操作HDFS：先要保证HDFS启动了：
启动spark集群：
以spark-shell运行在spark集群上：
?
查看下之前上传到HDFS上的”LICENSE.txt“文件：
用spark读取这个文件：
使用count统计该文件的行数：
?我们可以看到count 耗时为0.239708s
对该RDD进行cache操作并执行count使得缓存生效：
执行count结果为：
此时耗时为0.21132s
再执行count操作：
此时耗时为0.029580s，这时因为我们自己基于cache后的数据进行操作的。
接着我们对上面的rdd进行wordcount操作：
通过saveAsTextFile把数据存到HDFS中：
我们通过web控制台查看下运行结果：
我们通过命令行看下part-00000和part-00001内容：
[spark@S1PA222 ~]$?hadoop fs -cat /data/resultLicenseWordCount/part-00000
15/01/22 13:51:32 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
(under,10)
(Unless,3)
(Contributions),1)
(offer,1)
(agree,1)
(BUSINESS,2)
(NON-INFRINGEMENT,,1)
(its,4)
(materials,2)
(event,1)
(intentionally,2)
(Grant,2)
(writing,1)
(include,3)
(responsibility,,1)
(have,2)
(MERCHANTABILITY,,1)
(Contribution,3)
(Massachusetts,1)
(express,2)
("Your"),1)
((i),1)
(However,,1)
(been,2)
(files;,1)
(This,1)
(stating,1)
(2-Clause,1)
(conditions.,1)
(non-exclusive,,2)
(appropriateness,1)
(marked,1)
(risks,1)
(any,28)
(IS",4)
(implementation,1)
(filed.,1)
(Sections,1)
(fee,1)
(losses),,1)
(out,1)
(contract,2)
(DISTRIBUTION,1)
(4.,1)
(file,6)
(documentation,,2)
(wherever,1)
(unless,1)
(below).,1)
(names,,1)
(verbal,,1)
(ANY,10)
(version,1)
(file.,2)
(are,10)
(no-charge,,2)
(2.,1)
(from,,1)
(reproduction,,3)
(2011-2014,,1)
(assume,1)
(licenses,1)
(DATA,,2)
(IS,2)
(recommend,1)
(prominent,1)
(revisions,,1)
("[]",1)
(FITNESS,3)
(otherwise,,3)
(distribution,,1)
(necessarily,1)
(Apache,5)
(grant,1)
(CONTRIBUTORS,4)
(as,15)
(irrevocable,2)
(inclusion,2)
(purpose,2)
(products,1)
(ARE,2)
(merely,1)
(File,1)
(Definitions.,1)
(form,10)
(IMPLIED,4)
(Warranty,1)
(Patent,1)
(incurred,1)
(8.,1)
(repository,1)
(contributors,1)
("printed,1)
(sell,,2)
(:,3)
(malfunction,,1)
(Version,2)
(origin,1)
(alongside,1)
(CRC,1)
(implied.,1)
(contract,,1)
(representatives,,1)
(warranty,1)
(offer,,1)
(org.apache.hadoop.util.bloom.*,1)
(KIND,,2)
(is,10)
(conspicuously,1)
(found,1)
(charge,1)
(make,,1)
(file,,1)
(associated,1)
(even,1)
(same,1)
((Don‘t,1)
(outstanding,1)
(link,1)
([name,1)
(Trademarks.,1)
(notice,2)
(endorse,1)
(shall,15)
(contact,1)
(Redistributions,4)
(using,1)
(class,1)
(name),1)
(behalf,5)
(form.,1)
(We,1)
(INTERRUPTION),2)
(responsible,1)
(annotations,,1)
(THIS,4)
(subject,1)
(acting,1)
(permitted,2)
(OUT,2)
(BASIS,,2)
(has,2)
(Accepting,1)
(defend,,1)
(University,1)
([yyyy],1)
((http://www.one-lab.org),1)
(EVENT,2)
(granting,1)
(portions,1)
(implied,,1)
(NOTICE,5)
(infringed,1)
(limitation,,1)
(names,2)
(electronic,,1)
(PURPOSE,2)
(licensable,1)
(section),1)
(conditions,14)
(EVEN,2)
(acts),1)
(law,3)
(licenses.,1)
(compression,1)
(readable,1)
(solely,1)
(configuration,1)
(information.,1)
(litigation,2)
(represent,,1)
(warranty,,1)
(shares,,1)
(supersede,1)
(governed,1)
(marks,,1)
(http://code.google.com/p/lz4/,1)
(modification,,2)
(fifty,1)
(sent,1)
(places:,1)
(means,2)
(identifying,1)
(this,22)
(Works",1)
(Louvain,1)
(prior,1)
(slicing-by-8,1)
(PROCUREMENT,2)
(changed,1)
(describing,1)
(only,4)
(contributory,1)
(normally,1)
(indirect,,2)
(WITHOUT,2)
(Works,12)
(documentation,3)
(agreement,1)
(otherwise,3)
("AS,4)
(damages,,1)
(patent,,1)
(APACHE,1)
(without,6)
("NOTICE",1)
(Limitation,1)
(SUBSTITUTE,2)
(Contribution(s),3)
(Subject,2)
(Submission,1)
(UCL,1)
(TITLE,,1)
(trademarks,,1)
((iii),1)
(2.0,1)
(Fast,1)
(exercise,1)
(accepting,2)
(example,1)
(distribution.,2)
(interfaces,1)
(conditions:,1)
(act,1)
(incorporated,2)
(provides,2)
(limited,4)
(LZ4,3)
(2008,2009,2010,1)
(can,2)
(contents,1)
(PURPOSE.,1)
(recipients,1)
("Contribution",1)
(failure,1)
(communication,3)
(commercial,1)
(works,1)
(language,1)
(permissions,3)
(WARRANTIES,4)
(media,1)
(reserved.,2)
(Works,,2)
(How,1)
(WARRANTIES,,2)
(controlled,1)
(Warranty.,1)
(2.0,,1)
((http://www.opensource.org/licenses/bsd-license.php),1)
(own,4)
(submit,1)
(SHALL,2)
(reasonable,1)
(reason,1)
(agreed,3)
(systems,1)
(patent,5)
(form,,4)
(Technology.,1)
(advised,1)
(systems,,1)
(classes:,1)
(HOWEVER,2)
(distribution,3)
(DAMAGES,2)
((c),2)
(src/main/native/src/org/apache/hadoop/util:,1)
(PROFITS;,2)
(perpetual,,2)
(applies,1)
(apply,2)
(subcomponents,2)
(modify,2)
(owner],1)
(one,1)
(modifying,1)
(counterclaim,1)
(January,1)
(discussing,1)
(CONTRACT,,2)
(with,16)
((C),1)
(infringement,,1)
(2004,1)
(lawsuit),1)
(specific,2)
(LZ,1)
(warranties,1)
(reproducing,1)
(promote,1)
(beneficial,1)
(ADVISED,2)
((a),1)
(other,9)
(date,1)
(met:,2)
(publicly,2)
(from,4)
(LIMITED,4)
(display,,1)
(MERCHANTABILITY,2)
(damages,3)
(SUBCOMPONENTS:,1)
(negligence),,1)
(remain,1)
(CONDITIONS,4)
(their,2)
(electronic,1)
(identification,1)
(determining,1)
(consistent,1)
(display,1)
(writing,,3)
(trade,1)
(third-party,2)
(,1299)
(description,1)
(REPRODUCTION,,1)
(attached,1)
(list,4)
(*,34)
(INDIRECT,,2)
(designated,1)
(Contribution.",1)
(complies,1)
(addendum,1)
(damages.,1)
(Yann,1)
(EXPRESS,2)
(License;,1)
(6.,1)
(GOODS,2)
(subsequently,1)
(included,2)
(replaced,1)
(notice,,5)
[spark@S1PA222 ~]$?? hadoop fs -cat /data/resultLicenseWordCount/part-00001
15/01/22 13:52:29 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
(For,6)
(reproduce,,1)
("Contributor",1)
((or,3)
(nothing,1)
(work.,1)
(content,1)
(HOLDERS,2)
(add,2)
(through,1)
(All,2)
(perform,,1)
(result,1)
(goodwill,,1)
(herein,1)
(direct,,1)
(used,1)
(To,1)
(harmless,1)
(9.,1)
(these,1)
(control,,1)
(INCIDENTAL,,2)
(indicated,1)
(part,4)
(alone,1)
(different,1)
(forms,,2)
(purposes,4)
(https://groups.google.com/forum/#!forum/lz4c,1)
(be,7)
(/**,2)
(carry,1)
(separable,1)
(including,5)
(contained,1)
(combination,1)
(calculation,1)
(license,7)
(FOR,6)
(thereof,,2)
(ARISING,2)
(constitutes,1)
(but,5)
(types.,1)
(stated,2)
(archives.,1)
(obligations,,1)
(5.,1)
(Works;,3)
(nor,1)
("Legal,1)
(Work,20)
(whole,,2)
(Copyright,5)
(at,3)
(copyright,,1)
(Redistribution,2)
(object,1)
(copy,3)
(indemnify,,1)
(asserted,1)
(HADOOP,1)
(attach,1)
("control",1)
(support,,1)
("Object",1)
(give,1)
(THEORY,2)
(may,10)
(except,2)
("Work",1)
(sublicense,,1)
(IF,2)
(granted,2)
(project,2)
(authorized,2)
(SPECIAL,,2)
(BY,2)
(retain,2)
(or,65)
(transfer,1)
(fields,1)
(Licensor,,1)
((b),1)
((ii),1)
(2005,,1)
(of,75)
(does,1)
(transformation,1)
((INCLUDING,2)
(DIRECT,,2)
(management,1)
(modified,1)
(Licensed,1)
(percent,1)
(Header,1)
(original,2)
(Contributor,,1)
(native,1)
((INCLUDING,,2)
(PARTICULAR,3)
(limitations,1)
(THE,10)
(INCLUDING,,2)
(power,,1)
(CAUSED,2)
(de,1)
(appropriate,1)
(against,,1)
(TORT,2)
("Source",1)
(each,4)
(1.,1)
(following,10)
(Liability.,2)
(acceptance,1)
("You",1)
(sole,1)
(from),1)
(See,1)
(tracking,1)
(for,19)
(cause,2)
(alleging,1)
(obtain,1)
(reproduce,3)
(source,,1)
(control,2)
(EXEMPLARY,,2)
(TERMS,2)
(terms,8)
(syntax,1)
(SERVICES;,2)
(made,,1)
(BUT,4)
(compiled,1)
(issue,1)
("submitted",1)
(OneLab,1)
(algorithm,1)
(was,1)
(While,1)
(entity,,1)
(do,3)
(PROVIDED,2)
(no,2)
(License,10)
(entity,3)
(Contributions.,2)
(mean,10)
(individual,3)
(Institute,1)
(computer,1)
(notices,9)
(Neither,1)
(Licensor,8)
(STRICT,2)
(made,1)
(authorship,,2)
(bind,1)
((the,1)
(indemnity,,1)
(distribute,3)
(You,24)
(grants,2)
(brackets,1)
(meet,1)
(for,,1)
(service,1)
(in,31)
(trademark,,1)
(boilerplate,1)
(WAY,2)
(LOSS,2)
(distributed,3)
(LIABILITY,,4)
(submitted,2)
(public,1)
(OF,19)
(managed,1)
(derived,2)
(Source,8)
(use,,4)
(name,2)
(definition,,2)
(that,25)
(src/main/native/src/org/apache/hadoop/io/compress/lz4/{lz4.h,lz4.c,lz4hc.h,lz4hc.c},,1)
(customary,1)
(BSD,1)
(thereof,1)
(claims,2)
(CONSEQUENTIAL,2)
(translation,1)
(format.,1)
(construed,1)
(DAMAGE.,2)
(applicable,3)
(binary,4)
(regarding,1)
(European,1)
(excluding,3)
(END,1)
((d),1)
(choose,1)
(NO,2)
(BE,2)
(direct,2)
(retain,,1)
(modifications,,3)
(forum,1)
(owner,4)
(USE,2)
(informational,1)
(The,3)
(legal,1)
((50%),1)
(document.,1)
(received,1)
(such,17)
(institute,1)
(distribute,,2)
(WHETHER,2)
(page",1)
((except,1)
(loss,1)
(common,1)
(additions,1)
(BSD-style,1)
(Appendix,1)
(Use,1)
(disclaimer,2)
(resulting,1)
(ON,2)
(hereby,2)
(License.,11)
(software,3)
(whom,1)
(along,1)
(lists,,1)
(required,4)
(OR,18)
(ownership,2)
(SOFTWARE,2)
(the,122)
(includes,1)
(obligations,1)
(import,,1)
(not,11)
(either,2)
(terminate,1)
(if,4)
(stoppage,,1)
(provided,9)
(submitted.,1)
(all,3)
(permission.,1)
("License");,1)
(written,2)
(generated,2)
(consequential,1)
(Derivative,17)
(AND,11)
(rights,3)
(http://www.apache.org/licenses/,1)
(terms.,1)
(Catholique,1)
(deliberate,1)
(entity.,2)
(Work,,4)
(special,,1)
(Additional,1)
(Legal,3)
(034819,1)
(least,1)
(text,4)
(on,11)
(editorial,1)
(redistributing,2)
("License",1)
(against,1)
(permission,1)
(9,1)
(separate,2)
(and/or,3)
(LICENSE,1)
(union,1)
((and,1)
(1,1)
(including,,1)
(Entity,3)
(negligent,1)
(LIABLE,2)
(IN,6)
(use,8)
(enclosed,2)
(contains,1)
(files,1)
(Entity",1)
(Work.,1)
(owner.,1)
(preferred,1)
(modifications,3)
(brackets!),1)
(available,1)
(code,5)
(http://www.apache.org/licenses/LICENSE-2.0,1)
(more,1)
(possibility,1)
(product,1)
(liable,1)
(SUCH,2)
(direction,1)
(must,8)
(making,1)
(Disclaimer,1)
(disclaimer.,2)
(Commission,1)
(OTHERWISE),2)
(Hadoop,1)
((an,1)
(APPENDIX:,1)
("Licensor",1)
(DISCLAIMED.,2)
("Derivative,1)
(elaborations,,1)
(incidental,,1)
(prepare,1)
(A,3)
(exercising,1)
(*/,3)
(which,2)
(pertain,2)
(explicitly,1)
(tort,1)
(3.,1)
(also,1)
(conversions,1)
(liability,2)
(whether,4)
(character,1)
(should,1)
(thereof.,1)
(of,,3)
(your,4)
(royalty-free,,2)
(entities,1)
(or,,1)
(NEGLIGENCE,2)
(author,1)
("Not,1)
(source,9)
(then,2)
((including,3)
(Redistribution.,1)
(attribution,4)
(by,21)
(TO,,4)
(defined,1)
(OWNER,2)
(If,2)
(an,6)
(/*,1)
(Collet.,1)
(improving,1)
(grossly,1)
(COPYRIGHT,4)
(above,,1)
(theory,,1)
(mailing,1)
(7.,1)
(Notwithstanding,1)
(code,,2)
(cross-claim,1)
(provide,1)
((such,1)
(arising,1)
(Object,4)
(In,1)
(-,7)
(those,3)
(work,,2)
(easier,1)
(based,1)
(medium,,1)
(within,8)
(worldwide,,2)
(authorship.,1)
(files.,1)
(inability,1)
(you,2)
(POSSIBILITY,2)
(cannot,1)
(copies,1)
(a,21)
(statement,1)
(above,4)
(state,1)
(work,5)
(by,,3)
(to,41)
(appear.,1)
(Your,9)
(where,1)
(liability.,1)
(governing,1)
(NOT,4)
(License,,6)
(hold,1)
(and,51)
(copyright,15)
(USE,,3)
(compliance,1)
(SOFTWARE,,2)
(comment,1)
(additional,4)
(executed,1)
(mechanical,1)
(Contributor,8)
[spark@S1PA222 ~]$