sort the shard by perf instead of storage

[bigning]

Summary: We tried this idea before with default GreedyPartitioner, but we didn't land it, because:

1. we don't see significantly QPS improvment
2. Concern that if we don't place the largest shard first, it may end-up with not finding a plan

but with the memoryBalancedPartitioner, in order to pusrse memryBalanced, we see very perf-imlbalanced plan for ads FM model on APS.

here is one before/after plan: before: https://www.internalfb.com/intern/everpaste/?handle=GD9CQhfUInYhieQEANW6oPyEmXEObsIXAAAz

after: https://www.internalfb.com/intern/everpaste/?handle=GE6FQhdC2AlbY60AANFsOJbtk5AKbsIXAAAz

it's significatnly more balanced.

Reviewed By: henrylhtsang

Differential Revision: D50425650

[facebook-github-bot]

This pull request was exported from Phabricator. Differential Revision: D50425650

[facebook-github-bot]

Hi @bigning!

Thank you for your pull request.

We require contributors to sign our Contributor License Agreement, and yours needs attention.

You currently have a record in our system, but the CLA is no longer valid, and will need to be resubmitted.

Process

In order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA.

Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with CLA signed. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.

If you have received this in error or have any questions, please contact us at [email protected]. Thanks!