Multiplexing. Common network/protocol functions. Multiplexing: Sharing resource(s) among users of the resource.

Transcription

1 Common network/protocol functions Goals: Identify, study common architectural components, protocol mechanisms Synthesis: big picture Depth: Important topics not covered in introductory courses Overview: Signaling State Multiplexing / Resource Allocation Randomization Indirection Service location Network virtualization with slides from Leon-Garcia and Widjaja, Shenker and Stoica 1 Multiplexing Multiplexing: Sharing resource(s) among users of the resource. Users Resources In this lecture: The Resources are Bandwidth (Link Capacity) Queues (Buffers) The Users are Phone Calls TCP/UDP flows, packets Other types of resources: CPU Storage Frequency spectrum and other types of users? 2 1

2 The resources and the users H1 R1 R2 H4 H2 H5 H3 R1 output queue 1.5 Mbps bandwidth H6 3 From Multiplexing to QoS Basic facts of life: Bandwidth is finite. Cannot support traffic demands beyond capacity. 1 Mbps phone R1 R2 FTP server 1.5 Mbps Example: 1Mbps IP phone, FTP share 1.5 Mbps link Bursts of FTP can congest router, cause large delays/audio loss. What s to be done? Move away from the best-effort paradigm. provide Quality of Service (QoS). 4 2

3 QoS: What is it? QoS Network provides applications with levels of performance guarantees needed for applications to function. Types of guarantees (service classes) Best-effort (elastic apps) Hard real-time (real-time apps) e.g., bounded loss / delay Soft real-time (tolerant apps) e.g., probabilistic loss / delay How to implement QoS? A set of five principles 5 Principle 1. Traffic/Guarantees specification Two 1Mbps IP phones share 1.5 Mbps link Want applications to specify: 1) How much bandwidth they need, 2) What levels of guarantees they want. 1 Mbps phone 1 Mbps phone R1 1.5 Mbps Traffic/guarantees specification Principle 1 Traffic/guarantees specification (service contract) needed for router to plan whether it can provide certain levels of performance guarantees. R2 6 3

4 Principle 2. Traffic classification 1Mbps IP phone, FTP share 1.5 Mbps link Bursts of FTP can congest router, cause audio loss. Want to give priority to audio over FTP. Can FTP server declare how much bandwidth it needs? 1 Mbps phone R1 voice FTP packets R2 FTP server 1.5 Mbps packet marking Principle 2 Packet marking needed for router to distinguish between different classes; and new router policy to treat packets accordingly. 7 Principle 3. Traffic isolation What if applications misbehave (audio sends higher than declared rate)? Want to force source adhere to traffic specification. 1 Mbps phone R1 R2 FTP server 1.5 Mbps link packet policing / shaping Principle 3 Provide protection (isolation) for one class from others. 8 4

5 Principle 4. Call admission Bandwidth is finite Cannot support more than available. To provide isolation, some flows have to be sacrificed. 1 Mbps phone R1 R2 1 Mbps phone 1.5 Mbps link Principle 4 Call Admission: network may block call (e.g., busy signal) if it cannot meet needs. 9 Principle 5. Resource sharing Allocating fixed (non-sharable) bandwidth Inefficient if flows don t use it Circuit/packet switching; scheduling 1 Mbps phone R1 1 Mbps logical link R2 FTP server Principle Mbps link 0.5 Mbps logical link While providing isolation, it is desirable to use resources as efficiently as possible. 10 5

6 Service Classes vs. Principles Traffic / Guarantees Specification Traffic Classification Traffic Isolation Call Admission Resource Sharing Best Effort Yes/No????? Hard real-time Soft real-time?????????? 11 Back to Multiplexing: many dimensions resource unavailability block, drop queue guaranteed on demand statistical reservations shared among class packet burst call per user user granularity Other dimensions? time granularity 12 6

7 Outline Scheduling Policing Admission Control General class-based link sharing (multiplexing) Concrete IETF proposals to do things in practice IntServ DiffServ Focus on packet-level multiplexing! 13 Scheduling And Policing Packets Scheduling: choose next packet to send on link. FIFO (first in first out) scheduling: send in order of arrival to queue. Real-world example: Stop sign Discard policy: Tail drop: drop arriving packet RED 14 7

8 Scheduling Policies: more Strict Priority scheduling: Transmit highest priority queued packet. Multiple classes, with different priorities Class may depend on marking or other header info, e.g. IP source/dest, port numbers, etc.. Real-world example: Reservations versus walk-ins arrivals time packet service departures 1 time Scheduling Policies: still more Round robin scheduling: Multiple classes Cyclically scan class queues, serving one from each class (if available). Real-world example: 4-way stop (distributed scheduling) 16 8

9 Scheduling Policies: still more Weighted Fair Queuing: Generalized Round Robin Each class gets weighted amount of service in each cycle. 17 Excursion: Fairness (1) How to divide a resource fairly? Philosophical question many notions of fairness exist! see also economics, law... (Gini index, Jain s fairness index, etc.) Important concept: max-min fairness Max-Min Fairness A max-min fair scheduler maximizes the minimum rate of any data flow. (First, the smallest rate is maximized, then the second smallest, etc.) 18 9

10 Excursion: Fairness (2) Max-min: Can only increase one rate if...?... there is not lower rate which would decrease Is FIFO max-min fair? No, larger flow gets larger share... Is Round Robin max-min fair? In case packets of the flows have same size: yes. Throughput compared to fixed division of resource? Max-min better, allows to exploit bandwidth not used by certain flows 19 Excursion: Fairness (3) Max-Min Algorithm 1. Start with all rates equal to 0 2. Grow all rates together at the same pace, until one or several link capacity limits are hit. The rates for the sources that use these links are not increased any more. 3. Continue increasing the rates for other sources. (All the sources that are stopped have a bottleneck link.) 4. The algorithm continues until it is not possible to increase. When the algorithm terminates, all sources have been stopped at some time and thus have a bottleneck link

11 Policing Mechanisms Goal: limit traffic to not exceed declared parameters Bits/second Peak rate Average rate Burst size? Time Three commonly-used criteria: (Long term) Average Rate: How many pkts can be sent per unit time (in the long run) crucial question: what is interval length: 100 packets per sec or 6000 packets per min have same average! Peak Rate: e.g., 6000 pkts per min. (ppm) avg.; ppm peak rate (Max.) Burst Size: max. number of pkts sent consecutively (with no 21 intervening idle) Leaky Bucket Algorithm Used to police arrival rate + burst size of a packet flow(s) water poured irregularly leaky bucket water drains at a constant rate Leak rate corresponds to long-term rate Bucket depth corresponds to maximum allowable burst arrival 1 packet per unit time Assume constant-length packet Let X = bucket content at last conforming packet arrival Let t a last conforming packet arrival time = depletion in bucket 22 11

12 Leaky Bucket Algorithm Arrival of a packet at time t a X = X - (t a - LCT) Depletion rate: 1 packet per unit time Current bucket content X < 0? Interarrival time Yes b = L+I = Bucket Depth I = increment per arrival, nominal interarrival time Non-empty No X = 0 Nonconforming packet Yes X > L? empty arriving packet would cause overflow No X = X + I LCT = t a conforming packet X = value of the leaky bucket counter X = auxiliary variable LCT = last conformance time conforming packet 23 Leaky Bucket Example I = 4 L = 6 Packet arrival Nonconforming Time L+I Bucket content I * * * * * * * * * Time Non-conforming packets not allowed into bucket & hence not included in calculations 24 12

13 Policing Mechanisms (more) Token bucket, WFQ combine to provide guaranteed upper bound on delay, i.e., QoS guarantee! arriving traffic token rate, r bucket size, b per-flow rate, R WFQ D = b/r max 25 Admission Control Users watch either one of two movies Star Wars (with the declared parameters) Silence of the Lambs (with the declared parameters) Concrete Problem: How many users can be admitted at a C=100Mbps link such that the delay for each user/movie is less than d=200ms? SW SOTL C=100Mbps 26 13

14 Admission Control (Contd.) Peak rate admission control Provides hard-guarantees The formula: Dual Leaky-bucket admission control Provides hard-guarantees The formula: Statistical admission control Provides soft-guarantees, e.g., (no formula here) Average rate admission control Only qualitative guarantees (e.g., delay is always finite) The formula: 27 Admission Control. Numerical Example Multiplexing Gain 28 14

15 General Model of Class-based Link Scheduling estimator class 1 class 2 classifier class 3 scheduler class 4 29 Link sharing among classes The question: Sharing link among classes of packets in times of overload Isolation among classes Sharing between classes when link not fully used. link link flow1 flow2 flow3 NSF ARPA DOE 30 15

16 Link Scheduling Framework Each class guaranteed some share (fraction) of bandwidth (over suitable time interval) if needed Use it or lose it: unused bandwidth should be used by others who can use it Under-limit class: used less than guaranteed share Over-limit class: used more than guaranteed share. Not a bad thing if not needed by others! At-limit class Unsatisfied class: has a persistent backlog and is under limit (persistent backlog intentionally not defined) Satisfied: not unsatisfied 31 Link Scheduling Hierarchies link 50% 40% 10% Agency A Agency B Agency C ftp http smtp IP ATM rt nrt 30% 10% 10% 25% 15% 9% 1% Classes may be divided into subclasses, which can then further divide class bandwidth according to link scheduling guidelines 32 16

17 Link Scheduling Guidelines A class can continue unregulated if one of the following hold: the class is not overlimit the class has a notoverlimit ancestor at level i, and there are no unsatisfied classes in link sharing structure at levels lower than i Agency A link Agency B Agency C ftp http smtp IP ATM rt nrt 33 Example 1 link legend under limit at limit A B over limit satisfied unsatisfied backlog A1 A2 B1 B2 Q; Which classes need to be regulated? 34 17

18 Example 2 link legend under limit at limit A B over limit satisfied unsatisfied backlog A1 A2 B1 B2 Q; Which classes need to be regulated? 35 Example 3 link legend under limit at limit over limit satisfied unsatisfied backlog A1 A2 B1 B2 Q; Which classes need to be regulated? 36 18

19 Example 4 link legend under limit at limit over limit satisfied unsatisfied backlog A1 A2 B1 B2 Q; Which classes need to be regulated? 37 Link Sharing Summary Timescales over which persistent backlog and under/over limit defined are crucial Provide rationale basis for determining who is available to be scheduled in a multi-class, multi-objective system (elegantly) Devil is in the details E.g., malicious users, parallel flows

20 QoS in the Internet. Part I. IETF Integrated Services Architecture for providing QOS guarantees in IP networks for individual application sessions Resource reservation: routers maintain state info (a la VC) of allocated resources, QoS req s Admit/deny new call setup requests: Question: can newly arriving flow be admitted with performance guarantees while not violated QoS guarantees made to already admitted flows? 39 Call Admission Arriving session must: Declare its QOS requirement R-spec: defines the QOS being requested Characterize traffic it will send into network T-spec: defines traffic characteristics Signaling protocol: Needed to carry R-spec and T-spec to routers (where reservation is required) RSVP 40 20

21 Intserv QoS: Service models [rfc2211, rfc 2212] Guaranteed service: Worst case traffic arrival: leaky-bucket-policed source Simple (mathematically provable) bound on delay [Parekh 1992, Cruz 1988] arriving traffic token rate, r bucket size, b WFQ Controlled load service: A quality of service closely approximating the QoS that same flow would receive from an unloaded network element." per-flow rate, R D = b/r max 41 Integrated Services Example Sender Install per flow state Receiver 42 21

22 Recall RSVP Signaling protocol for establishing per flow (soft) state Carry resource requests from hosts to routers Collect needed information from routers to hosts At each hop Consult admission control and policy module Set up admission state or informs the requester of failure Decouples routing from reservation 43 Integrated Services Example: Data Path Per-flow classification Sender Receiver 44 22

23 Integrated Services Example: Data Path Sender Per-flow buffer management Receiver 45 Integrated Services Example Per-flow scheduling Sender Receiver 46 23

24 How Things Fit Together Routing Messages Routing RSVP Admission Control Control Plane RSVP messages Forwarding Table Per Flow QoS Table Data Plane Data In Route Lookup Classifier Scheduler Data Out 47 QoS in the Internet. Part II. IETF Differentiated Services Want qualitative service classes behaves like a wire relative service distinction: Platinum, Gold, Silver Scalability: Simple functions in network core, relatively complex functions at edge routers (or hosts) Signaling, maintaining per-flow router state difficult with large number of flows Don t define service classes, provide functional components to build service classes 48 24

25 Diffserv Architecture Edge router: Per-flow traffic management Marks packets as in-profile and out-profile b marking r scheduling. Core router: Per class traffic management Buffering and scheduling based on marking at edge Preference given to in-profile packets 49 Edge-router Packet Marking Profile: pre-negotiated rate A, bucket size B Packet marking at edge based on per-flow profile Rate A B User packets Possible usage of marking: Class-based marking: packets of different classes marked differently Intra-class marking: conforming portion of flow marked differently than non-conforming one 50 25

26 Classification and Conditioning Packet is marked in the Type of Service (TOS) in IPv4, and Traffic Class in IPv6 6 bits used for Differentiated Service Code Point (DSCP) and determine PHB that the packet will receive 2 bits are currently unused 51 Classification and Conditioning May be desirable to limit traffic injection rate of some class: User declares traffic profile (e.g., rate, burst size) Traffic metered, shaped if non-conforming 52 26

27 Forwarding (PHB) PHB result in a different observable (measurable) forwarding performance behavior PHB does not specify what mechanisms to use to ensure required PHB performance behavior Examples: Class A gets x% of outgoing link bandwidth over time intervals of a specified length Class A packets leave first before packets from class B 53 Forwarding (PHB) PHBs being developed: Expedited Forwarding: pkt departure rate of a class equals or exceeds specified rate logical link with a minimum guaranteed rate Assured Forwarding: 4 classes of traffic each guaranteed minimum amount of bandwidth each with three drop preference partitions 54 27

28 Have a nice holiday! 55 28