Queries per second about pgreplay HOT 3 CLOSED

#!/usr/bin/env python3
import hashlib
import argparse
import sys
import os
import csv

CSV_FIELDS = ['log_time', 'user_name', 'database_name', 'process_id', 'connection_from', 'session_id',
  'session_line_num', 'command_tag', 'session_start_time', 'virtual_transaction_id',
  'transaction_id', 'error_severity', 'sql_state_code', 'message', 'detail', 'hint', 'internal_query', 'internal_query_pos',
  'context', 'query', 'query_pos', 'location', 'application_name']
CSV_IDS = { CSV_FIELDS[i] : i for i in range(0, len(CSV_FIELDS) ) }

def main():

    parser = argparse.ArgumentParser(description='Split postgres csv log file into roughly equal chunks by session id')
    parser.add_argument('--log-file', type=str, help='The log file to parse')
    parser.add_argument('--split-count', type=int, help='Number to split the log file into')

    args = parser.parse_args()
    buckets = [[] for i in range(args.split_count)]
    csv.field_size_limit(sys.maxsize)
    with open(args.log_file, 'r') as csvfile:
        reader = csv.reader(csvfile)
        for row in reader:
            try:
                bucket_number = int(hashlib.sha256(row[CSV_IDS['session_id']].encode('utf-8')).hexdigest(), 16) % args.split_count
                buckets[bucket_number].append(row)
            except IndexError:
                print("index error encountered for row:{}".format(row))
                continue
    for index in range(args.split_count):
        split_file_name = 'split_file_{}_{}'.format(index, os.path.basename(args.log_file))
        with open(split_file_name, mode='w', encoding='utf-8') as split_file:
            writer = csv.writer(split_file, quoting=csv.QUOTE_MINIMAL)
            for row in buckets[index]:
                writer.writerow(row)

if __name__ == '__main__':
    try:
        main()
    except KeyboardInterrupt:
        print('Interrupted')
        try:
            sys.exit(0)
        except SystemExit:
            os._exit(0)