From 6c64ffcf949170ba1714fd389c018c6eaac88d15 Mon Sep 17 00:00:00 2001 From: Joe Lothan Date: Mon, 25 May 2026 21:53:57 -0400 Subject: [PATCH] upped concurrent s3 requests to speed up cc-index download --- pipeline/01_cc_index/query.sh | 1 + 1 file changed, 1 insertion(+) diff --git a/pipeline/01_cc_index/query.sh b/pipeline/01_cc_index/query.sh index 05634bf..d480486 100755 --- a/pipeline/01_cc_index/query.sh +++ b/pipeline/01_cc_index/query.sh @@ -118,6 +118,7 @@ if [ -d "$LOCAL_INDEX" ] && [ "$(ls -A "$LOCAL_INDEX"/*.parquet 2>/dev/null)" ]; else echo "Downloading CC-Index parquet files..." mkdir -p "$LOCAL_INDEX" + aws configure set default.s3.max_concurrent_requests 50 aws s3 sync "$S3_PATH" "$LOCAL_INDEX/" --quiet echo "Downloaded $(ls "$LOCAL_INDEX"/*.parquet | wc -l) parquet files" fi