Day 2 global_state_and_snapshot_algorithms

Chapter 4: Global State and Snapshot Recording
Algorithms

Ajay Kshemkalyani and Mukesh Singhal

Distributed Computing: Principles, Algorithms, and Systems

Cambridge University Press

A. Kshemkalyani and M. Singhal (Distributed Computing) lobal State and Snapshot Recording Algorithms
G CUP 2008 1 / 51


Introduction

Recording the global state of a distributed system on-the-fly is an important
paradigm.
The lack of globally shared memory, global clock and unpredictable message
delays in a distributed system make this problem non-trivial.
This chapter first defines consistent global states and discusses issues to be
addressed to compute consistent distributed snapshots.
Then several algorithms to determine on-the-fly such snapshots are presented
for several types of networks.

G CUP 2008 2 / 51


System model

The system consists of a collection of n processes p1 , p2 , ..., pn that are
connected by channels.
There are no globally shared memory and physical global clock and processes
communicate by passing messages through communication channels.
Cij denotes the channel from process pi to process pj and its state is denoted
by SCij .
The actions performed by a process are modeled as three types of events:
Internal events,the message send event and the message receive event.
For a message mij that is sent by process pi to process pj , let send(mij ) and
rec(mij ) denote its send and receive events.

G CUP 2008 3 / 51


System model

At any instant, the state of process pi , denoted by LSi , is a result of the
sequence of all the events executed by pi till that instant.
For an event e and a process state LSi , e∈LSi iff e belongs to the sequence
of events that have taken process pi to state LSi .
For an event e and a process state LSi , e∈LSi iff e does not belong to the
sequence of events that have taken process pi to state LSi .
For a channel Cij , the following set of messages can be defined based on the
local states of the processes pi and pj

Transit: transit(LSi , LSj ) = {mij |send(mij ) ∈ LSi rec(mij ) ∈ LSj }

G CUP 2008 4 / 51


Models of communication

Recall, there are three models of communication: FIFO, non-FIFO, and Co.
In FIFO model, each channel acts as a first-in first-out message queue and
thus, message ordering is preserved by a channel.
In non-FIFO model, a channel acts like a set in which the sender process adds
messages and the receiver process removes messages from it in a random
order.
A system that supports causal delivery of messages satisfies the following
property: “For any two messages mij and mkj , if send(mij ) −→ send(mkj ),
then rec(mij ) −→ rec(mkj )”.

G CUP 2008 5 / 51


Consistent global state

The global state of a distributed system is a collection of the local states of
the processes and the channels.
Notationally, global state GS is defined as,
GS = { i LSi , i ,j SCij }
A global state GS is a consistent global state iff it satisfies the following two
conditions :
C1: send(mij )∈LSi ⇒ mij ∈SCij ⊕ rec(mij )∈LSj . (⊕ is Ex-OR
operator.)
C2: send(mij )∈LSi ⇒ mij ∈SCij ∧ rec(mij )∈LSj .

G CUP 2008 6 / 51


Interpretation in terms of cuts

A cut in a space-time diagram is a line joining an arbitrary point on each
process line that slices the space-time diagram into a PAST and a FUTURE.
A consistent global state corresponds to a cut in which every message
received in the PAST of the cut was sent in the PAST of that cut.
Such a cut is known as a consistent cut.
For example, consider the space-time diagram for the computation illustrated
in Figure 4.1.
Cut C1 is inconsistent because message m1 is ﬂowing from the FUTURE to
the PAST.
Cut C2 is consistent and message m4 must be captured in the state of
channel C21 .

G CUP 2008 7 / 51


C C2
1
e1
1
e2
1
e3
1
4
e1
p
1 m1
1
e2 e22 e23 e4
2 m m
5
p2 4
1 m2
e e2
3
3
e3 4
e3
5
e3
p3 3

m
1
e4 3 e42
p4

time

Figure 4.1: An Interpretation in Terms of a Cut.

G CUP 2008 8 / 51


Issues in recording a global state

The following two issues need to be addressed:
I1: How to distinguish between the messages to be recorded in the
snapshot from those not to be recorded.

-Any message that is sent by a process before recording its
snapshot, must be recorded in the global snapshot (from C1).
-Any message that is sent by a process after recording its snapshot,
must not be recorded in the global snapshot (from C2).
I2: How to determine the instant when a process takes its snapshot.

-A process pj must record its snapshot before processing a message
mij that was sent by process pi after recording its snapshot.

G CUP 2008 9 / 51


Snapshot algorithms for FIFO channels

Chandy-Lamport algorithm
The Chandy-Lamport algorithm uses a control message, called a marker
whose role in a FIFO system is to separate messages in the channels.
After a site has recorded its snapshot, it sends a marker, along all of its
outgoing channels before sending out any more messages.
A marker separates the messages in the channel into those to be included in
the snapshot from those not to be recorded in the snapshot.
A process must record its snapshot no later than when it receives a marker on
any of its incoming channels.

G CUP 2008 10 / 51



The algorithm can be initiated by any process by executing the “Marker
Sending Rule” by which it records its local state and sends a marker on each
outgoing channel.
A process executes the “Marker Receiving Rule” on receiving a marker. If the
process has not yet recorded its local state, it records the state of the channel
on which the marker is received as empty and executes the “Marker Sending
Rule” to record its local state.
The algorithm terminates after each process has received a marker on all of
its incoming channels.
All the local snapshots get disseminated to all other processes and all the
processes can determine the global state.

G CUP 2008 11 / 51



Marker Sending Rule for process i
1 Process i records its state.
2 For each outgoing channel C on which a marker
has not been sent, i sends a marker along C
before i sends further messages along C.
Marker Receiving Rule for process j
On receiving a marker along channel C:
if j has not recorded its state then
Record the state of C as the empty set
Follow the “Marker Sending Rule”
else
Record the state of C as the set of messages
received along C after j’s state was recorded
and before j received the marker along C

G CUP 2008 12 / 51


Correctness and Complexity

Correctness
Due to FIFO property of channels, it follows that no message sent after the
marker on that channel is recorded in the channel state. Thus, condition C2
is satisﬁed.
When a process pj receives message mij that precedes the marker on channel
Cij , it acts as follows: If process pj has not taken its snapshot yet, then it
includes mij in its recorded snapshot. Otherwise, it records mij in the state of
the channel Cij . Thus, condition C1 is satisﬁed.
Complexity
The recording part of a single instance of the algorithm requires O(e)
messages and O(d) time, where e is the number of edges in the network and
d is the diameter of the network.

G CUP 2008 13 / 51


Properties of the recorded global state

The recorded global state may not correspond to any of the global states that
occurred during the computation.
This happens because a process can change its state asynchronously before
the markers it sent are received by other sites and the other sites record their
states.
◮ But the system could have passed through the recorded global states in some
equivalent executions.
◮ The recorded global state is a valid state in an equivalent execution and if a
stable property (i.e., a property that persists) holds in the system before the
snapshot algorithm begins, it holds in the recorded global snapshot.
◮ Therefore, a recorded global state is useful in detecting stable properties.

G CUP 2008 14 / 51


Spezialetti-Kearns algorithm
There are two phases in obtaining a global snapshot: locally recording the
snapshot at every process and distributing the resultant global snapshot to all the
initiators.
Efficient snapshot recording
In the Spezialetti-Kearns algorithm, a markers carries the identifier of the
initiator of the algorithm. Each process has a variable master to keep track of
the initiator of the algorithm.
A key notion used by the optimizations is that of a region in the system. A
region encompasses all the processes whose master field contains the
identifier of the same initiator.
When the initiator’s identifier in a marker received along a channel is different
from the value in the master variable, the sender of the marker lies in a
different region.
The identifier of the concurrent initiator is recorded in a local variable
id-border -set.

G CUP 2008 15 / 51


The state of the channel is recorded just as in the Chandy-Lamport algorithm
(including those that cross a border between regions).
Snapshot recording at a process is complete after it has received a marker
along each of its channels.
After every process has recorded its snapshot, the system is partitioned into
as many regions as the number of concurrent initiations of the algorithm.
Variable id-border -set at a process contains the identiﬁers of the neighboring
regions.
Eﬃcient dissemination of the recorded snapshot
In the snapshot recording phase, a forest of spanning trees is implicitly
created in the system. The initiator of the algorithm is the root of a spanning
tree and all processes in its region belong to its spanning tree.

G CUP 2008 16 / 51


Eﬃcient dissemination of the recorded snapshot

If pi receives its ﬁrst marker from pj then process pj is the parent of process
pi in the spanning tree.
When an intermediate process in a spanning tree has received the recorded
states from all its child processes and has recorded the states of all incoming
channels, it forwards its locally recorded state and the locally recorded states
of all its descendent processes to its parent.
When the initiator receives the locally recorded states of all its descendents
from its children processes, it assembles the snapshot for all the processes in
its region and the channels incident on these processes.
The initiator exchanges the snapshot of its region with the initiators in
adjacent regions in rounds.
The message complexity of snapshot recording is O(e) irrespective of the
number of concurrent initiations of the algorithm. The message complexity of
assembling and disseminating the snapshot is O(rn2 ) where r is the number
of concurrent initiations.

G CUP 2008 17 / 51


Snapshot algorithms for non-FIFO channels

In a non-FIFO system, a marker cannot be used to delineate messages into
those to be recorded in the global state from those not to be recorded in the
global state.
In a non-FIFO system, either some degree of inhibition or piggybacking of
control information on computation messages to capture out-of-sequence
messages.

G CUP 2008 18 / 51


Lai-Yang algorithm

The Lai-Yang algorithm fulﬁlls this role of a marker in a non-FIFO system by
using a coloring scheme on computation messages that works as follows:
1 Every process is initially white and turns red while taking a snapshot. The
equivalent of the “Marker Sending Rule” is executed when a process turns
red.
2 Every message sent by a white (red) process is colored white (red).
3 Thus, a white (red) message is a message that was sent before (after) the
sender of that message recorded its local snapshot.
4 Every white process takes its snapshot at its convenience, but no later than
the instant it receives a red message.

G CUP 2008 19 / 51


Lai-Yang algorithm

4 Every white process records a history of all white messages sent or received
by it along each channel.
5 When a process turns red, it sends these histories along with its snapshot to
the initiator process that collects the global snapshot.
6 The initiator process evaluates transit(LSi , LSj ) to compute the state of a
channel Cij as given below:
SCij = white messages sent by pi on Cij − white messages received by pj on
Cij
= {send(mij )|send(mij ) ∈ LSi } − {rec(mij )|rec(mij ) ∈ LSj }.

G CUP 2008 20 / 51


Mattern’s algorithm
Mattern’s algorithm is based on vector clocks and assumes a single initiator
process and works as follows:
1 The initiator “ticks” its local clock and selects a future vector time s at
which it would like a global snapshot to be recorded. It then broadcasts this
time s and freezes all activity until it receives all acknowledgements of the
receipt of this broadcast.
2 When a process receives the broadcast, it remembers the value s and returns
an acknowledgement to the initiator.
3 After having received an acknowledgement from every process, the initiator
increases its vector clock to s and broadcasts a dummy message to all
processes.
4 The receipt of this dummy message forces each recipient to increase its clock
to a value ≥ s if not already ≥ s.
5 Each process takes a local snapshot and sends it to the initiator when (just
before) its clock increases from a value less than s to a value ≥ s.
6 The state of Cij is all messages sent along Cij , whose timestamp is smaller
than s and which are received by pj after recording LSj .
G CUP 2008 21 / 51



A termination detection scheme for non-FIFO channels is required to detect
that no white messages are in transit.
One of the following schemes can be used for termination detection:
First method:
Each process i keeps a counter cntri that indicates the diﬀerence between the
number of white messages it has sent and received before recording its
snapshot.
It reports this value to the initiator process along with its snapshot and
forwards all white messages, it receives henceforth, to the initiator.
Snapshot collection terminates when the initiator has received i cntri
number of forwarded white messages.

G CUP 2008 22 / 51



Second method:
Each red message sent by a process carries a piggybacked value of the number
of white messages sent on that channel before the local state recording.
Each process keeps a counter for the number of white messages received on
each channel.
A process can detect termination of recording the states of incoming channels
when it receives as many white messages on each channel as the value
piggybacked on red messages received on that channel.

G CUP 2008 23 / 51


Snapshots in a causal delivery system

The causal message delivery property CO provides a built-in message
synchronization to control and computation messages.
Two global snapshot recording algorithms, namely, Acharya-Badrinath and
Alagar-Venkatesan exist that assume that the underlying system supports
causal message delivery.
In both these algorithms recording of process state is identical and proceed as
follows :
An initiator process broadcasts a token, denoted as token, to every process
including itself.
Let the copy of the token received by process pi be denoted tokeni .
A process pi records its local snapshot LSi when it receives tokeni and sends
the recorded snapshot to the initiator.
The algorithm terminates when the initiator receives the snapshot recorded
by each process.

G CUP 2008 24 / 51


Snapshots in a causal delivery system

Correctness
For any two processes pi and pj , the following property is satisﬁed:

send(mij ) ∈ LSi ⇒ rec(mij ) ∈ LSj .

This is due to the causal ordering property of the underlying system as
explained next.
◮ Let a message mij be such that rec(tokeni ) −→ send(mij ).
◮ Then send(tokenj ) −→ send(mij ) and the underlying causal ordering property
ensures that rec(tokenj ), at which instant process pj records LSj , happens
before rec(mij ).
◮ Thus, mij whose send is not recorded in LSi , is not recorded as received in LSj .
Channel state recording is diﬀerent in these two algorithms and is discussed
next.

G CUP 2008 25 / 51


Channel state recording in Acharya-Badrinath algorithm

Each process pi maintains arrays SENTi [1, ...N] and RECDi [1, ..., N].
SENTi [j] is the number of messages sent by process pi to process pj .
RECDi [j] is the number of messages received by process pi from process pj .
Channel states are recorded as follows:
When a process pi records its local snapshot LSi on the receipt of tokeni , it
includes arrays RECDi and SENTi in its local state before sending the
snapshot to the initiator.

G CUP 2008 26 / 51


Channel state recording in Acharya-Badrinath algorithm

When the algorithm terminates, the initiator determines the state of channels as
follows:
The state of each channel from the initiator to each process is empty.
The state of channel from process pi to process pj is the set of messages
whose sequence numbers are given by {RECDj [i] + 1, . . . , SENTi [j]}.
Complexity:
This algorithm requires 2n messages and 2 time units for recording and
assembling the snapshot, where one time unit is required for the delivery of a
message.
If the contents of messages in channels state are required, the algorithm
requires 2n messages and 2 time units additionally.

G CUP 2008 27 / 51


Channel state recording in Alagar-Venkatesan algorithm

A message is referred to as old if the send of the message causally precedes
the send of the token.
Otherwise, the message is referred to as new.
In Alagar-Venkatesan algorithm channel states are recorded as follows:
1 When a process receives the token, it takes its snapshot, initializes the state
of all channels to empty, and returns Done message to the initiator. Now
onwards, a process includes a message received on a channel in the channel
state only if it is an old message.
2 After the initiator has received Done message from all processes, it
broadcasts a Terminate message.
3 A process stops the snapshot algorithm after receiving a Terminate message.

G CUP 2008 28 / 51


Algorithms Features
Chandy- Baseline algorithm. Requires FIFO channels. O(e) messages
Lamport to record snapshot and O(d) time.
Spezialetti- supports concurrent initiators, eﬃcient assembly
Kearns and distribution of a snapshot. Assumes bidirectional channels.
O(e) messages to record, O(rn2 ) messages to assemble and
distribute snapshot.
Lai-Yang Works for non-FIFO channels. Markers piggybacked
on computation messages. Message history required
to compute channel states.
Li et al. Small message history
needed as channel states are computed incrementally.
Mattern No message history required. Termination detection
required to compute channel states.
Acharya- Requires causal delivery support, Centralized computation of channel
Badrinath states, Channel message contents need not be known.
Requires 2n messages, 2 time units.
Alagar-Venkatesan Requires causal delivery support, Distributed computation of channel
states. Requires 3n messages, 3 time units, small messages.
n = # processes, u = # edges on which messages were sent after previous snapshot, e = # channels, d is the
diameter of the network, r = # concurrent initiators.

G CUP 2008 29 / 51


Necessary and suﬃcient conditions for consistent global
snapshots

Many applications require that local process states are periodically recorded
and analyzed during execution or post martem.
A saved intermediate state of a process during its execution is called a local
checkpoint of the process.
A consistent snapshot consists of a set of local states that occurred
concurrently or had a potential to occur simultaneously.
Processes take checkpoints asynchronously. The i th (i ≥ 0) checkpoint of
process pp is assigned the sequence number i and is denoted by Cp,i .
We assume that each process takes an initial checkpoint before execution
begins and takes a virtual checkpoint after execution ends.
The i th checkpoint interval of process pp consists of all the computation
performed between its (i − 1)th and i th checkpoints (and includes the
(i − 1)th checkpoint but not i th ).

G CUP 2008 30 / 51


Even if two local checkpoints do not have a causal path between them, they may
not belong to the same consistent global snapshot.

An Example:
Consider the execution shown in the Figure 4.2.
Although neither of the checkpoints C1,1 and C3,2 happened before the other,
they cannot be grouped together with a checkpoint on process p2 to form a
consistent global snapshot.

G CUP 2008 31 / 51


C 1,0 C 1,1 C 1,2
p1
m1 m3 m5
C 2,0 C 2,1 C 2,2 C 2,3
p2
m m4 m6
C 3,0 2 C 3,1 C3,2 C 3,3
p3

Legend: A checkpoint

Figure 4.2: An Illustration of zigzag paths.

G CUP 2008 32 / 51


Necessary and sufficient conditions for consistent global
snapshots

To describe the necessary and sufficient conditions for a consistent snapshot,
Netzer and Xu defined a generalization of the Lamport’s happen before
relation, called a zigzag path.
A zigzag path between two checkpoints is a causal path, however, a zigzag
path allows a message to be sent before the previous one in the path is
received.
In the Figure 4.2 although a causal path does not exist from C1,1 to C3,2 , a
zigzag path does exist from C1,1 to C3,2 .
This zigzag path means that no consistent snapshot exists in this execution
that contains both C1,1 and C3,2 .

G CUP 2008 33 / 51


Zigzag paths and consistent global snapshots

Deﬁnition
A zigzag path exists from a checkpoint Cx,i to a checkpoint Cy,j iﬀ there exists
messages m1 , m2 , ...mn (n≥1) such that
1 m1 is sent by process px after Cx,i .
2 If mk (1≤k≤n) is received by process pz , then mk+1 is sent by pz in the same
or a later checkpoint interval (although mk+1 may be sent before or after mk
is received), and
3 mn is received by process py before Cy,j .

Example:
In the Figure 4.2 a zigzag path exists from C1,1 to C3,2 due to messages m3 and
m4 .

G CUP 2008 34 / 51


Zigzag cycle
Deﬁnition
A checkpoint C is involved in a zigzag cycle iﬀ there is a zigzag path from C to
itself.
In Figure 4.3, C2,1 is on a zigzag cycle formed by messages m1 and m2 .

C 1,0 C 1,1 C1,2
p1
m3
m1
C 2,0 C 2,1 m2 C 2,2 C 2,3
p
2 m
4
C 3,0 C 3,1 C3,2
p
3

Figure 4.3: A zigzag cycle, inconsistent snapshot, and consistent snapshot.

G CUP 2008 35 / 51


Difference between a zigzag path and a causal path

A causal path exists from a checkpoint A to another checkpoint B iff there is
chain of messages starting after A and ending before B such that each
message is sent after the previous one in the chain is received.
A zigzag path consists of such a message chain, however, a message in the
chain can be sent before the previous one in the chain is received, as long as
the send and receive are in the same checkpoint interval.
Thus a causal path is always a zigzag path, but a zigzag path need not be a
causal path.
Another difference between a zigzag path and a causal path is that a zigzag
path can form a cycle but a causal path never forms a cycle.

G CUP 2008 36 / 51


Consistent global snapshots

Netzer and Xu proved that if no zigzag path (or cycle) exists between any two
checkpoints from a set S of checkpoints, then a consistent snapshot can be
formed that includes the set S of checkpoints and vice versa.
The absence of a causal path between checkpoints in a snapshot corresponds
to the necessary condition for a consistent snapshot, and the absence of a
zigzag path between checkpoints in a snapshot corresponds to the necessary
and suﬃcient conditions for a consistent snapshot.
A set of checkpoints S can be extended to a consistent snapshot if and only if
no checkpoint in S has a zigzag path to any other checkpoint in S.
A checkpoint can be a part of a consistent snapshot if and only if it is not
invloved in a Z-cycle.

G CUP 2008 37 / 51


Finding consistent global snapshots in a distributed
computation

Discuss how individual local checkpoints can be combined with those from
other processes to form global snapshots that are consistent.
Manivannan-Netzer-Singhal analyzed the set of all consistent snapshots that
can be built from a set of checkpoints S.

Definition
Let A, B be individual checkpoints and R, S be sets of checkpoints. Let be a
relation defined over checkpoints and sets of checkpoints such that
1 A B iff a Z-path exists from A to B,
2 A S iff a Z-path exists from A to some member of S,
3 S A iff a Z-path exists from some member of S to A, and
4 R S iff a Z-path exists from some member of R to some member of S.

G CUP 2008 38 / 51


S S deﬁnes that no Z-path (including Z-cycle) exists from any member of S to
any other member of S and implies that checkpoints in S are all from diﬀerent
processes.
In this notations, the results of Netzer and Xu can be expressed as follows:
Theorem 4.1:
A set of checkpoints S can be extended to a consistent global snapshot if and
only if S S.
Corollary 4.1
A checkpoint C can be part of a consistent global snapshot if and only if it is not
involved in a Z-cycle.
Corollary 4.2
A set of checkpoints S is a consistent global snapshot if and only if S S and
|S| = N, where N is the number of processes.

G CUP 2008 39 / 51


Finding consistent global snapshots

Given a set S of checkpoints such that S S, we ﬁrst discuss what checkpoints
from other processes can be combined with S to build a consistent global
snapshot.
First Observation:
None of the checkpoints that have a Z-path to or from any of the
checkpoints in S can be used.
Only those checkpoints that have no Z-paths to or from any of the
checkpoints in S are candidates for inclusion in the consistent snapshot.
We call the set of all such candidates the Z-cone of S and all checkpoints
that have no causal path to or from any checkpoint in S the C-cone of S.
A causal path is always Z-path, the Z-cone of S is a subset of the C-cone of
S for an arbitrary S as shown in the Figure 4.4

G CUP 2008 40 / 51


S

Edge of C − cone Edges of Z − cone Edge of C − cone

Z − paths to S Z − unordered with S Z − paths from S
( Z − cone)
Casual paths to S Casually unordered with S Casual paths from S
(C − cone)

Figure 4.4: The Z-cone and the C-cone associated with a set of checkpoints S.

G CUP 2008 41 / 51


Second Observation:
Although candidates for building a consistent snapshot from S must lie in the
Z-cone of S, not all checkpoints in the Z-cone can form a consistent snapshot
with S. If a checkpoint in the Z-cone is involved in a Z-cycle, then it cannot be
part of a consistent snapshot.

Definition
Let S be a set of checkpoints such that S S. Then, for each process pq , the
q
set Suseful is defined as
q
Suseful = {Cq,i | (S Cq,i ) ∧ (Cq,i S) ∧ (Cq,i Cq,i )}.

In addition, we define
q
Suseful = Suseful .
q

G CUP 2008 42 / 51


Lemma 4.1
“Let S be a set of checkpoints such that S S. Let Cq,i be any checkpoint of
process pq such that Cq,i ∈ S. Then S ∪ {Cq,i } can be extended to a consistent
snapshot if and only if Cq,i ∈ Suseful .”

Lemma 4.1 states that if we are given a set S such that S S, we are
guaranteed that any single checkpoint from Suseful can belong to a consistent
global snapshot that also contains S.

G CUP 2008 43 / 51


Third observation

Although none of the checkpoints in Suseful has a Z-path to or from any
checkpoint in S, Z-paths may exist between members of Suseful .
One ﬁnal constraint is placed on the set T we choose from Suseful to build a
consistent snapshot from S: checkpoints in T must have no Z-paths between
them. Furthermore, since S S, from Theorem 4.1 at least one such T
must exist.
Theorem 4.2:
Let S be a set of checkpoints such that S S and let T be any set of
checkpoints such that S ∩ T = ∅. Then, S ∪ T is a consistent global snapshot if
and only if
1 T ⊆ Suseful ,
2 T T , and
3 |S ∪ T | = N.

G CUP 2008 44 / 51


Manivannan-Netzer-Singhal algorithm for enumerating
consistent snapshots
An algorithm due to Manivannan-Netzer-Singhal that explicitly computes all
consistent snapshots that include a given set a set of checkpoints S.
1: ComputeAllCgs(S) {
2: let G = ∅
3: if S S then
4: let AllProcs be the set of all processes not represented in S
5: ComputeAllCgsFrom(S, AllProcs)
6: return G
7: }
8: ComputeAllCgsFrom(T , ProcSet) {
9: if (ProcSet = ∅) then
10: G = G ∪ {T }
11: else
12: let pq be any process in ProcSet
q
13: for each checkpoint C ∈ Tuseful do
14: ComputeAllCgsFrom(T ∪ {C }, ProcSet {pq })
15: }

G CUP 2008 45 / 51


Manivannan-Netzer-Singhal algorithm

The algorithm restricts its selection of checkpoints to those within the Z-cone of
S and it checks for the presence of Z-cycles within the Z-cone.
Correctness:
The following theorem argues the correctness of the algorithm.
Theorem 4.3:
Let S be a set of checkpoints and G be the set returned by ComputeAllCgs(S). If
S S, then T ∈ G if and only if T is a consistent snapshot containing S. That
is, G contains exactly the consistent snapshots that contain S.

G CUP 2008 46 / 51


Finding Z-paths in a distributed computation

Discuss a method for determining the existence of Z-paths between checkpoints in
a distributed computation that has terminated or has stopped execution, using the
rollback-dependency graph (R-graph).

Deﬁnition
The rollback-dependency graph of a distributed computation is a directed graph
G = (V , E ), where the vertices V are the checkpoints of the distributed
computation and an edge (Cp,i , Cq,j ) from checkpoint Cp,i to checkpoint Cq,j
belongs to E if
1 p = q and j = i + 1, or
2 p = q and a message m sent from the i th checkpoint interval of pp is
received by pq in its j th checkpoint interval (i, j > 0).

G CUP 2008 47 / 51


Example of an R-graph

Figure 4.6 shows shows the R-graph of the computation shown in Figure 4.5.
In Figure 4.6, C1,3 , C2,3 , and C3,3 represent the volatile checkpoints, the
checkpoints representing the last state the process attained before
terminating.
We denote the fact that there is a path from C to D in the R-graph by
rd
C D. It only denotes the existence of a path; it does not specify any
particular path.

G CUP 2008 48 / 51


C 1,0 C 1,1 C 1,2
p1
m1 m3
C 2,0 C 2,1 m4 C
2,2
p2
m m5 m6
C 3,0 2 C 3,1 C3,2
p3

Figure 4.5: A distributed computation.

G CUP 2008 49 / 51


C C 1,1 C C
1,0 1,2 1,3

C 2,0 C C 2,3
2,1
Volatile
C 2,2 checkpoints

C
3,0

C 3,1 C 3,2 C 3,3

Figure 4.6: The R-graph of the computation in Figure 4.5.

G CUP 2008 50 / 51


Example of an R-graph

The following theorem establishes the correspondence between the paths in the
R-graph and the Z-paths between checkpoints.
Theorem:
Let G = (V , E ) be the R-graph of a distributed computation. Then, for any two
checkpoints Cp,i and Cq,j , Cp,i Cq,j if and only if
1 p = q and i < j, or
rd
2 Cp,i +1 Cq,j in G (note that in this case p could still be equal to q).
Examples:
In Figure 4.5, a zigzag path exists from C1,1 to C3,1 because in the
rd
corresponding R-graph, shown in Figure 4.6, C1,2 C3,1 .
Likewise, C2,1 is on a Z-cycle because in the corresponding R-graph, shown in
rd
Figure 4.6, C2,2 C2,1 .

G CUP 2008 51 / 51

Day 2 global_state_and_snapshot_algorithms

More Related Content

What's hot (20)

Viewers also liked (20)

Similar to Day 2 global_state_and_snapshot_algorithms (20)

Recently uploaded (20)

Day 2 global_state_and_snapshot_algorithms