Trust-Sensitive Scheduling on the Open Grid

1
Trust-Sensitive Scheduling on the Open Grid

• Jon B. Weissmanwith help from Jason Sonnek and
  Abhishek Chandra
• Department of Computer Science
• University of Minnesota
• Trends in HPDC Workshop
• Amsterdam 2006

2
Background

• Public donation-based infrastructures are
  attractive
• positives cheap, scalable, fault tolerant
  (UW-Condor, _at_home, ...)
• negatives hostile - uncertain resource
  availability/connectivity, node behavior,
  end-user demand gt best effort service

3
Background

• Such infrastructures have been used for
  throughput-based applications
• just make progress, all tasks equal
• Service applications are more challenging
• all tasks not equal
• explicit boundaries between user requests
• may even have SLAs, QoS, etc.

4
Service Model

• Distributed Service
• request -gt set of independent tasks
• each task mapped to a donated node
• makespan
• E.g. BLAST service
• user request (input sequence) chunk of DB form
  a task

5
BOINC BLAST
workunit input_sequence chunk of DB generated
when a request arrives
6
The Challenge

• Nodes are unreliable
• timeliness heterogeneity, bottlenecks,
• cheating hacked, malicious (gt 1 of SETi nodes),
  misconfigured
• failure
• churn
• For a service, this matters

7
Some data- timeliness
Computation Heterogeneity - both across and
within nodes
PlanetLab lower bound
Communication Heterogeneity - both across and
within nodes
8
The Problem for Today

• Deal with node misbehavior
• Result verification
• application-specific verifiers not general
• redundancy voting
• Most approaches assume ad-hoc replication
• under-replicate task re-execution ( latency)
• over-replicate wasted resources (v throughput)
• Using information about the past behavior of a
  node, we can intelligently size the amount of
  redundancy

9
System Model
10
Problems with ad-hoc replication
Unreliable node
Task x sent to group A
Reliable node
Task y sent to group B
11
Smart Replication

• Reputation
• ratings based on past interactions with clients
• simple sample-based prob. (ri) over window t
• extend to worker group (assuming no collusion) gt
  likelihood of correctness (LOC)
• Smarter Redundancy
• variable-sized worker groups
• intuition higher reliability clients gt smaller
  groups

12
Terms

• LOC (Likelihood of Correctness), lg
• computes the actual probability of getting a
  correct answer from a group of clients (group g)
• Target LOC (ltarget)
• the task success-rate that the system tries to
  ensure while forming client groups
• related to the statistics of the underlying
  distribution

13
Trust Sensitive Scheduling

• Guiding metrics
• throughput r is the number of successfully
  completed tasks in an interval
• success rate s ratio of throughput to number of
  tasks attempted

14
Scheduling Algorithms

• First-Fit
• attempt to form the first group that satisfies
  ltarget
• Best-Fit
• attempt to form a group that best satisfies
  ltarget
• Random-Fit
• attempt to form a random group that satisfies
  ltarget
• Fixed-size
• randomly form fixed sized groups. Ignore client
  ratings.
• Random and Fixed are our baselines
• Min group size 3

15
Scheduling Algorithms
16
Scheduling Algorithms (contd)
17
Different Groupings
ltarget .5
18
Evaluation

• Simulated a wide-variety of node reliability
  distributions
• Set ltarget to be the success rate of Fixed
• goal match success rate of fixed (which
  over-replicates) yet achieve higher throughput
• if desired, can drive tput even higher (but
  success rate would suffer)

19
Comparison
gain 25-250 open question how much better
could we have done?
20
Non-stationarity

• Nodes may suddenly shift gears
• deliberately malicious, virus, detach/rejoin
• underlying reliability distribution changes
• Solution
• window-based rating (reduce t 20 from infinite)
• Experiment blackout at round 300 (30
  effected)

21
Role of ltarget

• Key parameter
• Too large
• groups will be too large (low throughput)
• Too small
• groups will be too small (low success rate)
• Adaptively learn it (parameterless)
• maximizing r s goodput
• or could bias toward r or s

22
Adaptive algorithm

• Multi-objective optimization
• choose target LOC to simultaneously maximize
  throughput r and success rate s
• a1 r a2 s
• use weighted combination to reduce multiple
  objectives to a single objective
• employ hill-climbing and feedback techniques to
  control dynamic parameter adjustment

23
Adapting ltarget

• Blackout example

24
Throughput (a11, a20)
25
Current/Future Work

• Implementation of reputation-based scheduling
  framework (BOINC and PL)
• Mechanisms to retain node identities (hence ri)
  under node churn
• node signatures that capture the
  characteristics of the node

26
Current/Future Work (contd)

• Timeliness
• extending reliability to encompass time
• a node whose performance is highly variable is
  less reliable
• Client collusion
• detection group signatures
• prevention
• combine quiz-based tasks with reputation systems
• form random-groupings

27

• Thank you.