Mailing-List: contact common-dev-help@hadoop.apache.org; run by ezmlm
Precedence: bulk
Reply-To: common-dev@hadoop.apache.org
Received-SPF: neutral (athena.apache.org: local policy)
DomainKey-Signature: a=rsa-sha1; s=serpent; d=yahoo-inc.com; c=nofws; q=dns;
	h=received:from:to:date:subject:thread-topic:thread-index:
	message-id:references:in-reply-to:accept-language:
	content-language:x-ms-has-attach:x-ms-tnef-correlator:acceptlanguage:
	content-type:content-transfer-encoding:mime-version;
	b=XJA5huQF7qtZuZVSliT04JfkZ56Cv6uUAkyT/iWu7o4oifAbipYO6z8bQa4ZJF7q
From: Amogh Vasekar <amogh@yahoo-inc.com>
To: "common-dev@hadoop.apache.org" <common-dev@hadoop.apache.org>,
        "core-dev@hadoop.apache.org" <core-dev@hadoop.apache.org>
Date: Wed, 30 Sep 2009 10:58:01 +0530
Subject: RE: last map task taking too long
Thread-Topic: last map task taking too long
Thread-Index: AcpBao8dXgnXgFEYQmOyuUiWGFryrQAI+law
Message-ID: 
 <616DA47B2EF5B944B91846785B512FF4CFC728015C@EGL-EX07VS01.ds.corp.yahoo.com>
References: <25673359.post@talk.nabble.com>
 <c7d45fc70909291801w84dd9cfs276421c3b7319c1c@mail.gmail.com>
 <25673431.post@talk.nabble.com>
In-Reply-To: <25673431.post@talk.nabble.com>
Accept-Language: en-US
Content-Language: en-US
acceptlanguage: en-US
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable
MIME-Version: 1.0

Hi,
Can you provide info on the input like compression etc? Also, are you using=
 cached files in your map tasks? It might be helpful if you paste the logs =
here after blanking your system specific info., as then one can find out wh=
ere till the reduce it went or if the copy phase started at all.

Thanks,
Amogh

-----Original Message-----
From: achilles852 [mailto:faheemkhan@gmail.com]=20
Sent: Wednesday, September 30, 2009 6:38 AM
To: core-dev@hadoop.apache.org
Subject: Re: last map task taking too long


Basically, it finishes what it is supposed to do (I view the logs to find
out), but does not move onto the reduce stage.


Ted Dunning wrote:
>=20
> Is that last map task actually running, or is it pending?
>=20
> On Tue, Sep 29, 2009 at 5:57 PM, achilles852 <faheemkhan@gmail.com> wrote=
:
>=20
>>
>> Hey.. I am trying to write a small mapreduce program. I launch a few map
>> tasks, each of which should complete within a certain time (say 5
>> minutes)... all the tasks complete within 5 minutes except the last one =
-
>> which takes around 10 times more the time taken by all other map
>> tasks.....any idea why this is happening?
>>
>> I am using Hadoop version 0.19.2, tried running it locally as well as on
>> EC2.
>> --
>> View this message in context:
>> http://www.nabble.com/last-map-task-taking-too-long-tp25673359p25673359.=
html
>> Sent from the Hadoop core-dev mailing list archive at Nabble.com.
>>
>>
>=20
>=20
> --=20
> Ted Dunning, CTO
> DeepDyve
>=20
>=20

--=20
View this message in context: http://www.nabble.com/last-map-task-taking-to=
o-long-tp25673359p25673431.html
Sent from the Hadoop core-dev mailing list archive at Nabble.com.