Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/bad_join.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/bad_join.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/bad_join.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/bad_join.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,23 @@ +register $zebraJar; +--fs -rmr $outputDir + + +--a1 = LOAD '$inputDir/unsorted1' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,byte2'); +--a2 = LOAD '$inputDir/unsorted2' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,byte2'); + +--sort1 = order a1 by byte2; +--sort2 = order a2 by byte2; + +--store sort1 into '$outputDir/100Msortedbyte21' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2];[byte2]'); +--store sort2 into '$outputDir/100Msortedbyte22' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2];[byte2]'); + +rec1 = load '$outputDir/100Msortedbyte21' using org.apache.hadoop.zebra.pig.TableLoader('','sorted'); +rec2 = load '$outputDir/100Msortedbyte22' using org.apache.hadoop.zebra.pig.TableLoader('','sorted'); + +joina = join rec1 by byte2, rec2 by byte2 using "merge" ; + +E = foreach joina generate $0 as count, $1 as seed, $2 as int1, $3 as str2, $4 as byte2; + +store E into '$outputDir/bad3' using org.apache.hadoop.zebra.pig.TableStorer(''); + +
Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/collecion4.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/collecion4.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/collecion4.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/collecion4.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,16 @@ +register /grid/0/dev/hadoopqa/jars/zebra.jar; + +a1 = LOAD '/data/SDS_HTable' USING org.apache.hadoop.zebra.pig.TableLoader('MLF_viewinfo'); +--limitedVals = LIMIT a1 10; +--dump limitedVals; + +store a1 into '/data/collection_viewinfo1' using org.apache.hadoop.zebra.pig.TableStorer('[MLF_viewinfo]'); + +a2 = LOAD '/data/collection_viewinfo1' USING org.apache.hadoop.zebra.pig.TableLoader('MLF_viewinfo'); +--limitedVals = LIMIT a2 10; +--dump limitedVals; + + +store a2 into '/data/collection_viewinfo2' using org.apache.hadoop.zebra.pig.TableStorer('[MLF_viewinfo]'); + + Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/config URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/config?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/config (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/config Thu Dec 24 16:28:16 2009 @@ -0,0 +1,5 @@ +zebraJar=/grid/0/dev/hadoopqa/jars/zebra.jar +inputDir=/data/zebraStress/input +outputDir=/data/zebraStress/output +unsorted1=unsorted1 +unsorted2=unsorted2 Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/join.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/join.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/join.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/join.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,18 @@ +register $zebraJar; +--fs -rmr $outputDir + + + +rec1 = load '$outputDir/u1' using org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1', 'sorted'); +rec2 = load '$outputDir/u2' using org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1', 'sorted'); + + +joina = join rec1 by long1, rec2 by long1 using "merge" ; + +E = foreach joina generate $0 as count, $1 as seed, $2 as int1, $3 as str2, $4 as long1; +joinE = order E by long1 parallel 25; + + + +store joinE into '$outputDir/j1' using org.apache.hadoop.zebra.pig.TableStorer(''); + Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/join2.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/join2.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/join2.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/join2.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,18 @@ +register $zebraJar; +--fs -rmr $outputDir + + + +rec1 = load '$outputDir/u3' using org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1', 'sorted'); +rec2 = load '$outputDir/u4' using org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1', 'sorted'); + + +joina = join rec1 by long1, rec2 by long1 using "merge" ; + +E = foreach joina generate $0 as count, $1 as seed, $2 as int1, $3 as str2, $4 as long1; +joinE = order E by long1 parallel 25; + + + +store joinE into '$outputDir/j2' using org.apache.hadoop.zebra.pig.TableStorer(''); + Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/join_after_union.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/join_after_union.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/join_after_union.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/join_after_union.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,39 @@ +register $zebraJar; +--fs -rmr $outputDir + + +a1 = LOAD '$inputDir/25Munsorted1' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1'); +a2 = LOAD '$inputDir/25Munsorted2' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1'); +a3 = LOAD '$inputDir/25Munsorted3' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1'); +a4 = LOAD '$inputDir/25Munsorted4' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1'); + +sort1 = order a1 by long1; +sort2 = order a2 by long1; +sort3 = order a3 by long1; +sort4 = order a4 by long1; + +store sort1 into '$outputDir/25Msorted1' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); +store sort2 into '$outputDir/25Msorted2' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); +store sort3 into '$outputDir/25Msorted3' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); +store sort4 into '$outputDir/25Msorted4' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); + + +joinl = LOAD '$outputDir/25Msorted1,$outputDir/25Msorted2' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1', 'sorted'); +joinll = order joinl by long1; +store joinll into '$outputDir/unionl' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); + + +joinr = LOAD '$outputDir/25Msorted3,$outputDir/25Msorted4' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1', 'sorted'); +joinrr = order joinr by long1; +store joinrr into '$outputDir/unionr' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); + + +rec1 = load '$outputDir/unionl' using org.apache.hadoop.zebra.pig.TableLoader(); +rec2 = load '$outputDir/unionr' using org.apache.hadoop.zebra.pig.TableLoader(); + + +joina = join rec1 by long1, rec2 by long1 using "merge" ; + +E = foreach joina generate $0 as count, $1 as seed, $2 as int1, $3 as str2, $4 as long1; + +store E into '$outputDir/join_after_union_1' using org.apache.hadoop.zebra.pig.TableStorer(''); Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/join_after_union10k.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/join_after_union10k.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/join_after_union10k.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/join_after_union10k.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,43 @@ +register $zebraJar; +--fs -rmr $outputDir + + +a1 = LOAD '$inputDir/10k1' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1'); +a2 = LOAD '$inputDir/10k2' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1'); +a3 = LOAD '$inputDir/10k3' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1'); +a4 = LOAD '$inputDir/10k4' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1'); + +sort1 = order a1 by long1 parallel 6; +sort2 = order a2 by long1 parallel 5; +sort3 = order a3 by long1 parallel 7; +sort4 = order a4 by long1 parallel 4; + +store sort1 into '$outputDir/sortedlong110k1' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); +store sort2 into '$outputDir/sortedlong110k2' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); +store sort3 into '$outputDir/sortedlong110k3' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); +store sort4 into '$outputDir/sortedlong110k4' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); + + +joinl = LOAD '$outputDir/sortedlong110k1,$outputDir/sortedlong110k2' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1', 'sorted'); +joinll = order joinl by long1 parallel 7; +store joinll into '$outputDir/union10kl' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); + + +joinr = LOAD '$outputDir/sortedlong110k3,$outputDir/sortedlong110k4' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1', 'sorted'); +joinrr = order joinr by long1 parallel 4; +store joinrr into '$outputDir/union10kr' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); + + +rec1 = load '$outputDir/union10kl' using org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1', 'sorted'); +rec2 = load '$outputDir/union10kr' using org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1', 'sorted'); + + +joina = join rec1 by long1, rec2 by long1 using "merge" ; + +E = foreach joina generate $0 as count, $1 as seed, $2 as int1, $3 as str2, $4 as long1; +joinE = order E by long1 parallel 25; + +limitedVals = LIMIT joina 10; +dump limitedVals; + +store joinE into '$outputDir/join_after_union_10k' using org.apache.hadoop.zebra.pig.TableStorer(''); Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/join_after_union2.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/join_after_union2.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/join_after_union2.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/join_after_union2.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,39 @@ +register $zebraJar; +--fs -rmr $outputDir + + +--a1 = LOAD '$inputDir/25Munsorted1' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1'); +--a2 = LOAD '$inputDir/25Munsorted2' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1'); +--a3 = LOAD '$inputDir/25Munsorted3' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1'); +--a4 = LOAD '$inputDir/25Munsorted4' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1'); + +--sort1 = order a1 by long1 parallel 6; +--sort2 = order a2 by long1 parallel 5; +--sort3 = order a3 by long1 parallel 7; +--sort4 = order a4 by long1 parallel 4; + +--store sort1 into '$outputDir/25Msorted11' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); +--store sort2 into '$outputDir/25Msorted21' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); +--store sort3 into '$outputDir/25Msorted31' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); +--store sort4 into '$outputDir/25Msorted41' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); + + +joinl = LOAD '$outputDir/25Msorted11,$outputDir/25Msorted21' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1', 'sorted'); +joinll = order joinl by long1 parallel 7; +store joinll into '$outputDir/unionl1' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); + + +joinr = LOAD '$outputDir/25Msorted31,$outputDir/25Msorted41' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1', 'sorted'); +joinrr = order joinr by long1 parallel 4; +store joinrr into '$outputDir/unionr1' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); + + +rec1 = load '$outputDir/unionl1' using org.apache.hadoop.zebra.pig.TableLoader(); +rec2 = load '$outputDir/unionr1' using org.apache.hadoop.zebra.pig.TableLoader(); + + +joina = join rec1 by long1, rec2 by long1 using "merge" ; + +E = foreach joina generate $0 as count, $1 as seed, $2 as int1, $3 as str2, $4 as long1; +joinE = order E by long1 parallel 25; +store joinE into '$outputDir/join_after_union_11' using org.apache.hadoop.zebra.pig.TableStorer(''); Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/join_after_union3.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/join_after_union3.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/join_after_union3.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/join_after_union3.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,43 @@ +register $zebraJar; +--fs -rmr $outputDir + + +--a1 = LOAD '$inputDir/25Munsorted1' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1'); +--a2 = LOAD '$inputDir/25Munsorted2' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1'); +--a3 = LOAD '$inputDir/25Munsorted3' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1'); +--a4 = LOAD '$inputDir/25Munsorted4' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1'); + +--sort1 = order a1 by long1 parallel 6; +--sort2 = order a2 by long1 parallel 5; +--sort3 = order a3 by long1 parallel 7; +--sort4 = order a4 by long1 parallel 4; + +--store sort1 into '$outputDir/25Msorted11' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); +--store sort2 into '$outputDir/25Msorted21' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); +--store sort3 into '$outputDir/25Msorted31' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); +--store sort4 into '$outputDir/25Msorted41' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); + + +--joinl = LOAD '$outputDir/25Msorted11,$outputDir/25Msorted21' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1', 'sorted'); +--joinll = order joinl by long1 parallel 7; +--store joinll into '$outputDir/unionl1' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); + + +--joinr = LOAD '$outputDir/25Msorted31,$outputDir/25Msorted41' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1', 'sorted'); +--joinrr = order joinr by long1 parallel 4; +--store joinrr into '$outputDir/unionr1' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); + + +rec1 = load '$outputDir/unionl1' using org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1', 'sorted'); +rec2 = load '$outputDir/unionr1' using org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1', 'sorted'); + + +joina = join rec1 by long1, rec2 by long1 using "merge" ; + +E = foreach joina generate $0 as count, $1 as seed, $2 as int1, $3 as str2, $4 as long1; +joinE = order E by long1 parallel 25; + +--limitedVals = LIMIT joina 10; +--dump limitedVals; + +store joinE into '$outputDir/join_after_union_13' using org.apache.hadoop.zebra.pig.TableStorer(''); Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/join_jira.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/join_jira.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/join_jira.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/join_jira.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,40 @@ +register $zebraJar; +--fs -rmr $outputDir + +--a1 = LOAD '$inputDir/10k1' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1'); +--a2 = LOAD '$inputDir/10k2' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1'); +--a3 = LOAD '$inputDir/10k3' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1'); +--a4 = LOAD '$inputDir/10k4' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1'); + +--sort1 = order a1 by long1 parallel 6; +--sort2 = order a2 by long1 parallel 5; +--sort3 = order a3 by long1 parallel 7; +--sort4 = order a4 by long1 parallel 4; + +--store sort1 into '$outputDir/sortedlong110k1' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); +--store sort2 into '$outputDir/sortedlong110k2' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); +--store sort3 into '$outputDir/sortedlong110k3' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); +--store sort4 into '$outputDir/sortedlong110k4' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); + +joinl = LOAD '$outputDir/sortedlong110k1,$outputDir/sortedlong110k2' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1', 'sorted'); +--joinll = order joinl by long1 parallel 7; +--store joinll into '$outputDir/union10kl' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); + +joinr = LOAD '$outputDir/sortedlong110k3,$outputDir/sortedlong110k4' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1', 'sorted'); +--joinrr = order joinr by long1 parallel 4; +--store joinrr into '$outputDir/union10kr' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); + +--rec1 = load '$outputDir/union10kl' using org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1', 'sorted'); +--rec2 = load '$outputDir/union10kr' using org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1', 'sorted'); + +--joina = join rec1 by long1, rec2 by long1 using "merge" ; + +joina = join joinl by long1, joinr by long1 using "merge" ; + +E = foreach joina generate $0 as count, $1 as seed, $2 as int1, $3 as str2, $4 as long1; +joinE = order E by long1 parallel 25; + +limitedVals = LIMIT joinE 10; +dump limitedVals; + +store joinE into '$outputDir/join_jira' using org.apache.hadoop.zebra.pig.TableStorer(''); Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/join_jira1.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/join_jira1.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/join_jira1.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/join_jira1.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,27 @@ +register /grid/0/dev/hadoopqa/jars/zebra.jar; + +--a1 = load '1.txt' as (a:int, b:float,c:long,d:double,e:chararray,f:bytearray,r1(f1:chararray,f2:chararray),m1:map[]); +--a2 = load '2.txt' as (a:int, b:float,c:long,d:double,e:chararray,f:bytearray,r1(f1:chararray,f2:chararray),m1:map[]); + +--sort1 = order a1 by a parallel 6; +--sort2 = order a2 by a parallel 5; + +--store sort1 into 'asort1' using org.apache.hadoop.zebra.pig.TableStorer('[a,b,c,d]'); +--store sort2 into 'asort2' using org.apache.hadoop.zebra.pig.TableStorer('[a,b,c,d]'); +--store sort1 into 'asort3' using org.apache.hadoop.zebra.pig.TableStorer('[a,b,c,d]'); +--store sort2 into 'asort4' using org.apache.hadoop.zebra.pig.TableStorer('[a,b,c,d]'); + +joinl = LOAD 'asort1,asort2' USING org.apache.hadoop.zebra.pig.TableLoader('a,b,c,d', 'sorted'); + +joinr = LOAD 'asort3,asort4' USING org.apache.hadoop.zebra.pig.TableLoader('a,b,c,d', 'sorted'); + + +joina = join joinl by a, joinr by a using "merge" ; +dump joina; +--E = foreach joina generate $0 as count, $1 as seed, $2 as int1, $3 as str2, $4 as long1; +--joinE = order E by long1 parallel 25; + +--limitedVals = LIMIT joinE 10; +--dump limitedVals; + +--store joinE into 'join_jira' using org.apache.hadoop.zebra.pig.TableStorer(''); Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/readme URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/readme?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/readme (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/readme Thu Dec 24 16:28:16 2009 @@ -0,0 +1,10 @@ +1. run pig scritp,for example, +java -cp /grid/0/dev/hadoopqa/jing1234/conf:/grid/0/dev/hadoopqa/jars/pig.jar:/grid/0/dev/hadoopqa/jars/tfile.jar:/grid/0/dev/hadoopqa/jars/zebra.jar org.apache.pig.Main -m config -M stress_union_02.pig + +2.compile ToolTestComparator.java from contrib/zebra/src/test/org/apache/hadoop/zebra/mapred/ToolTestComparator.java +and ship the ToolTestComparator.class to cluster +run the tool to verifiy, for example, +java -DwhichCluster="realCluster" -DHADOOP_HOME=$HADOOP_HOME -DUSER=$USER org.apache.hadoop.zebra.mapred.ToolTestComparator -verifyOption merge-join -pathTable1 /data/zebraStress/output/join4 -sortCol 4 -numbCols 5 -sortString byte1,int1 + +3. For details on how to run,please refer to +http://twiki.corp.yahoo.com/pub/Grid/Release2TestPlan/zebra_stress_test.html Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/sortSimpleString.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/sortSimpleString.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/sortSimpleString.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/sortSimpleString.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,9 @@ +register /grid/0/dev/hadoopqa/jars/zebra.jar; + +--test case : unsort table is /data/all1, sort table is /data/bcookie_sort, sort on bcookie + +a1 = LOAD '/data/all1' USING org.apache.hadoop.zebra.pig.TableLoader(); + +a1order = order a1 by SF_bcookie; + +STORE a1order INTO '/data/bcookie_sort' USING org.apache.hadoop.zebra.pig.TableStorer('[SF_bcookie,SF_yuid,SF_ip];[SF_action,SF_afcookie,SF_browser,SF_bucket,SF_cbrn,SF_csc,SF_datestamp,SF_dst_spaceid,SF_dstid,SF_dstpvid,SF_error,SF_match_ts,SF_media,SF_ms,SF_os,SF_pcookie,SF_pg_load_time,SF_pg_size,SF_pg_spaceid,SF_query_term,SF_referrer,SF_server_code,SF_src_spaceid,SF_srcid,SF_srcpvid,SF_timestamp,SF_type,SF_ultspaceid,SF_ydod,MF_demog];[MF_page_params,MF_clickinfo,MLF_viewinfo]'); Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_join_01.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_join_01.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_join_01.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_join_01.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,23 @@ + +register $zebraJar; +--fs -rmr $outputDir + + +--a1 = LOAD '$inputDir/unsorted1' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2'); +--a2 = LOAD '$inputDir/unsorted2' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2'); + +--sort1 = order a1 by str2; +--sort2 = order a2 by str2; + +--store sort1 into '$outputDir/sorted11' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2]'); +--store sort2 into '$outputDir/sorted21' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2]'); + +rec1 = load '$outputDir/sorted11' using org.apache.hadoop.zebra.pig.TableLoader(); +rec2 = load '$outputDir/sorted21' using org.apache.hadoop.zebra.pig.TableLoader(); + +joina = join rec1 by str2, rec2 by str2 using "merge" ; + +E = foreach joina generate $0 as count, $1 as seed, $2 as int1, $3 as str2; + + +store E into '$outputDir/join1' using org.apache.hadoop.zebra.pig.TableStorer(''); Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_join_02.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_join_02.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_join_02.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_join_02.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,22 @@ + +register $zebraJar; +--fs -rmr $outputDir + + +a1 = LOAD '$inputDir/unsorted1' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2'); +a2 = LOAD '$inputDir/unsorted2' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2'); + +sort1 = order a1 by str2; +sort2 = order a2 by str2; + +store sort1 into '$outputDir/100Msortedstr21' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2]'); +store sort2 into '$outputDir/100Msortedstr22' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2]'); + +rec1 = load '$outputDir/100Msortedstr21' using org.apache.hadoop.zebra.pig.TableLoader('','sorted'); +rec2 = load '$outputDir/100Msortedstr22' using org.apache.hadoop.zebra.pig.TableLoader('','sorted'); + +joina = join rec1 by str2, rec2 by str2 using "merge" ; + +E = foreach joina generate $0 as count, $1 as seed, $2 as int1, $3 as str2; + +store E into '$outputDir/join2' using org.apache.hadoop.zebra.pig.TableStorer(''); Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_join_03.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_join_03.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_join_03.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_join_03.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,22 @@ + +register $zebraJar; +--fs -rmr $outputDir + + +a1 = LOAD '$inputDir/unsorted1' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,byte2'); +a2 = LOAD '$inputDir/unsorted2' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,byte2'); + +sort1 = order a1 by byte2; +sort2 = order a2 by byte2; + +store sort1 into '$outputDir/100Msortedbyte21' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,byte2]'); +store sort2 into '$outputDir/100Msortedbyte22' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,byte2]'); + +rec1 = load '$outputDir/100Msortedbyte21' using org.apache.hadoop.zebra.pig.TableLoader('','sorted'); +rec2 = load '$outputDir/100Msortedbyte22' using org.apache.hadoop.zebra.pig.TableLoader('','sorted'); + +joina = join rec1 by byte2, rec2 by byte2 using "merge" ; + +E = foreach joina generate $0 as count, $1 as seed, $2 as int1, $3 as str2, $4 as byte2; + +store E into '$outputDir/join3' using org.apache.hadoop.zebra.pig.TableStorer(''); Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_join_04.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_join_04.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_join_04.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_join_04.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,32 @@ + +register $zebraJar; +--fs -rmr $outputDir + + +--a1 = LOAD '$inputDir/unsorted1' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,byte1'); +--a2 = LOAD '$inputDir/unsorted2' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,byte1'); + +--sort1 = order a1 by byte1,int1; +--sort2 = order a2 by byte1,int1; + +--store sort1 into '$outputDir/sortedbyteint1' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,byte1]'); +--store sort2 into '$outputDir/sortedbyteint2' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,byte1]'); + +rec1 = load '$outputDir/sortedbyteint1' using org.apache.hadoop.zebra.pig.TableLoader(); +rec2 = load '$outputDir/sortedbyteint2' using org.apache.hadoop.zebra.pig.TableLoader(); + +joina = join rec1 by (byte1,int1), rec2 by (byte1,int1) using "merge" ; + +E = foreach joina generate $0 as count, $1 as seed, $2 as int1, $3 as str2, $4 as byte1; + + +--limitedVals = LIMIT E 5; +--dump limitedVals; + +--store E into '$outputDir/join4' using org.apache.hadoop.zebra.pig.TableStorer(''); + + +join4 = load '$outputDir/join4' using org.apache.hadoop.zebra.pig.TableLoader(); +orderjoin = order join4 by byte1,int1; +store orderjoin into '$outputDir/join4_order' using org.apache.hadoop.zebra.pig.TableStorer(''); + Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_join_05.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_join_05.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_join_05.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_join_05.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,21 @@ + +register /grid/0/dev/hadoopqa/jars/zebra.jar; + +a1 = LOAD '/user/hadoopqa/zebra/data/unsorted1' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2'); +a2 = LOAD '/user/hadoopqa/zebra/data/unsorted2' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2'); + +sort1 = order a1 by str2; +sort2 = order a2 by str2; + +store sort1 into '/user/hadoopqa/zebra/temp/sorted1' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2]'); +store sort2 into '/user/hadoopqa/zebra/temp/sorted2' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2]'); + +rec1 = load '/user/hadoopqa/zebra/temp/sorted1' using org.apache.hadoop.zebra.pig.TableLoader(); +rec2 = load '/user/hadoopqa/zebra/temp/sorted2' using org.apache.hadoop.zebra.pig.TableLoader(); + +joina = join rec1 by str2, rec2 by str2 using "merge" ; + +limitedVals = LIMIT joina 5; +dump limitedVals; + +--store joina into '/user/hadoopqa/zebra/temp/join1' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2];[count,seed,int1,str2]'); Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_load_store_00.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_load_store_00.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_load_store_00.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_load_store_00.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,17 @@ +register $zebraJar; +fs -rmr $outputDir + +a1 = LOAD '$inputDir/$unsorted1' USING org.apache.hadoop.zebra.pig.TableLoader('m1'); +--limitedVals = LIMIT a1 10; +--dump limitedVals; + +store a1 into '$outputDir/store1' using org.apache.hadoop.zebra.pig.TableStorer('[m1]'); + +a2 = LOAD '$outputDir/store1' USING org.apache.hadoop.zebra.pig.TableLoader('m1'); +--limitedVals = LIMIT a2 10; +--dump limitedVals; + + +store a2 into '$outputDir/store2' using org.apache.hadoop.zebra.pig.TableStorer('[m1]'); + + Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_load_store_01.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_load_store_01.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_load_store_01.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_load_store_01.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,17 @@ +register $zebraJar; +fs -rmr $outputDir + +a1 = LOAD '$inputDir/$unsorted1' USING org.apache.hadoop.zebra.pig.TableLoader(); +--limitedVals = LIMIT a1 10; +--dump limitedVals; + +store a1 into '$outputDir/store1' using org.apache.hadoop.zebra.pig.TableStorer(''); + +a2 = LOAD '$outputDir/store1' USING org.apache.hadoop.zebra.pig.TableLoader(); +--limitedVals = LIMIT a2 10; +--dump limitedVals; + + +store a2 into '$outputDir/store2' using org.apache.hadoop.zebra.pig.TableStorer(''); + + Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_load_store_02.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_load_store_02.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_load_store_02.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_load_store_02.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,27 @@ +register $zebraJar; +--fs -rmr $outputDir + + + +--a1 = LOAD '$inputDir/unsorted1' USING org.apache.hadoop.zebra.pig.TableLoader('int1,int2,str1,str2,byte1,byte2'); +--limitedVals = LIMIT a1 10; +--dump limitedVals; + +--store a1 into '$outputDir/mix1' using org.apache.hadoop.zebra.pig.TableStorer('[int1];[int2];[byte2];[str2,str1]'); + +--a2 = LOAD '$outputDir/mix1' USING org.apache.hadoop.zebra.pig.TableLoader('byte2,int2,int1,str1,str2'); +--limitedVals = LIMIT a2 10; +--dump limitedVals; + + +--store a2 into '$outputDir/mix1_2' using org.apache.hadoop.zebra.pig.TableStorer('[int1];[int2];[byte2];[str2,str1]'); + +a3 = LOAD '$outputDir/mix1_2' USING org.apache.hadoop.zebra.pig.TableLoader('byte2,int2,int1,str1,str2'); +--limitedVals = LIMIT a2 10; +--dump limitedVals; + + +store a3 into '$outputDir/mix1_1' using org.apache.hadoop.zebra.pig.TableStorer('[int1];[int2];[byte2];[str2,str1]'); + +--if only store once, and compare mix1 with mix1_1, table one has column number 6, table two has 5 (default column for table one) +--now we should compare mix1_1 and mix1_2 . they should be idential Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_load_store_03.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_load_store_03.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_load_store_03.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_load_store_03.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,16 @@ +register $zebraJar; +--fs -rmr $outputDir + + +a1 = LOAD '$inputDir/unsorted1' USING org.apache.hadoop.zebra.pig.TableLoader('m1'); +--limitedVals = LIMIT a1 10; +--dump limitedVals; + +store a1 into '$outputDir/store1' using org.apache.hadoop.zebra.pig.TableStorer('[m1]'); + +a2 = LOAD '$outputDir/store1' USING org.apache.hadoop.zebra.pig.TableLoader('m1'); +--limitedVals = LIMIT a2 10; +--dump limitedVals; + + +store a2 into '$outputDir/store2' using org.apache.hadoop.zebra.pig.TableStorer('[m1]'); Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_load_store_04.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_load_store_04.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_load_store_04.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_load_store_04.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,18 @@ +register $zebraJar; +--fs -rmr $outputDir + + + +a1 = LOAD '$inputDir/unsorted1' USING org.apache.hadoop.zebra.pig.TableLoader('c1'); +--limitedVals = LIMIT a1 10; +--dump limitedVals; + +store a1 into '$outputDir/c1' using org.apache.hadoop.zebra.pig.TableStorer('[c1]'); + +a2 = LOAD '$outputDir/c1' USING org.apache.hadoop.zebra.pig.TableLoader('c1'); +--limitedVals = LIMIT a2 10; +--dump limitedVals; + + +store a2 into '$outputDir/c1_2' using org.apache.hadoop.zebra.pig.TableStorer('[c1]'); + Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_load_store_05.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_load_store_05.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_load_store_05.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_load_store_05.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,27 @@ +register $zebraJar; +--fs -rmr $outputDir + + + +a1 = LOAD '$inputDir/unsorted1' USING org.apache.hadoop.zebra.pig.TableLoader('int1,int2,str1,str2,byte1,byte2,r1'); +--limitedVals = LIMIT a1 10; +--dump limitedVals; + +store a1 into '$outputDir/r1' using org.apache.hadoop.zebra.pig.TableStorer('[int1];[int2];[byte2];[str2,str1,r1]'); + +a2 = LOAD '$outputDir/r1' USING org.apache.hadoop.zebra.pig.TableLoader('byte2,int2,int1,str1,str2,r1'); +--limitedVals = LIMIT a2 10; +--dump limitedVals; + + +store a2 into '$outputDir/r1_2' using org.apache.hadoop.zebra.pig.TableStorer('[int1];[int2];[byte2];[str2,str1,r1]'); + +a3 = LOAD '$outputDir/r1_2' USING org.apache.hadoop.zebra.pig.TableLoader('byte2,int2,int1,str1,str2,r1'); +--limitedVals = LIMIT a2 10; +--dump limitedVals; + + +store a3 into '$outputDir/r1_1' using org.apache.hadoop.zebra.pig.TableStorer('[int1];[int2];[byte2];[str2,str1,r1]'); + +--if only store once, and compare r1 with r1_1, table one has column number 6, table two has 5 (default column for table one) +--now we should compare r1_1 and r1_2 . they should be identia Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_sort_01.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_sort_01.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_sort_01.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_sort_01.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,11 @@ +register $zebraJar; +--fs -rmr $outputDir + + +a1 = LOAD '$inputDir/$unsorted1' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,int2,str1,str2,byte1,byte2,float1,long1,double1,m1,r1,c1'); + +store a1 into '$outputDir/unsorted1' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,int2,str1,str2,byte1,byte2,float1,long1,double1];[m1#{a}];[r1,c1]'); + +sort1 = ORDER a1 BY int2; + +store sort1 into '$outputDir/sorted111' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,int2,str1,str2,byte1,byte2,float1,long1,double1];[m1#{a}];[r1,c1]'); Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_sort_01_save.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_sort_01_save.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_sort_01_save.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_sort_01_save.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,11 @@ + + +register /grid/0/dev/hadoopqa/jars/zebra.jar; + +a1 = LOAD '/user/hadoopqa/zebra/data/unsorted1' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2'); + +store a1 into '/user/hadoopqa/zebra/temp/unsorted1' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2]'); + +sort1 = ORDER a1 BY str2; + +store sort1 into '/user/hadoopqa/zebra/temp/sorted1' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2]'); Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_sort_02.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_sort_02.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_sort_02.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_sort_02.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,11 @@ +register $zebraJar; +--fs -rmr $outputDir + + +a1 = LOAD '$inputDir/$unsorted1' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,int2,str1,str2,byte1,byte2,float1,long1,double1,m1,r1,c1'); + +--store a1 into '$outputDir/unsortedbyte2' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,int2,str1,str2,byte1,byte2,float1,long1,double1];[m1#{a}];[r1,c1]'); + +sort1 = ORDER a1 BY byte2; + +store sort1 into '$outputDir/sortedbyte2_1' using org.apache.hadoop.zebra.pig.TableStorer('[seed,int1,int2,str1,str2,byte1,byte2,float1,long1,double1];[m1#{a},r1,c1]'); Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_sort_03.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_sort_03.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_sort_03.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_sort_03.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,11 @@ +register $zebraJar; +--fs -rmr $outputDir + + +a1 = LOAD '$inputDir/$unsorted1' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,int2,str1,str2,byte1,byte2,float1,long1,double1,m1,r1,c1'); + +--store a1 into '$outputDir/unsortedbyte2' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,int2,str1,str2,byte1,byte2,float1,long1,double1];[m1#{a}];[r1,c1]'); + +sort1 = ORDER a1 BY byte2; + +store sort1 into '$outputDir/sortedbyte2_1' using org.apache.hadoop.zebra.pig.TableStorer('[seed,int1,int2,str1,str2,byte1,byte2,float1,long1,double1];[m1#{a},r1,c1]'); Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_union_01.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_union_01.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_union_01.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_union_01.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,20 @@ +register $zebraJar; +--fs -rmr $outputDir + + +--a1 = LOAD '$inputDir/25Munsorted1' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int2,str2,byte2'); +--a2 = LOAD '$inputDir/25Munsorted2' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int2,str2,byte2'); + +--sort1 = order a1 by int2; +--sort2 = order a2 by int2; + +--store sort1 into '$outputDir/sortedint21' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int2,str2,byte2]'); +--store sort2 into '$outputDir/sortedint22' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int2,str2,byte2]'); + +rec1 = load '$outputDir/sortedint21' using org.apache.hadoop.zebra.pig.TableLoader(); +rec2 = load '$outputDir/sortedint22' using org.apache.hadoop.zebra.pig.TableLoader(); + +joina = LOAD '$outputDir/sortedint21,$outputDir/sortedint22' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int2,str2,byte2', 'sorted'); + +joinaa = order joina by int2; +store joinaa into '$outputDir/union1' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int2,str2,byte2]'); Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_union_02.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_union_02.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_union_02.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_union_02.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,20 @@ +register $zebraJar; +--fs -rmr $outputDir + + +a1 = LOAD '$inputDir/25Munsorted1' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,byte1'); +a2 = LOAD '$inputDir/25Munsorted2' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,byte1'); + +sort1 = order a1 by byte1; +sort2 = order a2 by byte1; + +--store sort1 into '$outputDir/sortedbyte1' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,byte1]'); +--store sort2 into '$outputDir/sortedbyte2' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,byte1]'); + +rec1 = load '$outputDir/sortedbyte1' using org.apache.hadoop.zebra.pig.TableLoader(); +rec2 = load '$outputDir/sortedbyte2' using org.apache.hadoop.zebra.pig.TableLoader(); + +joina = LOAD '$outputDir/sortedbyte1,$outputDir/sortedbyte2' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,byte1', 'sorted'); + +joinaa = order joina by byte1; +store joinaa into '$outputDir/union2' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,byte1]'); Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_union_02_2.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_union_02_2.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_union_02_2.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_union_02_2.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,20 @@ +register $zebraJar; +--fs -rmr $outputDir + + +a1 = LOAD '$inputDir/25Munsorted3' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,byte1'); +a2 = LOAD '$inputDir/25Munsorted4' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,byte1'); + +sort1 = order a1 by byte1; +sort2 = order a2 by byte1; + +store sort1 into '$outputDir/sortedbyte3' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,byte1]'); +store sort2 into '$outputDir/sortedbyte4' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,byte1]'); + +rec1 = load '$outputDir/sortedbyte3' using org.apache.hadoop.zebra.pig.TableLoader(); +rec2 = load '$outputDir/sortedbyte4' using org.apache.hadoop.zebra.pig.TableLoader(); + +joina = LOAD '$outputDir/sortedbyte3,$outputDir/sortedbyte4' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,byte1', 'sorted'); + + +store joina into '$outputDir/union2_2' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,byte1]'); Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_union_03.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_union_03.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_union_03.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_union_03.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,22 @@ +register $zebraJar; +--fs -rmr $outputDir + + +a1 = LOAD '$inputDir/25Munsorted3' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2'); +a2 = LOAD '$inputDir/25Munsorted4' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2'); + +sort1 = order a1 by str2; +sort2 = order a2 by str2; + +--store sort1 into '$outputDir/strsorted1' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2]'); +--store sort2 into '$outputDir/strsorted2' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2]'); + +rec1 = load '$outputDir/strsorted1' using org.apache.hadoop.zebra.pig.TableLoader(); +rec2 = load '$outputDir/strsorted2' using org.apache.hadoop.zebra.pig.TableLoader(); + +joina = LOAD '$outputDir/strsorted1,$outputDir/strsorted2' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2', 'sorted'); + +joinaa = order joina by str2; + +store joinaa into '$outputDir/union3' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2]'); + Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_union_04.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_union_04.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_union_04.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/stress_union_04.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,20 @@ +register $zebraJar; +--fs -rmr $outputDir + + +--a1 = LOAD '$inputDir/25Munsorted1' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int2,str2,byte2'); +--a2 = LOAD '$inputDir/25Munsorted2' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int2,str2,byte2'); + +--sort1 = order a1 by int2,byte2; +--sort2 = order a2 by int2,byte2; + +--store sort1 into '$outputDir/sortedintbyte21' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int2,str2,byte2]'); +--store sort2 into '$outputDir/sortedintbyte22' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int2,str2,byte2]'); + +rec1 = load '$outputDir/sortedintbyte21' using org.apache.hadoop.zebra.pig.TableLoader(); +rec2 = load '$outputDir/sortedintbyte22' using org.apache.hadoop.zebra.pig.TableLoader(); + +joina = LOAD '$outputDir/sortedintbyte21,$outputDir/sortedintbyte22' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int2,str2,byte2', 'sorted'); + +joinaa = order joina by int2,byte2; +store joinaa into '$outputDir/union4' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int2,str2,byte2]'); Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/testjoing1.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/testjoing1.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/testjoing1.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/testjoing1.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,23 @@ + +register $zebraJar; +--fs -rmr $outputDir + + +--a1 = LOAD '$inputDir/unsorted1' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2'); +--a2 = LOAD '$inputDir/unsorted2' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2'); + +--sort1 = order a1 by str2; +--sort2 = order a2 by str2; + +--store sort1 into '$outputDir/sorted11' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2]'); +--store sort2 into '$outputDir/sorted21' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2]'); + +rec1 = load '$outputDir/sorted11' using org.apache.hadoop.zebra.pig.TableLoader('','sorted'); +rec2 = load '$outputDir/sorted21' using org.apache.hadoop.zebra.pig.TableLoader('','sorted'); + +joina = join rec1 by str2, rec2 by str2 using "merge" ; + +E = foreach joina generate $0 as count, $1 as seed, $2 as int1, $3 as str2; + + +store E into '$outputDir/testjoin21' using org.apache.hadoop.zebra.pig.TableStorer(''); Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/union1.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/union1.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/union1.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/union1.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,17 @@ +register $zebraJar; +--fs -rmr $outputDir + + +a1 = LOAD '$inputDir/25Munsorted1' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1'); +a2 = LOAD '$inputDir/25Munsorted2' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1'); + +sort1 = order a1 by long1 parallel 6; +sort2 = order a2 by long1 parallel 5; + +store sort1 into '$outputDir/25MS1' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); +store sort2 into '$outputDir/25MS2' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); + + +union1 = LOAD '$outputDir/25MS1,$outputDir/25MS2' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1', 'sorted'); +orderunion1 = order union1 by long1 parallel 7; +store orderunion1 into '$outputDir/u1' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/union2.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/union2.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/union2.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/union2.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,17 @@ +register $zebraJar; +--fs -rmr $outputDir + + +a1 = LOAD '$inputDir/25Munsorted3' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1'); +a2 = LOAD '$inputDir/25Munsorted4' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1'); + +sort1 = order a1 by long1 parallel 6; +sort2 = order a2 by long1 parallel 5; + +store sort1 into '$outputDir/25MS3' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); +store sort2 into '$outputDir/25MS4' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); + + +union1 = LOAD '$outputDir/25MS3,$outputDir/25MS4' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1', 'sorted'); +orderunion1 = order union1 by long1 parallel 7; +store orderunion1 into '$outputDir/u2' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/union3.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/union3.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/union3.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/union3.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,17 @@ +register $zebraJar; +--fs -rmr $outputDir + + +a1 = LOAD '$inputDir/50Munsorted1' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1'); +a2 = LOAD '$inputDir/50Munsorted2' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1'); + +sort1 = order a1 by long1 parallel 6; +sort2 = order a2 by long1 parallel 5; + +store sort1 into '$outputDir/50MS1' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); +store sort2 into '$outputDir/50MS2' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); + + +union1 = LOAD '$outputDir/50MS1,$outputDir/50MS2' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1', 'sorted'); +orderunion1 = order union1 by long1 parallel 7; +store orderunion1 into '$outputDir/u3' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); Added: hadoop/pig/trunk/contrib/zebra/src/test/stress/union4.pig URL: http://svn.apache.org/viewvc/hadoop/pig/trunk/contrib/zebra/src/test/stress/union4.pig?rev=893785&view=auto ============================================================================== --- hadoop/pig/trunk/contrib/zebra/src/test/stress/union4.pig (added) +++ hadoop/pig/trunk/contrib/zebra/src/test/stress/union4.pig Thu Dec 24 16:28:16 2009 @@ -0,0 +1,17 @@ +register $zebraJar; +--fs -rmr $outputDir + + +a1 = LOAD '$inputDir/50Munsorted3' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1'); +a2 = LOAD '$inputDir/50Munsorted4' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1'); + +sort1 = order a1 by long1 parallel 6; +sort2 = order a2 by long1 parallel 5; + +store sort1 into '$outputDir/50MS3' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); +store sort2 into '$outputDir/50MS4' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]'); + + +union1 = LOAD '$outputDir/50MS3,$outputDir/50MS4' USING org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1', 'sorted'); +orderunion1 = order union1 by long1 parallel 7; +store orderunion1 into '$outputDir/u4' using org.apache.hadoop.zebra.pig.TableStorer('[count,seed,int1,str2,long1]');
