hadoop-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Xuzhan Sun <sunxuz...@outlook.com>
Subject 答复: Can Pseudo-Distributed Mode take advantage of multi-core structure?
Date Tue, 24 Mar 2015 17:27:58 GMT
So I can set up the pseudo distributed mode without virtual machine and get the same performance?
Am I right?

Sent from my Windows Phone
发件人: Michael Segel<mailto:msegel_hadoop@hotmail.com>
发送时间: ‎2015/‎3/‎25 1:17
收件人: user@hadoop.apache.org<mailto:user@hadoop.apache.org>
主题: Re: Can Pseudo-Distributed Mode take advantage of multi-core structure?

Short answer yes.
> On Mar 24, 2015, at 11:53 AM, Xuzhan Sun <sunxuzhan@outlook.com> wrote:
> Hello,
> I want to do some test on my single node cluster for Speed. I know it is easy to set
up the Pseudo-Distributed Mode, and Hadoop will start one Java process for each single map/reduce.
> My question is: is it parallel enough on multi-core CPU? I mean if I have 4 mappers at
the same time while my CPU have 4 cores, will the 4 mappers be running on different cores
at the same time?
> I know another way to simulate a Hadoop cluster with one machine is to use virtual machine
software such as VMware to simulate multiple machines and set up a cluster upon these virtual
machines. What's the difference between the two methods for SPEED and PARALLEL on multi-core
> Thanks,
> Xuzhan

View raw message