Mailing-List: contact dev-help@hbase.apache.org; run by ezmlm
Precedence: bulk
Reply-To: dev@hbase.apache.org
Received-SPF: pass (athena.apache.org: domain of jason.rutherglen@gmail.com
 designates 209.85.220.169 as permitted sender)
DomainKey-Signature: a=rsa-sha1; c=nofws;
        d=gmail.com; s=gamma;
        h=mime-version:in-reply-to:references:date:message-id:subject:from:to
         :content-type:content-transfer-encoding;
        b=rrMagqdy0RnKSZ5+byxdWHgpupqqCIb7MKfSRqSkVMQoKCBug5TGhhjsevM/d9TSr6
         nHN9LFlbdq3hXMTDHuyHGm7EsZ4rWeVHp/H6JTwcw1P446tkgqBCguJv5X7dghTt1d7y
         bp90yRE1AS6oWsvLVvkGuGEHlbykqo3Pslbr0=
MIME-Version: 1.0
In-Reply-To: <BANLkTimV=KfUmEfpDhm1C5ymLNa85EM7Kg@mail.gmail.com>
References: <BANLkTi=_Gqfivum=vd0e1XfaVA3mcNVXxA@mail.gmail.com>
	<636E56F7-5C3B-4D60-9053-9D6BE67EBAF9@gmail.com>
	<BANLkTikG1nWUvMNp32yV-PU_Me4W0O87iQ@mail.gmail.com>
	<BANLkTinv9jTQPOMNxdyM2bbJPbwse71+Tw@mail.gmail.com>
	<BANLkTimCtXpKB23q+9Gs7zipW7t7gN8W5g@mail.gmail.com>
	<BANLkTikmx0k7A9=_UDuG=mYCqaoRgb+Lqw@mail.gmail.com>
	<BANLkTimV=KfUmEfpDhm1C5ymLNa85EM7Kg@mail.gmail.com>
Date: Mon, 6 Jun 2011 09:07:41 -0700
Message-ID: <BANLkTimY21fLBq1mt--+ZR8hz+U9NO6zgA@mail.gmail.com>
Subject: Re: Pluggable block index
From: Jason Rutherglen <jason.rutherglen@gmail.com>
To: dev@hbase.apache.org
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable

> Are you sure that is a good idea?  Surely the disk seeks would destroy
> you on index load?

I'm not sure what you mean there.  We can create a total HFile block
key index that has pointers to within blocks, eg, they'll store a
block index int, and a position (within the block) int.  Where would
the index load occur as this method should allow faster key lookup?

On Sun, Jun 5, 2011 at 11:37 PM, Ryan Rawson <ryanobjc@gmail.com> wrote:
> On Sun, Jun 5, 2011 at 11:33 PM, Jason Rutherglen
> <jason.rutherglen@gmail.com> wrote:
>> Ok, the block index is only storing the first key of each block?
>> Hmm... I think we can store a pointer to an exact position in the
>> block, or at least allow that (for the FST implementation).
>
> Are you sure that is a good idea? =A0Surely the disk seeks would destroy
> you on index load?
>