Mailing-List: contact hbase-user-help@hadoop.apache.org; run by ezmlm
Precedence: bulk
Reply-To: hbase-user@hadoop.apache.org
Received-SPF: pass (athena.apache.org: domain of mccarbc@gmail.com designates
 209.85.221.172 as permitted sender)
DomainKey-Signature: a=rsa-sha1; c=nofws;
        d=gmail.com; s=gamma;
        h=content-type:mime-version:subject:from:in-reply-to:date
         :content-transfer-encoding:message-id:references:to:x-mailer;
        b=vFvnj9KTAtrXatUts1+h54JiyTIY52yPw635rU2IWUR6sM+DbZeZl5wXH/u8SqAJds
         e9uKjyAEFH248fLCqzQx4l3s/5cgQaYq0f4vBc2D8nt/Pbowo3xI5fc2iRlyobmeoy8k
         iTRtNGc/t2CdV+BPQOQ3hZWWqRUXhvYMfbcHE=
Content-Type: text/plain; charset=us-ascii
Mime-Version: 1.0 (Apple Message framework v1077)
Subject: Re: Question regarding scalability of regionservers
From: Brad McCarty <mccarbc@gmail.com>
In-Reply-To: <7c962aed1002162123t6993c99ha0a57ff945523a5a@mail.gmail.com>
Date: Wed, 17 Feb 2010 11:27:40 -0800
Content-Transfer-Encoding: quoted-printable
Message-Id: <3A0AC11C-2A52-4FC4-9ABC-B5BAA2BE160E@gmail.com>
References: <4B547288-9D43-4DD5-913A-A6836E4DB3E1@gmail.com>
 <7c962aed1002162123t6993c99ha0a57ff945523a5a@mail.gmail.com>
To: hbase-user@hadoop.apache.org

Thanks for the answers.  We're just about ready with our test cluster =
and we will try this test specifically.

The number of Tomcat servers hitting a common row is currently 40 with =
potentially up to 100 threads each (at peak intervals).

You also said:=20
> This is hbase.  You don't buy bigger hardware, you just add nodes =
(smile).


Not sure if that was tongue-in-cheek, because adding nodes wouldn't =
address the hot row issue would it??

Thanks again
Brad


On Feb 16, 2010, at 9:23 PM, Stack wrote:

> On Tue, Feb 16, 2010 at 7:28 PM, Brad McCarty <mccarbc@gmail.com> =
wrote:
>=20
>> I read in another post that if one has a "hot" row in a table, =
meaning very heavy read access to the same row, that the regionserver =
managing the region with that row can become a single bottleneck.
>>=20
>=20
> If hot, it'll probably get stapled into cache.
>=20
>=20
>> Is my understanding accurate?  If so, then assuming I can cache the =
data in the memstore, will CPU utilization become the likely limiting =
resource on that regionserver?
>=20
> Yes.  That should be the case.
>=20
>=20
> Also, if I'm hitting the region server from many client servers
> (Tomcat app servers), will the socket connection management overhead
> on the regionserver overwhelm that server?
>>=20
>=20
> How many clients?  4 or 500 tomcat threads?
>=20
> The way the ipc between hbase client and server works is that it keeps
> up a single socket connection and multiplexes request/response over
> this one connection.  This is how hadoop rpc works.
>=20
>=20
>> If that's true, are there any other steps that can be taken to =
mitigate that risk, other than buying bigger hardware?
>>=20
>=20
> This is hbase.  You don't buy bigger hardware, you just add nodes =
(smile).
>=20
> The proper answer to your questions above is for you to give it a test
> run.  Try setting up a cluster of about 5 hbase nodes and try a tomcat
> server requesting playing a query log that resembles what you might
> have in production.
>=20
> Yours,
> St.Ack