ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

[PPML] Update documentation of PPML Occlum on Azure (#6372)

Browse source 
* update with Azure Marketplace

* update

* update
This commit is contained in:
Jiao Wang 2022-10-31 18:59:07 -07:00 committed by GitHub
parent 2629bb0645
commit 4dac556c68
2 changed files with 36 additions and 26 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
docs/readthedocs/source/doc/PPML/Overview/azure_ppml.md
View file

@ -29,7 +29,7 @@ az group create \
#### 2.2.2 Create Linux client with SGX support #### 2.2.2 Create Linux client with SGX support
Create Linux VM through Azure [CLI](https://docs.microsoft.com/en-us/azure/developer/javascript/tutorial/nodejs-virtual-machine-vm/create-linux-virtual-machine-azure-cli)/[Portal](https://docs.microsoft.com/en-us/azure/virtual-machines/linux/quick-create-portal)/Powershell. Create Linux VM through Azure [CLI](https://docs.microsoft.com/en-us/azure/developer/javascript/tutorial/nodejs-virtual-machine-vm/create-linux-virtual-machine-azure-cli)/[Portal](https://docs.microsoft.com/en-us/azure/virtual-machines/linux/quick-create-portal)/Powershell.
For size of the VM, please choose DC-V3 Series VM with more than 4 vCPU cores. For size of the VM, please choose DCSv3 Series VM with more than 4 vCPU cores.
#### 2.2.3 Pull BigDL PPML image and run on Linux client #### 2.2.3 Pull BigDL PPML image and run on Linux client
* Go to Azure Marketplace, search "BigDL PPML" and find `BigDL PPML: Secure Big Data AI on Intel SGX` product. Click "Create" button which will lead you to `Subscribe` page. * Go to Azure Marketplace, search "BigDL PPML" and find `BigDL PPML: Secure Big Data AI on Intel SGX` product. Click "Create" button which will lead you to `Subscribe` page.
@ -38,7 +38,7 @@ On `Subscribe` page, input your subscription, your Azure container registry, you
* Go to your Azure container regsitry, check `Repostirories`, and find `intel_corporation/bigdl-ppml-trusted-big-data-ml-python-graphene` * Go to your Azure container regsitry, check `Repostirories`, and find `intel_corporation/bigdl-ppml-trusted-big-data-ml-python-graphene`
* Login to the created VM. Then login to your Azure container registry, pull BigDL PPML image using this command: * Login to the created VM. Then login to your Azure container registry, pull BigDL PPML image using this command:
```bash ```bash
docker pull myContainerRegistry/intel_corporation/bigdl-ppml-trusted-big-data-ml-python-graphene docker pull myContainerRegistry.azurecr.io/intel_corporation/bigdl-ppml-trusted-big-data-ml-python-graphene
``` ```
* Start container of this image * Start container of this image
@ -46,7 +46,7 @@ On `Subscribe` page, input your subscription, your Azure container registry, you
#!/bin/bash #!/bin/bash
export LOCAL_IP=YOUR_LOCAL_IP export LOCAL_IP=YOUR_LOCAL_IP
export DOCKER_IMAGE=intel_corporation/bigdl-ppml-trusted-big-data-ml-python-graphene export DOCKER_IMAGE=myContainerRegistry.azurecr.io/intel_corporation/bigdl-ppml-trusted-big-data-ml-python-graphene
sudo docker run -itd \ sudo docker run -itd \
--privileged \ --privileged \
@ -317,7 +317,7 @@ bash bigdl-ppml-submit.sh \
--num-executors 2 \ --num-executors 2 \
--conf spark.cores.max=8 \ --conf spark.cores.max=8 \
--name spark-decrypt-sgx \ --name spark-decrypt-sgx \
--conf spark.kubernetes.container.image=intelanalytics/bigdl-ppml-trusted-big-data-ml-python-graphene:$BIGDL_VERSION \ --conf spark.kubernetes.container.image=myContainerRegistry.azurecr.io/intel_corporation/bigdl-ppml-trusted-big-data-ml-python-graphene:$BIGDL_VERSION \
--conf spark.kubernetes.driver.podTemplateFile=/ppml/trusted-big-data-ml/azure/spark-driver-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.podTemplateFile=/ppml/trusted-big-data-ml/azure/spark-executor-template-az.yaml \
--jars local://$SPARK_EXTRA_JAR_PATH \ --jars local://$SPARK_EXTRA_JAR_PATH \
@ -439,7 +439,7 @@ bash bigdl-ppml-submit.sh \
--num-executors 2 \ --num-executors 2 \
--conf spark.cores.max=8 \ --conf spark.cores.max=8 \
--name spark-tpch-sgx \ --name spark-tpch-sgx \
--conf spark.kubernetes.container.image=intelanalytics/bigdl-ppml-trusted-big-data-ml-python-graphene:$BIGDL_VERSION \ --conf spark.kubernetes.container.image=myContainerRegistry.azurecr.io/intel_corporation/bigdl-ppml-trusted-big-data-ml-python-graphene:$BIGDL_VERSION \
--conf spark.kubernetes.driver.podTemplateFile=/ppml/trusted-big-data-ml/azure/spark-driver-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.podTemplateFile=/ppml/trusted-big-data-ml/azure/spark-executor-template-az.yaml \
--conf spark.sql.auto.repartition=true \ --conf spark.sql.auto.repartition=true \

48
docs/readthedocs/source/doc/PPML/Overview/azure_ppml_occlum.md
View file

@ -22,55 +22,65 @@ Key points:
## Prerequisites ## Prerequisites
* Set up Azure VM on Azure * Set up Azure VM on Azure
* [DCsv3](https://docs.microsoft.com/en-us/azure/virtual-machines/dcv3-series) for [single node spark example](#single-node-spark-examples-on-azure). * Create a [DCSv3](https://docs.microsoft.com/en-us/azure/virtual-machines/dcv3-series) VM for [single node spark example](#single-node-spark-examples-on-azure).
* [Azure Kubernetes Service (AKS)](https://azure.microsoft.com/en-us/services/kubernetes-service/) for [distributed Spark examples](#distributed-spark-example-on-aks). * Prepare image of Spark (Required for distributed Spark examples only)
* Prepare image of Spark * Login to the created VM, then download [Spark 3.1.2](https://archive.apache.org/dist/spark/spark-3.1.2/spark-3.1.2-bin-hadoop3.2.tgz) and extract Spark binary. Install OpenJDK-8, and `export SPARK_HOME=${Spark_Binary_dir}`.
* (Required for distributed Spark examples only) Download [Spark 3.1.2](https://archive.apache.org/dist/spark/spark-3.1.2/spark-3.1.2-bin-hadoop3.2.tgz) and extract Spark binary. Install OpenJDK-8, and `export SPARK_HOME=${Spark_Binary_dir}`. * Go to Azure Marketplace, search "BigDL PPML" and find `BigDL PPML: Secure Big Data AI on Intel SGX (experimental and reference only, Occlum Edition)` product. Click "Create" button which will lead you to `Subscribe` page.
On `Subscribe` page, input your subscription, your Azure container registry, your resource group and your location. Then click `Subscribe` to subscribe BigDL PPML Occlum to your container registry.
Pull the image from [Dockerhub](https://hub.docker.com/r/intelanalytics/bigdl-ppml-azure-occlum). * On the created VM, login to your Azure container registry, then pull BigDL PPML Occlum image using this command:
```bash ```bash
docker pull intelanalytics/bigdl-ppml-azure-occlum:2.1.0 docker pull myContainerRegistry.azurecr.io/intel_corporation/bigdl-ppml-azure-occlum:latest
```
* Set up [Azure Kubernetes Service (AKS)](https://azure.microsoft.com/en-us/services/kubernetes-service/) for [distributed Spark examples](#distributed-spark-example-on-aks).
* Follow the [guide](https://learn.microsoft.com/en-us/azure/confidential-computing/confidential-enclave-nodes-aks-get-started) to deploy an AKS with confidential computing Intel SGX nodes.
* Install Azure CLI on the created VM or your local machine according to [Azure CLI guide](https://docs.microsoft.com/en-us/cli/azure/install-azure-cli).
* Login to AKS with such command:
```bash
az aks get-credentials --resource-group myResourceGroup --name myAKSCluster
```
* Create the RBAC to AKS
```bash
kubectl create serviceaccount spark
kubectl create clusterrolebinding spark-role --clusterrole=edit --serviceaccount=default:spark --namespace=default
``` ```
## Single Node Spark Examples on Azure ## Single Node Spark Examples on Azure
Single node Spark Examples require 1 Azure VM with SGX. All examples are running in SGX. You can apply it to your application with a few changes in dockerfile or scripts.
### SparkPi example ### SparkPi example
Run the SparkPi example with `run_spark_on_occlum_glibc.sh`. On the VM, Run the SparkPi example with `run_spark_on_occlum_glibc.sh`.
```bash ```bash
docker run --rm -it \ docker run --rm -it \
--name=azure-ppml-example-with-occlum \ --name=azure-ppml-example-with-occlum \
--device=/dev/sgx/enclave \ --device=/dev/sgx/enclave \
--device=/dev/sgx/provision \ --device=/dev/sgx/provision \
intelanalytics/bigdl-ppml-azure-occlum:2.1.0 bash myContainerRegistry.azurecr.io/intel_corporation/bigdl-ppml-azure-occlum:latest bash
cd /opt cd /opt
bash run_spark_on_occlum_glibc.sh pi bash run_spark_on_occlum_glibc.sh pi
``` ```
### Nytaxi example with Azure NYTaxi ### Nytaxi example with Azure NYTaxi
Run the Nytaxi example with `run_azure_nytaxi.sh`. On the VM, run the Nytaxi example with `run_azure_nytaxi.sh`.
```bash ```bash
docker run --rm -it \ docker run --rm -it \
--name=azure-ppml-example-with-occlum \ --name=azure-ppml-example-with-occlum \
--device=/dev/sgx/enclave \ --device=/dev/sgx/enclave \
--device=/dev/sgx/provision \ --device=/dev/sgx/provision \
intelanalytics/bigdl-ppml-azure-occlum:2.1.0 bash myContainerRegistry.azurecr.io/intel_corporation/bigdl-ppml-azure-occlum:latest bash
bash run_azure_nytaxi.sh bash run_azure_nytaxi.sh
``` ```
You should get Nytaxi dataframe count and aggregation duration when succeed. You should get Nytaxi dataframe count and aggregation duration when succeed.
## Distributed Spark Examples on AKS ## Distributed Spark Examples on AKS
Clone the repository to the VM:
```bash
git clone https://github.com/intel-analytics/BigDL-PPML-Azure-Occlum-Example.git
```
### SparkPi on AKS ### SparkPi on AKS
Configure environment variables in `run_spark_pi.sh`, `driver.yaml` and `executor.yaml`. Then you can submit SparkPi task with `run_spark_pi.sh`. In `run_spark_pi.sh` script, update `IMAGE` variable to `myContainerRegistry.azurecr.io/intel_corporation/bigdl-ppml-azure-occlum:latest`, and configure your AKS address. In addition, configure environment variables in `driver.yaml` and `executor.yaml` too. Then you can submit SparkPi task with `run_spark_pi.sh`.
```bash ```bash
bash run_spark_pi.sh bash run_spark_pi.sh
@ -78,7 +88,7 @@ bash run_spark_pi.sh
### Nytaxi on AKS ### Nytaxi on AKS
Configure environment variables in `run_nytaxi_k8s.sh`, `driver.yaml` and `executor.yaml`. Then you can submit Nytaxi query task with `run_nytaxi_k8s.sh`. In `run_nytaxi_k8s.sh` script, update `IMAGE` variable to `myContainerRegistry.azurecr.io/intel_corporation/bigdl-ppml-azure-occlum:latest`, and configure your AKS address. In addition, configure environment variables in `driver.yaml` and `executor.yaml` too. Then you can submit Nytaxi query task with `run_nytaxi_k8s.sh`.
```bash ```bash
bash run_nytaxi_k8s.sh bash run_nytaxi_k8s.sh
``` ```