[PPML] Fix BigDL Graphene Azure scripts (#5767)

* update * update submit scripts
intel-analytics · Sep 16, 2022 · ce260ec · ce260ec
1 parent e4fcf7e
commit ce260ec
Show file tree

Hide file tree

Showing 6 changed files with 20 additions and 21 deletions.
diff --git a/docs/readthedocs/source/doc/PPML/Overview/azure_ppml.md b/docs/readthedocs/source/doc/PPML/Overview/azure_ppml.md
@@ -298,9 +298,9 @@ export TF_MKL_ALLOC_MAX_BYTES=10737418240 && \
     --conf spark.driver.defaultJavaOptions="-Dlog4j.configuration=/ppml/trusted-big-data-ml/work/spark-3.1.2/conf/log4j2.xml" \
     --conf spark.executor.defaultJavaOptions="-Dlog4j.configuration=/ppml/trusted-big-data-ml/work/spark-3.1.2/conf/log4j2.xml" \
     --conf spark.kubernetes.authenticate.driver.serviceAccountName=spark \
-    --conf spark.kubernetes.container.image=intelanalytics/bigdl-ppml-trusted-big-data-ml-python-graphene:2.1.1-SNAPSHOT \
-    --conf spark.kubernetes.driver.podTemplateFile=/ppml/trusted-big-data-ml/spark-driver-template-kv.yaml \
-    --conf spark.kubernetes.executor.podTemplateFile=/ppml/trusted-big-data-ml/spark-executor-template-kv.yaml \
+    --conf spark.kubernetes.container.image=intelanalytics/bigdl-ppml-trusted-big-data-ml-python-graphene:2.1.0-SNAPSHOT \
+    --conf spark.kubernetes.driver.podTemplateFile=/ppml/trusted-big-data-ml/azure/spark-driver-template-az.yaml \
+    --conf spark.kubernetes.executor.podTemplateFile=/ppml/trusted-big-data-ml/azure/spark-executor-template-az.yaml \
     --conf spark.kubernetes.executor.deleteOnTermination=false \
     --conf spark.network.timeout=10000000 \
     --conf spark.executor.heartbeatInterval=10000000 \
@@ -345,7 +345,7 @@ export TF_MKL_ALLOC_MAX_BYTES=10737418240 && \
     --conf spark.bigdl.kms.key.data=$DATA_KEY_PATH \
     --class $SPARK_JOB_MAIN_CLASS \
     --verbose \
-    local://$SPARK_EXTRA_JAR_PATH \
+    $SPARK_EXTRA_JAR_PATH \
     $ARGS
 
 ```
@@ -378,7 +378,7 @@ Generate primary key and data key, then save to file system.
 
 The example code of generate primary key and data key is like below:
 ```
-java -cp '/ppml/trusted-big-data-ml/work/bigdl-2.1.0-SNAPSHOT/lib/bigdl-ppml-spark_3.1.2-2.1.0-SNAPSHOT-jar-with-dependencies.jar:/ppml/trusted-big-data-ml/work/spark-3.1.2/conf/:/ppml/trusted-big-data-ml/work/spark-3.1.2/jars/* \
+java -cp '/ppml/trusted-big-data-ml/work/bigdl-2.1.0-SNAPSHOT/jars/*:/ppml/trusted-big-data-ml/work/spark-3.1.2/conf/:/ppml/trusted-big-data-ml/work/spark-3.1.2/jars/* \
    -Xmx10g \
    com.intel.analytics.bigdl.ppml.examples.GenerateKeys \
    --kmsType AzureKeyManagementService \
@@ -392,7 +392,7 @@ Encrypt data with specified BigDL `AzureKeyManagementService`
 
 The example code of encrypt data is like below:
 ```
-java -cp '/ppml/trusted-big-data-ml/work/bigdl-2.1.0-SNAPSHOT/lib/bigdl-ppml-spark_3.1.2-2.1.0-SNAPSHOT-jar-with-dependencies.jar:/ppml/trusted-big-data-ml/work/spark-3.1.2/conf/:/ppml/trusted-big-data-ml/work/spark-3.1.2/jars/* \
+java -cp '/ppml/trusted-big-data-ml/work/bigdl-2.1.0-SNAPSHOT/jars/*:/ppml/trusted-big-data-ml/work/spark-3.1.2/conf/:/ppml/trusted-big-data-ml/work/spark-3.1.2/jars/* \
    -Xmx10g \
    com.intel.analytics.bigdl.ppml.examples.tpch.EncryptFiles \
    --kmsType AzureKeyManagementService \
@@ -432,7 +432,7 @@ OUTPUT_DIR=xxx/output
 
 export TF_MKL_ALLOC_MAX_BYTES=10737418240 && \
   /opt/jdk8/bin/java \
-    -cp '/ppml/trusted-big-data-ml/work/bigdl-2.1.0-SNAPSHOT/lib/bigdl-ppml-spark_3.1.2-2.1.0-SNAPSHOT-jar-with-dependencies.jar:/ppml/trusted-big-data-ml/work/spark-3.1.2/conf/:/ppml/trusted-big-data-ml/work/spark-3.1.2/jars/*' \
+    -cp '/ppml/trusted-big-data-ml/work/bigdl-2.1.0-SNAPSHOT/jars/*:/ppml/trusted-big-data-ml/work/spark-3.1.2/conf/:/ppml/trusted-big-data-ml/work/spark-3.1.2/jars/*' \
     -Xmx10g \
     -Dbigdl.mklNumThreads=1 \
     org.apache.spark.deploy.SparkSubmit \
@@ -448,9 +448,9 @@ export TF_MKL_ALLOC_MAX_BYTES=10737418240 && \
     --conf spark.driver.defaultJavaOptions="-Dlog4j.configuration=/ppml/trusted-big-data-ml/work/spark-3.1.2/conf/log4j2.xml" \
     --conf spark.executor.defaultJavaOptions="-Dlog4j.configuration=/ppml/trusted-big-data-ml/work/spark-3.1.2/conf/log4j2.xml" \
     --conf spark.kubernetes.authenticate.driver.serviceAccountName=spark \
-    --conf spark.kubernetes.container.image=intelanalytics/bigdl-ppml-trusted-big-data-ml-python-graphene:2.1.1-SNAPSHOT \
-    --conf spark.kubernetes.driver.podTemplateFile=/ppml/trusted-big-data-ml/spark-driver-template-kv.yaml \
-    --conf spark.kubernetes.executor.podTemplateFile=/ppml/trusted-big-data-ml/spark-executor-template-kv.yaml \
+    --conf spark.kubernetes.container.image=intelanalytics/bigdl-ppml-trusted-big-data-ml-python-graphene:2.1.0-SNAPSHOT \
+    --conf spark.kubernetes.driver.podTemplateFile=/ppml/trusted-big-data-ml/azure/spark-driver-template-az.yaml \
+    --conf spark.kubernetes.executor.podTemplateFile=/ppml/trusted-big-data-ml/azure/spark-executor-template-az.yaml \
     --conf spark.kubernetes.executor.deleteOnTermination=false \
     --conf spark.network.timeout=10000000 \
     --conf spark.executor.heartbeatInterval=10000000 \
@@ -495,7 +495,7 @@ export TF_MKL_ALLOC_MAX_BYTES=10737418240 && \
     --conf spark.bigdl.kms.key.data=$DATA_KEY_PATH \
     --class $SPARK_JOB_MAIN_CLASS \
     --verbose \
-    /ppml/trusted-big-data-ml/work/bigdl-2.1.0-SNAPSHOT/lib/bigdl-ppml-spark_3.1.2-2.1.0-SNAPSHOT-jar-with-dependencies.jar \
+    /ppml/trusted-big-data-ml/work/bigdl-2.1.0-SNAPSHOT/jars/bigdl-ppml-spark_3.1.2-2.1.0-SNAPSHOT.jar \
     $INPUT_DIR $OUTPUT_DIR aes_cbc_pkcs5padding plain_text [QUERY]
 ```
 

diff --git a/ppml/trusted-big-data-ml/python/docker-graphene/azure/generate-keys.sh b/ppml/trusted-big-data-ml/python/docker-graphene/azure/generate-keys.sh
@@ -11,8 +11,8 @@ openssl x509 -req -days 9999 -in server.csr -signkey server.key -out server.crt
 # Use sudo on cat if necessary.
 # Changing from redirection to tee to elude permission denials.
 
-cat server.key | sudo tee server.pem
-cat server.crt | sudo tee -a server.pem
+cat server.key | tee server.pem
+cat server.crt | tee -a server.pem
 openssl pkcs12 -export -in server.pem -out keystore.pkcs12
 keytool -importkeystore -srckeystore keystore.pkcs12 -destkeystore keystore.jks -srcstoretype PKCS12 -deststoretype JKS
 openssl pkcs12 -in keystore.pkcs12 -nodes -out server.pem

diff --git a/ppml/trusted-big-data-ml/python/docker-graphene/azure/secretProviderClass.yaml b/ppml/trusted-big-data-ml/python/docker-graphene/azure/secretProviderClass.yaml
@@ -20,4 +20,4 @@ spec:
           objectName: key-pass
           objectType: secret
           objectVersion: ""
-    tenantId: <tenant-id>
+    tenantId: <tenant-id>
diff --git a/ppml/trusted-big-data-ml/python/docker-graphene/azure/spark-driver-template-az.yaml b/ppml/trusted-big-data-ml/python/docker-graphene/azure/spark-driver-template-az.yaml
@@ -33,7 +33,7 @@ spec:
         #sgx.intel.com/enclave: 10
         #sgx.intel.com/provision: 10
   volumes:
-    - name: secretes-store01
+    - name: secrets-store01
       csi:
         driver: secrets-store.csi.k8s.io
         readOnly: true
@@ -50,4 +50,4 @@ spec:
         secretName: ssl-keys
     - name: kube-config
       secret:
-        secretName: kubeconf
+        secretName: kubeconf
diff --git a/ppml/trusted-big-data-ml/python/docker-graphene/azure/spark-executor-template-az.yaml b/ppml/trusted-big-data-ml/python/docker-graphene/azure/spark-executor-template-az.yaml
@@ -30,7 +30,7 @@ spec:
         #sgx.intel.com/enclave: 10
         #sgx.intel.com/provision: 10
   volumes:
-    - name: secretes-store01
+    - name: secrets-store01
       csi:
         driver: secrets-store.csi.k8s.io
         readOnly: true

diff --git a/ppml/trusted-big-data-ml/python/docker-graphene/azure/submit-spark-sgx-az.sh b/ppml/trusted-big-data-ml/python/docker-graphene/azure/submit-spark-sgx-az.sh
@@ -1,5 +1,4 @@
 #set -x
-#SPARK_EXTRA_JAR_PATH=/ppml/trusted-big-data-ml/work/spark-3.1.2/examples/jars/spark-encrypt-io.jar
 SPARK_EXTRA_JAR_PATH=
 SPARK_JOB_MAIN_CLASS=
 ARGS=
@@ -34,8 +33,8 @@ export TF_MKL_ALLOC_MAX_BYTES=10737418240 && \
     --conf spark.executor.defaultJavaOptions="-Dlog4j.configuration=/ppml/trusted-big-data-ml/work/spark-3.1.2/conf/log4j2.xml" \
     --conf spark.kubernetes.authenticate.driver.serviceAccountName=spark \
     --conf spark.kubernetes.container.image=intelanalytics/bigdl-ppml-trusted-big-data-ml-python-graphene:2.1.0-SNAPSHOT \
-    --conf spark.kubernetes.driver.podTemplateFile=/ppml/trusted-big-data-ml/spark-driver-template-az.yaml \
-    --conf spark.kubernetes.executor.podTemplateFile=/ppml/trusted-big-data-ml/spark-executor-template-az.yaml \
+    --conf spark.kubernetes.driver.podTemplateFile=/ppml/trusted-big-data-ml/azure/spark-driver-template-az.yaml \
+    --conf spark.kubernetes.executor.podTemplateFile=/ppml/trusted-big-data-ml/azure/spark-executor-template-az.yaml \
     --conf spark.kubernetes.executor.deleteOnTermination=false \
     --conf spark.network.timeout=10000000 \
     --conf spark.executor.heartbeatInterval=10000000 \
@@ -80,5 +79,5 @@ export TF_MKL_ALLOC_MAX_BYTES=10737418240 && \
     --conf spark.bigdl.kms.key.data=$DATA_KEY_PATH \
     --class $SPARK_JOB_MAIN_CLASS \
     --verbose \
-    local://$SPARK_EXTRA_JAR_PATH \
+    $SPARK_EXTRA_JAR_PATH \
     $ARGS