use tini to start model server

[yupbank]

Even though model server itself can be the entry point itself but then run with PID 1 would make the server not responding to SIGINT or SIGTERM

which is problematic during k8s rolling up new version

Using Tini has several benefits:

• It protects you from software that accidentally creates zombie processes,
  which can (over time!) starve your entire system for PIDs (and make it
  unusable).
• It ensures that the default signal handlers work for the software you run
  in your Docker image. For example, with Tini, SIGTERM properly terminates
  your process even if you didn't explicitly install a signal handler for it.
• It does so completely transparently! Docker images that work without Tini
  will work with Tini without any changes.

---

This change is 

[yupbank]

/assign @jlewi @lluunn

[lluunn]

Sorry I am not familiar with tini.
Could you update some description about what's tini and what does it do?
Also, is it common to use that in k8s?

Thanks

[yupbank]

sure.. i have updated..

i think it's common, like we use it for nginx when deploy with docker

[lluunn]

Thanks! I can see we use tini in jupyter image as well.
/lgtm

[k8s-ci-robot]

[APPROVALNOTIFIER] This PR is APPROVED

This pull-request has been approved by: lluunn

The full list of commands accepted by this bot can be found here.

The pull request process is described here

Needs approval from an approver in each of these files:

• OWNERS [lluunn]

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment