ITU-T G 1040-2006 Network Contribution to Transaction Time《网络馈送到处理时间》.pdf

1、 International Telecommunication Union ITU-T G.1040TELECOMMUNICATION STANDARDIZATION SECTOR OF ITU (02/2006) SERIES G: TRANSMISSION SYSTEMS AND MEDIA, DIGITAL SYSTEMS AND NETWORKS Quality of service and performance Generic and user-related aspects Network contribution to transaction time ITU-T Recom

2、mendation G.1040 ITU-T G-SERIES RECOMMENDATIONS TRANSMISSION SYSTEMS AND MEDIA, DIGITAL SYSTEMS AND NETWORKS INTERNATIONAL TELEPHONE CONNECTIONS AND CIRCUITS G.100G.199 GENERAL CHARACTERISTICS COMMON TO ALL ANALOGUE CARRIER-TRANSMISSION SYSTEMS G.200G.299 INDIVIDUAL CHARACTERISTICS OF INTERNATIONAL

3、CARRIER TELEPHONE SYSTEMS ON METALLIC LINES G.300G.399 GENERAL CHARACTERISTICS OF INTERNATIONAL CARRIER TELEPHONE SYSTEMS ON RADIO-RELAY OR SATELLITE LINKS AND INTERCONNECTION WITH METALLIC LINES G.400G.449 COORDINATION OF RADIOTELEPHONY AND LINE TELEPHONY G.450G.499 TRANSMISSION MEDIA CHARACTERISTI

4、CS G.600G.699 DIGITAL TERMINAL EQUIPMENTS G.700G.799 DIGITAL NETWORKS G.800G.899 DIGITAL SECTIONS AND DIGITAL LINE SYSTEM G.900G.999 QUALITY OF SERVICE AND PERFORMANCE GENERIC AND USER-RELATED ASPECTS G.1000G.1999 TRANSMISSION MEDIA CHARACTERISTICS G.6000G.6999 DATA OVER TRANSPORT GENERIC ASPECTS G.

5、7000G.7999 ETHERNET OVER TRANSPORT ASPECTS G.8000G.8999 ACCESS NETWORKS G.9000G.9999 For further details, please refer to the list of ITU-T Recommendations. ITU-T Rec. G.1040 (02/2006) i ITU-T Recommendation G.1040 Network contribution to transaction time Summary This Recommendation defines a new pe

6、rformance metric for networks that transport short data transactions, such as those associated with credit cards and other point-of-sale transactions. The main factors contributing to transaction time are packet network performance and host processing time. The new metric is called network contribut

7、ion to transaction time (NCTT), and it uses packet transfer performance levels (such as round-trip time and packet loss ratio) as inputs in order to estimate the portion of transaction time attributable to the network alone. Since this is the portion under the control of the network operator, knowle

8、dge of this value is useful for operators and users alike. The scope of this Recommendation is limited to the performance of the path between user-network interfaces (UNI-UNI) and uses limited configuration information from transaction client and host systems. Source ITU-T Recommendation G.1040 was

9、approved on 22 February 2006 by ITU-T Study Group 12 (2005-2008) under the ITU-T Recommendation A.8 procedure. ii ITU-T Rec. G.1040 (02/2006) FOREWORD The International Telecommunication Union (ITU) is the United Nations specialized agency in the field of telecommunications. The ITU Telecommunicatio

10、n Standardization Sector (ITU-T) is a permanent organ of ITU. ITU-T is responsible for studying technical, operating and tariff questions and issuing Recommendations on them with a view to standardizing telecommunications on a worldwide basis. The World Telecommunication Standardization Assembly (WT

11、SA), which meets every four years, establishes the topics for study by the ITU-T study groups which, in turn, produce Recommendations on these topics. The approval of ITU-T Recommendations is covered by the procedure laid down in WTSA Resolution 1. In some areas of information technology which fall

12、within ITU-Ts purview, the necessary standards are prepared on a collaborative basis with ISO and IEC. NOTE In this Recommendation, the expression “Administration“ is used for conciseness to indicate both a telecommunication administration and a recognized operating agency. Compliance with this Reco

13、mmendation is voluntary. However, the Recommendation may contain certain mandatory provisions (to ensure e.g. interoperability or applicability) and compliance with the Recommendation is achieved when all of these mandatory provisions are met. The words “shall“ or some other obligatory language such

14、 as “must“ and the negative equivalents are used to express requirements. The use of such words does not suggest that compliance with the Recommendation is required of any party. INTELLECTUAL PROPERTY RIGHTS ITU draws attention to the possibility that the practice or implementation of this Recommend

15、ation may involve the use of a claimed Intellectual Property Right. ITU takes no position concerning the evidence, validity or applicability of claimed Intellectual Property Rights, whether asserted by ITU members or others outside of the Recommendation development process. As of the date of approva

16、l of this Recommendation, ITU had not received notice of intellectual property, protected by patents, which may be required to implement this Recommendation. However, implementors are cautioned that this may not represent the latest information and are therefore strongly urged to consult the TSB pat

17、ent database. ITU 2006 All rights reserved. No part of this publication may be reproduced, by any means whatsoever, without the prior written permission of ITU. ITU-T Rec. G.1040 (02/2006) iii CONTENTS Page 1 Scope 1 2 References. 1 3 Abbreviations 1 4 Network contribution to transaction time. 2 4.1

18、 Data transaction time 2 4.2 Definition of network contribution to transaction time 3 4.3 Calculation of network contribution to transaction time 3 4.4 Example of network contribution to transaction time 4 5 Measurement methodology considerations 5 6 Format for results 6 iv ITU-T Rec. G.1040 (02/200

19、6) Introduction Users would like to reduce the complexities of network performance to a “single number“, one that captures all service aspects, quantifies their individual experience with the service over time, and simplifies reporting and rebate reconciliation. This Recommendation defines such an o

20、verall metric for data transactions. Users purchase IP networking capabilities to conduct transactions using either voice or data communications. Voice transactions are largely free-form, while data transactions are structured according to well-specified, and often standardized protocols. When the p

21、rotocol behaviour of the client and server are known, it is possible to estimate the packet transport networks contribution to the overall transaction time experienced by users. The bases for the estimates are real measurements of packet loss and delay. Users may measure transaction time using any o

22、f the available means, including integrated instruments in the application programs, test transactions launched by measurement equipment, and passive monitoring at strategic locations. Most of these techniques measure a time interval that is attributable to both network performance, client performan

23、ce in terms of processing time, and host/server performance. This Recommendation defines a metric that uses the networks packet delay and packet loss performance to isolate an estimate of the networks contribution to transaction time. The metric can be customized for each specific user and/or transa

24、ction type. When a user measures their typical transaction time, this metric can account for the portion attributable to the network. When the user measures longer transaction times and inquires about cause, it is possible to say if the network contributed to the increase, and how much. The new metr

25、ic is called “network contribution to transaction time“ (NCTT). It differs from the handshake time defined elsewhere in that NCTT does not include host processing times. There is no perceptual interpretation proposed as part of this metric. User organizations will often have individual objective cri

26、teria for transaction time performance, and the criteria may vary depending on various circumstances. ITU-T Rec. G.1010 gives guidance regarding response times for various applications, and ITU-T Rec. Y.1541 provides performance objectives for IP-based networks. ITU-T Rec. G.1040 (02/2006) 1 ITU-T R

27、ecommendation G.1040 Network contribution to transaction time 1 Scope The scope of this Recommendation is limited to the definition, description, and examples of the network contribution to transaction time (NCTT) performance metric for short data transactions with relevance to network providers and

28、 users. This is a metric derived primarily from the performance characteristics of the user-network interface to user-network interface (UNI-UNI) path, although it also uses limited configuration information from clients and hosts. This performance metric is intended to be applied in situations wher

29、e packet network communications are used to complete repetitive data transactions, such as credit card authorization for purchase, and where measurements of the supporting networks performance are available. The NCTT metric is derived from packet transfer delays and packet loss ratios from client to

30、 host and host to client, effectively a round-trip across the network. Measurements will usually supply the needed network characterization, and measurement considerations are given below. 2 References The following ITU-T Recommendations and other references contain provisions which, through referen

31、ce in this text, constitute provisions of this Recommendation. At the time of publication, the editions indicated were valid. All Recommendations and other references are subject to revision; users of this Recommendation are therefore encouraged to investigate the possibility of applying the most re

32、cent edition of the Recommendations and other references listed below. A list of the currently valid ITU-T Recommendations is regularly published. The reference to a document within this Recommendation does not give it, as a stand-alone document, the status of a Recommendation. 1 ITU-T Recommendatio

33、n G.1000 (2001), Communications Quality of Service: A framework and definitions. 2 ITU-T Recommendation G.1010 (2001), End-user multimedia QoS categories. 3 ITU-T Recommendation Y.1540 (2002), Internet protocol data communication service IP packet transfer and availability performance parameters. 4

34、ITU-T Recommendation Y.1541 (2006), Network performance objectives for IP-based services. 3 Abbreviations This Recommendation uses the following abbreviations: ICMP Internet Control Message Protocol NCTT Network Contribution to Transaction Time RT Round-Trip RTO Retransmission Time-Out RTT Round-Tri

35、p Time TCP Transmission Control Protocol UDP User Datagram Protocol UNI User-Network Interface 2 ITU-T Rec. G.1040 (02/2006) 4 Network contribution to transaction time This clause defines the metric called network contribution to transaction time (NCTT). The metric uses UNI-UNI packet transfer perfo

36、rmance levels (such as round-trip time and packet loss ratio) as inputs in order to estimate the portion of transaction time attributable to the network alone. Since this is the portion under the control of the network operator, and knowledge of this value is useful for operators and customers alike

37、. 4.1 Data transaction time A typical data transaction takes the form of a packet conversation, where the client identifies itself to a remote host and submits some request for processing on behalf of a user. The host, after assuring the identities and authorization of the client device and user, pe

38、rforms the request and communicates the result. In the case of “short“ transactions considered here, the result is a simple confirmation of the request to exchange funds, or an account balance. The reference path and reference transaction (illustrating a transaction with eight round-trip exchanges)

39、are described in Figures 1 and 2 below. Figure 1/G.1040 Reference path Figure 2/G.1040 Reference transaction The following time periods can be identified in each packet exchange: 4.1.1 Client to host transfer time The time for a packet to traverse the UNI-UNI path between client and a host, identica

40、l to packet transfer delay defined in ITU-T Rec. Y.1540. 4.1.2 Host processing time The time a host takes to prepare a response or acknowledgement packet, defined as the interval beginning when the last bit of the clients packet passes the hosts UNI and ending when the first bit of the packet contai

41、ning a valid response passes the hosts UNI toward the client. ITU-T Rec. G.1040 (02/2006) 3 4.1.3 Client processing time The time a client takes to prepare a response or acknowledgement packet, defined as the interval beginning when the last bit of the hosts packet passes the clients UNI and ending

42、when the first bit of the packet containing a valid response passes the clients UNI toward the host. 4.1.4 Host to client transfer time The time for a packet to traverse the UNI-UNI path between host and a client, identical to packet transfer delay defined in ITU-T Rec. Y.1540. 4.1.5 Client retransm

43、ission time-out interval The time a client will wait for acknowledgement or response to its packet transmission. 4.1.6 Host retransmission time-out interval The time a host will wait for acknowledgement or response to its packet transmission. 4.1.7 Data transaction time The total time to complete a

44、transaction, as observed at the client UNI. This is the sum of all the component times for a given transaction type, where the number and direction of exchanges and device configurations are specified. 4.1.8 Round-trip exchange A round-trip exchange, sometimes simply called an exchange, is a compone

45、nt of a data transaction where one packet traverses the network from UNI to UNI, and a response packet traverses the network in the opposite direction. An exchange may begin at a client and proceed from client to remote host to client, or begin at the remote host. 4.2 Definition of network contribut

46、ion to transaction time The main network factors contributing to transaction time are packet network performance, retransmission time for lost packets, and device processing time (which is often highly variable, and beyond the network providers control). Removing the device processing times leaves t

47、he time attributable to network performance, in particular the round-trip packet transfer times and the time to recover from packet loss. Network contribution to transaction time (NCTT) is defined as the sum of the round-trip times necessary to complete a given transaction type, plus the time for re

48、covery from any lost packets during the transaction. A given transaction type will specify the number and direction of exchanges and the retransmission time-out interval. 4.3 Calculation of network contribution to transaction time The network contribution to transaction time can be calculated as fol

49、lows: ()()RTOLRTTENCTT +=4 ITU-T Rec. G.1040 (02/2006) where: E is the number of round-trip exchanges needed to complete a transaction RTT is the mean round-trip time for packet transfer L is the number of round-trip exchanges that experience a packet loss RTO is the retransmission time-out (assumed to be the same at client and host) L the number of losses experienced during a transaction, is dependent on the round-trip packet loss probability, p. If two one-way loss probabilities are given, then we have: ( ) ( ) wayotherwayRTpppp= 111