| Computing in Network Research Group | P. Liu |
| Internet-Draft | H. Yao |
| Intended status: Informational | L. Geng |
| Expires: January 11, 2021 | China Mobile |
| July 10, 2020 |
Differential Computing Resource Reservation
draft-liu-coin-differential-reservation-00
Computing in the network may require the embedded computing capability in the network device, such as gateway, switch, etc, and there might be so much distributed computing task in the network. Some new applications like AR/VR, motion control put forward higher demand of network than before, and AI is also considered to be used in the app and network.
In order to satisfy their demands, network may not only need to reserve bandwidth resource, but also reserve computing resource. This document analyzes the requirements of Serial distributed computing model and give some reference solutions.
The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", "SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and "OPTIONAL" in this document are to be interpreted as described in RFC 2119.
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 January 11, 2021.
Copyright (c) 2020 IETF Trust and the persons identified as the document authors. All rights reserved.
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 Simplified BSD License text as described in Section 4.e of the Trust Legal Provisions and are provided without warranty as described in the Simplified BSD License.
From cloud computing to edge computing, computing power is distributed to the customer side. In the future network and computing convergence system, computing power will be distributed as ubiquitous endogenous resources in each node of the network. The user's request can be satisfied by calling the nearest node resource, which is no longer limited to a specific node.
Resource reservation is usually used to guarantee the QoS of specific application traffic. The reservation of network resources is same in an end-to-end path, which means the reserved bandwidth resources will not change from the client to the server, but computing is different. Distributed computing will bring different computing power, and different resources need to be reserved for different nodes. For example, AI algorithm now has a model of step-by-step iteration at multiple nodes. The previous iteration will affect the next calculation results, and the computing resources required for each iteration are not the same. From the perspective of network standard, we hope to regard computing resources as the dimensions to measure network performance, such as the same bandwidth, path, etc., while the traditional technologies of resource reservation have not considered the reservation of computing resources, and have not considered the differentiated resource reservation model.
Existing resource reservation protocols, such as Resource ReSerVation Protocol(RSVP) and Path Computation Element Protocol (PCEP) , can be used to reserve bandwidth resources. RSVP is a traditional protocol, which only focuses on how to initiate the reservation of resources, not the establishment of path. Later, RSVP-TE protocol was developed for MPLS. PCEP was designed to separate the path calculation and path establishment functions of RSVP-TE firstly, which means that the path calculation part before resource reservation can be realized. Therefore, RSVP and PCEP can be used together or separately.
Resource reservation is currently regarded as the key technology configuration scheme to guarantee network QoS. In order to solve the problem of bandwidth competition caused by the simultaneous arrival of specific data flow and common data flow on the network node, the bandwidth reservation management of data from the source node to the destination node end-to-end is realized, so as to ensure the real-time data flow QoS and delay requirements. The general process is as follows:
The sender client initiates the request of resource reservation by the path message. After determining the path, the sender sends the request along the path, carrying the network requirements (latency, etc.) to the receiver.
The receiver calculates the bandwidth and other resources that need to be reserved for the network according to the request of the sender. Then it returns according to the original path, and informs the equipment to reserve resources one by one.
Path Computation Element Protocol (PCEP) is a centralized configuration technology, which is usually used in software defined network (SDN) as the South interface calculation and configuration path information. PCE can improve the agility of the network. Any change in network can be programmed using PCECC to learn the change and react to it quickly and efficiently.
PEC can initiate resource reservation application to each device in the path by the PCLRResv message. This message is sent by Path Computation Element (PCE) to Path Computation Client (PCC) to sent reserved label range for the network. The objects supported in this message are stateful PCE request parameters objects, setting the unique identifier for mapping request/response between PCEP and PCC.
In the model of computing in the network, the computing resource may be distributed in multiple nodes. A task may be divided into several parts to be executed by multiple nodes, including serial distribution and parallel distribution. Parallel distribution can reserve resources separately. However, in the serial computing model, the calculation process of serial distribution algorithm is sequential, and the results of the previous calculation need to be used in the later calculation, so it will bring the following two problems:
Different computing nodes on the same path need different reserved computing resources.
The bandwidth resources to be reserved maybe different after the previous calculations in the same path.
A typical example is the artificial intelligence algorithm, which involves the multi-layer convolution iterative process and can be completed by multiple computing device in serial. As shown in the figure, 20%, 30% and 50% tasks are calculated on network device 1, 3 and server respectively, and the calculation results of device 1 will affect the subsequent calculation of device 3 and server. Then,
Network device 1, 3 and server need to reserve corresponding computing resources respectively.
Since devices 1 and 3 calculated, the traffic will change after passing through devices 1 and 3, so the bandwidth resources to be reserved are different.
Traditional RSVP and other protocols do not consider the calculation attribute, so the reserved value of bandwidth resource along the path is unchanged, and the calculation resource cannot be reserved. PCEP also dosen't consider about the comuputing resource.
+------+ +--------+
|Client| ->| Server |
+------+ \ +--------+ +--------+ +--------+ / +--------+
\->|network | |network | |network |->/ 50% of
|device 1|-->|device 2|-->|device 3| computing
+--------+ +--------+ +--------+ tasks
20% of 30% of
computing computing
tasks tasks
Serial distributed computing model
This scheme provides distributed and centralized resource reservation reference scheme. It should be noted that for serial distributed computing, we assume that the application side implements the following functions:
The number of steps are involved in the calculation.
The computing proportion of calculation required at each node.
For bandwidth changes after each step of calculation, if this item cannot be implemented, the same bandwidth resources will be reserved by default.
Distributed resource reservation can be implemented by extending RSVP or RSVP-TE protocol. The server receives the client's service request, calculating the resource reservation strategy and return it. The process is as follows:
1. The client sends the service request, carrying the service requirements and the collected resource status of each node on the path. They will be collected and added to the information that carried by the service request.
2. The server receives the client's service request, then generates the resource reservation strategy for target nodes on the path based on the the service requirements and the resource status of each node, and return the resource reservation strategy to each target node along the path to reserve the resource.
The resource status at least includes the computing resource status such as the catergery of chip, algorithm, etc. It can also includes the network resource status such as bandwidth, delay, etc.
The resource reservation strategy at least includes the computing resource reservation information of target nodes, which is as follows:
1. Determine the serial distributed computing subtasks and computing resources required by each computing subtask based on the service request.
2. Select the target nodes for each computing subtask and generate the computing resources reservation information to inform each target node to reserve resource based on the computing resource status of each node and the computing resources required by each computing subtask.
Moreover, if the bandwidth change after each subtask can be calculated, the resource reservation strategy can also carrying the bandwidth resources reservation information.
It can be realized by defining new object of RSVP or RSVP-TE to reserve different resources in each target nodes. The object can be customized and extended with variable length. For example, redefining a new class num as 30, carries the following message body:
[L = 0, IPv4, 64, IP address1, bandwidth 1, computing resource 1]
[L = 0, IPv4, 64, IP address2, bandwidth 2, computing resource 2]
[L = 0, IPv4, 64, IP address3, bandwidth 3, computing resource 3]
[L = 0, IPv4, 64, IP address4, bandwidth 4, computing resource 4]
......
It should be noted that the extended object can not only carry the collected resources status of each node in the PATH message, but also return the resource reservation strategy in the RESV message.
Centralized resource reservation can be realized by the network manager. The manager receives the service request, calculates the network and computing resources needed, and initiates resource reservation configuration for the target nodes along the path.The process is as follows:
The client sends a service request to the network manager.
Network manager selects the path according to the service request and get the resource status of each node on the path.
Network manager generates the resource reservation strategy based on the client's service request and resource status of each node.
Network manager sends resource reservation strategy to target nodes to reserve the resource.
The resource status at least includes the computing resource status. The resource reservation strategy at least includes the computing resource reservation information of each target node. Which are the same with chapter 4.1.
If at least one node in the selected path does not meet the resource reservation requirements, it is necessary to re-select at least one node in the path and get the resource status of the re-selected node until the path meets the requirements of the resource reservation strategy.
By adding calculation force resource reservation field to resource reservation object in PECP message, each calculation force flow has a dynamic resource range based on the minimum reserved resource.
+---------+---------+-----------+----------+--------+ | Object | Label | Reserverd |Interface | In/ | | Type | ID | Bandwidth |IP Address| Out | +---------+---------+-----------+----------+--------+
PCEP extension
It can also send resource reservation configuration to the target nodes by netconf and defining the Yang structure. The reference Yang module is as follows.
module: rs-computing-network
+--rw rs-computing-network
+--rw added-device[id]
| +--rw service id string
| +--rw user id string
| +--rw bandwitdh mbps
| +--rw computing resource tbd
+--rw deleted-device[id]
Yang Module
The draft proposes a method of differential reservation of computing power and bandwidth resources. Because the traditional network does not include computing power, the reservation of network resources is the same on the path. This scheme can accurately reserve computing power and network resources for the serial distributed computing services. It also present the reference methods to realize different resource reservation.Of course, there may be more and more appropriate methods to achieve serial distributed computing power and network resource reservation, which may require more analysis and discussion.
TBD.
TBD.
| [RFC2119] | Bradner, S., "Key words for use in RFCs to Indicate Requirement Levels", BCP 14, RFC 2119, DOI 10.17487/RFC2119, March 1997. |
| [RFC5440] | Vasseur, JP. and JL. Le Roux, "Path Computation Element (PCE) Communication Protocol (PCEP)", RFC 5440, DOI 10.17487/RFC5440, March 2009. |