This may be more appropriate for the [email protected] list, but I believe the post at [1] is still accurate. In short, there is one split per region, which makes sense because there isn't another good way (that I'm aware of) to locate keys for the start and stop of the scan used by each map task.
[1] http://www.larsgeorge.com/2009/01/how-to-use-hbase-with-hadoop.html On 8/15/11 9:16 AM, "zhangshuai01" <[email protected]> wrote: >hi,all! > > >well all knows that bloksize and filesplit control the number of >mappers(in hadoop-0.20.2). > > >But when using the HBASE as input, how is the number of mappers decided? > > >thanks a lot! > > >Shuai Zhang ---------------------------------------------------------------------- CONFIDENTIALITY NOTICE This message and any included attachments are from Cerner Corporation and are intended only for the addressee. The information contained in this message is confidential and may constitute inside or non-public information under international, federal, or state securities laws. Unauthorized forwarding, printing, copying, distribution, or use of such information is strictly prohibited and may be unlawful. If you are not the addressee, please promptly delete this message and notify the sender of the delivery error by e-mail or you may call Cerner's corporate offices in Kansas City, Missouri, U.S.A at (+1) (816)221-1024.
