1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
#!/bin/bash
# # # # # # # # # # # # # # # # # # # # # #
# @file :fmp_insight.sh
# @desc :fmp job
# # # # # # # # # # # # # # # # # # # # # #
source ../dmp_env.sh
data=$1
jobId=$2
output_path="s3://mob-emr-test/dataplatform/fmp/data/insight"
# --conf spark.driver.extraJavaOptions="-XX:+UseG1GC" \
# --conf spark.executor.extraJavaOptions="-XX:+UseG1GC" \
# --conf spark.memory.offHeap.enabled=true \
# --conf spark.memory.offHeap.size=6442450944 \
spark-submit --class mobvista.dmp.datasource.fmp.FmpInsightJob \
--queue "fmp" \
--name "mobvista.dmp.datasource.fmp.FmpInsightJob_wangjf" \
--conf spark.sql.shuffle.partitions=1000 \
--conf spark.default.parallelism=1000 \
--conf spark.sql.broadcastTimeout=1200 \
--conf spark.kryoserializer.buffer.max=256m \
--conf spark.yarn.executor.memoryOverhead=2048 \
--conf spark.sql.files.maxPartitionBytes=134217728 \
--conf spark.sql.adaptive.enabled=true \
--conf spark.sql.adaptive.advisoryPartitionSizeInBytes=134217728 \
--conf spark.driver.extraJavaOptions="-XX:+UseG1GC" \
--conf spark.executor.extraJavaOptions="-XX:+UseG1GC" \
--master yarn --deploy-mode cluster --executor-memory 10g --driver-memory 6g --executor-cores 5 --num-executors 64 \
../${JAR} \
-data ${data// /###} -output ${output_path} -coalesce 1
if [[ $? -ne 0 ]]; then
update_time=`date '+%Y-%m-%d %H:%M:%S'`
mysql -h dataplatform-app-tag.c5yzcdreb1xr.us-east-1.rds.amazonaws.com -P 3306 -u apptag_rw -p'7gyLEVtkER3u8c9' <<EOF
UPDATE dmp_fmp.job_profile SET update_time = '${update_time}', flag = 2 WHERE job_id = '${jobId}';
EOF
exit 255
fi