RTGWG N. Zhang, Ed.
Internet-Draft S. Zhang, Ed.
Intended status: Standards Track X. Yi, Ed.
Expires: 20 April 2025 China Unicom
X. Geng
H. Shi
Huawei
17 October 2024
Deep Collaboration between Application and Network
draft-zhang-rtgwg-collaboration-app-net-01
Abstract
This document analyzes the necessarity of deep collaboration between
the application and network. Besides, the problem, usecase and
requirement of bidirectional awareness between the application and
network are discussed.
Status of This Memo
This Internet-Draft is submitted in full conformance with the
provisions of BCP 78 and BCP 79.
Internet-Drafts are working documents of the Internet Engineering
Task Force (IETF). Note that other groups may also distribute
working documents as Internet-Drafts. The list of current Internet-
Drafts is at https://datatracker.ietf.org/drafts/current/.
Internet-Drafts are draft documents valid for a maximum of six months
and may be updated, replaced, or obsoleted by other documents at any
time. It is inappropriate to use Internet-Drafts as reference
material or to cite them other than as "work in progress."
This Internet-Draft will expire on 20 April 2025.
Copyright Notice
Copyright (c) 2024 IETF Trust and the persons identified as the
document authors. All rights reserved.
Zhang, et al. Expires 20 April 2025 [Page 1]
Internet-Draft Deep Collaboration between Application a October 2024
This document is subject to BCP 78 and the IETF Trust's Legal
Provisions Relating to IETF Documents (https://trustee.ietf.org/
license-info) in effect on the date of publication of this document.
Please review these documents carefully, as they describe your rights
and restrictions with respect to this document. Code Components
extracted from this document must include Revised BSD License text as
described in Section 4.e of the Trust Legal Provisions and are
provided without warranty as described in the Revised BSD License.
Table of Contents
1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . 2
2. Conventions and Definitions . . . . . . . . . . . . . . . . . 3
3. Problem statement . . . . . . . . . . . . . . . . . . . . . . 3
3.1. Awareness of network by application . . . . . . . . . . . 4
3.2. Awareness of application by network . . . . . . . . . . . 4
4. Use Cases . . . . . . . . . . . . . . . . . . . . . . . . . . 4
4.1. High-speed IoV . . . . . . . . . . . . . . . . . . . . . 4
4.2. Massive Data Transmission . . . . . . . . . . . . . . . . 5
4.3. Industrial Internet . . . . . . . . . . . . . . . . . . . 5
4.4. Sharing and Circulation of Data . . . . . . . . . . . . . 6
5. Requirement . . . . . . . . . . . . . . . . . . . . . . . . . 6
5.1. The ability of network awareness by application . . . . . 6
5.1.1. Accurate measurement of network indicators . . . . . 6
5.1.2. Cross cloud measurement . . . . . . . . . . . . . . . 6
5.1.3. Obtaining of measured network indicators by
application . . . . . . . . . . . . . . . . . . . . . 6
5.2. The ability of application awareness by network . . . . . 6
5.2.1. Fine grained awareness of application requirements . 7
5.2.2. Computing status awareness of server applications . . 7
6. Deployment case . . . . . . . . . . . . . . . . . . . . . . . 7
6.1. IoV solution based on application and network
collaboration . . . . . . . . . . . . . . . . . . . . . . 7
7. Security Considerations . . . . . . . . . . . . . . . . . . . 7
8. IANA Considerations . . . . . . . . . . . . . . . . . . . . . 7
9. References . . . . . . . . . . . . . . . . . . . . . . . . . 7
9.1. Normative References . . . . . . . . . . . . . . . . . . 8
9.2. Informative References . . . . . . . . . . . . . . . . . 8
Authors' Addresses . . . . . . . . . . . . . . . . . . . . . . . 9
1. Introduction
In the digital age, users have increasingly high expectations for
application services, seeking smooth, stable, and high-quality
experiences anytime and anywhere. This growing demand has led to the
emergence of new service scenarios, such as IoV and Industrial
Internet etc., which have higher and differentiated requirements for
both network and application services. These emerging services have
Zhang, et al. Expires 20 April 2025 [Page 2]
Internet-Draft Deep Collaboration between Application a October 2024
also driven the rapid development of technologies like cloud
computing and big data. As the scale of network and computing
resources expands, so does resource consumption. Currently,
applications and networks operate independently and are unable to
interact to ensure flexible and efficient resource scheduling.
Deep collaboration between applications and networks allows for the
accurate acquisition of application and network requirements and
statuses through mutual awareness. This enables dynamic adjustment
of resource allocation and scheduling strategies, leading to
efficient utilization of computing and network resources.
Ultimately, users benefit from the best possible service experience.
As technology advances and service scenarios expand, the importance
of deep collaboration between applications and networks will only
grow.
2. Conventions and Definitions
The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT",
"SHOULD", "SHOULD NOT", "RECOMMENDED", "NOT RECOMMENDED", "MAY", and
"OPTIONAL" in this document are to be interpreted as described in BCP
14 RFC2119 [RFC8174] when, and only when, they appear in all
capitals, as shown here. Abbreviations and definitions used in this
document: *IOAM: In Situ Operations, Administration, and Maintenance.
*IFIT: In-situ Flow Information Telemetry. *TWAMP: Two-Way Active
Measurement Protocol. *quic: A transport protocal. *DPI: Deep Packet
Inspection. *ACL: Access Control List. *SDN:
Software Defined Network. *CATS: Computing-Aware Traffic Steering.
3. Problem statement
User Server
+-----+ /-------\ +-----+
|App x| / \ |App x|
| |<-->| network |<-->| |
|App y| \ / |App y|
+-----+ \-------/ +-----+
In various scenarios, different applications have different
transmission requirements for the network. For example, some
applications in the IoV scenario have serious requirement for ultra-
low delay, while some applications in industrial internet have high
requirement for real time available bandwidth. If applications and
networks can achieve deep collaboration, network resources and
application requirements can be dynamically and accurately matched.
In this way, not only can the stability and user experience of the
application be improved, but the utilization efficiency of network
and computing resources can also be enhanced.
Deep collaboration between applications and networks must address two
main issues:
Zhang, et al. Expires 20 April 2025 [Page 3]
Internet-Draft Deep Collaboration between Application a October 2024
1.The precise awareness of network status by applications.
2.The awareness of application requirements and status by networks.
3.1. Awareness of network by application
Applications need to aware network indicators, such as available
bandwidth, delay, and packet loss, in real-time to dynamically adjust
data transmission policies. For example, low-priority packets can be
dropped to save the resource when the network is congested. This
helps save network resources and ensures service continuity and
efficiency.
3.2. Awareness of application by network
To intelligently allocate network resources and schedule computing
resources, networks need to understand the resource requirements of
different user applications and be aware of application statuses on
computing servers. This enables the network to provide
differentiated service guarantees for various applications.
4. Use Cases
4.1. High-speed IoV
In high-speed Internet of Vehicles (IoV), vehicles like cars, trains,
and subways need to communicate with other vehicles, infrastructure,
or cloud services to run onboard applications. These applications
fall into two categories:
1.Applications affecting driving, such as autonomous driving, remote
control, and intelligent driving services, which require extremely
low network delay for quick judgments and responses. Any delay could
lead to serious accidents.
2.Applications unrelated to driving, such as voice communications,
streaming media, and other entertainment services.
The diverse applications in high-speed IoV have complex requirements
for network and computing resources. Therefore, deep collaboration
between the network and applications is essential for efficient and
flexible scheduling of computing and network resources..
Zhang, et al. Expires 20 April 2025 [Page 4]
Internet-Draft Deep Collaboration between Application a October 2024
4.2. Massive Data Transmission
Massive Data Transmission (MDT) [I-D.liu-rtgwg-mdt-in-high-bdp] is a
predictable time-efficient application that requires data
transmission to be completed within a specified time. This
application is not sensitive to transmission delay, but requires a
considerable amount of network resources.
1.Before starting transmission, different tasks have different
demands of data size and expected completion time. This leads to
differentiated requirements of real-time available bandwidth for
different tasks..
2.After the transmission task is initiated, network devices need to
identify MDT applications and corresponding account information based
on certain identifiers to perform traffic record.
At the beginning of data transmission, application and network
collaboration can ensure the complete delivery of data without
affecting other services on the existing network. At the end of data
transmission, the network needs to accurately perceive MDT
applications for reasonable billing.
4.3. Industrial Internet
There are diverse scenarios in the industrial Internet, such as
automatic control production, video surveillance, remote robot
operation, etc. These applications have different requirements for
network reliability, bandwidth and latency, etc.
1.Many industrial control tasks require systems to respond within
strict time constraints, so automatic control applications have high
requirements for deterministic network delay.
2.Video surveillance requires the transmission of a large amount of
video data and real-time reflection of factory conditions.
Therefore, the network must have sufficient real-time available
bandwidth to support the real-time transmission of high-definition
videos.
3.Remote robot operation requires real-time transmission of control
instructions and feedback data, thus requiring ultra-low network
transmission delay to ensure accuracy and real-time operation.
Various applications in the industrial Internet have different
requirements for network resources. The collaboration between the
application and network can match the most suitable network resources
for corresponding applications.
Zhang, et al. Expires 20 April 2025 [Page 5]
Internet-Draft Deep Collaboration between Application a October 2024
4.4. Sharing and Circulation of Data
Institutions such as enterprises or hospitals may have demand for
data sharing and circulation, but these data often involve sensitive
information.. Therefore, it is necessary to classify and identify the
sensitivity level of data and bring this information to network, so
that the circulation scope of sensitive data can be controlled.
5. Requirement
5.1. The ability of network awareness by application
Applications cannot directly monitor network status but require the
network to accurately measure and communicate network indicators.
5.1.1. Accurate measurement of network indicators
Network status measurement can be achieved in two ways:
1.Directly marking the real service message or embedding measurement
information in it, as with IOAM [RFC9197] and IFIT
[I-D.song-opsawg-ifit-framework].
2.Indirectly simulating the service message and periodically
reporting measurement information, as with TWAMP.
The first method can reflect network indicators such as delay, packet
loss, and jitter in real-time, actively detecting service failures.
5.1.2. Cross cloud measurement
In cross cloud scenarios, performance testing of traffic between
cloud is required.
5.1.3. Obtaining of measured network indicators by application
To enable application awareness of measurement information, the
measurement data obtained by the receiver needs to be sent back to
the sender. [I-D.gao-quic-network-awareness-ack] defines a QUIC ACK
frame format to return network indicators to the sender.
5.2. The ability of application awareness by network
Network awareness of applications includes understanding application
requirements and server application statuses to provide the best
services.
Zhang, et al. Expires 20 April 2025 [Page 6]
Internet-Draft Deep Collaboration between Application a October 2024
5.2.1. Fine grained awareness of application requirements
The characteristic information of different application needs to be
obtained by network, including application type and requirement of
application, etc. Technologies such as DPI, ACL, and SDN can achieve
the parsing of application attributes. Besides, application
requirement information also needs to be carried into network to
achieve accurate and fast matching of network resources.
5.2.2. Computing status awareness of server applications
The network needs to be aware of the computing status of server
applications, such as computing capability and load, to guide traffic
to the optimal computing service node. The CATS group has conducted
in-depth research on this issue. [I-D.ietf-cats-framework] and
[I-D.yi-cats-hybrid-solution] define several frameworks for computing
awareness, while [I-D.shi-cats-analysis-of-metric-distribution]
discusses methods for distributing computing status information.
6. Deployment case
6.1. IoV solution based on application and network collaboration
The IoV solution based on application and network collaboration has
been deployed and validated for the first time in Hebei, China. In
this solution, the CATS, IFIT and identification technology were used
to achieve deep collaboration between application and network, which
provided high quality and more flexible solution for high-speed IoV.
Firstly, the hybrid CATS scheme used in this solution comprehensively
considered computing and network status for service selection and
path computation, which provided high quality computing service with
the optimal service site and optimal forwarding path for vehicle
terminal applications. Secondly, IFIT and innovative in-cloud
virtual router [I-D.hy-srv6ops-sfc-in-cloud-uc] technology were used
to achieve end-to-end network performance awareness. Thirdly,
identification technology was used to identify multiple application
types, so that the differentiated service scheduling and assurance
have been achieved.
7. Security Considerations
TBD
8. IANA Considerations
TBD
9. References
Zhang, et al. Expires 20 April 2025 [Page 7]
Internet-Draft Deep Collaboration between Application a October 2024
9.1. Normative References
[RFC2119] Bradner, S., "Key words for use in RFCs to Indicate
Requirement Levels", BCP 14, RFC 2119,
DOI 10.17487/RFC2119, March 1997,
<https://www.rfc-editor.org/info/rfc2119>.
[RFC8174] Leiba, B., "Ambiguity of Uppercase vs Lowercase in RFC
2119 Key Words", BCP 14, RFC 8174, DOI 10.17487/RFC8174,
May 2017, <https://www.rfc-editor.org/info/rfc8174>.
9.2. Informative References
[I-D.liu-rtgwg-mdt-in-high-bdp]
Ying, "Use Cases and Requirements of Massive Data
Transmission(MDT) in High Bandwidth-delay Product (BDP)
Network", Work in Progress, Internet-Draft, draft-liu-
rtgwg-mdt-in-high-bdp-01, 5 July 2024,
<https://datatracker.ietf.org/doc/html/draft-liu-rtgwg-
mdt-in-high-bdp-01>.
[RFC9197] Brockners, F., Ed., Bhandari, S., Ed., and T. Mizrahi,
Ed., "Data Fields for In Situ Operations, Administration,
and Maintenance (IOAM)", RFC 9197, DOI 10.17487/RFC9197,
May 2022, <https://www.rfc-editor.org/info/rfc9197>.
[I-D.song-opsawg-ifit-framework]
Song, H., Qin, F., Chen, H., Jin, J., and J. Shin,
"Framework for In-situ Flow Information Telemetry", Work
in Progress, Internet-Draft, draft-song-opsawg-ifit-
framework-21, 23 October 2023,
<https://datatracker.ietf.org/doc/html/draft-song-opsawg-
ifit-framework-21>.
[I-D.yi-cats-hybrid-solution]
Yi, X., Pang, R., and H. Shi, "Hybrid Computing and
Network Awareness and Routing Solution for CATS", Work in
Progress, Internet-Draft, draft-yi-cats-hybrid-solution-
03, 24 July 2024, <https://datatracker.ietf.org/doc/html/
draft-yi-cats-hybrid-solution-03>.
[I-D.gao-quic-network-awareness-ack]
xing, G., Han, M., Ruan, Z., and H. Shi, "QUIC network
awareness Acknowledgements", Work in Progress, Internet-
Draft, draft-gao-quic-network-awareness-ack-00, 3 July
2024, <https://datatracker.ietf.org/doc/html/draft-gao-
quic-network-awareness-ack-00>.
Zhang, et al. Expires 20 April 2025 [Page 8]
Internet-Draft Deep Collaboration between Application a October 2024
[I-D.ietf-cats-framework]
Li, C., Du, Z., Boucadair, M., Contreras, L. M., and J.
Drake, "A Framework for Computing-Aware Traffic Steering
(CATS)", Work in Progress, Internet-Draft, draft-ietf-
cats-framework-03, 17 September 2024,
<https://datatracker.ietf.org/doc/html/draft-ietf-cats-
framework-03>.
[I-D.shi-cats-analysis-of-metric-distribution]
Shi, H., Du, Z., Yi, X., and T. Yang, "Design analysis of
methods for distributing the computing metric", Work in
Progress, Internet-Draft, draft-shi-cats-analysis-of-
metric-distribution-03, 16 October 2024,
<https://datatracker.ietf.org/doc/html/draft-shi-cats-
analysis-of-metric-distribution-03>.
[I-D.hy-srv6ops-sfc-in-cloud-uc]
He, T. and X. Yi, "Use Cases and Requirements for Service
Function Chaining based on SRv6 in cloud.", Work in
Progress, Internet-Draft, draft-hy-srv6ops-sfc-in-cloud-
uc-00, 17 October 2024,
<https://datatracker.ietf.org/api/v1/doc/document/draft-
hy-srv6ops-sfc-in-cloud-uc/>.
Authors' Addresses
Naihan Zhang (editor)
China Unicom
Beijing
China
Email: zhangnh12@chinaunicom.cn
Shuai Zhang (editor)
China Unicom
Beijing
China
Email: zhangs366@chinaunicom.cn
Xinxin Yi (editor)
China Unicom
Beijing
China
Email: yixx3@chinaunicom.cn
Zhang, et al. Expires 20 April 2025 [Page 9]
Internet-Draft Deep Collaboration between Application a October 2024
Xuesong Geng
Huawei
Beijing
China
Email: gengxuesong@huawei.com
Hang Shi
Huawei
Beijing
China
Email: shihang9@huawei.com
Zhang, et al. Expires 20 April 2025 [Page 10]