Mailing-List: contact user-help@kudu.apache.org; run by ezmlm
Precedence: bulk
Reply-To: user@kudu.apache.org
MIME-Version: 1.0
In-Reply-To: <9BE34F6A-08F8-4E44-B729-8B99B2082A88@gmail.com>
References: <9BE34F6A-08F8-4E44-B729-8B99B2082A88@gmail.com>
From: Todd Lipcon <todd@cloudera.com>
Date: Thu, 17 Nov 2016 21:12:50 -0800
Message-ID: <CADY20s7mpeGhXNbxdW3ENL+B2w-BLdYOKB0zi0DtJawR1Gsi2g@mail.gmail.com>
Subject: Re: Drill on Kudu
To: user@kudu.apache.org
Content-Type: multipart/alternative; boundary=001a11470694c3793d05418c5c2b
archived-at: Fri, 18 Nov 2016 05:13:21 -0000

--001a11470694c3793d05418c5c2b
Content-Type: text/plain; charset=UTF-8

On Thu, Nov 17, 2016 at 6:16 PM, MattK <bsg075@gmail.com> wrote:

> If I understand Kudu correctly, it manages its own cluster, and does not
> rely on ZK for coordiantion (?).
>
> Correct.


> When using the Kudu storage configuration in Drill 1.7/8, is it necessary
> to run multiple Drillbits, and is there a concept of data locality with
> Drill on Kudu?
>

I believe Drill does expose locality. However, on the Kudu side I don't
think anyone has tested Drill integration in nearly a year, so it's
possible that things aren't working as expected anymore.


>
> Or is a single standalone Drillbit used when only A Kudu cluster is the
> target, and the Kudu handles the work pushed down from the single Drillbit?
>
>
Should be possible, but I don't think the Drill/Kudu integration
implemented much in the way of filter pushdown, so may not actually work.

In general I think the Drill mailing list is a better spot for this
question, since the Drill/Kudu integration is managed in their source
repository and part of their releases.

-Todd
-- 
Todd Lipcon
Software Engineer, Cloudera

--001a11470694c3793d05418c5c2b
Content-Type: text/html; charset=UTF-8
Content-Transfer-Encoding: quoted-printable

<div dir=3D"ltr"><div class=3D"gmail_extra"><div class=3D"gmail_quote">On T=
hu, Nov 17, 2016 at 6:16 PM, MattK <span dir=3D"ltr">&lt;<a href=3D"mailto:=
bsg075@gmail.com" target=3D"_blank">bsg075@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">If I understand Kudu correctly, it manage=
s its own cluster, and does not rely on ZK for coordiantion (?).<br>
<br></blockquote><div>Correct.</div><div>=C2=A0</div><blockquote class=3D"g=
mail_quote" style=3D"margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-l=
eft:1ex">
When using the Kudu storage configuration in Drill 1.7/8, is it necessary t=
o run multiple Drillbits, and is there a concept of data locality with Dril=
l on Kudu?<br></blockquote><div><br></div><div>I believe Drill does expose =
locality. However, on the Kudu side I don&#39;t think anyone has tested Dri=
ll integration in nearly a year, so it&#39;s possible that things aren&#39;=
t working as expected anymore.</div><div>=C2=A0</div><blockquote class=3D"g=
mail_quote" style=3D"margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-l=
eft:1ex">
<br>
Or is a single standalone Drillbit used when only A Kudu cluster is the tar=
get, and the Kudu handles the work pushed down from the single Drillbit?<br=
>
<br></blockquote><div><br></div><div>Should be possible, but I don&#39;t th=
ink the Drill/Kudu integration implemented much in the way of filter pushdo=
wn, so may not actually work.</div><div><br></div><div>In general I think t=
he Drill mailing list is a better spot for this question, since the Drill/K=
udu integration is managed in their source repository and part of their rel=
eases.</div><div><br></div><div>-Todd</div></div>-- <br><div class=3D"gmail=
_signature" data-smartmail=3D"gmail_signature">Todd Lipcon<br>Software Engi=
neer, Cloudera</div>
</div></div>

--001a11470694c3793d05418c5c2b--