Looks like attachments are not coming through. Here is the script from Corbin inline.
One thing you might want to try is to switch your cogroups to skewed join and see if that solves the issue: http://hadoop.apache.org/pig/docs/r0.6.0/piglatin_ref1.html#Skewed+Joins Olga --------------------------------------------topurl.pig------------------ ------------------------------------------- set job.name 'Generate topurl reports for $out_file1' %default dir_prefix '../..' %default storage 'BinStorage()' %default tynt_udfs 'tynt-udfs.jar' %default topN '20' /* default to 30 days time period so that alltime report will get 14*30=420 min page views*/ %default timeperiod '30' %default min_page_views_per_day '14' register $dir_prefix/udfs/target/$tynt_udfs register $dir_prefix/udfs/lib/piggybank.jar ---------------------summarize address bar stats----------------------------------- addbar_stats = LOAD '$in_file1/addbarstats' USING $storage AS (site:chararray, url:chararray, guid:chararray, cnt:long); grouped_addbar_by_url = GROUP addbar_stats BY (site, url) PARALLEL 180; addbar_stats_by_url = FOREACH grouped_addbar_by_url GENERATE FLATTEN(group) AS (site, url), COUNT(addbar_stats) AS addbarcnt, SUM(addbar_stats.cnt) AS addbarvisits; STORE addbar_stats_by_url INTO '$out_file1/addbarstatsbyurl' USING $storage; grouped_addbar_stats_by_site = GROUP addbar_stats_by_url BY site PARALLEL 180; addbar_stats_by_site = FOREACH grouped_addbar_stats_by_site GENERATE group AS site, SUM(addbar_stats_by_url.addbarcnt) AS addbarcnt, SUM(addbar_stats_by_url.addbarvisits) AS addbarvisits; STORE addbar_stats_by_site INTO '$out_file1/addbarstatsbysite' USING $storage; ----------------------calculate ratio------------------------------------------ clickstatsbyurl = LOAD '$in_file1/clickstatsbyurl' USING $storage AS (site:chararray, url:chararray, cnt:long, tracecnt:long, tcnt:long, pcnt:long, wcnt:long, utracecnt:long, utcnt:long, upcnt:long, uwcnt:long); viewstatsbyurl = LOAD '$in_file1/viewstatsbyurl' USING $storage AS (site:chararray, url:chararray, title:chararray, cnt:long, etcnt:long, et1cnt:long, et2cnt:long, et3cnt:long, et6cnt:long, et7cnt:long); light_clickstatsbyurl = FOREACH clickstatsbyurl GENERATE site, url, cnt; light_viewstatsbyurl_noisy = FOREACH viewstatsbyurl GENERATE site, url, title, cnt, etcnt; light_viewstatsbyurl = FILTER light_viewstatsbyurl_noisy BY url != '-'; --light_addbarstatsbyurl = FOREACH addbar_stats_by_url GENERATE site, url, addbarvisits; --joined_stats_for_ratio = COGROUP light_viewstatsbyurl BY (site, url) INNER, light_clickstatsbyurl BY (site, url) OUTER, light_addbarstatsbyurl BY (site, url) OUTER; --flattened_stats_for_ratio = FOREACH joined_stats_for_ratio GENERATE FLATTEN(light_viewstatsbyurl) AS (site, url, title, cnt, etcnt), -- (IsEmpty(light_clickstatsbyurl)?0:MAX(light_clickstatsbyurl.cnt)) as clickcnt, -- (IsEmpty(light_addbarstatsbyurl)?0:MAX(light_addbarstatsbyurl.addbarvisi ts)) as addbarcnt; joined_stats_for_ratio = COGROUP light_viewstatsbyurl BY (site, url) INNER, light_clickstatsbyurl BY (site, url) OUTER; flattened_stats_for_ratio = FOREACH joined_stats_for_ratio GENERATE FLATTEN(light_viewstatsbyurl) AS (site, url, title, cnt, etcnt), (IsEmpty(light_clickstatsbyurl)?0:MAX(light_clickstatsbyurl.cnt)) as clickcnt; ratio_by_url = FOREACH flattened_stats_for_ratio { generated_traffic = clickcnt+etcnt; total_traffic = cnt; ti = ((float)(generated_traffic))/((float)total_traffic); GENERATE site, url, title, ((ti>1)?(-ti):ti) AS ratio, generated_traffic AS gviews, total_traffic AS views; } ------------------------combined with #copies---------------------------------------- copystatsbyurl = LOAD '$in_file1/copystatsbyurl' USING $storage AS (site:chararray, url:chararray, lcnt:long, scnt:long, icnt:long, acnt:long); light_copystatsbyurl = FOREACH copystatsbyurl GENERATE site, url, lcnt+scnt+icnt AS cnt; all_stats_by_url = COGROUP ratio_by_url BY (site, url) INNER, light_copystatsbyurl BY (site, url) OUTER PARALLEL 62; all_urls = FOREACH all_stats_by_url GENERATE FLATTEN(ratio_by_url) AS (site, url, title, ratio, gviews, views), (IsEmpty(light_copystatsbyurl)?0:MAX(light_copystatsbyurl.cnt)) as copies; grouped_urls_by_site = GROUP all_urls BY site; top_ratios = FOREACH grouped_urls_by_site { filtered_by_minpageviews = FILTER all_urls BY views > ($min_page_views_per_day*$timeperiod); order_by_ratio = ORDER filtered_by_minpageviews BY ratio DESC; top_by_ratio = LIMIT order_by_ratio $topN; GENERATE group AS site, top_by_ratio.(url, title, ratio, gviews, views, copies) AS tops; } top_gviews = FOREACH grouped_urls_by_site { order_by_gviews = ORDER all_urls BY gviews DESC; top_by_gviews = LIMIT order_by_gviews $topN; GENERATE group AS site, top_by_gviews.(url, title, ratio, gviews, views, copies) AS tops; } top_views = FOREACH grouped_urls_by_site { order_by_views = ORDER all_urls BY views DESC; top_by_views = LIMIT order_by_views $topN; GENERATE group AS site, top_by_views.(url, title, ratio, gviews, views, copies) AS tops; } top_copies = FOREACH grouped_urls_by_site { order_by_copies = ORDER all_urls BY copies DESC; top_by_copies = LIMIT order_by_copies $topN; GENERATE group AS site, top_by_copies.(url, title, ratio, gviews, views, copies) AS tops; } grouped_tops = JOIN top_ratios BY site, top_gviews BY site, top_views BY site, top_copies BY site; top_urls = FOREACH grouped_tops GENERATE top_ratios::site AS site, top_ratios::tops, top_gviews::tops, top_views::tops, top_copies::tops; store top_urls into '$out_file1/topurls' USING $storage; -----Original Message----- From: Corbin Hoenes [mailto:[email protected]] Sent: Thursday, May 06, 2010 11:57 AM To: Olga Natkovich Subject: Re: SpillableMemoryManager - low memory handler called I have attached the script... please let me know if you have more questions.
On May 6, 2010, at 12:36 PM, Olga Natkovich wrote: > This is just a warning saying that your job is spilling to the disk. > Please, if you can, post a script that is causing this issue. In 0.6.0 > we moved large chunk of the code away from using SpillableMemoryManager > but it is still used in some places. More changes are coming in 0.7.0 as > well. > > Olga > > -----Original Message----- > From: Corbin Hoenes [mailto:[email protected]] > Sent: Thursday, May 06, 2010 11:31 AM > To: [email protected] > Subject: Re: SpillableMemoryManager - low memory handler called > > 0.6 > > Sent from my iPhone > > On May 6, 2010, at 12:16 PM, "Olga Natkovich" <[email protected]> > wrote: > >> Which version of Pig are you using? >> >> -----Original Message----- >> From: Corbin Hoenes [mailto:[email protected]] >> Sent: Thursday, May 06, 2010 10:29 AM >> To: [email protected] >> Subject: SpillableMemoryManager - low memory handler called >> >> Hi Piggers - Seeing an issue with a particular script where our job is >> taking 6hrs 42min to complete. >> >> syslogs are showing loads of these: >> INFO : org.apache.pig.impl.util.SpillableMemoryManager - low memory >> handler called (Usage threshold exceeded) init = 5439488(5312K) used = >> 283443200(276800K) committed = 357957632(349568K) max = >> 357957632(349568K) >> INFO : org.apache.pig.impl.util.SpillableMemoryManager - low memory >> handler called (Usage threshold exceeded) init = 5439488(5312K) used = >> 267128840(260868K) committed = 357957632(349568K) max = >> 357957632(349568K) >> One iteresting thing is it's the map phase that is slow and one of the >> mappers is getting 8GB of input while the other 2000 or so mappers are >> getting MBs and hundreds of MBs of data. >> >> Any where I can start looking? >> >>
