Return-Path: 
 <issues-return-131332-apmail-hbase-issues-archive=hbase.apache.org@hbase.apache.org>
X-Original-To: apmail-hbase-issues-archive@www.apache.org
Delivered-To: apmail-hbase-issues-archive@www.apache.org
Received: from mail.apache.org (hermes.apache.org [140.211.11.3])
	by minotaur.apache.org (Postfix) with SMTP id 1C6AB10072
	for <apmail-hbase-issues-archive@www.apache.org>;
 Mon, 13 Jan 2014 05:23:06 +0000 (UTC)
Received: (qmail 5015 invoked by uid 500); 13 Jan 2014 05:22:59 -0000
Delivered-To: apmail-hbase-issues-archive@hbase.apache.org
Received: (qmail 4985 invoked by uid 500); 13 Jan 2014 05:22:56 -0000
Mailing-List: contact issues-help@hbase.apache.org; run by ezmlm
Precedence: bulk
List-Help: <mailto:issues-help@hbase.apache.org>
List-Unsubscribe: <mailto:issues-unsubscribe@hbase.apache.org>
List-Post: <mailto:issues@hbase.apache.org>
List-Id: <issues.hbase.apache.org>
Delivered-To: mailing list issues@hbase.apache.org
Received: (qmail 4962 invoked by uid 99); 13 Jan 2014 05:22:51 -0000
Received: from arcas.apache.org (HELO arcas.apache.org) (140.211.11.28)
    by apache.org (qpsmtpd/0.29) with ESMTP; Mon, 13 Jan 2014 05:22:51 +0000
Date: Mon, 13 Jan 2014 05:22:51 +0000 (UTC)
From: "Lars Hofhansl (JIRA)" <jira@apache.org>
To: issues@hbase.apache.org
Message-ID: <JIRA.12688420.1389487361358.85259.1389590571672@arcas>
In-Reply-To: <JIRA.12688420.1389487361358@arcas>
References: <JIRA.12688420.1389487361358@arcas>
Subject: [jira] [Commented] (HBASE-10320) Avoid ArrayList.iterator() in
 tight loops
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit
X-JIRA-FingerPrint: 30527f35849b9dde25b450d4833f0394


    [ https://issues.apache.org/jira/browse/HBASE-10320?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13869295#comment-13869295 ] 

Lars Hofhansl commented on HBASE-10320:
---------------------------------------

bq. Where should we see the improvement overall?
Scanning with ExplicitColumnTracker (i.e. a scan where some columns were added with addColumn) and where all/most data is filtered out at the server (by a filter or a coprocessor).
So in PE the FilteredScanTest might do it. If you run that, let me know what you find. Might be that in all but extreme cases this is just in the noise. I think PE has relatively large columns (1000 bytes), so it might not show.

Will wait with commit until we've had a PE test.

> Avoid ArrayList.iterator() in tight loops
> -----------------------------------------
>
>                 Key: HBASE-10320
>                 URL: https://issues.apache.org/jira/browse/HBASE-10320
>             Project: HBase
>          Issue Type: Bug
>          Components: Performance
>            Reporter: Lars Hofhansl
>         Attachments: 10320-0.94-v2.txt, 10320-0.94.txt
>
>
> I noticed that in a profiler (sampler) run ScanQueryMatcher.setRow(...) showed up at all.
> In turns out that the expensive part is iterating over the columns in ExcplicitColumnTracker.reset(). I did some microbenchmarks and found that
> {code}
> private ArrayList<X> l;
> ...
> for (int i=0; i<l.size(); i++) {
>    X = l.get(i);
>    ...
> }
> {code}
> Is twice as fast as:
> {code}
> private ArrayList<X> l;
> ...
> for (X : l) {
>    ...
> }
> {code}
> The indexed version asymptotically approaches the iterator version, but even at 1m entries it is still faster.
> In my tight loop scans this provides for a 5% performance improvement overall when the ExcplicitColumnTracker is used.



--
This message was sent by Atlassian JIRA
(v6.1.5#6160)