Hi Sean and Aseem,

thanks both. A simple thing which sped things up greatly was simply to load our sql (for one record effectively) directly and then convert to a dataframe, rather than using Spark to load it. Sounds stupid, but this took us from > 5 seconds to ~1 second on a very small instance.

Aseem: can you explain your solution a bit more? I'm not sure I understand it. At the moment we load our models from S3 (RandomForestClassificationModel.load(..) ) and then store that in an object property so that it persists across requests - this is in Scala. Is this essentially what you mean?

On 12 October 2016 at 10:52, Aseem Bansal <asmbansal2@gmail.com> wrote:

Faced a similar issue. Our solution was to load the model, cache it after converting it to a model from mllib and then use that instead of ml model. 

On Tue, Oct 11, 2016 at 10:22 PM, Sean Owen <sowen@cloudera.com> wrote:
I don't believe it will ever scale to spin up a whole distributed job to serve one request. You can look possibly at the bits in mllib-local. You might do well to export as something like PMML either with Spark's export or JPMML and then load it into a web container and score it, without Spark (possibly also with JPMML, OpenScoring)

On Tue, Oct 11, 2016, 17:53 Nicolas Long <nicolaslong@gmail.com> wrote:
Hi all,

so I have a model which has been stored in S3. And I have a Scala webapp which for certain requests loads the model and transforms submitted data against it.

I'm not sure how to run this quickly on a single instance though. At the moment Spark is being bundled up with the web app in an uberjar (sbt assembly).

But the process is quite slow. I'm aiming for responses < 1 sec so that the webapp can respond quickly to requests. When I look the Spark UI I see:

Summary Metrics for 1 Completed Tasks

Metric    Min    25th percentile    Median    75th percentile    Max
Duration    94 ms    94 ms    94 ms    94 ms    94 ms
Scheduler Delay    0 ms    0 ms    0 ms    0 ms    0 ms
Task Deserialization Time    3 s    3 s    3 s    3 s    3 s
GC Time    2 s    2 s    2 s    2 s    2 s
Result Serialization Time    0 ms    0 ms    0 ms    0 ms    0 ms
Getting Result Time    0 ms    0 ms    0 ms    0 ms    0 ms
Peak Execution Memory    0.0 B    0.0 B    0.0 B    0.0 B    0.0 B

I don't really understand why deserialization and GC should take so long when the models are already loaded. Is this evidence I am doing something wrong? And where can I get a better understanding on how Spark works under the hood here, and how best to do a standalone/bundled jar deployment?