From 7a88e4f73fbfaddc7fe54098b0ad79e792953020 Mon Sep 17 00:00:00 2001
From: Ingo Mueller <ingo.mueller@inf.ethz.ch>
Date: Fri, 29 Apr 2022 17:44:56 +0200
Subject: [PATCH] [config] Add and document other config variables.

---
 experiments/common/config.sh.template | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/experiments/common/config.sh.template b/experiments/common/config.sh.template
index 62cc209..1ea3193 100644
--- a/experiments/common/config.sh.template
+++ b/experiments/common/config.sh.template
@@ -8,7 +8,16 @@ S3_REGION=""  # The S3 region; e.g. "eu-central-1"
 S3_INPUT_BUCKET=""  # The S3 bucket name where datasets are stored without the 's3://' prefix; e.g. "my-new-bucket"
 S3_INPUT_PATH=s3://${S3_INPUT_BUCKET}/  # The full path within the bucket where the data is stored; e.g. s3://my-new-bucket/path/to/folder
 
+# Create a user with read-only access to S3 or just the bucket above and
+# create an access key for that user as described in this guide:
+# https://aws.amazon.com/premiumsupport/knowledge-center/create-access-key/
+# Then paste the key components into the variables below. This is required only
+# by the experiments with RDataFrames.
+S3_SECRET_KEY='...'
+S3_ACCESS_KEY='...'
+
 # GCP specific values
 GS_REGION=""  # The GCS region; e.g. "europe-west4-a"
 GS_INPUT_BUCKET=""  # The GCS bucket name where datasets are stored without the 'gs://' prefix; e.g. "my-new-bucket"
-GS_INPUT_PATH=gs://${GS_INPUT_BUCKET}/  # The full path within the bucket where the data is stored; e.g. gs://my-new-bucket/path/to/folder
\ No newline at end of file
+GS_INPUT_PATH=gs://${GS_INPUT_BUCKET}/  # The full path within the bucket where the data is stored; e.g. gs://my-new-bucket/path/to/folder
+GS_DATASET_ID='iris_hep_benchmark_data' # "namespace" for BigQuery tables. This value should work fine.