소스 검색

Modernized the settings and renamed the file to match with instructions.

Carter Shanklin 11 년 전
부모
커밋
b80eca60be
2개의 변경된 파일58개의 추가작업 그리고 29개의 파일을 삭제
  1. 0 29
      sample-queries-tpcds/init.settings
  2. 58 0
      sample-queries-tpcds/testbench.settings

+ 0 - 29
sample-queries-tpcds/init.settings

@@ -1,29 +0,0 @@
-set hive.enforce.bucketing=true;
-set hive.enforce.sorting=true;
-set hive.map.aggr=true;
-set hive.optimize.bucketmapjoin=false;
-set hive.optimize.bucketmapjoin.sortedmerge=false;
-set hive.mapred.reduce.tasks.speculative.execution=false;
-set hive.auto.convert.join=true;
-set hive.auto.convert.sortmerge.join=false;
-set hive.auto.convert.sortmerge.join.noconditionaltask=false;
-set hive.auto.convert.join.noconditionaltask=true;
-set hive.optimize.reducededuplication.min.reducer=1;
-set hive.optimize.mapjoin.mapreduce=true;
-set mapred.reduce.parallel.copies=30;
-
-set mapreduce.map.output.compress=true;
-set mapreduce.map.output.compress.codec=org.apache.hadoop.io.compress.DefaultCodec;
-set tez.runtime.intermediate-output.should-compress=true;
-set tez.runtime.intermediate-output.compress.codec=org.apache.hadoop.io.compress.SnappyCodec;
-set tez.runtime.intermdiate-input.is-compressed=true;
-set tez.runtime.intermediate-input.compress.codec=org.apache.hadoop.io.compress.SnappyCodec;
-
--- Hive 13 optimizations.
-set hive.execution.engine=tez;
-set hive.tez.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat;
-set hive.orc.splits.include.file.footer=true;
-set hive.vectorized.execution.enabled=true;
-set hive.exec.local.cache=true;
-
-set hive.root.logger=ERROR,console;

+ 58 - 0
sample-queries-tpcds/testbench.settings

@@ -0,0 +1,58 @@
+set ambari.hive.db.schema.name=hive;
+set fs.file.impl.disable.cache=true;
+set fs.hdfs.impl.disable.cache=true;
+set hive.auto.convert.join.noconditionaltask=true;
+set hive.auto.convert.join=true;
+set hive.auto.convert.sortmerge.join.noconditionaltask=true;
+set hive.auto.convert.sortmerge.join=true;
+set hive.compactor.abortedtxn.threshold=1000;
+set hive.compactor.check.interval=300;
+set hive.compactor.delta.num.threshold=10;
+set hive.compactor.delta.pct.threshold=0.1f;
+set hive.compactor.initiator.on=false;
+set hive.compactor.worker.threads=0;
+set hive.compactor.worker.timeout=86400;
+set hive.compute.query.using.stats=true;
+set hive.enforce.bucketing=true;
+set hive.enforce.sorting=true;
+set hive.enforce.sortmergebucketmapjoin=true;
+set hive.exec.failure.hooks=org.apache.hadoop.hive.ql.hooks.ATSHook;
+set hive.exec.post.hooks=org.apache.hadoop.hive.ql.hooks.ATSHook;
+set hive.exec.pre.hooks=org.apache.hadoop.hive.ql.hooks.ATSHook;
+set hive.execution.engine=mr;
+set hive.limit.pushdown.memory.usage=0.04;
+set hive.map.aggr=true;
+set hive.mapjoin.bucket.cache.size=10000;
+set hive.mapred.reduce.tasks.speculative.execution=false;
+set hive.metastore.cache.pinobjtypes=Table,Database,Type,FieldSchema,Order;
+set hive.metastore.client.socket.timeout=60;
+set hive.metastore.execute.setugi=true;
+set hive.metastore.warehouse.dir=/apps/hive/warehouse;
+set hive.optimize.bucketmapjoin.sortedmerge=false;
+set hive.optimize.bucketmapjoin=true;
+set hive.optimize.index.filter=true;
+set hive.optimize.mapjoin.mapreduce=true;
+set hive.optimize.reducededuplication.min.reducer=4;
+set hive.optimize.reducededuplication=true;
+set hive.orc.splits.include.file.footer=false;
+set hive.security.authorization.enabled=false;
+set hive.security.metastore.authorization.manager=org.apache.hadoop.hive.ql.security.authorization.StorageBasedAuthorizationProvider;
+set hive.semantic.analyzer.factory.impl=org.apache.hivealog.cli.HCatSemanticAnalyzerFactory;
+set hive.server2.enable.doAs=false;
+set hive.server2.tez.default.queues=default;
+set hive.server2.tez.initialize.default.sessions=false;
+set hive.server2.tez.sessions.per.default.queue=1;
+set hive.stats.autogather=true;
+set hive.tez.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat;
+set hive.txn.manager=org.apache.hadoop.hive.ql.lockmgr.DummyTxnManager;
+set hive.txn.max.open.batch=1000;
+set hive.txn.timeout=300;
+set hive.vectorized.execution.enabled=true;
+set hive.vectorized.groupby.checkinterval=1024;
+set hive.vectorized.groupby.flush.percent=1;
+set hive.vectorized.groupby.maxentries=1024;
+
+-- These values need to be tuned appropriately to your cluster. These examples are for reference.
+-- set hive.tez.container.size=4096;
+-- set hive.tez.java.opts=-Xmx3800m;
+-- set hive.auto.convert.join.noconditionaltask.size=1252698795;