Architecture Guide

1 Architecture

1. Single-Container Deployment

1. The business system prepares the device scan data to be processed as input in the working data directory according to the documentation requirements;

2. The business system calls the interface provided by the LCC Docker image over HTTP to start the execution of the reconstruction algorithm:

    e.g.: http://xxx/api {  --pass in the input data folder path  --pass in the input configuration parameters  --pass in the results folder path }   

3. The business system can poll the API to check whether the reconstruction execution has finished; after it finishes, it retrieves the result data from the results folder path.

4. The address of the reconstruction progress callback API can be passed in via the hookUrl parameter.

Linux Server (With Docker Runtime + Nvidia Container Driver, etc.)CustomerBusiness SystemXGRID LCCPrivate Deployment Edition(Docker Image + ResidentOperation)HTTP Interface 1HTTP Interface 2USB DongleorOnline AuthorizationAuthorized operationMount working directoryWorking data directory shared by the business system and the Docker image/work└ /job1└ /input└ /output└ job2└ /input└ /output

2. Multi-Container Deployment Architecture

Docker containers on a multi-GPU server can each mount one GPU, forming multiple LCC reconstruction container nodes.

Multiple container nodes support two management modes:

1) Independent Multi-Container

Each container can be treated as an independent node, providing an independent API port, with task management and scheduling handled by the external business system itself.

Each container serves only as an LCC reconstruction compute node, independent of one another. This is equivalent to repeating multiple single-container deployments.

Customer Linux Server (Nvidia Docker Runtime + Nvidia Driver)CustomerBusinessSystemLCC DockerContainer 0(Node 0)GPU 0LCC DockerContainer 1(Node 1)GPU 1LCC DockerContainer 2(Node 2)GPU 2APIAPIAPIMountData StorageUSB DongleorOnline AuthorizationObtain authorizationNote: LCC retrieves license informationat startup; no working data istransmitted.

2) Container Cluster ( Single-Machine Multi-GPU *)

Multiple containers on the local machine can be managed as a cluster through the Consul registry.

During deployment, one container node must be designated as the master node, and the reconstruction tasks within multiple nodes are controlled by calling the master node's API.

At the same time, the master node provides a platform-based management interface for direct graphical management (reference: WebUI Trial Guide).

Customer Linux Server (Nvidia Docker Runtime + Nvidia Driver)CustomerBusiness SystemUserLCC DockerContainer 0(Master Node)GPU 0LCC DockerContainer 1(Sub-node 1)GPU 1LCC DockerContainer 2(Sub-node 2)GPU 2Service RegistryDockerContainerAPIUIMountData StorageUSB DongleorOnline AuthorizationObtain authorizationNote: LCC retrieves license informationat startup; no working data istransmitted.

* Note

Multiple container nodes must be able to access the same /work disk directory in order to work in parallel and collaboratively to accelerate the completion of a single reconstruction task (because during an LCC reconstruction task, a large number of disk cache files are shared). Therefore, in the current version, it is recommended to create a multi-container cluster on a single-machine multi-GPU server.

3. Cluster Task Scheduling Strategy

1) Multiple Container Nodes Complete a Single Task in Parallel

An LCC reconstruction task takes a long time, but some of its steps can be split and handed off to multiple container nodes to complete in parallel, thereby shortening the overall completion time of the task.

LCC Reconstruction TaskSingle container node execution:Container Node 0Step 1Step 2Step 3Step 4...Multiple container nodes in parallel:Container Node 0Step 1Step 2 (1)Step 3Step 4...Idle nodes found in the clusterContainer Node 1Step 2 (2)Container Node 2Step 2 (3)Container nodes use a preemptive strategy1) First come, first served2) Released after completion3) Queued in chronological orderSplit Step 2 into chunks anddistribute them to other idlecontainer nodesShortens the task'stotal execution time

* Note

The container nodes in the current version use a preemptive strategy. If you want to complete a certain task with the highest priority as quickly as possible, it is recommended not to execute other tasks in the cluster first. This way, when the task needs to run in parallel, more available nodes can be obtained.

In subsequent versions, a more complex priority configuration strategy will be upgraded.

2) Multiple Container Nodes Complete Multiple Tasks in Parallel

When there are a large number of tasks, it is recommended to schedule them in a way where each container node processes one task.

This maximizes the number of tasks executed simultaneously and ensures that every container node is working at all times.

LCC Reconstruction TaskEach container node runs one task:Container Node 0Step 1Step 2Step 3Step 4...Container Node 1Step 1Step 2Step 3Step 4...Container Node 2Step 1Step 2Step 3Step 4...

* Note

The cluster in the current version uses strategy 1) Multiple Container Nodes Complete a Single Task in Parallel by default.

In subsequent versions, more complex strategy configuration parameters will be upgraded.

4. Licensing Architecture

1) Offline Authorization

Deployment Server Room - Same Network SegmentCodeMeter License(USB Dongle / Soft License)Number of licenses:1 + NDefault 1, N can be increasedN is the number of node add-on pack SKUsLicenseLCC Software RuntimeContainer No. 1(License -1)LCC Software RuntimeContainer No. 2(License -1)LCC Software RuntimeContainer No. 3(License -1)LCC Software RuntimeContainer No. ...(License -1)

2) Online Authorization

InternetXGRIDS License Service CenterWithin the user accountNumber of LCC Server licenses: NLicenseThis userLCC Software RuntimeContainer No. 1(License -1)This userLCC Software RuntimeContainer No. 2(License -1)This userLCC Software RuntimeContainer No. 3(License -1)This userLCC Software RuntimeContainer No. ...(License -1)