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.
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.
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.
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.
@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Outdated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.
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.
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. |
|
I'm trying to add a similar system, Trino. |
This PR adds results for Presto. https://prestodb.io/