Service Level Agreements and QoS: what do we measure and why Omer F. Rana

1
Service Level Agreements and QoS what do we
measure and why?Omer F. Rana

• o.f.rana_at_cs.cardiff.ac.uk
• School of Computer Science, Cardiff University,
  UK
• Welsh eScience Centre, UK

2
QoS Management

• QoS has been explored in
• Computer Networks
• Bandwidth, Delay, Packet loss rate and Jitter.
• Multimedia Applications
• Frame rate and computation resource.
• Grid Computing
• Network QoS, computation and storage
  requirements.

3
Continue

• QoS management
• Covers a range of different activities, from
  resource specification, selection and allocation
  through to resource release.
• QoS system should address the following
• Specifying QoS requirements
• Mapping of QoS requirements to resource
  capability
• Negotiating QoS with resource owners
• Establishing contracts / SLAs with clients
• Reserving and allocating resources
• Monitoring parameters associated with QoS
  sessions
• Adapting to varying resource quality
  characteristics
• Terminating QoS sessions
• User Expectations vs. Resource Management

4
When QoS is needed?

• Interactive sessions
• Computation steering (control parameters data
  exchange)
• Interactive visualization (visualization
  simulations services)
• Response within a limited time span
• Co-scheduling or co-location support

From SCIRun, University of Utah

• Application QoS
• User perception, response time, appl. Security,
  etc.
• Middleware QoS
• Comp., Memory and Storage
• Network QoS
• BW, Packet loss, Delay, Jitter

5
What is a Service Level Agreement (SLA)?
A relationship between a client and provider in
the context of a particular capability (service)
provision
Provider
Client
Can you do X for me for Y in return?
SLA
SLA
SLA-Offer
SLA-Accept SLA-Reject
Yes
P2P Search, Directory Service
Distinguish between Discovery of suitable
provider Establishment of an SLA
6
What is an SLA?
Provider
Client
Can you do X for me for Y in return?
SLA
SLA
SLA-Offer
SLA-CounterOffer
No, but I can do Z for Y
SLA-Accept SLA-Reject
Accept
7
What is an SLA?
Provider
Client
Can you do X for me for Y in return?
SLA
SLA
SLA-Offer
SLA-CounterOffer
No
Negotiation Phase (Single or Multi-Round)
SLA-Offer
Dependency
Can you do Z for me for Y in return?
8
Variations
Providers
Client
SLA
SLA
SLA dependencies For an SLA to be valid,
another SLA has to be agreed (e.g. co-allocation)
Multi-provider SLA Single SLA is divided across
multiple providers (e.g. workflow composition)
9
QoS Context

• QoS
• Per Service
• Per Workflow (Set of Services)
• Workflow
• Aggregating metrics across services
• Support through some workflow enactor

10
What is an SLA?

• Dynamically established and managed relationship
  between two parties
• Objective is delivery of a service by one of
  the parties in the context of the agreement
• Delivery involves
• Functional
• QoS Properties

www.utilityserve.com SLA
11
Forming the Agreement

• Distinguish between
• Agreement itself
• Mechanisms that lead to the formation of the
  agreement
• Mechanisms that lead to agreement
• Negotiation (single or multi-shot)
• One-shot creation
• Policy-based creation of agreements, etc.

12
WS-Agreement
Agreement
Information about Agreement Initiator Responder Ex
piration Time
Name/ID
Context
Information about Service Service Description
Terms (generally, these are domain dependent)
Terms Composition
Service Terms
Information about Service Level Service Level
Objectives, Qualifying Conditions for the
agreement to be valid, Penalty Terms, etc
Guarantee Terms
13
WS-Agreement Terms
From Viktor Yarmolenko (U Manchester)
14
SLA Life Cycle

• Identify Provider
• On completion of a discovery phase
• Define SLA
• Define what is being requested
• Agree on SLA terms
• Agree on Service Level Objectives
• Monitor SLA Violation
• Confirm whether SLOs are being violated
• Destroy SLA
• Expire SLA
• Penalty for SLA Violation

15
CATNETs Metrics Pyramid
16
SLA Classes

• Guaranteed
• constraints to be exactly observed
• SLA is precisely/exactly defined
• adaptation algorithm/optimization heuristics
• Controlled-load
• some constraints may be observed
• Range-oriented SLA
• optimization heuristics
• Best-effort
• any resources will do
• no adaptation support

17
Adaptation Algorithm

• Assume a total capacity C CG CA CB
• where G, A B denotes guaranteed,
  adaptive and best effort
• Adapt(c(u,t), g(u))
• Net capacity NG(t) CG(t)
• If NG(t) lt 0 (guarantees cant be honoured)
• Then ADD ( - CG(t))
  from A to G
• ADD (CA(t) - CG(t))
  from A to B
• Before invoking the adaptive function
• Ensuring that the request at time (t) g(u)
  --- (SLA)
• Ensuring that CG

CG(t) Capacity in guaranteed block at time
t g(u) guarantee to user user u
18
SLA Adaptation
Aim compensation for QoS degradation for
guaranteed class only

• Assume capacityTotal C CG CA CB
• best effort can uses the adaptive capacity, as
  long as its not used by the guaranteed
• When QoS degrades for guaranteed
• Then adaptive is utilized to compensate for the
  degradation
• best effort can still utilize the remaining
  capacity of the adaptive, as long as its not used
  by the guaranteed
• When the congested capacity is restored, the
  adaptive capacity can be used entirely by the
  best effort

• Before invoking the adaptive function
• Ensuring that the request at time (t) the
  agreed upon in the SLA
• Ensuring that the total capacities within all
  SLAs at time (t) CG

19
SLA Adaptation

• If we define a set QoS a1, a2, ..., an ,
  where each ai represents a different parameter of
  interest such as CPU, network bandwidth, etc.
• Then we could compare sets QoSx a1x, ...,
  anx and
• QoSy a1y, ..., any
• QoS values specified in SLA as ay ai ax
  Or ai x, y, z
• Assume the existence of a cost function Cost(ai)
  ci ai
• Then Service_ Cost (QoS)
• The proposed heuristic Total Cost max
• n is the total number of active services

The QoS broker implements this heuristic by
varying the resource quality selection, based
on the agreed upon in the SLA, aiming to Optimize
resource utilization and maximize the overall
cost.
This heuristic could be mapped to the Generalized
Assignment Problem (GAP)
20
Resources
Policy Manager
Reservation Manager
Allocation Manager
QoS Grid Service
Grid QoS service interface
Grid Node
21
Main components

• Policy Manager
• To provide dynamic info about the domain-specific
  resource characteristics and policy
• Reservation Manger
• To provide advance/immediate resource reservation
• Data structure contains reservation entries
• Interact with policy manager for resource char.
• Allocation Manger
• To interact with the underlying resource manager
  for resource allocation (e.g DSRT, Bandwidth
  Broker)

22
SLA
SLA
SLA
Joint work with Argonne National Lab. (Gregor von
Lazweski et al.)
23
Reservation Approaches

• Resource reservation / allocation based on two
  strategies
• Time-domain reserve the whole compute power of
  Grid node.
• Guaranteed exclusive access
• Resource-domain reserve a CPU slot of the Grid
  node.
• Shared access guaranteed resource capacity
• Suitable for light weight applications/services.

24
Best Effort
25
Guaranteed
26
(No Transcript)