Adding new model from s3 url via management api does not store it into the model store directory about serve

[harshbafna]

@chauhang : This is by design, as the mar file name on S3 might conflict with the existing mar file in the model_store. The model files from s3 are directly downloaded and extracted in a temp location and loaded into TorchServe.

Also, we are currently working on checkpoint related feature, where the mar files for all the currently registered models, inclusive of the ones downloaded from S3, are backed up by TorchServe in checkpoint's model-store and the models will be directly loaded locally when the checkpoint is restored.

[chauhang]

@mycpuorg If there is a conflict in the name of the models in the model store and the one being downloaded, it should raise a duplicate name error. Storing models from S3 in yet another temp store is confusing from a Operations point of view. There should be only one model store per deployment to keep things simple for ops.

Let's review this after the Persistent store feature is ready.

[harshbafna]

This has been fixed as part of snapshot feature.

[mycpuorg]

PR #171 is merged to master