE8jdeEOJUX_n7z81tioQTUhqHMmmtwvDb8jR0w4pAdkQxBnA@mail.gmail.com>
Date: Sun, 23 Dec 2012 23:09:59 +0800
Message-ID: 
 <CAK_MoStioYZ=6hcBRBqnxSO=nAGco-WNh8VzWieyngi+WG-uWg@mail.gmail.com>
Subject: Re: reducer tasks start time issue
From: Lin Ma <linlma@gmail.com>
To: user@hadoop.apache.org, rishi@infoobjects.com
Content-Type: multipart/alternative; boundary=20cf307cfd026e397204d186797c

--20cf307cfd026e397204d186797c
Content-Type: text/plain; charset=ISO-8859-1

Thanks Rishi,

My question is answered.

regards,
Lin

On Sun, Dec 23, 2012 at 12:09 AM, Rishi Yadav <rishi@infoobjects.com> wrote:

> Hi Lin,
>
> Reduce task starts as soon as output is ready from Mappers. The reduce
> method does not get called until all Mappers are done. If that's not the
> case, all operations which are not commutative and associative will yield
> incorrect result.
>
>
>
> Thanks and Regards,
>
> Rishi Yadav
>
> (o) 408.988.2000x113 ||  (f) 408.716.2726
>
> InfoObjects Inc || http://www.infoobjects.com *(Big Data Solutions)*
>
> *INC 500 Fastest growing company in 2012 || 2011*
>
> *Best Place to work in Bay Area 2012 - *SF Business Times and the Silicon
> Valley / San Jose Business Journal
>
> 2041 Mission College Boulevard, #280 || Santa Clara, CA 95054
>
>
>
>
> On Sat, Dec 22, 2012 at 5:25 AM, Lin Ma <linlma@gmail.com> wrote:
>
>> Hi guys,
>>
>> Supposing in a Hadoop job, there are both mappers and reducers. My
>> question is, reducer tasks cannot begin until all mapper tasks complete? If
>> so, why designed in this way?
>>
>> thanks in advance,
>> Lin
>>
>
>

--20cf307cfd026e397204d186797c
Content-Type: text/html; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable

Thanks Rishi,<br><br>My question is answered.<br><br>regards,<br>Lin<br><br=
><div class=3D"gmail_quote">On Sun, Dec 23, 2012 at 12:09 AM, Rishi Yadav <=
span dir=3D"ltr">&lt;<a href=3D"mailto:rishi@infoobjects.com" target=3D"_bl=
ank">rishi@infoobjects.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">Hi Lin,<div><br></div><div>=
Reduce task starts as soon as output is ready from Mappers. The reduce meth=
od does not get called until all Mappers are done. If that&#39;s not the ca=
se, all operations which are not commutative and associative will yield inc=
orrect result.=A0</div>

<div><br></div><div><br></div></div><div class=3D"gmail_extra"><br clear=3D=
"all"><div>


<p><font size=3D"1">Thanks and Regards,</font></p><p><font size=3D"1">Rishi=
 Yadav</font></p><p></p><p><font face=3D"&#39;arial narrow&#39;, sans-serif=
" size=3D"1">(o) <a href=3D"tel:408.988.2000x113" value=3D"+14089882000" ta=
rget=3D"_blank">408.988.2000x113</a> || =A0(f) <a href=3D"tel:408.716.2726"=
 value=3D"+14087162726" target=3D"_blank">408.716.2726</a></font></p>
<p></p>
<p><font face=3D"&#39;arial narrow&#39;, sans-serif" size=3D"1">InfoObjects=
 Inc ||=A0<a href=3D"http://www.infoobjects.com/" target=3D"_blank">http://=
www.infoobjects.com</a>=A0<b>(Big Data Solutions)</b></font></p><p><font fa=
ce=3D"&#39;arial narrow&#39;, sans-serif" size=3D"1"><b>INC 500 Fastest gro=
wing company in 2012 || 2011</b></font></p>

<p><font size=3D"1"><b><font face=3D"&#39;arial narrow&#39;, sans-serif">Be=
st Place to work in Bay Area 2012 </font>-<font color=3D"#333333">=A0</font=
></b></font><span style=3D"line-height:20px"><font color=3D"#333333" face=
=3D"&#39;arial narrow&#39;, sans-serif" size=3D"1">SF Business Times and th=
e Silicon Valley / San Jose Business Journal</font></span></p>

<p><span style=3D"font-size:x-small"><font face=3D"&#39;arial narrow&#39;, =
sans-serif">2041 Mission College Boulevard, #280 ||=A0Santa Clara, CA 95054=
=A0</font></span></p><p><br></p><p></p></div><div><div class=3D"h5">
<br><br><div class=3D"gmail_quote">On Sat, Dec 22, 2012 at 5:25 AM, Lin Ma =
<span dir=3D"ltr">&lt;<a href=3D"mailto:linlma@gmail.com" target=3D"_blank"=
>linlma@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:1ex">

Hi guys,<br><br>Supposing in a Hadoop job, there are both mappers and reduc=
ers. My question is, reducer tasks cannot begin until all mapper tasks comp=
lete? If so, why designed in this way?<br><br>thanks in advance,<br>Lin<br>


</blockquote></div><br></div></div></div>
</blockquote></div><br>

--20cf307cfd026e397204d186797c--