-
Notifications
You must be signed in to change notification settings - Fork 149
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add Presto #195
base: main
Are you sure you want to change the base?
Add Presto #195
Conversation
Co-authored-by: Archy-X <63976867+Archy-X@users.noreply.github.com>
|
||
The benchmarks are based on Presto version `0.287`. | ||
|
||
We assume that a Presto cluster is already running. For more information, visit [Getting Started](https://prestodb.io/getting-started/). |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Need to add instructions on how to install Presto on an empty machine with Ubuntu on AWS.
These instructions should be in the form of a shell script; see benchmark.sh
in other directories.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
It's probably not possible to have a single script to set up a cluster since the environment is complicated, what should I do?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Having a standard setup is important otherwise different setups may not give identical results.
Would be nice if you can do either of the following:
- You can create an AWS AMI and add that AMI id in the README.
- You can setup a docker-compose based setup of Presto.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@allenshen13 As the other commenters said already, benchmark.sh
is supposed to be as automatic as possible. This ensures reproducibility and comparability with other systems.
Looking at https://prestodb.io/docs/current/installation/deploy-docker.html, it seem fairly easy to deploy a single-node Presto cluster. The JVM config file could be stored within /presto and copied to the right place by "benchmarks.h". It would be great to have Presto included, would you like to continue this PR?
presto/README.md
Outdated
---------- | ||
## Steps | ||
|
||
1. Download the parquet file and upload it to an S3 Bucket ex. s3://your-bucket/clickbench-parquet/hits/hits.parquet. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
We already have it,
s3://clickhouse-public-datasets/hits_compatible/hits.parquet
or
s3://clickhouse-public-datasets/hits_compatible/athena_partitioned/hits_{0..99}.parquet
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Okay, made a note of this in the README.
@Archy-X Still interested in completing this PR? Otherwise, please close it, thanks. |
@rschu1ze, we do want to have Presto and Trino, as well as Starburst Cloud, in ClickBench. |
I am no longer able to work on this, but @wanglinsong or @xpengahana may be able to provide an update/take over. |
This PR adds results for Presto. https://prestodb.io/