{"draft":"draft-ietf-bmwg-hash-stuffing-08","doc_id":"RFC4814","title":"Hash and Stuffing: Overlooked Factors in Network Device Benchmarking","authors":["D. Newman","T. Player"],"format":["ASCII","HTML"],"page_count":"26","pub_status":"INFORMATIONAL","status":"INFORMATIONAL","source":"Benchmarking Methodology","abstract":"Test engineers take pains to declare all factors that affect a given\r\nmeasurement, including intended load, packet length, test duration,\r\nand traffic orientation.  However, current benchmarking practice\r\noverlooks two factors that have a profound impact on test results.\r\nFirst, existing methodologies do not require the reporting of\r\naddresses or other test traffic contents, even though these fields\r\ncan affect test results.  Second, \"stuff\" bits and bytes inserted in\r\ntest traffic by some link-layer technologies add significant and\r\nvariable overhead, which in turn affects test results.  This document\r\ndescribes the effects of these factors; recommends guidelines for\r\ntest traffic contents; and offers formulas for determining the\r\nprobability of bit- and byte-stuffing in test traffic.  This memo provides information for the Internet community.","pub_date":"March 2007","keywords":["bmwg","benchmarking","testing","bit-stuffing","byte-stuffing"],"obsoletes":[],"obsoleted_by":[],"updates":[],"updated_by":[],"see_also":[],"doi":"10.17487\/RFC4814","errata_url":null}