Chapter 07

Spin Locks and Contention
Companion slides for The Art of Multiprocessor Programming by Maurice Herlihy & Nir Shavit
Focus so far: Correctness and Progress

Models
Accurate (we never lied to you) But idealized (so we forgot to mention a few things)
Protocols
Elegant Important But nave
Art of Multiprocessor Programming 2
New Focus: Performance

Models
More complicated (not the same as complex!) Still focus on principles (not soon obsolete)
Protocols
Elegant (in their fashion) Important (why else would we pay attention) And realistic (your mileage may vary)
Kinds of Architectures
SISD (Uniprocessor)
Single instruction stream Single data stream
SIMD (Vector)
Single instruction Multiple data
MIMD (Multiprocessors)
Multiple instruction Multiple data.
Kinds of Architectures
SISD (Uniprocessor)
Single instruction stream Single data stream
SIMD (Vector)
Single instruction Multiple data
Our space
MIMD (Multiprocessors)
Multiple instruction Multiple data.
(1) Art of Multiprocessor Programming 5
MIMD Architectures
memory
Shared Bus
Distributed
Memory Contention Communication Contention Communication Latency

Today: Revisit Mutual Exclusion

Think of performance, not just correctness and progress Begin to understand how performance depends on our software properly utilizing the multiprocessor machines hardware And get to know a collection of locking algorithms
Art of Multiprocessor Programming 7 (1)
What Should you do if you cant get a lock?

Keep trying
spin or busy-wait Good if delays are short
Give up the processor

Good if delays are long Always good on uniprocessor
Art of Multiprocessor Programming
8 (1)
What Should you do if you cant get a lock?

Keep trying
spin or busy-wait Good if delays are short
Give up the processor

Good if delays are long Always good on uniprocessor
our focus
Basic Spin-Lock
. .
CS spin lock critical section Resets lock upon exit
10
Basic Spin-Lock
lock introduces sequential bottleneck
. .
11
Basic Spin-Lock
lock suffers from contention
. .
12
Basic Spin-Lock
. .
Notice: these are distinct phenomena

Basic Spin-Lock
. .
Seq Bottleneck no parallelism

Basic Spin-Lock
. .
Contention ???
Review: Test-and-Set
Boolean value Test-and-set (TAS)
Swap true with current value Return value tells if prior value was true or false
Can reset just by writing false TAS aka getAndSet

public class AtomicBoolean { boolean value;
public synchronized boolean getAndSet(boolean newValue) { boolean prior = value; value = newValue; return prior; }
17 (5)
public synchronized boolean getAndSet(boolean newValue) { boolean prior = value; value = newValue; return prior; } Package
java.util.concurrent.atomic
18
public synchronized boolean getAndSet(boolean newValue) { boolean prior = value; value = newValue; return prior; }
Swap old and new values

AtomicBoolean lock = new AtomicBoolean(false) boolean prior = lock.getAndSet(true)
20
AtomicBoolean lock = new AtomicBoolean(false) boolean prior = lock.getAndSet(true)
Swapping in true is called test-and-set or TAS
21 (5)
Test-and-Set Locks
Locking
Lock is free: value is false Lock is taken: value is true
Acquire lock by calling TAS

If result is false, you win If result is true, you lose
Release lock by writing false

Test-and-set Lock
class TASlock { AtomicBoolean state = new AtomicBoolean(false);
void lock() { while (state.getAndSet(true)) {} } void unlock() { state.set(false); }}
Test-and-set Lock
void lock() { while (state.getAndSet(true)) {} } void unlock() { state.set(false); Lock state }}
is AtomicBoolean
24
Test-and-set Lock
void lock() { while (state.getAndSet(true)) {} } void unlock() { state.set(false); Keep trying until }}
lock acquired
25
Test-and-set Lock
class TASlock { Release lock AtomicBoolean state = by resetting new AtomicBoolean(false); state to false
void lock() { while (state.getAndSet(true)) {} } void unlock() { state.set(false); }}
Space Complexity
TAS spin-lock has small footprint N thread spin-lock uses O(1) space As opposed to O(n) Peterson/Bakery How did we overcome the W(n) lower bound? We used a RMW operation
Performance
Experiment
n threads Increment shared counter 1 million times
How long should it take? How long does it take?
28
Graph
time
no speedup because of sequential bottleneck
ideal
threads
Mystery #1
TAS lock
time
Ideal
threads
What is going on?

30 (1)
Test-and-Test-and-Set Locks
Lurking stage
Wait until lock looks free Spin while read returns true (lock taken) As soon as lock looks available Read returns false (lock free) Call TAS to acquire lock If TAS loses, back to lurking
Pouncing state
Test-and-test-and-set Lock
class TTASlock { AtomicBoolean state = new AtomicBoolean(false);
void lock() { while (true) { while (state.get()) {} if (!state.getAndSet(true)) return; } }
Wait until lock looks free


Then try to acquire it
34
Mystery #2
TAS lock
time
TTAS lock Ideal
threads
Mystery
Both
TAS and TTAS Do the same thing (in our model)
Except that
TTAS performs much better than TAS Neither approaches ideal
36
Opinion
Our memory abstraction is broken TAS & TTAS methods
Are provably the same (in our model) Except they arent (in field tests)
Need a more detailed model
37
Bus-Based Architectures
cache
cache
Bus
cache
memory
Random access memory (10s of cycles)
cache cache
Bus
cache
memory
Shared Bus Broadcast medium One broadcaster at a time Processors and memory all snoop
cache cache
Bus
cache
memory
Per-Processor Caches Bus-Based Architectures Small Fast: 1 or 2 cycles Address & state information
cache
cache
Bus
cache
memory
Jargon Watch
Cache hit
I found what I wanted in my cache Good Thing
42
Jargon Watch
Cache hit
I found what I wanted in my cache Good Thing
Cache miss
I had to shlep all the way to memory for that data Bad Thing
Cave Canem
This model is still a simplification
But not in any essential way Illustrates basic principles
Will discuss complexities later
44
Processor Issues Load Request
cache
cache
Bus
cache
memory
data
45

Gimme data
cache
cache
Bus
cache
memory
data
46
Memory Responds
cache
Got your data right here
cache
Bus
cache
Bus
memory
data
47

Gimme data
data
cache
Bus
cache
memory
data
48

Gimme data
data
cache
Bus
cache
memory
data
49

I got data
data
cache
Bus
cache
memory
data
50
I got data
Other Processor Responds
data
cache
Bus
cache
Bus
memory
data
51
Other Processor Responds
data
cache
Bus
cache
Bus
memory
data
52
Modify Cached Data
data
data
Bus
cache
memory
data
53 (1)
Modify Cached Data
data
data data
Bus
cache
memory
data
54 (1)
Modify Cached Data
data
data
Bus
cache
memory
data
55
Modify Cached Data
data
data
Bus
cache
Whats up with the other copies?memory

data
56
Cache Coherence
We have lots of copies of data
Original copy in memory Cached copies at processors
Some processor modifies its own copy

What do we do with the others? How to avoid confusion?
57
Write-Back Caches
Accumulate changes in cache Write back when needed
Need the cache for something else Another processor wants it
On first modification
Invalidate other entries Requires non-trivial protocol
Write-Back Caches
Cache entry has three states
Invalid: contains raw seething bits Valid: I can read but I cant write Dirty: Data has been modified
Intercept other load requests Write back to memory before using cache
59
Invalidate
data
data
Bus
cache
memory
data
60
Invalidate
Mine, all mine!
data
data
Bus Bus
cache
memory
data
61
Invalidate
Uh,oh
data cache
data
Bus Bus
cache
memory
data
62
Invalidate
Other caches lose read permission
cache
data
Bus
cache
memory
data
63
Invalidate
Other caches lose read permission
cache
data
Bus
cache
This cache acquires write permission
memory
data
64
Invalidate
Memory provides data only if not present in any cache, so no need to change it now (expensive) data cache cache
Bus
memory
data
65 (2)
Another Processor Asks for Data
cache
data
Bus Bus
cache
memory
data
66 (2)
Owner Responds
Here it is!
cache
data
Bus Bus
cache
memory
data
67 (2)
End of the Day
data
data
Bus
cache
data memory Reading OK, no writing

Art of Multiprocessor Programming 68 (1)
Mutual Exclusion
What do we want to optimize?
Bus bandwidth used by spinning threads Release/Acquire latency Acquire latency for idle lock
69
Simple TASLock
TAS invalidates cache lines Spinners
Miss in cache Go to bus
Thread wants to release lock

delayed behind spinners
70
Test-and-test-and-set
Wait until lock looks free
Spin on local cache No bus use while lock busy
Problem: when lock is released

Invalidation storm
71
Local Spinning while Lock is Busy
busy
busy
Bus
busy
memory
busy
72
On Release
invalid
invalid
Bus
free
memory
free
73
Everyone misses, rereads
On Release
invalid miss
invalid miss
Bus
free
memory
free
74 (1)
Everyone tries TAS
On Release
TAS() invalid
TAS() invalid
Bus
free
memory
free
75 (1)
Problems
Everyone misses
Reads satisfied sequentially
Everyone does TAS

Invalidates others caches
Eventually quiesces after lock acquired

How long does this take?
Measuring Quiescence Time

X = time of ops that dont use the bus Y = time of ops that cause intensive bus traffic
P1 P2 Pn
In critical section, run ops X then ops Y. As long as Quiescence time is less than X, no drop in performance.
By gradually varying X, can determine the exact time to quiesce.

Quiescence Time
Increses linearly with the number of processors for bus architecture
time
threads
78
Mystery Explained
TAS lock
time
TTAS lock Ideal
Better than threads TAS but still not as good as ideal

79
Solution: Introduce Delay

If the lock looks free But I fail to get it There must be contention Better to back off than to collide again
time
r2d r1d d
spin lock
80
Dynamic Example: Exponential Backoff
time
4d 2d d
spin lock
If I fail to get lock wait random duration before retry Each subsequent failure doubles expected wait
Exponential Backoff Lock

public class Backoff implements lock { public void lock() { int delay = MIN_DELAY; while (true) { while (state.get()) {} if (!lock.getAndSet(true)) return; sleep(random() % delay); if (delay < MAX_DELAY) delay = 2 * delay; }}}

public class Backoff implements lock { public void lock() { int delay = MIN_DELAY; while (true) { while (state.get()) {} if (!lock.getAndSet(true)) return; sleep(random() % delay); if (delay < MAX_DELAY) delay = 2 * delay; Fix minimum delay }}}

public class Backoff implements lock { public void lock() { int delay = MIN_DELAY; while (true) { while (state.get()) {} if (!lock.getAndSet(true)) return; sleep(random() % delay); if (delay < MAX_DELAY) delay = 2 * delay; Wait until lock looks free }}}

public class Backoff implements lock { public void lock() { int delay = MIN_DELAY; while (true) { while (state.get()) {} if (!lock.getAndSet(true)) return; sleep(random() % delay); if (delay < MAX_DELAY) delay = 2 * delay; If we win, return }}}

public class Backoff implements lock { for{ random duration publicBack void off lock() int delay = MIN_DELAY; while (true) { while (state.get()) {} if (!lock.getAndSet(true)) return; sleep(random() % delay); if (delay < MAX_DELAY) delay = 2 * delay; }}}

public class Backoff implements lock { Double delay, within reason public voidmax lock() { int delay = MIN_DELAY; while (true) { while (state.get()) {} if (!lock.getAndSet(true)) return; sleep(random() % delay); if (delay < MAX_DELAY) delay = 2 * delay; }}}
Spin-Waiting Overhead
TTAS Lock
time
Backoff lock
threads
Backoff: Other Issues

Good
Easy to implement Beats TTAS lock
Bad
Must choose parameters carefully Not portable across platforms
89
Idea
Avoid useless invalidations
By keeping a queue of threads
Each thread
Notifies next in line Without bothering the others
90
Anderson Queue Lock

next
idle
flags
91
Anderson Queue Lock

next
acquiring getAndIncrement
flags
92
Anderson Queue Lock

next
acquiring getAndIncrement
flags
93
Anderson Queue Lock

next
acquired
Mine!
flags
94
Anderson Queue Lock

next
acquired
acquiring
flags
95
Anderson Queue Lock

next
acquired
acquiring
flags
getAndIncrement
F F F F F F F
96
Anderson Queue Lock

next
acquired
acquiring
flags
getAndIncrement
F F F F F F F
97
Anderson Queue Lock

next
acquired
acquiring
flags
98
Anderson Queue Lock

next
released
acquired
flags
99
Anderson Queue Lock

next
released
acquired
flags
Yow!
100
Anderson Queue Lock

class ALock implements Lock { boolean[] flags={true,false,,false}; AtomicInteger next = new AtomicInteger(0); ThreadLocal<Integer> mySlot;
101
Anderson Queue Lock

One flag per thread
102
Anderson Queue Lock

Next flag to use

Anderson Queue Lock

Thread-local variable
Anderson Queue Lock

public lock() { mySlot = next.getAndIncrement(); while (!flags[mySlot % n]) {}; flags[mySlot % n] = false; }
public unlock() { flags[(mySlot+1) % n] = true; }
105
Anderson Queue Lock

public unlock() { flags[(mySlot+1) % n] = true; Take next }
slot
106
Anderson Queue Lock

public unlock() { flags[(mySlot+1) % n] = true; Spin until told }
to go
107
Anderson Queue Lock

public lock() { myslot = next.getAndIncrement(); while (!flags[myslot % n]) {}; flags[myslot % n] = false; }
public unlock() { flags[(myslot+1) % n] = true; } Prepare slot for
re-use
108
Anderson Queue Lock

public lock() Tell { next thread to mySlot = next.getAndIncrement(); while (!flags[mySlot % n]) {}; flags[mySlot % n] = false; }
public unlock() { flags[(mySlot+1) % n] = true; }
go
109
Local Spinning
next
released
acquired
Spin on my bit
flags
Unfortunately many bits share cache line

False Sharing
next
Result: contention flags
released
acquired
gets cache invalidation on F F of store F account by threads it is not waiting for

111
Spin on my bit Spinning thread
Line Art 1 of Multiprocessor Programming Line 2
The Solution: Padding

next
released
acquired
Spin on my line
flags
Line Art 1 of Multiprocessor Programming Line 2
112
Performance
TTAS
Shorter handover than backoff queue Curve is practically flat Scalable performance
113
Anderson Queue Lock

Good
First truly scalable lock Simple, easy to implement Back to FIFO order (like Bakery)
114
Anderson Queue Lock

Bad
Space hog One bit per thread one cache line per thread
What if unknown number of threads? What if small number of actual contenders?
115
CLH Lock
FIFO order Small, constant-size overhead per thread
116
Initially
idle
tail
false
Initially
idle
tail
false
Queue tail
118
Initially
idle
Lock is free
tail
false
Initially
idle
tail
false
Purple Wants the Lock

acquiring
tail
false

acquiring
tail
false
true
122

acquiring
Swap
tail
false
true
123
Purple Has the Lock

acquired
tail
false
true
124
Red Wants the Lock

acquired acquiring
tail
false
true
true
125
Red Wants the Lock

acquired acquiring
Swap
tail
false
true
true
126
Red Wants the Lock

acquired acquiring
tail
false
true
true
127
Red Wants the Lock

acquired acquiring
tail
false
true
true
128
Red Wants the Lock

acquired acquiring
Implicit Linked list tail

false
true
true
129
Red Wants the Lock

acquired acquiring
tail
false
true
true
130
Red Wants the Lock

acquired acquiring
true
Actually, it spins on cached copy
tail
false
true
true
131
Purple Releases
release acquiring
false
Bingo!
true
132
tail
false
false
Purple Releases
released acquired
tail
true
Space Usage
Let
L = number of locks N = number of threads
ALock
O(LN)
CLH lock
O(L+N)
CLH Queue Lock

class Qnode { AtomicBoolean locked = new AtomicBoolean(true); }
135
CLH Queue Lock

class Qnode { AtomicBoolean locked = new AtomicBoolean(true); }
Not released yet
136
CLH Queue Lock

class CLHLock implements Lock { AtomicReference<Qnode> tail; ThreadLocal<Qnode> myNode = new Qnode(); public void lock() { Qnode pred = tail.getAndSet(myNode); while (pred.locked) {} }}
CLH Queue Lock

Queue tail
138
CLH Queue Lock

Thread-local Qnode
139
CLH Queue Lock

class CLHLock implements Lock { AtomicReference<Qnode> tail; ThreadLocal<Qnode> myNode Swap in my node = new Qnode(); public void lock() { Qnode pred = tail.getAndSet(myNode); while (pred.locked) {} }}
CLH Queue Lock

class CLHLock implements Lock { AtomicReference<Qnode> tail; ThreadLocal<Qnode> myNode Spin until predecessor = new Qnode(); releases lock public void lock() { Qnode pred = tail.getAndSet(myNode); while (pred.locked) {} }}
CLH Queue Lock

Class CLHLock implements Lock { public void unlock() { myNode.locked.set(false); myNode = pred; } }
142
CLH Queue Lock

Notify successor
143
CLH Queue Lock

Recycle predecessors node

144
CLH Queue Lock

Class CLHLock implements Lock { public void unlock() { myNode.locked.set(false); myNode = pred; } } (we dont actually reuse myNode. Code in book shows how its done.)
CLH Lock
Good
Lock release affects predecessor only Small, constant-sized space
Bad
Doesnt work for uncached NUMA architectures
146
NUMA Architecturs
Acronym:
Non-Uniform Memory Architecture
Illusion:
Flat shared memory
Truth:
No caches (sometimes) Some memory regions faster than others
NUMA Machines
Spinning on local memory is fast

NUMA Machines
Spinning on remote memory is slow

CLH Lock
Each thread spins on predecessors memory Could be far away
150
MCS Lock
FIFO order Spin on local memory only Small, Constant-size overhead
151
Initially
idle
tail
false
Acquiring
acquiring
(allocate Qnode)
true
tail
false
Acquiring
acquired
swap
tail
false
true
154
Acquiring
acquired
true
tail
false
Acquired
acquired
true
tail
false
Acquiring
acquired acquiring
false
tail
swap
true
157
Acquiring
acquired acquiring
false
tail
true
Acquiring
acquired acquiring
false
tail
true
Acquiring
acquired acquiring
false
tail
true
Acquiring
acquired acquiring
true
tail
true false
Acquiring
acquired acquiring
true
Yes!
false true
tail
162
MCS Queue Lock

class Qnode { boolean locked = false; qnode next = null; }
163
MCS Queue Lock

class MCSLock implements Lock { AtomicReference tail; public void lock() { Qnode qnode = new Qnode(); Qnode pred = tail.getAndSet(qnode); if (pred != null) { qnode.locked = true; pred.next = qnode; while (qnode.locked) {} }}}
MCS Queue Lock

class MCSLock implements Lock { Make a AtomicReference tail; QNode public void lock() { Qnode qnode = new Qnode(); Qnode pred = tail.getAndSet(qnode); if (pred != null) { qnode.locked = true; pred.next = qnode; while (qnode.locked) {} }}}
MCS Queue Lock

class MCSLock implements Lock { AtomicReference tail; public void lock() { Qnode qnode = new Qnode(); Qnode pred = tail.getAndSet(qnode); if (pred != null) { qnode.locked = true;add my Node to pred.next = qnode; the tail of while (qnode.locked) {} queue }}}
MCS Queue Lock

class MCSLock implements Lock { Fix if queue AtomicReference tail; was non-empty public void lock() { Qnode qnode = new Qnode(); Qnode pred = tail.getAndSet(qnode); if (pred != null) { qnode.locked = true; pred.next = qnode; while (qnode.locked) {} }}}
MCS Queue Lock

class MCSLock implements Lock { AtomicReference tail; Wait until public void lock() { unlocked Qnode qnode = new Qnode(); Qnode pred = tail.getAndSet(qnode); if (pred != null) { qnode.locked = true; pred.next = qnode; while (qnode.locked) {} }}}
MCS Queue Unlock

class MCSLock implements Lock { AtomicReference tail; public void unlock() { if (qnode.next == null) { if (tail.CAS(qnode, null) return; while (qnode.next == null) {} } qnode.next.locked = false; }}
MCS Queue Lock

class MCSLock implements Lock { AtomicReference tail; public void unlock() { if (qnode.next == null) { if (tail.CAS(qnode, null) return; while (qnode.next == null) {} } qnode.next.locked = false; Missing successor? }}
MCS Queue Lock

class MCSLock implements Lock { If really no successor, AtomicReference tail; return public void unlock() { if (qnode.next == null) { if (tail.CAS(qnode, null) return; while (qnode.next == null) {} } qnode.next.locked = false; }}
MCS Queue Lock

class MCSLock implements Lock { Otherwise wait for AtomicReference tail; successor to catch up public void unlock() { if (qnode.next == null) { if (tail.CAS(qnode, null) return; while (qnode.next == null) {} } qnode.next.locked = false; }}
MCS Queue Lock

class MCSLock implements Lock { AtomicReference queue; Pass lock to successor public void unlock() { if (qnode.next == null) { if (tail.CAS(qnode, null) return; while (qnode.next == null) {} } qnode.next.locked = false; }}
Purple Release
releasing swap
false false
By looking at the queue, I see another thread is releasing activeswap
Purple Release
false false
By looking at the queue, I see another thread is releasing activeswap
Purple Release
false false I have to wait for that thread to finish

176
Purple Release
releasing prepare to spin
true false
Purple Release
releasing spinning
true false
Purple Release
releasing spinning
false true false

Purple Release
releasing Acquired lock
false true false

Abortable Locks
What if you want to give up waiting for a lock? For example
Timeout Database transaction aborted by user
181
Back-off Lock
Aborting is trivial
Just return from lock() call
Extra benefit:
No cleaning up Wait-free Immediate return
182
Queue Locks
Cant just quit
Thread in line behind will starve
Need a graceful way out
183
Queue Locks
spinning spinning spinning
true
true
true
184
Queue Locks
locked spinning spinning
false
true
true
185
Queue Locks
locked spinning
false
true
186
Queue Locks
locked
false
187
Queue Locks
spinning spinning spinning
true
true
true
188
Queue Locks
spinning spinning
true
true
true
189
Queue Locks
locked spinning
false
true
true
190
Queue Locks
spinning
false
true
191
Queue Locks
pwned
false
true
192
Abortable CLH Lock

When a thread gives up
Removing node in a wait-free way is hard
Idea:
let successor deal with it.
193
Initially
idle Pointer to predecessor (or null)
tail
A
Initially
idle Distinguished available node means lock is free
tail
A
Acquiring
acquiring
tail
A
Null predecessor Acquiring means lock not released or acquiring aborted
A
Acquiring
acquiring
Swap
A
Acquiring
acquiring
A
Acquired
locked
Pointer to AVAILABLE means lock is free.
A
Normal Case
locked spinning spinning
Null means lock is not free & request not aborted

One Thread Aborts

locked Timed out spinning
202
Successor Notices
locked Timed out spinning
Non-Null means predecessor aborted

Recycle Predecessors Node

locked spinning
204
Spin on Earlier Node

locked spinning
205
Spin on Earlier Node

released spinning
A The lock is now mine

Time-out Lock
public class TOLock implements Lock { static Qnode AVAILABLE = new Qnode(); AtomicReference<Qnode> tail; ThreadLocal<Qnode> myNode;
207
Time-out Lock
Distinguished node to signify free lock

Time-out Lock
Tail of the queue

Time-out Lock
Remember my node
Time-out Lock
public boolean lock(long timeout) { Qnode qnode = new Qnode(); myNode.set(qnode); qnode.prev = null; Qnode myPred = tail.getAndSet(qnode); if (myPred== null || myPred.prev == AVAILABLE) { return true; }
211
Time-out Lock
public boolean lock(long timeout) { Qnode qnode = new Qnode(); myNode.set(qnode); qnode.prev = null; Qnode myPred = tail.getAndSet(qnode); if (myPred == null || myPred.prev == AVAILABLE) { return true; }
Create & initialize node

Time-out Lock
public boolean lock(long timeout) { Qnode qnode = new Qnode(); myNode.set(qnode); qnode.prev = null; Qnode myPred = tail.getAndSet(qnode); if (myPred == null || myPred.prev == AVAILABLE) { return true; }
Swap with tail

Time-out Lock
public boolean lock(long timeout) { Qnode qnode = new Qnode(); myNode.set(qnode); qnode.prev = null; Qnode myPred = tail.getAndSet(qnode); if (myPred == null || myPred.prev == AVAILABLE) { return true; } ...
If predecessor absent or released, we are done

214
Time-out Lock
locked
spinning
spinning
long start = now(); while (now()- start < timeout) { Qnode predPred = myPred.prev; if (predPred == AVAILABLE) { return true; } else if (predPred != null) { myPred = predPred; } }
Time-out Lock
long start = now(); while (now()- start < timeout) { Qnode predPred = myPred.prev; if (predPred == AVAILABLE) { return true; } else if (predPred != null) { myPred = predPred; } Keep trying for a }
while
216
Time-out Lock
long start = now(); while (now()- start < timeout) { Qnode predPred = myPred.prev; if (predPred == AVAILABLE) { return true; } else if (predPred != null) { myPred = predPred; } } prev field
Spin on predecessors
217
Time-out Lock
long start = now(); while (now()- start < timeout) { Qnode predPred = myPred.prev; if (predPred == AVAILABLE) { return true; } else if (predPred != null) { myPred = predPred; } } Predecessor released
lock
218
Time-out Lock
long start = now(); while (now()- start < timeout) { Qnode predPred = myPred.prev; if (predPred == AVAILABLE) { return true; } else if (predPred != null) { myPred = predPred; } Predecessor aborted, } advance one
Time-out Lock
if (!tail.compareAndSet(qnode, myPred)) qnode.prev = myPred; return false; } }
What do I do when I time out?
220
Time-out Lock
Do I have a successor? If CAS fails: I do have a successor, tell it about myPred

Time-out Lock
If CAS succeeds: no successor, simply return false

Time-Out Unlock
public void unlock() { Qnode qnode = myNode.get(); if (!tail.compareAndSet(qnode, null)) qnode.prev = AVAILABLE; }
223
Time-out Unlock
If CAS failed: exists successor, notify successor it can enter

Timing-out Lock
CAS successful: set tail to null, no clean up since no successor waiting

One Lock To Rule Them All?

TTAS+Backoff, CLH, MCS, ToLock Each better than others in some way There is no one solution Lock we pick really depends on:
the application the hardware which properties are important
This work is licensed under a Creative Commons AttributionShareAlike 2.5 License.

You are free: to Share to copy, distribute and transmit the work to Remix to adapt the work Under the following conditions: Attribution. You must attribute the work to The Art of Multiprocessor Programming (but not in any way that suggests that the authors endorse you or your use of the work). Share Alike. If you alter, transform, or build upon this work, you may distribute the resulting work only under the same, similar or a compatible license. For any reuse or distribution, you must make clear to others the license terms of this work. The best way to do this is with a link to http://creativecommons.org/licenses/by-sa/3.0/. Any of the above conditions can be waived if you get permission from the copyright holder. Nothing in this license impairs or restricts the author's moral rights.
227

Chapter 07

Uploaded by

Document Information

Original Description:

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Chapter 07

Uploaded by

Copyright:

Available Formats

Spin Locks and Contention

Focus so far: Correctness and Progress

New Focus: Performance

Memory Contention Communication Contention Communication Latency

Today: Revisit Mutual Exclusion

What Should you do if you cant get a lock?

Give up the processor

Art of Multiprocessor Programming

What Should you do if you cant get a lock?

Give up the processor

CS spin lock critical section Resets lock upon exit

Art of Multiprocessor Programming

CS spin lock critical section Resets lock upon exit

Art of Multiprocessor Programming

CS spin lock critical section Resets lock upon exit

Art of Multiprocessor Programming

CS spin lock critical section Resets lock upon exit

Notice: these are distinct phenomena

CS spin lock critical section Resets lock upon exit

Seq Bottleneck no parallelism

CS spin lock critical section Resets lock upon exit

Can reset just by writing false TAS aka getAndSet

Art of Multiprocessor Programming

Art of Multiprocessor Programming

Swap old and new values

Art of Multiprocessor Programming

Swapping in true is called test-and-set or TAS

Art of Multiprocessor Programming

Acquire lock by calling TAS

Release lock by writing false

Art of Multiprocessor Programming

Art of Multiprocessor Programming

How long should it take? How long does it take?

Art of Multiprocessor Programming

What is going on?

Wait until lock looks free

void lock() { while (true) { while (state.get()) {} if (!state.getAndSet(true)) return; } }

Then try to acquire it

TTAS lock Ideal

Art of Multiprocessor Programming

Need a more detailed model

Art of Multiprocessor Programming

Art of Multiprocessor Programming

Will discuss complexities later

Art of Multiprocessor Programming

Processor Issues Load Request

Processor Issues Load Request

Processor Issues Load Request

Processor Issues Load Request

Processor Issues Load Request

Other Processor Responds

Other Processor Responds

Modify Cached Data

Modify Cached Data

Modify Cached Data

Modify Cached Data

Whats up with the other copies?memory

Some processor modifies its own copy

Art of Multiprocessor Programming

Art of Multiprocessor Programming

Mine, all mine!

This cache acquires write permission

Art of Multiprocessor Programming