Diapositive 1

1

• SQUARE
• Scalable Quorum-based Atomic Memory with
• Local Reconfiguration
• Vincent Gramoli, Emmanuelle Anceaume, Antonino
  Virgillito

2
Context and Motivations

• Distributed systems become
• Large-scale
• Dynamic
• Unpredictable
• Challenges in Distributed Shared Memory
• Atomic Consistency
• Load Support

3
Distributed Shared Memory (DSM)

• Atomic Consistency
• Object Composition we focus on a single object
• Read operations return the last value written
• Replicated Object
• Replica is a node maintaining the value of the
  object
• Memory is the set of replicas
• Read/Write Operations ABD95
• Any client can read and modify (write) the object
• To do so, it contacts quorums (a.k.a. mutually
  intersecting sets) of replicas

4
Existing DSM solutions

• Lack of Independence
• Non-terminating operation may block others
  undefinitely
• Lack of Scalability
• Lack of Adaptiveness

Memory
Clients keep track of all memory
replicas (replacing a replica is complex)
Memory
Memory
Underloaded Memory (unused resource)
Overloaded Memory (bursts of load)
5
System Model

• Object replicated on failure-prone nodes
• The replicas r1, , rk share a 2-dim coordinate
  space

r1 r1 r2 r3 r4
r5 r6 r7 r8 r8


rk-1
rk
6
System Model

• Unreliable communication through neighborhood
• Each replica ri can communicate only with its
  nearest neighbors

ri

7
System Model

• Topology takeover mechanism (CAN RFH01)
• Upon node failure/departure the space sharing is
  modified accordingly

If a node ri fails, a takeover node rj replaces it
rj
ri

8
System Model

• Topology takeover mechanism (CAN RFH01)
• Upon node failure/departure the space sharing is
  modified accordingly

If a node ri fails, a takeover node rj replaces it
rj

9
Introducing our Dynamic Quorums

• Dual-type Dynamic Quorums
• Vertical Quorum All replicas responsible of an
  abscissa x
• Horizontal Quorum All replicas responsible of an
  ordinate y
• Intersection for Atomicity requirement
• Values are propagated (consulted) at a vertical
  (horizontal) quorum
• Thus, all consultations obtain the lastly
  propagated value

x





For any horizontal quorum H and any vertical
quorum V H ? V ? Ø
y
10
SQUARE features

• Atomicity and Independence
• Atomic operations are independent from each other
• Local Knowledge
• Reactive Quorum Access wrapping around the torus
• Fast Adaptive Read Operations
• Single phase operations accessing a single
  horizontal quorum is sufficient
• Memory Adaptiveness
• If overloaded (global approximation), then expand
  
• If underloaded (local observation), then shrink

11
Operation Execution

• Basic Write Operation
• Get up-to-date value,
• 2) Propagate the value to write (and a higher
  version number) twice on the same vertical quorum

• Fast Adaptive Read Op
• Get up-to-date value once on a single horizontal
  quorum.

• Basic Read Operation
• Get up-to-date value,
• 2) Propagate this value on a vertical Quorum.

12
Adjustment of the overlay size





SQUARE thwarts if the requested replica is
overloaded Other replicas on its diagonal are
contacted in turn until a non-overloaded one is
found





SQUARE expands if all contacted replicas are
overloaded A node outside the memory is added,
and the object value is replicated at this node.





SQUARE shrinks if a replica gets underloaded The
replica simply leaves the memory after neighbors
notification.
13
Simulation Results

• Self-Adaptiveness

14
Simulation Results

• Load-Balancing

15
Conclusion

• Atomic Consistency is guaranteed
• Using dynamic quorum intersection,
• Each failed/leaving participant is replaced to
  ensure quorum availability.
• Adaptiveness makes the algorithm tunable
• Minimizing operation latency as much as possible,
• Maximizing capability to support bursts of load.
• Perspective on operation speed up
• Kleinbergs model to route in polylog(q) hops

16
Some References

• CGG05 Reconfigurable distributed storage for
  dynamic networks.
• G. Chockler, S. Gilbert, V. Gramoli, P. M.
  Musial, and A. A. Shvartsman.
• In Proc. of 9th Intl Conf. on Principles of
  Distributed Systems (OPODIS05), 2005.
• AGGV05 P2P Architecture for Self-Atomic Memory
• E. Anceaume, M. Gradinariu, V. Gramoli, A.
  Virgillito
• In Proc of the 8th Intl Symposium on Parallel
  Architectures, Algorithms,and Networks
  (I-SPAN05)
• 214219, 2005.
• RFH01 A Scalable Content Adressable Network
• S. Ratnasamy, P. Francis, M. Handley, R. Karp,
  S. Shenker
• In Proc. of the ACM SIGCOMM, 161172, 2001.
• ABD95 Sharing Memory Robustly in Message
  Passing SystemsH. Attiya, A. Bar-Noy, D. Dolev
• In Journal of the ACM, 42(1)124142, 1995.

17
Simulation Results

• Operation Latency

Request rate Read latency Write latency Max. memory size Max. hor quorum size Max. vert. quorum size
1/250 478.6 733.3 10 5 6
1/200 621.8 812.5 14 4 8
1/100 1131.8 1395.8 24 3 14
1/50 1500.7 2173.5 46 8 23
1/25 2407.9 3500.9 98 11 51
18
Simulation Results

• Fault-tolerance

19
Simulation Results

• Scalability