Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research...

48
Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport

Transcript of Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research...

Page 1: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Distributed Snapshots: Determining Global States

of Distributed Systems

Joshua Eberhardt

Research Paper: Kanianthra Mani Chandy and Leslie Lamport

Page 2: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Background What is a distributed system?

Set of autonomous computers Communication network Software that integrates it into a single entity

Page 3: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Figure 1

Page 4: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Overview Introduction Model of a Distributed System Global-state Detection Algorithm

Motivation Termination

Stability Detection

Page 5: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Overview Introduction Model of a Distributed System Global-state Detection Algorithm

Motivation Termination

Stability Detection

Page 6: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Processes in Distributed Systems Process is an instance of a computer

program being executed. Processes in a distributed system

communicate by sending and receiving messages.

A process can record its own state and the message it sends and receives.

Page 7: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Global States and Processes To determine a global state, a process p

must cooperate with other processes to record their own states and send them to p.

Main problem is to devise an algorithm to record global states.

Page 8: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Global State Detection Problems Let y, be a predicate function defined over

the global states of the a distributed system D. (In other words, y(S) is true or false for a global

state S of D) The predicate y is a stable property of D if

y(S) implies y(S’) for global states S’ of D reachable from S of D

Page 9: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Going Further Many distributed system problems can be

formulated as the general problem of creating an algorithm by which a process in a distributed system can determine whether a stable property y holds.

Examples Deadlock Detection Termination Detection

Page 10: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Structure of Distributed Algorithms

Structured as sequence of phases. Transient Part Stable Part

Stability needs to be detected so that one phase can be terminated and another initiated. Termination of a Computational Phase vs.

Termination of a Computation

Page 11: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Termination Phase The overall problem can be partitioned into

the problems of detecting the termination of one phase and initiating a new phase.

Example of a stable property The kth computational phase has terminated

where k = 1, 2, 3, … Thus we can determine the termination of the kth

phase for any given k.

Page 12: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Overview Introduction Model of a Distributed System Global-state Detection Algorithm

Motivation Termination

Properties Stability Detection

Page 13: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Channels A distributed system consists of a finite set

of processes and a finite set of channels. Properties of channels.

Infinite buffers Error-free Deliver messages in order sent.

Page 14: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Linking the Terms State of a channel

Sequence of messages sent along the channel. Process

Defined by a set of states, including the initial state and a set of events.

Event An atomic action that may change the state of a

process and the state of at most one channel that is incident of the process.

Page 15: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Figure 2

Distributed system with processes p, q, r and channels C1, C2, C3, C4.

Page 16: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Events Can be defined by

Process p in which the event occurs State s of p before the event State s’ of p after the event Channel c whose state is altered by the event Message M sent along channel c

Based on these definitions we can define event e into a 5-tuple. <p, s, s’, M, c>

Page 17: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Expanding to Global States Global state of a distributed system is a set

of component process and channel states. Initially, all of the states are at their initial state,

and as a consequence all of the channels would be the empty sequence.

Occurrences of events may change the global state.

Page 18: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Events and Global States Remember e = <p, s, s’, M, c> We can say e can occur in a global state S:

The state of p in S is s If c is directed towards p, then the state of c in S

is a sequence of messages with M at the head. If c is directed away from p, then the state of c in

S is a sequence of messages with M at the tail.

Page 19: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Going Further If c is directed towards p, then the state of c

in S is a sequence of messages with M at the head. Define a function next where next(S, e) is the

global state immediately after the occurrence of event e in global state S.

The value of next(S, e) is defined only if event e can occur in global state S.

Page 20: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Computational Model Let seq = (ei: 0 < i < n) be a sequence of

events in component processes of a distributed system.

Si+1 = next(Si, ei) for (0 < i < n) where S0 is the initial global state.

We can say seq is a computation of the system iff ei can occur in Si

Page 21: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Example: Single Token Conversation (Deterministic)

Simple distributed system

State Transition Diagram of a Process

Page 22: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Example: Single Token Conversation (Deterministic)

Page 23: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Example: Message Passing (Nondeterministic)

New State Transition Diagrams

Page 24: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Example: Message Passing (Nondeterministic)

More then one way to change the initial global states, all subsequent states would then be different.

Page 25: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Overview Introduction Model of a Distributed System Global-state Detection Algorithm

Motivation Termination

Properties Stability Detection

Page 26: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Motivation How it works:

Each process records its own state and the 2 processes that a channel is incident on cooperate in recording the channel state.

Algorithm is to be superimposed on the underlying computation.

Next example will show how we can record the state of a channel instantaneously. Let c be a channel from p to q.

Page 27: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Single Token Example

Assume the state of process p is recorded as “in p”. Now assume that the global state transitions to “in c”. Suppose the states of c, c’, and q were also recorded in the global state “in c”.

This global state shows that there are two tokens! This shows inconsistency because the state of p was recorded

before p sent the message along c and the state of c is recorded after p sent the message.

Page 28: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Notation Let n be the number of messages sent

along c before p’s state is recorded. Let n’ be the number of messages sent

along c before c’s state is recorded. In our example, this inconsistency shows

that n < n’ or (0 < 1)

Page 29: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Another scenario

Suppose the state of c is recorded in global state “in p”. The system then transitions to the global state “in c” and the states of c’, p

and q are recorded in the global state “in c”. The recorded state shows no tokens in the system! This shows inconsistency when the state of c is recorded before p sends a

message along c and the state of p is recorded after p sends a message along c. Other words n > n’ (1 > 0)

To maintain consistency, n = n’

Page 30: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

In Relation to Messages Received Let m be the number of messages received along

c before q’s state is recorded. Let m’ be the number of messages received along

c before c’s state is recorded. To show consistency, m = m’ So for every state the number of messages

received along a channel can’t exceed the number of messages sent along that channel. In other words n > m and n’ > m’.

Page 31: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Bank Example

Page 32: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Bank Example

Page 33: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Bank Example

Page 34: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Important Details to Not e The state of channel c that is recorded must be

the sequence of messages sent along the channel before the sender’s state is recorded.

If n’ = m’, the recorded state of c must be the empty sequence.

If n’ > m’, the recorded state of c must be the (m’ + 1)st…… nth messages sent by p along c.

Page 35: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Markers From these conditions we can devise an

algorithm by which q can record the state of the channel c.

Process p sends a marker after the nth message it sends along c and before sending any messages further along c.

The state of c is the sequence of messages received by q after q records its own state and before q sends the marker along c.

To ensure n > m, q must record its state after receiving a marker along c and before q receives further messages along c.

Page 36: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Algorithm Outline Marker Sending Rule for a Process p

For each channel c, incident on and directed away from p:

p sends a marker along c after p records its state and before p sends further messages along c.

Page 37: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Algorithm Outline Marker Receiving Rule for a Process q

On receiving a marker along a channel c: if (q hasn’t recorded its state)

record qq records c as the empty sequence

elseq records the state of c as the

sequence of messages received along c after q’s state was recorded and before q received the marker along c

Page 38: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Overview Introduction Model of a Distributed System Global-state Detection Algorithm

Motivation Termination

Properties Stability Detection

Page 39: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Termination of the Algorithm The marker receiving and sending rules

guarantee that if a marker is received along every channel, then each process will record its state and the states of all incoming channels.

Page 40: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Finite Time To ensure that the global state recording

algorithm terminates in finite time, each process ensures No marker remains forever in an incident input

channel. It records its state within finite time of initiation of

the algorithm.

Page 41: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Finite Time If process records its state and there is a

channel from p to q, then q will record its state in finite time.

Termination in finite time is ensured if for every process q, q records its state or there is a path from p which records its state to q.

Page 42: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Overview Introduction Model of a Distributed System Global-state Detection Algorithm

Motivation Termination

Stability Detection

Page 43: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Stability Detection Motivation

It is a paradigm for many practical problems, such as distributed deadlock detection.

Can be defined as follows Input: A stable property of y Output: Boolean value definite with the property

(y(Si) definite) or (definite y(Sf)) where S i

represents the global state when initiated and S frepresents the global state when it is terminated.

Page 44: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

What this means Input of the algorithm is based on the function of

y. During execution of the algorithm the value y(S)

for any global state S may be determined by a process in the system.

With the output of the algorithm stored in the boolean value definite, we mean that Process p enters and thereafter remains in some special

state to signal that definite = true or false.

Page 45: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Definite value Definite = true

Implies the stable property holds when the algorithm terminates.

Definite = false Implies the stable property doesn’t hold when the

algorithm is initiated.

Page 46: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Solution begin

record a global state S*;definite := y(S*);

end. Correctness of the stability detection algorithm

S* is reachable from Si

Sf is reachable from S* (Theorem) y(S) y(S’) for all S’ reachable from S (definition of stable

property)

Page 47: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

Conclusion Distributed systems are applied to many

applications used today, especially in database applications.

Its important to know how each of the processes interact with each other and to know the global state of the system to ensure it is consistent.

Page 48: Distributed Snapshots: Determining Global States of Distributed Systems Joshua Eberhardt Research Paper: Kanianthra Mani Chandy and Leslie Lamport.

References Chandy, K. M. and Lamport L. Distributed

Snapshots: Determining Global States of Distributed Systems

http://www.eecs.ucf.edu/~dcm/Teaching/COT4810-Spring2011/Literature/ChandyAndLamport.pdf

Llewellyn M. Intro to OS: (Distributed Process Management)

http://www.cs.ucf.edu/courses/cop4600/sum2010/distributed%20process%20management%20-%20part%202%20(12).pdf