[ https://issues.apache.org/jira/browse/HIVE-26383 ]
Pravin Sinha deleted comment on HIVE-26383:
-------------------------------------
was (Author: pkumarsinha):
The query file 'innerjoin_cal_with_insert' doesn't exist in trunk code. The
content is as follows:
{code:java}
set hive.mapred.mode=nonstrict;
set hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat;create
database db1;create table db1.tab1
( csid bigint,
type_n string,
c_c_a_c string,
cn_i_g string,
c_a_k_v string,
i_p_m string,
igd string,
iec string,
cavv string,
ptt string,
dev string,
vtt string,
apv string,
apv_ENR string,
mndm string,
aamad string,
pnwp string,
ictch string,
eie string,
saie string,
shipg_addr_ctry_nm string,
vco_flow_type string)
stored as PARQUET TBLPROPERTIES ("parquet.compress"="SNAPPY");
create table db1.tab2
(
csid bigint,
usr_sid bigint,
ENRLL_CHNL_TYP_NM string,
USR_PYMT_CHNL_TYP_NM string,
dflt_iso_ctry_cd bigint,
ENRLL_CTRY_NM string,
ENRLL_REGN_NM string,
ENRLL_REGN_CD string,
PYMT_INSTRMT_pntz string,
ptmp_TYP_CD string,
ptmp_TYP_NM string,
VCOP_Enroll_TS string,
VCOP_USER_FLAG string,
tti_gra_ISO_CTRY_CD string,
tti_gra_CTRY_NM string,
ciic_CTRY_CD string,
ciic_CTRY_NM string,
ciic_REGN_NM string,
ciic_REGN_CD string)
stored as PARQUET TBLPROPERTIES ("parquet.compress"="SNAPPY");
create table db1.tab3
(
csid bigint,
usr_extrnl_id string,
coreln_id string,
usr_Acct_typ_nm string,
tmpt_bejkl_pntz bigint,
tyui_bejkl_pntz bigint,
tmpt_bejkl_pntz_Intnt_tmpt_NM string,
tyui_bejkl_pntz_Intnt_tyui_NM string,
Intnt_Mrch_Ind string,
tmpt_API_KEY_VAL string,
Intnt_tmpt_NM string,
CLNT_TYP_NM string,
tmpt_ISO_CTRY_CD string,
tmpt_CTRY_NM string,
tmpt_REGN_CD string,
tmpt_REGN_NM string,
ctghi_GUID string,
ctghi_LGL_NM string,
ctghi_TRD_NM string,
ctghi_CTRY_NM string,
ctghi_RGN_NM string,
ctghi_RGN_CD string,
ctghi_CTRY_CD string,
Intnt_Mrch_Version string,
INTENT_gtslmnbprg_gst string,
tmpt_RM string,
tmpt_CTRY_CD string,
tmpt_LGL_NM string,
tmpt_oeiw string)
stored as PARQUET TBLPROPERTIES ("parquet.compress"="SNAPPY");create table
db1.tab4
(
csid bigint,
pymt_instrmt_extrnl_id string,
paresStatus string,
xid string,
Erica string,
hgty_BIN string,
ISS_gst string,
ISSUER_BID string,
hgty_CTRY_NM string,
hgty_CTRY_CD int,
hgty_REGN_NM string,
hgty_REGN_CD string,
ISS_HOLDG_BID_gst string,
ISS_HOLDING_BID int,
ptmp_BRND_CD string,
ACCT_NUM string,
RWRD_PGM_ID string,
RWRD_PGM_NM string,
RPIN_RLLUP_CD string,
tti_gra_PSTL_CD string,
tti_gra_PRVNC_CD string,
tkarh string)
stored as PARQUET TBLPROPERTIES ("parquet.compress"="SNAPPY");create table
db1.tab5
(
csid bigint,
latest_ts string,
Intnt_Month string,
CORELN_ID string,
Initiated_Flag string,
Initiated_Date string,
Initiated_ts string,
Completed_Flag string,
ERROR_FLAG string,
UPDATED_FLAG string,
Abandoned_Flag string,
TOKENIZED_FLAG string,
INTENT_3DS_FLAG string,
INTENT_CANCEL_FLAG string,
INTENT_FAILURE_FLAG string,
Completed_Date string,
Completed_ts string,
Successful_Flag string,
Successful_Date string,
Successful_ts string,
I_TTL_AMT string,
I_TTL_AMT_USD string,
C_TTL_AMT string,
C_TTL_AMT_USD string,
S_TTL_AMT string,
S_TTL_AMT_USD string)
stored as PARQUET TBLPROPERTIES ("parquet.compress"="SNAPPY");
create table db1.tab6
(
csid bigint,
browser_name string,
browser_version string,
browser_vendor string,
OS string,
DVC_TYP_NM string,
dceavt string)
stored as PARQUET TBLPROPERTIES ("parquet.compress"="SNAPPY");
create table db1.tab7
(
csid bigint,
cmpgn_callr_nm string,
cmpgn_callr_typ_nm string,
cmpgn_chnl_nm string,
cmpgn_extrnl_clnt_id string,
cmpgn_flw_nm string,
cmpgn_iso_ctry_cd bigint,
cmpgn_ni_callr_nm string,
cmpgn_ni_campgn_id string,
cmpgn_ni_cmpgn_nm string,
cmpgn_ni_flw_nm string,
cmpgn_ni_chnl_nm string,
cmpgn_ni_plcmnt_id string,
cmpgn_ni_prtflo_nm string,
cmpgn_ni_seg_nm string,
cmpgn_ni_site_id string,
cmpgn_rdrct_url_addr string,
cmpgn_usr_agnt_nm string,
cmpgn_clnt_api_key_id string,
CRDNL_vptpspgp_ID string )
stored as PARQUET TBLPROPERTIES ("parquet.compress"="SNAPPY");
create table db1.tab8
(
csid bigint,
ino_src_client_name string,
ino_srci_clnt_id string,
ino_usr_extrnl_id_typ_nm string,
ino_src_ntwrk_nm string,
ino_crptgm_typ string,
ino_client_typ_nm string,
ino_legal_name string,
ino_trade_name string,
pyt_upd_tran_typ_cd string,
pyt_upd_success_flg string)
stored as PARQUET TBLPROPERTIES ("parquet.compress"="SNAPPY");insert into
db1.tab1 values (1, '109515', null, 'test', 'test', '2018-01-10 15:03:55.0',
'2018-01-10', 109515, null, '45045501', 'id', null,'test', 'test', '2018-01-10
15:03:55.0', '2018-01-10', 109515, null, '45045501', 'id', null,null);
insert into db1.tab2 values (1, '109515', '11', 'test', '2018-01-10
15:03:55.0', '2018-01-10', 109515, null, '45045501', 'id', null,'test', 'test',
'2018-01-10 15:03:55.0', '2018-01-10', 109515, null, '45045501', 'id');
insert into db1.tab3 values (1, '109515', '11', 'test', '2018-01-10
15:03:55.0', '2018-01-10', 109515, null, '45045501', 'id', null,'test', 'test',
'2018-01-10 15:03:55.0', '2018-01-10', 109515, null, '45045501',
'id','2018-01-10', 109515, null, '45045501', 'id', null,'test', 'test',
'2018-01-10 15:03:55.0', '2018-01-10');
insert into db1.tab4 values (1, '109515', '11', 'test', '2018-01-10
15:03:55.0', '2018-01-10', 109515, null, '45045501', 'id', null,'test', 'test',
'2018-01-10 15:03:55.0', '2018-01-10', 109515, null, '45045501',
'id','2018-01-10', 109515, null);
insert into db1.tab5 values (1, '109515', '11', 'test', '2018-01-10
15:03:55.0', '2018-01-10', 109515, null, '45045501', 'id', null,'test', 'test',
'2018-01-10 15:03:55.0', '2018-01-10', 109515, null, '45045501',
'id','2018-01-10', 109515, null,'45045501', 'id', null,'test');
insert into db1.tab6 values (1, '109515', '11', 'test', '2018-01-10
15:03:55.0', '2018-01-10', 109515);
insert into db1.tab7 values (1, '109515', '11', 'test', '2018-01-10
15:03:55.0', '2018-01-10', 109515,1, '109515', '11', 'test', '2018-01-10
15:03:55.0', '2018-01-10', 109515,1, '109515', '11', 'test', '2018-01-10
15:03:55.0', '2018-01-10');
insert into db1.tab8 values (1, '109515', '11', 'test', '2018-01-10
15:03:55.0', '2018-01-10', 109515,1, '109515', '11', 'tes');
select * from db1.tab5 a5
inner join db1.tab1 a1
on a5.csid = a1.csid
inner join db1.tab2 a2
on a5.csid = a2.csid
inner join db1.tab3 a3
on a5.csid = a3.csid
inner join db1.tab4 a4
on a5.csid = a4.csid
inner join db1.tab6 a6
on a5.csid = a6.csid
inner join db1.tab7 a7
on a5.csid = a7.csid
--inner join addition of sub8
inner join db1.tab8 a8
on a5.csid = a8.csid;
{code}
> OOM during join query
> ---------------------
>
> Key: HIVE-26383
> URL: https://issues.apache.org/jira/browse/HIVE-26383
> Project: Hive
> Issue Type: Bug
> Reporter: Pravin Sinha
> Priority: Major
>
> {code:java}
> [ERROR]
> org.apache.hadoop.hive.cli.TestCliDriver.testCliDriver[innerjoin_cal_with_insert]
> Time elapsed: 100.73 s <<< ERROR!
> java.lang.OutOfMemoryError: GC overhead limit exceeded
> at java.util.HashMap.newTreeNode(HashMap.java:1784)
> at java.util.HashMap$TreeNode.putTreeVal(HashMap.java:2029)
> at java.util.HashMap.putVal(HashMap.java:639)
> at java.util.HashMap.put(HashMap.java:613)
> at java.util.HashSet.add(HashSet.java:220)
> at
> org.apache.hadoop.hive.ql.optimizer.calcite.stats.EstimateUniqueKeys.getUniqueKeys(EstimateUniqueKeys.java:229)
> at
> org.apache.hadoop.hive.ql.optimizer.calcite.stats.EstimateUniqueKeys.getUniqueKeys(EstimateUniqueKeys.java:304)
> at
> org.apache.hadoop.hive.ql.optimizer.calcite.stats.HiveRelMdRowCount.isKey(HiveRelMdRowCount.java:501)
> at
> org.apache.hadoop.hive.ql.optimizer.calcite.stats.HiveRelMdRowCount.analyzeJoinForPKFK(HiveRelMdRowCount.java:302)
> at
> org.apache.hadoop.hive.ql.optimizer.calcite.stats.HiveRelMdRowCount.getRowCount(HiveRelMdRowCount.java:102)
> at GeneratedMetadataHandler_RowCount.getRowCount_$(Unknown Source)
> at GeneratedMetadataHandler_RowCount.getRowCount(Unknown Source)
> at
> org.apache.calcite.rel.metadata.RelMetadataQuery.getRowCount(RelMetadataQuery.java:212)
> at
> org.apache.calcite.rel.rules.LoptOptimizeJoinRule.swapInputs(LoptOptimizeJoinRule.java:1882)
> at
> org.apache.calcite.rel.rules.LoptOptimizeJoinRule.createJoinSubtree(LoptOptimizeJoinRule.java:1756)
> at
> org.apache.calcite.rel.rules.LoptOptimizeJoinRule.addToTop(LoptOptimizeJoinRule.java:1233)
> at
> org.apache.calcite.rel.rules.LoptOptimizeJoinRule.addFactorToTree(LoptOptimizeJoinRule.java:927)
> at
> org.apache.calcite.rel.rules.LoptOptimizeJoinRule.createOrdering(LoptOptimizeJoinRule.java:728)
> at
> org.apache.calcite.rel.rules.LoptOptimizeJoinRule.findBestOrderings(LoptOptimizeJoinRule.java:459)
> at
> org.apache.calcite.rel.rules.LoptOptimizeJoinRule.onMatch(LoptOptimizeJoinRule.java:128)
> at
> org.apache.calcite.plan.AbstractRelOptPlanner.fireRule(AbstractRelOptPlanner.java:333)
> at org.apache.calcite.plan.hep.HepPlanner.applyRule(HepPlanner.java:542)
> at
> org.apache.calcite.plan.hep.HepPlanner.applyRules(HepPlanner.java:407)
> at
> org.apache.calcite.plan.hep.HepPlanner.executeInstruction(HepPlanner.java:243)
> at
> org.apache.calcite.plan.hep.HepInstruction$RuleInstance.execute(HepInstruction.java:127)
> at
> org.apache.calcite.plan.hep.HepPlanner.executeProgram(HepPlanner.java:202)
> at
> org.apache.calcite.plan.hep.HepPlanner.findBestExp(HepPlanner.java:189)
> at
> org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.executeProgram(CalcitePlanner.java:2468)
> at
> org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.executeProgram(CalcitePlanner.java:2427)
> at
> org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.applyJoinOrderingTransform(CalcitePlanner.java:2193)
> at
> org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.apply(CalcitePlanner.java:1750)
> at
> org.apache.hadoop.hive.ql.parse.CalcitePlanner$CalcitePlannerAction.apply(CalcitePlanner.java:1605)
> {code}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
