Mailing-List: contact hbase-user-help@hadoop.apache.org; run by ezmlm
Precedence: bulk
Reply-To: hbase-user@hadoop.apache.org
Received-SPF: pass (nike.apache.org: domain of edlinuxguru@gmail.com
 designates 74.125.78.27 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=RroHouRzIPDOo26DLO4Wro9H19xcxYoJkmu1uG5xYwmIxtrYioEShggRuA3bUESruT
         WgvsvBcQALTNuiOSMjyGlG9tLDKBG311/hvNlorShXaa00kEd/H3S682Kh0Qtdvh5QhP
         w0XYlyxYloWCKkCDkoXD2AbBpBh6P5xcFj2rc=
MIME-Version: 1.0
In-Reply-To: <7c962aed0912082043v6127556dx39e4927a337f257c@mail.gmail.com>
References: <cbbf4b570912081225t2841e92el43018f717f209e53@mail.gmail.com>
	 <78568af10912081421v302d19f9vb8127f0e8b869ebc@mail.gmail.com>
	 <470585.47255.qm@web65501.mail.ac4.yahoo.com>
	 <cbbf4b570912081530t257e40ffj665d15b0af281a0e@mail.gmail.com>
	 <7c962aed0912082043v6127556dx39e4927a337f257c@mail.gmail.com>
Date: Thu, 10 Dec 2009 16:06:44 -0500
Message-ID: <cbbf4b570912101306n1b50b583se439067b2c066bb8@mail.gmail.com>
Subject: Re: PrefixFilter performance question.
From: Edward Capriolo <edlinuxguru@gmail.com>
To: hbase-user@hadoop.apache.org
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable

On Tue, Dec 8, 2009 at 11:43 PM, stack <stack@duboce.net> wrote:
> Try using this filter instead:
>
> =A0 =A0 =A0scan.setFilter(FirstKeyOnlyFilter.new())
>
> Will only return row keys, if thats the effect you are looking for.
>
> St.Ack
>
>
> On Tue, Dec 8, 2009 at 3:30 PM, Edward Capriolo <edlinuxguru@gmail.com>wr=
ote:
>
>> On Tue, Dec 8, 2009 at 6:00 PM, Andrew Purtell <apurtell@apache.org>
>> wrote:
>> > I added an entry to the troubleshooting page up on the wiki:
>> >
>> > =A0 =A0http://wiki.apache.org/hadoop/Hbase/Troubleshooting#A16
>> >
>> > =A0- Andy
>> >
>> >
>> >
>> >
>> >
>> > ________________________________
>> > From: Ryan Rawson <ryanobjc@gmail.com>
>> > To: hbase-user@hadoop.apache.org
>> > Sent: Tue, December 8, 2009 5:21:25 PM
>> > Subject: Re: PrefixFilter performance question.
>> >
>> > You want:
>> >
>> >
>> http://hadoop.apache.org/hbase/docs/r0.20.2/api/org/apache/hadoop/hbase/=
client/HTable.html#scannerCaching
>> >
>> > The default is low because if a job takes too long processing, a
>> > scanner can time out, which causes unhappy jobs/people/emails.
>> >
>> > BTW I can read small rows out of a 19 node cluster at 7 million
>> > rows/sec using a map-reduce program. =A0Any individual process is doin=
g
>> > 40k+ rows/sec or so
>> >
>> > -ryan
>> >
>> > On Tue, Dec 8, 2009 at 12:25 PM, Edward Capriolo <edlinuxguru@gmail.co=
m>
>> wrote:
>> >> Hey all,
>> >>
>> >> I have been doing some performance evaluation with mysql vs hbase.
>> >>
>> >> I have a table webtable
>> >> {NAME =3D> 'webdata', FAMILIES =3D> [{NAME =3D> 'anchor', COMPRESSION=
 =3D>
>> >> 'NONE', VERSIONS =3D> '3', TTL =3D> '2147483647', BLOCKSIZE =3D> '655=
36',
>> >> IN_MEMORY =3D> 'false', BLOCKCACHE =3D> 'true'}, {NAME =3D> 'image',
>> >> COMPRESSION =3D> 'NONE', VERSIONS =3D> '3', TTL =3D> '2147483647', BL=
OCKSIZE
>> >> =3D> '65536', IN_MEMORY =3D> 'false', BLOCKCACHE =3D> 'true'}, {NAME =
=3D>
>> >> 'raw_data', COMPRESSION =3D> 'NONE', VERSIONS =3D> '3', TTL =3D>
>> >> '2147483647', BLOCKSIZE =3D> '65536', IN_MEMORY =3D> 'false', BLOCKCA=
CHE
>> >> =3D> 'true'}]}
>> >>
>> >> I have a normalized version in mysql. I currently have loaded
>> >>
>> >> nyhadoopdev6:60030 =A0 =A0 =A01260289750689 =A0 requests=3D4, regions=
=3D3,
>> usedHeap=3D99, maxHeap=3D997
>> >> nyhadoopdev7:60030 =A0 =A0 =A01260289862481 =A0 requests=3D0, regions=
=3D2,
>> usedHeap=3D181,
>> >> maxHeap=3D997
>> >> nyhadoopdev8:60030 =A0 =A0 =A01260289909059 =A0 requests=3D0, regions=
=3D2,
>> usedHeap=3D395,
>> >> maxHeap=3D997
>> >>
>> >> This is a snippet here.
>> >>
>> >> if (mysql) {
>> >> =A0 =A0 =A0 try {
>> >> =A0 =A0 =A0 =A0PreparedStatement ps =3D conn.prepareStatement("SELECT=
 * FROM
>> >> page WHERE page LIKE (?)");
>> >> =A0 =A0 =A0 =A0ps.setString(1,"http://www.s%");
>> >> =A0 =A0 =A0 =A0ResultSet rs =3D ps.executeQuery();
>> >> =A0 =A0 =A0 =A0while (rs.next() ){
>> >> =A0 =A0 =A0 =A0 =A0sPageCount++;
>> >> =A0 =A0 =A0 =A0}
>> >> =A0 =A0 =A0 =A0rs.close();
>> >> =A0 =A0 =A0 =A0ps.close();
>> >> =A0 =A0 =A0 } catch (SQLException ex) {System.out.println(ex); System=
.exit(1);
>> }
>> >> =A0 =A0 =A0}
>> >>
>> >> =A0 =A0 =A0if (hbase) {
>> >> =A0 =A0 =A0 =A0Scan s =3D new Scan();
>> >> =A0 =A0 =A0 =A0//s.setCacheBlocks(true);
>> >> =A0 =A0 =A0 =A0s.setFilter( new PrefixFilter(Bytes.toBytes("http://ww=
w.s") ) );
>> >> =A0 =A0 =A0 =A0ResultScanner scanner =3D table.getScanner(s);
>> >> =A0 =A0 =A0 =A0try {
>> >> =A0 =A0 =A0 =A0 =A0for (Result rr:scanner){
>> >> =A0 =A0 =A0 =A0 =A0 =A0sPageCount++;
>> >> =A0 =A0 =A0 =A0 =A0}
>> >> =A0 =A0 =A0 } finally {
>> >> =A0 =A0 =A0 =A0 scanner.close();
>> >> =A0 =A0 =A0 }
>> >>
>> >> =A0 =A0 =A0}
>> >>
>> >> I am seeing about .3 MS from mysql and 20. second performance from
>> >> Hbase. I have read some tuning docs but most seem geared for insertio=
n
>> >> speed, not search speed. I would think this would be a
>> >> Bread-and-butter search for hbase since the row keys are naturally
>> >> sorted lexicographically. I am not running a giant setup here, 3
>> >> nodes, 2x replication, but I would think that it is almost a non
>> >> factor here since these data is fairly small. Hints ?
>> >>
>> >
>> >
>> >
>> >
>>
>> I raised this to from 1-30 -> 18 sec
>> I raised this to 100 ->17 sec
>> I raised this to 1000 ->OOM
>>
>> The OOM pointed me in the direction that this comparison is not apples
>> to apples. In mysql the page table is normalized, but in HBASE it is
>> not. I see lots of data moving across the wire.
>>
>> I tried to filter to just move the ROW key across the wire but I do
>> not think I have it right...
>>
>> =A0List<Filter> filters =3D new ArrayList<Filter>();
>> =A0 =A0 =A0 =A0filters.add( new PrefixFilter(Bytes.toBytes("http://www.s=
") ) ) ;
>> =A0 =A0 =A0 =A0filters.add( new QualifierFilter( CompareOp.EQUAL, new
>> BinaryComparator(
>>
>> Bytes.toBytes("ROW")) ) );
>> =A0 =A0 =A0 =A0Filter f =3Dnew FilterList(Operator.MUST_PASS_ALL, filter=
s);
>> =A0 =A0 =A0 =A0s.setFilter(f);
>> =A0 =A0 =A0 =A0 ResultScanner scanner =3D table.getScanner(s);
>>
>

I have added the smallest family I have.

 s.addFamily( Bytes.toBytes("anchor") )

This drops the search to
spage_time:2266 ms

second consecutive search takes

~1000 ms

This is more reasonable, the time discrepancy now could be explained
because each entry has 5-10 random anchors associated with it.

I have used CE HBase 0.20.0 RPM. and guess what I do not have?
FirstKeyOnlyFilter :) I really like the layout Hbase layout/init
scripts this RPM provides. I can't seem to find the src.rpm for it
anywhere. If I do not find it in a few days, I might just to latest or
trunk. (side note Does anyone have the source RPM?)