total = 100000 data=range(total) jobSize = 5000 numJobs = (total // jobSize) + 1 numSegmentsPerJob = total // numJobs print numSegmentsPerJob print(numJobs) print('---') start = 0 count = 0 for i in range(numJobs): if i == numJobs-1: end = total else: end = start+numSegmentsPerJob shard = data[start:end] print(len(shard)) count += len(shard) start += numSegmentsPerJob print(count)