Return-Path: Delivered-To: apmail-hbase-user-archive@www.apache.org Received: (qmail 15086 invoked from network); 6 Oct 2010 21:37:40 -0000 Received: from unknown (HELO mail.apache.org) (140.211.11.3) by 140.211.11.9 with SMTP; 6 Oct 2010 21:37:40 -0000 Received: (qmail 74400 invoked by uid 500); 6 Oct 2010 21:37:39 -0000 Delivered-To: apmail-hbase-user-archive@hbase.apache.org Received: (qmail 74322 invoked by uid 500); 6 Oct 2010 21:37:39 -0000 Mailing-List: contact user-help@hbase.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: user@hbase.apache.org Delivered-To: mailing list user@hbase.apache.org Received: (qmail 74313 invoked by uid 99); 6 Oct 2010 21:37:39 -0000 Received: from nike.apache.org (HELO nike.apache.org) (192.87.106.230) by apache.org (qpsmtpd/0.29) with ESMTP; Wed, 06 Oct 2010 21:37:39 +0000 X-ASF-Spam-Status: No, hits=2.2 required=10.0 tests=FREEMAIL_FROM,HTML_MESSAGE,RCVD_IN_DNSWL_NONE,SPF_PASS,T_TO_NO_BRKTS_FREEMAIL X-Spam-Check-By: apache.org Received-SPF: pass (nike.apache.org: domain of weliam.cloud@gmail.com designates 209.85.214.41 as permitted sender) Received: from [209.85.214.41] (HELO mail-bw0-f41.google.com) (209.85.214.41) by apache.org (qpsmtpd/0.29) with ESMTP; Wed, 06 Oct 2010 21:37:33 +0000 Received: by bwz10 with SMTP id 10so49531bwz.14 for ; Wed, 06 Oct 2010 14:37:13 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:received:mime-version:received:in-reply-to :references:from:date:message-id:subject:to:content-type; bh=VyWmxLsGYwD6Cwm+126p6c7DjM61eDCyd1SceTQRitE=; b=iMzVmMrF0/K9HyiaOGE8XNOVcaBcD0QHb8/FeQmc9gGRj4AjD0mnx+IK+QJGRZMZCS ws+62vyHxuk1k56Nji8sEBWGuLY8P60ovjnxsaeHgf4hJOAU3bsiV/lcIP75ixTX7auO +M0nZAfzRwRt/IwHYnq5FzHhnoeFdJccnOE8Q= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:from:date:message-id:subject:to :content-type; b=uijxMj3KzNKbTv5w03I1EjhmcnSIHHjczHVTZqPlyoQD2nShg80tHNqOx67WTYzOyB 7M6bpq2tWVo5/GxzrlqwtL+lSRsyFGx27ZLqfIjD0K7wZQwb1cugRATrNRRATpQNqpjx loYQDVcqfpYQ0KT+KsxsGFxfQ0ccaVtnNDwcg= Received: by 10.204.79.199 with SMTP id q7mr10282731bkk.76.1286401026672; Wed, 06 Oct 2010 14:37:06 -0700 (PDT) MIME-Version: 1.0 Received: by 10.204.69.146 with HTTP; Wed, 6 Oct 2010 14:36:45 -0700 (PDT) In-Reply-To: References: From: William Kang Date: Wed, 6 Oct 2010 17:36:45 -0400 Message-ID: Subject: Re: Can I pick which region server to store my row? To: user@hbase.apache.org Content-Type: multipart/alternative; boundary=0016e6dd99053bc9630491f99419 X-Virus-Checked: Checked by ClamAV on apache.org --0016e6dd99053bc9630491f99419 Content-Type: text/plain; charset=ISO-8859-1 By the way, where can I get a stable version of 0.90? Thanks. Cao On Wed, Oct 6, 2010 at 12:54 PM, Jean-Daniel Cryans wrote: > Like Stack said, it's available in 0.90 which we're currently wrapping > up (so not in 0.20.x). > > Distributing regions and distributing blocks is orthogonal (ish, but > for this discussion let's not mix the two together), the former being > assumed by the HBase master and the latter being assumed by the > Namenode. Maybe this blog post can help you understanding how HBase > uses HDFS > http://www.larsgeorge.com/2009/10/hbase-architecture-101-storage.html > > J-D > > On Tue, Oct 5, 2010 at 8:38 PM, William Kang > wrote: > > So, I can use the 'move' command to manually balance the load? Is this > > available to 0.20.6? Was there any automatic balance mechanism in hbase > > before if the replicated block is not for load distribution purpose? > Thanks. > > > > > > William > > > > On Tue, Oct 5, 2010 at 11:19 PM, Stack wrote: > > > >> In 0.90, you can turn off the balancer and then distribute the regions > >> any way you wish with new 'move' command. > >> St.Ack > >> > >> On Tue, Oct 5, 2010 at 8:13 PM, Jean-Daniel Cryans > > >> wrote: > >> > A row is always served a single region, so the question is more about > >> > region distribution. In 0.20 and 0.89 you have no control over that > >> > (the best you can do is calling close_region in the shell, where is > >> > the region will be moved is "random"), but things are getting better > >> > in 0.90 where you'll be able to move regions manually. > >> > > >> > HBase doesn't create multiple copies of HFiles to distribute load, > >> > what happens is each block is replicated 3 times by HDFS and this is > >> > invisible to HBase. This is done for data safety rather than > >> > distributing the load. > >> > > >> > J-D > >> > > >> > On Tue, Oct 5, 2010 at 8:05 PM, William Kang > >> wrote: > >> >> Hi folks, > >> >> I have a general question about Hbase. Can we pick which region > server > >> we > >> >> want to save a particular row? The reason I am asking this is because > >> >> sometimes we want to manually balance region servers' load. If we > could > >> >> assign particular rows to particular region servers, we can have that > >> >> control. I understand that Hbase will balance its load automatically > by > >> >> create multiple copies of hfiles in HDFS. But, we do want to have > more > >> >> control over that. Is it possible or is it already in Hbase but we > >> didn't > >> >> find it? Many thanks. > >> >> > >> >> > >> >> William > >> >> > >> > > >> > > > --0016e6dd99053bc9630491f99419--