Point out the correct statement.(a) The right number of reduces seems to be 0.95 or 1.75(b) Increasing the number of reduces increases the framework overhead(c) With 0.95 all of the reduces can launch immediately and start transferring map outputs as the maps finish(d) All of the mentionedThis question was addressed to me in an interview for job.My question is based upon MapReduce Features in portion Developing a MapReduce Application of Hadoop

Point out the correct statement.(a) The right number of reduces seems

1.	Point out the correct statement.(a) The right number of reduces seems to be 0.95 or 1.75(b) Increasing the number of reduces increases the framework overhead(c) With 0.95 all of the reduces can launch immediately and start transferring map outputs as the maps finish(d) All of the mentionedThis question was addressed to me in an interview for job.My question is based upon MapReduce Features in portion Developing a MapReduce Application of Hadoop
Answer» Right choice is (C) With 0.95 all of the reduces can launch IMMEDIATELY and start transferring MAP outputs as the maps finish The BEST I can explain: With 1.75 the faster nodes will finish their FIRST round of reduces and launch a second wave of reduces doing a much better job of load balancing.

Discussion

No Comment Found

Related InterviewSolutions

The _____________ can also be used to distribute both jars and native libraries for use in the map and/or reduce tasks.(a) DistributedLog(b) DistributedCache(c) DistributedJars(d) None of the mentionedI have been asked this question during an interview.I want to ask this question from MapReduce Features in section Developing a MapReduce Application of Hadoop
____________ is the primary interface by which user-job interacts with the JobTracker.(a) JobConf(b) JobClient(c) JobServer(d) All of the mentionedThe question was asked by my school principal while I was bunking the class.Asked question is from MapReduce Features topic in section Developing a MapReduce Application of Hadoop
The standard output (stdout) and error (stderr) streams of the task are read by the TaskTracker and logged to _________(a) ${HADOOP_LOG_DIR}/user(b) ${HADOOP_LOG_DIR}/userlogs(c) ${HADOOP_LOG_DIR}/logs(d) None of the mentionedThe question was asked during an online exam.My question comes from MapReduce Features in division Developing a MapReduce Application of Hadoop
During the execution of a streaming job, the names of the _______ parameters are transformed.(a) vmap(b) mapvim(c) mapreduce(d) mapredThe question was posed to me in a national level competition.My question is based upon MapReduce Features in portion Developing a MapReduce Application of Hadoop
Jobs can enable task JVMs to be reused by specifying the job configuration _________(a) mapred.job.recycle.jvm.num.tasks(b) mapissue.job.reuse.jvm.num.tasks(c) mapred.job.reuse.jvm.num.tasks(d) all of the mentionedThe question was posed to me in examination.I want to ask this question from MapReduce Features topic in section Developing a MapReduce Application of Hadoop
Point out the wrong statement.(a) The task tracker has local directory to create localized cache and localized job(b) The task tracker can define multiple local directories(c) The Job tracker cannot define multiple local directories(d) None of the mentionedThe question was posed to me at a job interview.Question is taken from MapReduce Features topic in section Developing a MapReduce Application of Hadoop
Map output larger than ___________ percent of the memory allocated to copying map outputs.(a) 10(b) 15(c) 25(d) 35The question was asked in an international level competition.This intriguing question comes from MapReduce Features in division Developing a MapReduce Application of Hadoop
____________ specifies the number of segments on disk to be merged at the same time.(a) mapred.job.shuffle.merge.percent(b) mapred.job.reduce.input.buffer.percen(c) mapred.inmem.merge.threshold(d) io.sort.factorI got this question in an online interview.This question is from MapReduce Features in section Developing a MapReduce Application of Hadoop
Point out the correct statement.(a) The number of sorted map outputs fetched into memory before being merged to disk(b) The memory threshold for fetched map outputs before an in-memory merge is finished(c) The percentage of memory relative to the maximum heap size in which map outputs may not be retained during the reduce(d) None of the mentionedI had been asked this question during an online exam.I need to ask this question from MapReduce Features topic in portion Developing a MapReduce Application of Hadoop
Which of the following parameter is the threshold for the accounting and serialization buffers?(a) io.sort.spill.percent(b) io.sort.record.percent(c) io.sort.mb(d) None of the mentionedThe question was posed to me by my college director while I was bunking the class.My query is from MapReduce Features in division Developing a MapReduce Application of Hadoop

Discussion

No Comment Found

Related InterviewSolutions

Reply to Comment