Mailing-List: contact user-help@hbase.apache.org; run by ezmlm
Precedence: bulk
Reply-To: user@hbase.apache.org
Received-SPF: pass (athena.apache.org: local policy)
DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws;
  s=s1024; d=yahoo.com;
  h=X-YMail-OSG:Received:X-Rocket-MIMEInfo:X-RocketYMMF:X-Mailer:References:Message-ID:Date:From:Reply-To:Subject:To:In-Reply-To:MIME-Version:Content-Type;
  b=IsqA8ZEtL2RJsOUAQsmmfLQ4j+yUusMeJbj6g5VZSmvQ3R/hf5zZFywhn1nHS9sIBvYPTIGt3kckFzrxmvyEo2Q7YTGYoWsFpGehORpsOP1T7WB4ntEXj+iq5tmtjtorJ8NIHxTXSh5eAF1GRGpmEHXytg3zNChAw6nBum5+UQw=;
References: 
 <CAMpwW3q2+LF+JRSAz=f+ygf+D5229iT+iSXQC2d73VRP88gDng@mail.gmail.com>
 <1359151251.68831.YahooMailNeo@web140603.mail.bf1.yahoo.com>
Message-ID: <1359158215.20903.YahooMailNeo@web140605.mail.bf1.yahoo.com>
Date: Fri, 25 Jan 2013 15:56:55 -0800 (PST)
From: lars hofhansl <larsh@apache.org>
Reply-To: lars hofhansl <larsh@apache.org>
Subject: Re: Hbase scans taking a lot of time
To: "user@hbase.apache.org" <user@hbase.apache.org>,
  "dev@hbase.apache.org" <dev@hbase.apache.org>,
  lars hofhansl <larsh@apache.org>
In-Reply-To: <1359151251.68831.YahooMailNeo@web140603.mail.bf1.yahoo.com>
MIME-Version: 1.0
Content-Type: multipart/alternative;
 boundary="1254654340-1547007759-1359158215=:20903"

--1254654340-1547007759-1359158215=:20903
Content-Type: text/plain; charset=iso-8859-1
Content-Transfer-Encoding: quoted-printable

Sorry I meant scan caching. (not batching)=0A=0A=0A=0A_____________________=
___________=0A From: lars hofhansl <larsh@apache.org>=0ATo: "user@hbase.apa=
che.org" <user@hbase.apache.org>; "dev@hbase.apache.org" <dev@hbase.apache.=
org> =0ASent: Friday, January 25, 2013 2:00 PM=0ASubject: Re: Hbase scans t=
aking a lot of time=0A =0AEnable scan batching in Hive.=0AYou're probably p=
erforming 300m RPC requests, i.e. you're mostly measuring network latency.=
=0A=0A-- Lars=0A=0A=0A=0A________________________________=0AFrom: Vibhav Mu=
ndra <mundra@gmail.com>=0ATo: user@hbase.apache.org; dev@hbase.apache.org =
=0ASent: Friday, January 25, 2013 1:10 AM=0ASubject: Hbase scans taking a l=
ot of time=0A=0AI am facing a very strange problem with HBase.=0A=0AThis wh=
at I did:=0Aa) Create a table, using pre partioned splits.=0Ab) Also the co=
lumn familes are zipped with lzo compression.=0Ac) Using the above configur=
ation I am able to populate 2 million row per=0Amin in the Hbase.=0Ad) I ha=
ve created a table with 300 million odd rows, which roughy took me 3=0Ahour=
s to populate and the data size is of 25GB.=0A=0Ae) But when I query for da=
ta the performance I am getting is very bad.=0A=A0=A0 Basically this is wha=
t I am seeing: High CPU, no disk I/O and network=0AI/O is happening at the =
rate of 6~7MB secs.=0A=0A=0ABecause of this, if I scan the entries of the t=
able using Hive it is taking=0Aages.=0ABasically it is taking around 24 hou=
rs to scan the table. Any idea, of how=0Ato debug.=0A=0A=0A-Vibhav
--1254654340-1547007759-1359158215=:20903--