-
-
Save shntnu/320826671cac1d564e7f2374cdf3a1ca to your computer and use it in GitHub Desktop.
Calculate checksum corresponding to the entity-tag hash (ETag) of Amazon S3 objects
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/bin/bash | |
# | |
# Calculate checksum corresponding to the entity-tag hash (ETag) of Amazon S3 objects | |
# | |
# Usage: compute_etag.sh <filename> <part_size_mb> | |
# | |
# filename: file to process | |
# part_size_mb: chunk size in MiB used for multipart uploads. | |
# This is 8M by default for the AWS CLI See: | |
# https://docs.aws.amazon.com/cli/latest/topic/s3-config.html#multipart_chunksize | |
# | |
# The Etag for an S3 object can be obtained from the command-line using: | |
# aws s3api head-object --bucket <bucket-name> --key <key-name> --query ETag --output text | |
# Note that the Etag may or may not correspond to the MD5 digest, see here for details: | |
# https://docs.aws.amazon.com/AmazonS3/latest/API/API_Object.html | |
# Adapted from: https://gist.github.com/emersonf/7413337 | |
# Changes | |
# 7/23/2022 | |
# - Parallelized hash calculation | |
# - Removed need for temporary files | |
# Script requires: dd, md5sum, xxd | |
set -euo pipefail | |
NUM_PARALLEL=$(nproc) | |
# Minimum filesize in bytes to switch to multipart uploads | |
# https://docs.aws.amazon.com/cli/latest/topic/s3-config.html#multipart-threshold | |
MULTIPART_MINSIZE=$((8*1024*1024)) | |
if [[ $# -ne 2 ]]; then | |
echo "Usage: $0 file partSizeInMb"; | |
exit 0; | |
fi | |
file="$1" | |
partSizeInMb=$2 | |
if [[ ! -f "$file" ]]; then | |
echo "Error: $file not found." | |
exit 1; | |
fi | |
# Calculate checksum for a specified file chunk | |
# inputs: file, partSizeInMb, chunk | |
# output: chunk md5sum | |
hash_chunk(){ | |
file="$1" | |
partSizeInMb="$2" | |
chunk="$3" | |
skip=$((partSizeInMb * chunk)) | |
# output chunk + md5 (to allow sorting later) | |
dd bs=1M count="$partSizeInMb" skip="$skip" if="$file" 2> /dev/null | echo -e "$chunk $(md5sum)" | |
} | |
# Integer quotient a/b after rounding up | |
div_round_up(){ | |
echo $((($1 + $2 - 1)/$2)) | |
} | |
partSizeInB=$((partSizeInMb * 1024 * 1024)) | |
fileSizeInB=$(du -b "$file" | cut -f1 ) | |
parts=$(div_round_up fileSizeInB partSizeInB) | |
if [[ $fileSizeInB -gt $MULTIPART_MINSIZE ]]; then | |
export -f hash_chunk | |
etag=$(seq 0 $((parts-1)) | \ | |
xargs -P ${NUM_PARALLEL} -I{} bash -c 'hash_chunk "$@"' -- "$file" "$partSizeInMb" {} | \ | |
sort -n -k1,1 |tr -s ' '|cut -f2,3 -d' '|xxd -r -p|md5sum|cut -f1 -d' ')"-$parts" | |
else | |
etag=$(md5sum $file|cut -f1 -d' ') | |
fi | |
echo -e "${file}\t${etag}" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment