This is an automated email from the ASF dual-hosted git repository.
xxyu pushed a commit to branch kylin4_on_cloud
in repository https://gitbox.apache.org/repos/asf/kylin.git
The following commit(s) were added to refs/heads/kylin4_on_cloud by this push:
new 85e9f5a Fix 0314 (#1833)
85e9f5a is described below
commit 85e9f5a7970465ba15ad578b8ac693770f45c34b
Author: Tengting Xu <34978943+muk...@users.noreply.github.com>
AuthorDate: Mon Mar 14 11:47:30 2022 +0800
Fix 0314 (#1833)
* # switch on enable MDX
* # smaller default resources for query and job engine
* # update document when using glue
---
backup/properties/default/kylin.properties | 8 ++++----
.../properties/templates/kylin.properties.template | 8 ++++----
backup/scripts/prepare-ec2-env-for-kylin4.sh | 23 ++++++++++++++++++----
.../ec2-cluster-kylin4-template.yaml | 9 ++++++++-
cloudformation_templates/ec2-cluster-kylin4.yaml | 10 +++++++++-
kylin_configs.yaml | 5 +++++
readme/prerequisites.md | 2 +-
7 files changed, 50 insertions(+), 15 deletions(-)
diff --git a/backup/properties/default/kylin.properties
b/backup/properties/default/kylin.properties
index ef5ef94..aecaa8f 100644
--- a/backup/properties/default/kylin.properties
+++ b/backup/properties/default/kylin.properties
@@ -27,9 +27,9 @@ kylin.engine.spark-conf.spark.history.fs.logDirectory=s3a:/{{
S3_BUCKET_PATH }}/
kylin.engine.spark-conf.spark.master=spark://{{ SPARK_MASTER }}:7077
kylin.cube.cubeplanner.enabled=false
-kylin.engine.spark-conf.spark.executor.cores=3
-kylin.engine.spark-conf.spark.executor.instances=20
-kylin.engine.spark-conf.spark.executor.memory=12GB
+kylin.engine.spark-conf.spark.executor.cores=2
+kylin.engine.spark-conf.spark.executor.instances=4
+kylin.engine.spark-conf.spark.executor.memory=7GB
kylin.engine.spark-conf.spark.executor.memoryOverhead=1GB
### support prometheus
@@ -47,7 +47,7 @@ kylin.query.spark-conf.spark.master=spark://{{ SPARK_MASTER
}}:7077
kylin.query.spark-conf.spark.driver.cores=1
kylin.query.spark-conf.spark.driver.memory=8GB
kylin.query.spark-conf.spark.driver.memoryOverhead=1G
-kylin.query.spark-conf.spark.executor.instances=30
+kylin.query.spark-conf.spark.executor.instances=2
kylin.query.spark-conf.spark.executor.cores=2
kylin.query.spark-conf.spark.executor.memory=7G
kylin.query.spark-conf.spark.executor.memoryOverhead=1G
diff --git a/backup/properties/templates/kylin.properties.template
b/backup/properties/templates/kylin.properties.template
index ef5ef94..aecaa8f 100644
--- a/backup/properties/templates/kylin.properties.template
+++ b/backup/properties/templates/kylin.properties.template
@@ -27,9 +27,9 @@ kylin.engine.spark-conf.spark.history.fs.logDirectory=s3a:/{{
S3_BUCKET_PATH }}/
kylin.engine.spark-conf.spark.master=spark://{{ SPARK_MASTER }}:7077
kylin.cube.cubeplanner.enabled=false
-kylin.engine.spark-conf.spark.executor.cores=3
-kylin.engine.spark-conf.spark.executor.instances=20
-kylin.engine.spark-conf.spark.executor.memory=12GB
+kylin.engine.spark-conf.spark.executor.cores=2
+kylin.engine.spark-conf.spark.executor.instances=4
+kylin.engine.spark-conf.spark.executor.memory=7GB
kylin.engine.spark-conf.spark.executor.memoryOverhead=1GB
### support prometheus
@@ -47,7 +47,7 @@ kylin.query.spark-conf.spark.master=spark://{{ SPARK_MASTER
}}:7077
kylin.query.spark-conf.spark.driver.cores=1
kylin.query.spark-conf.spark.driver.memory=8GB
kylin.query.spark-conf.spark.driver.memoryOverhead=1G
-kylin.query.spark-conf.spark.executor.instances=30
+kylin.query.spark-conf.spark.executor.instances=2
kylin.query.spark-conf.spark.executor.cores=2
kylin.query.spark-conf.spark.executor.memory=7G
kylin.query.spark-conf.spark.executor.memoryOverhead=1G
diff --git a/backup/scripts/prepare-ec2-env-for-kylin4.sh
b/backup/scripts/prepare-ec2-env-for-kylin4.sh
index cdad91d..bfdfdfa 100644
--- a/backup/scripts/prepare-ec2-env-for-kylin4.sh
+++ b/backup/scripts/prepare-ec2-env-for-kylin4.sh
@@ -114,6 +114,8 @@ while [[ $# != 0 ]]; do
MDX_VERSION=$2
elif [[ $1 == "--support-glue" ]]; then
SUPPORT_GLUE=$2
+ elif [[ $1 == "--enable-mdx" ]]; then
+ ENABLE_MDX=$2
else
help
fi
@@ -153,6 +155,10 @@ if [[ -z "$MDX_DATABASE" ]]; then
MDX_DATABASE=kylin_mdx
fi
+if [[ -z "$ENABLE_MDX" ]]; then
+ ENABLE_MDX=false
+fi
+
LOCAL_CACHE_DIR=/home/ec2-user/ssd
### File name
@@ -426,7 +432,7 @@ function init_hive() {
fi
if [[ $SUPPORT_GLUE == "true" ]]; then
- cat <<EOF >${HIVE_HOME}/conf/hive-site.xml
+ cat <<EOF >${HIVE_HOME}/conf/hive-site.xml
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
@@ -661,7 +667,7 @@ function init_kylin() {
aws s3 cp ${PATH_TO_BUCKET}/properties/${CLUSTER_NUM}/kylin.properties
${KYLIN_HOME}/conf/kylin.properties --region ${CURRENT_REGION}
if [[ ${LOCAL_CACHE_SOFT_AFFINITY} == "true" ]]; then
- cat <<EOF >> ${KYLIN_HOME}/conf/kylin.properties
+ cat <<EOF >>${KYLIN_HOME}/conf/kylin.properties
kylin.query.spark-conf.spark.executor.extraJavaOptions=-Dhdp.version=current
-Dlog4j.configuration=spark-executor-log4j.properties -Dlog4j.debug
-Dkylin.hdfs.working.dir=\${kylin.env.hdfs-working-dir}
-Dkylin.metadata.identifier=\${kylin.metadata.url.identifier}
-Dkylin.spark.category=sparder -Dkylin.spark.identifier={{APP_ID}}
-Dalluxio.user.client.cache.dir=${LOCAL_CACHE_DIR}/alluxio-cache-{{APP_ID}}-{{EXECUTOR_ID}}
kylin.query.spark-conf.spark.driver.extraJavaOptions=-Dhdp.version=current
-Dalluxio.user.client.cache.dir=${LOCAL_CACHE_DIR}/alluxio-cache-driver
@@ -702,6 +708,9 @@ EOF
}
function prepare_mdx() {
+ if [[ ${ENABLE_MDX} == "false" ]]; then
+ return
+ fi
logging info "Preparing MDX ..."
if [[ -f ${HOME_DIR}/.prepared_mdx ]]; then
@@ -736,6 +745,9 @@ function prepare_mdx() {
}
function init_mdx() {
+ if [[ ${ENABLE_MDX} == "false" ]]; then
+ return
+ fi
if [[ -f ${HOME_DIR}/.inited_mdx ]]; then
logging warn "MDX already inited ..."
return
@@ -745,7 +757,7 @@ function init_mdx() {
aws s3 cp ${PATH_TO_BUCKET}/jars/mysql-connector-java-8.0.24.jar
$MDX_HOME/semantic-mdx/lib/ --region ${CURRENT_REGION}
fi
- if [[ ! -f $MDX_HOME/semantic-mdx/lib/kylin-jdbc-4.0.0-SNAPSHOT.jar ]]; then
+ if [[ ! -f $MDX_HOME/semantic-mdx/lib/kylin-jdbc-4.0.0-SNAPSHOT.jar ]]; then
logging info "Copy jdbc driver from $KYLIN_HOME to
$MDX_HOME/semantic-mdx/lib/ ..."
cp -f $KYLIN_HOME/lib/kylin-jdbc-*.jar $MDX_HOME/semantic-mdx/lib/
fi
@@ -812,7 +824,7 @@ function start_kylin() {
function sample_for_kylin() {
if [[ $SUPPORT_GLUE == "true" ]]; then
- return
+ return
fi
if [[ ${IS_SCALED} == "false" ]]; then
@@ -832,6 +844,9 @@ function restart_kylin() {
}
function start_mdx() {
+ if [[ ${ENABLE_MDX} == "false" ]]; then
+ return
+ fi
${MDX_HOME}/bin/mdx.sh start
}
diff --git a/cloudformation_templates/ec2-cluster-kylin4-template.yaml
b/cloudformation_templates/ec2-cluster-kylin4-template.yaml
index 57cced5..5b14a18 100644
--- a/cloudformation_templates/ec2-cluster-kylin4-template.yaml
+++ b/cloudformation_templates/ec2-cluster-kylin4-template.yaml
@@ -153,6 +153,9 @@ Parameters:
SupportGlue:
Type: String
Default: false
+ EnableMDX:
+ Type: String
+ Default: false
Mappings:
AWSRegionArch2AMI:
@@ -260,7 +263,7 @@ Resources:
#!/bin/bash -xe
cd /home/ec2-user
aws s3 cp
${PrivateBucketFullPath}/scripts/${PrivateKylin4ScriptFileName} . --region
${PrivateRegion}
- bash ${PrivateKylin4ScriptFileName} --bucket-url
${PrivateBucketPath} --region ${PrivateRegion} --db-host ${PrivateDbHost}
--db-password ${PrivateDbPass} --db-user ${PrivateDbUser} --db-port
${PrivateDbPort} --local-soft ${PrivateLocalCacheSoftAffinity} --cluster-num
${PrivateClusterNum} --is-scaled ${PrivateIsScaled} --hadoop-version
${PrivateHadoopVersion} --spark-version ${PrivateSparkVersion} --hive-version
${PrivateHiveVersion} --kylin-version ${PrivateKylinVersion} -- [...]
+ bash ${PrivateKylin4ScriptFileName} --bucket-url
${PrivateBucketPath} --region ${PrivateRegion} --db-host ${PrivateDbHost}
--db-password ${PrivateDbPass} --db-user ${PrivateDbUser} --db-port
${PrivateDbPort} --local-soft ${PrivateLocalCacheSoftAffinity} --cluster-num
${PrivateClusterNum} --is-scaled ${PrivateIsScaled} --hadoop-version
${PrivateHadoopVersion} --spark-version ${PrivateSparkVersion} --hive-version
${PrivateHiveVersion} --kylin-version ${PrivateKylinVersion} -- [...]
echo " Kylin4 is ready ..."
- PrivateBucketFullPath: !Ref BucketFullPath
PrivateKylin4ScriptFileName: !Ref Kylin4ScriptFileName
@@ -279,6 +282,7 @@ Resources:
PrivateHadoopVersion: !Ref HadoopVersion
PrivateMdxVersion: !Ref MdxVersion
PrivateSupportGlue: !Ref SupportGlue
+ PrivateEnableMDX: !Ref EnableMDX
Outputs:
IdOfInstance:
@@ -305,3 +309,6 @@ Outputs:
SupportGlue:
Description: is supported glue ?
Value: !Ref SupportGlue
+ EnableMDX:
+ Description: mdx is enabled?
+ Value: !Ref EnableMDX
diff --git a/cloudformation_templates/ec2-cluster-kylin4.yaml
b/cloudformation_templates/ec2-cluster-kylin4.yaml
index a4eb58b..e02fadf 100644
--- a/cloudformation_templates/ec2-cluster-kylin4.yaml
+++ b/cloudformation_templates/ec2-cluster-kylin4.yaml
@@ -154,6 +154,10 @@ Parameters:
Type: String
Default: false
+ EnableMDX:
+ Type: String
+ Default: false
+
Mappings:
AWSRegionArch2AMI:
cn-north-1:
@@ -260,7 +264,7 @@ Resources:
#!/bin/bash -xe
cd /home/ec2-user
aws s3 cp
${PrivateBucketFullPath}/scripts/${PrivateKylin4ScriptFileName} . --region
${PrivateRegion}
- bash ${PrivateKylin4ScriptFileName} --bucket-url
${PrivateBucketPath} --region ${PrivateRegion} --db-host ${PrivateDbHost}
--db-password ${PrivateDbPass} --db-user ${PrivateDbUser} --db-port
${PrivateDbPort} --local-soft ${PrivateLocalCacheSoftAffinity} --cluster-num
${PrivateClusterNum} --is-scaled ${PrivateIsScaled} --hadoop-version
${PrivateHadoopVersion} --spark-version ${PrivateSparkVersion} --hive-version
${PrivateHiveVersion} --kylin-version ${PrivateKylinVersion} -- [...]
+ bash ${PrivateKylin4ScriptFileName} --bucket-url
${PrivateBucketPath} --region ${PrivateRegion} --db-host ${PrivateDbHost}
--db-password ${PrivateDbPass} --db-user ${PrivateDbUser} --db-port
${PrivateDbPort} --local-soft ${PrivateLocalCacheSoftAffinity} --cluster-num
${PrivateClusterNum} --is-scaled ${PrivateIsScaled} --hadoop-version
${PrivateHadoopVersion} --spark-version ${PrivateSparkVersion} --hive-version
${PrivateHiveVersion} --kylin-version ${PrivateKylinVersion} -- [...]
echo " Kylin4 is ready ..."
- PrivateBucketFullPath: !Ref BucketFullPath
PrivateKylin4ScriptFileName: !Ref Kylin4ScriptFileName
@@ -279,6 +283,7 @@ Resources:
PrivateHadoopVersion: !Ref HadoopVersion
PrivateMdxVersion: !Ref MdxVersion
PrivateSupportGlue: !Ref SupportGlue
+ PrivateEnableMDX: !Ref EnableMDX
Outputs:
IdOfInstance:
@@ -305,3 +310,6 @@ Outputs:
SupportGlue:
Description: is supported glue ?
Value: !Ref SupportGlue
+ EnableMDX:
+ Description: mdx is enabled?
+ Value: !Ref EnableMDX
diff --git a/kylin_configs.yaml b/kylin_configs.yaml
index 658bcec..d924459 100644
--- a/kylin_configs.yaml
+++ b/kylin_configs.yaml
@@ -56,6 +56,9 @@ CIDR_IP: ${Cidr Ip}
# If you set `All` mode for Kylin, there will be a error when you query any
sql.
SUPPORT_GLUE: &SUPPORT_GLUE 'false'
+# Enable using MDX
+ENABLE_MDX: &ENABLE_MDX 'false'
+
# ============ AWS Configs End ============
# ============ Related Version of Services ============
@@ -246,6 +249,7 @@ EC2_KYLIN4_PARAMS:
HiveVersion: *HIVE_VERSION
MdxVersion: *MDX_VERSION
SupportGlue: *SUPPORT_GLUE
+ EnableMDX: *ENABLE_MDX
AssociatedPublicIp: *associated_public_ip
@@ -301,6 +305,7 @@ EC2_KYLIN4_SCALE_PARAMS:
HiveVersion: *HIVE_VERSION
MdxVersion: *MDX_VERSION
SupportGlue: *SUPPORT_GLUE
+ EnableMDX: *ENABLE_MDX
AssociatedPublicIp: *associated_public_ip
diff --git a/readme/prerequisites.md b/readme/prerequisites.md
index 361077d..2a6497d 100644
--- a/readme/prerequisites.md
+++ b/readme/prerequisites.md
@@ -14,7 +14,7 @@ git clone https://github.com/apache/kylin.git && cd kylin &&
git checkout kylin4
> Note:
>
-> `IAM` role must have the access which contains `AmazonEC2RoleforSSM`,
`AmazonSSMFullAccess,` and `AmazonSSMManagedInstanceCore`.
+> `IAM` role must have the access which contains `AmazonEC2RoleforSSM`,
`AmazonSSMFullAccess,` and `AmazonSSMManagedInstanceCore`, and
`AWSGlueConsoleFullAccess` (this role is needed if you want to use glue).
>
> This `IAM` Role will be used to initialize every ec2 instances which is
> for creating a kylin4 cluster on AWS. And it will configure in `Initialize
> Env of Local Machine` part.
