spark-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From JG Perrin <>
Subject RE: Loading objects only once
Date Thu, 28 Sep 2017 11:44:57 GMT
Maybe load the model on each executor’s disk and load it from there? Depending on how you
use the data/model, using something like Livy and sharing the same connection may help?

From: Naveen Swamy []
Sent: Wednesday, September 27, 2017 9:08 PM
Subject: Loading objects only once

Hello all,

I am a new user to Spark, please bear with me if this has been discussed earlier.

I am trying to run batch inference using DL frameworks pre-trained models and Spark. Basically,
I want to download a model(which is usually ~500 MB) onto the workers and load the model and
run inference on images fetched from the source like S3 something like this
rdd = sc.parallelize(load_from_s3)

I was able to get it running in local mode on Jupyter, However, I would like to load the model
only once and not every map operation. A setup hook would have nice which loads the model
once into the JVM, I came across this JIRA
 which suggests that I can use Singleton and static initialization. I tried to do this using
a Singleton metaclass following the thread here
Following this failed miserably complaining that Spark cannot serialize ctype objects with
pointer references.

After a lot of trial and error, I moved the code to a separate file by creating a static method
for predict that checks if a class variable is set or not and loads the model if not set.
This approach does not sound thread safe to me, So I wanted to reach out and see if there
are established patterns on how to achieve something like this.

Also, I would like to understand the executor->tasks->python process mapping, Does each
task gets mapped to a separate python process?  The reason I ask is I want to be to use mapPartition
method to load a batch of files and run inference on them separately for which I need to load
the object once per task. Any

Thanks for your time in answering my question.

Cheers, Naveen

View raw message