lock-free bounded MPMC ringbuffer failure - multithreading

I've been banging my head against (my attempt) at a lock-free multiple producer multiple consumer ring buffer. The basis of the idea is to use the innate overflow of unsigned char and unsigned short types, fix the element buffer to either of those types, and then you have a free loop back to beginning of the ring buffer.
The problem is - my solution doesn't work for multiple producers (it does though work for N consumers, and also single producer single consumer).
#include <atomic>
template<typename Element, typename Index = unsigned char> struct RingBuffer
{
std::atomic<Index> readIndex;
std::atomic<Index> writeIndex;
std::atomic<Index> scratchIndex;
Element elements[1 << (sizeof(Index) * 8)];
RingBuffer() :
readIndex(0),
writeIndex(0),
scratchIndex(0)
{
;
}
bool push(const Element & element)
{
while(true)
{
const Index currentReadIndex = readIndex.load();
Index currentWriteIndex = writeIndex.load();
const Index nextWriteIndex = currentWriteIndex + 1;
if(nextWriteIndex == currentReadIndex)
{
return false;
}
if(scratchIndex.compare_exchange_strong(
currentWriteIndex, nextWriteIndex))
{
elements[currentWriteIndex] = element;
writeIndex = nextWriteIndex;
return true;
}
}
}
bool pop(Element & element)
{
Index currentReadIndex = readIndex.load();
while(true)
{
const Index currentWriteIndex = writeIndex.load();
const Index nextReadIndex = currentReadIndex + 1;
if(currentReadIndex == currentWriteIndex)
{
return false;
}
element = elements[currentReadIndex];
if(readIndex.compare_exchange_strong(
currentReadIndex, nextReadIndex))
{
return true;
}
}
}
};
The main idea for writing was to use a temporary index 'scratchIndex' that acts a pseudo-lock to allow only one producer at any one time to copy-construct into the elements buffer, before updating the writeIndex and allowing any other producer to make progress. Before I am called heathen for implying my approach is 'lock-free' I realise that this approach isn't exactly lock-free, but in practice (if it would work!) it is significantly faster than having a normal mutex!
I am aware of a (more complex) MPMC ringbuffer solution here http://www.1024cores.net/home/lock-free-algorithms/queues/bounded-mpmc-queue, but I am really experimenting with my idea to then compare against that approach and find out where each excels (or indeed whether my approach just flat out fails!).
Things I have tried;
Using compare_exchange_weak
Using more precise std::memory_order's that match the behaviour I want
Adding cacheline pads between the various indices I have
Making elements std::atomic instead of just Element array
I am sure that this boils down to a fundamental segfault in my head as to how to use atomic accesses to get round using mutex's, and I would be entirely grateful to whoever can point out which neurons are drastically misfiring in my head! :)

This is a form of the A-B-A problem. A successful producer looks something like this:
load currentReadIndex
load currentWriteIndex
cmpxchg store scratchIndex = nextWriteIndex
store element
store writeIndex = nextWriteIndex
If a producer stalls for some reason between steps 2 and 3 for long enough, it is possible for the other producers to produce an entire queue's worth of data and wrap back around to the exact same index so that the compare-exchange in step 3 succeeds (because scratchIndex happens to be equal to currentWriteIndex again).
By itself, that isn't a problem. The stalled producer is perfectly within its rights to increment scratchIndex to lock the queue—even if a magical ABA-detecting cmpxchg rejected the store, the producer would simply try again, reload exactly the same currentWriteIndex, and proceed normally.
The actual problem is the nextWriteIndex == currentReadIndex check between steps 2 and 3. The queue is logically empty if currentReadIndex == currentWriteIndex, so this check exists to make sure that no producer gets so far ahead that it overwrites elements that no consumer has popped yet. It appears to be safe to do this check once at the top, because all the consumers should be "trapped" between the observed currentReadIndex and the observed currentWriteIndex.
Except that another producer can come along and bump up the writeIndex, which frees the consumer from its trap. If a producer stalls between steps 2 and 3, when it wakes up the stored value of readIndex could be absolutely anything.
Here's an example, starting with an empty queue, that shows the problem happening:
Producer A runs steps 1 and 2. Both loaded indices are 0. The queue is empty.
Producer B interrupts and produces an element.
Consumer pops an element. Both indices are 1.
Producer B produces 255 more elements. The write index wraps around to 0, the read index is still 1.
Producer A awakens from its slumber. It had previously loaded both read and write indices as 0 (empty queue!), so it attempts step 3. Because the other producer coincidentally paused on index 0, the compare-exchange succeeds, and the store progresses. At completion the producer lets writeIndex = 1, and now both stored indices are 1, and the queue is logically empty. A full queue's worth of elements will now be completely ignored.
(I should mention that the only reason I can get away with talking about "stalling" and "waking up" is that all the atomics used are sequentially consistent, so I can pretend that we're in a single-threaded environment.)
Note that the way that you are using scratchIndex to guard concurrent writes is essentially a lock; whoever successfully completes the cmpxchg gets total write access to the queue until it releases the lock. The simplest way to fix this failure is to just replace scratchIndex with a spinlock—it won't suffer from A-B-A and it's what's actually happening.

bool push(const Element & element)
{
while(true)
{
const Index currentReadIndex = readIndex.load();
Index currentWriteIndex = writeIndex.load();
const Index nextWriteIndex = currentWriteIndex + 1;
if(nextWriteIndex == currentReadIndex)
{
return false;
}
if(scratchIndex.compare_exchange_strong(
currentWriteIndex, nextWriteIndex))
{
elements[currentWriteIndex] = element;
// Problem here!
writeIndex = nextWriteIndex;
return true;
}
}
}
I've marked the problematic spot. Multiple threads can get to the writeIndex = nextWriteIndex at the same time. The data will be written in any order, although each write will be atomic.
This is a problem because you're trying to update two values using the same atomic condition, which is generally not possible. Assuming the rest of your method is fine, one way around this would be to combine both scratchIndex and writeIndex into a single value of double-size. For example, treating two uint32_t values as a single uint64_t value and operating atomically on that.

Related

using atomic c++11 to implement a thread safe down counter to zero

I'm new to atomic techniques and try to implement a safe thread version for the follow code:
// say m_cnt is unsigned
void Counter::dec_counter()
{
if(0==m_cnt)
return;
--m_cnt;
if(0 == m_cnt)
{
// Do seomthing
}
}
Every thread that calls dec_counter must decrement it by one and "Do something" should be done only one time - at when the counter is decremented to 0.
After fighting with it, I did the follow code that does it well (I think), but I wonder if this is the way to do it, or is there a better way. Thanks.
// m_cnt is std::atomic<unsigned>
void Counter::dec_counter()
{
// loop until decrement done
unsigned uiExpectedValue;
unsigned uiNewValue;
do
{
uiExpectedValue = m_cnt.load();
// if other thread already decremented it to 0, then do nothing.
if (0 == uiExpectedValue)
return;
uiNewValue = uiExpectedValue - 1;
// at the short time from doing
// uiExpectedValue = m_cnt.load();
// it is possible that another thread had decremented m_cnt, and it won't be equal here to uiExpectedValue,
// thus the loop, to be sure we do a decrement
} while (!m_cnt.compare_exchange_weak(uiExpectedValue, uiNewValue));
// if we are here, that means we did decrement . so if it was to 0, then do something
if (0 == uiNewValue)
{
// do something
}
}
The thing with atomic is that only that one statement is atomic.
If you write
std::atomic<int> i {20}
...
if (!--i)
...
Then just 1 thread will enter the if.
However, if you split up the change and the test, then other threads can get into the gap, and you may get strange results:
std::atomic<int> i {20}
...
--i;
// other thread(s) can modify i just here
if (!i)
...
Of course you can split the condition test for the decrement by using a local variable:
std::atomic<int> i {20}
...
int j=--i;
// other thread(s) can modify i just here
if (!j)
...
All the simple math operations are generally efficiently supported for small atomics in c++
For more complex types and expressions, you need to use the read/modify/write member methods.
These allow you to read the current value, calculate the new value, and then call compare_exchange_strong or compare_exchange_weak say "if the value has not changed, then store my new value, otherwise give me the new current value" a a single atomic operation. You can stick this in a loop and keep recalculating the new value until you are lucky enough that your thread is the only writer. If there are not too many threads trying too often to change the value this is reasonably efficient as well.

Is it possible to block on wait on a semaphore without using the data when it's available?

The software I'm working on is a data analyzer with a sliding window. I have 2 threads, one producer and one consumer, that use a circular buffer.
The consumer must process data only if the first element in the buffer is old enough, therefore there are at least X elements in the buffer. But after the processing, only X/4 data can be deleted, because of the moving window.
My solution below works quite well, except that I have a trade-off between being fast (busy form of waiting in the check), or being efficient (sleep for some time). The problem is that the sleep time varies according to load, thread scheduling and elaboration complexity, so I can potentially slow down the performances.
Is there a way to poll a semaphore to check if there are at least X elements, blocking the thread otherwise, but acquiring only X/4 after the processing has been done? The tryAcquire option does not work because when it wakes the thread consumes all the data, and not one half.
I've thought about copyng the elements in a second buffer, but actually there are 7 circular buffers of big data, therefore I'd like to avoid data duplication, or even data moving.
//common structs
QSemaphore written;
QSemaphore free;
int writtenIndex = 0;
int readIndex = 0;
myCircularBuffer buf;
bool scan = true;
//producer
void produceData(data d)
{
while ( free.tryAcquire(1, 1000) == false && scan == true)
{
//avoid deadlock!
//once per second give up waiting and check if closing
}
if (scan == false) return;
buf.at(writtenIndex) = d;
writtenIndex = (writtenIndex+1) % bufferSize;
written.release();
}
//consumer
void consumeData()
{
while(1)
{
//here goes the problem: usleep (slow), sched_yield (B.F.O.W.) or what?
if (buf.at(writtenIndex).age - buf.at(readIndex).age < X)
{
//usleep(100); ? how much time?
//sched_yield(); ?
//tryAcquire not an option!
continue;
}
processTheData();
written.acquire(X/4);
readIndex = (readIndex + X/4) % bufferSize;
free.release(X/4);
}

Does the following lock-free code exhibit a race-condition?

Within the Kubernetes Go repo on Github.com,
There is a lock-free implementation of a HighWaterMark data-structure. This code relies on atomic operations to achieve thread-safe code that is free of data races.
// HighWaterMark is a thread-safe object for tracking the maximum value seen
// for some quantity.
type HighWaterMark int64
// Update returns true if and only if 'current' is the highest value ever seen.
func (hwm *HighWaterMark) Update(current int64) bool {
for {
old := atomic.LoadInt64((*int64)(hwm))
if current <= old {
return false
}
if atomic.CompareAndSwapInt64((*int64)(hwm), old, current) {
return true
}
}
}
This code relies on the atomic.LoadInt64 and atomic.CompareAndSwapInt64 functions within the standard library to achieve data race free code...which I believe it does but I believe there is another problem of a race condition.
If two competing threads (goroutines) are executing such code there exists an edge case where after the atomic.LoadInt64 occurs in the first thread, the second thread could have swapped out for a higher value. But after the first thread thinks the current int64 is actually larger than the old int64 a swap will happen. This swap would then effectively lower the stored value due to observing a stale old value.
If another thread got in the middle, the CompareAndSwap would fail and the loop would start over.
Think of CompareAndSwap as
if actual == expected {
actual = newval
}
but done atomically
So this code says:
old = hwm // but done in a thread safe atomic read way
if old < current {
set hwm to current if hwm == old // atomically compare and then set value
}
when CAS (CompareAndSwap) fails, it returns false, causing the loop to start over until either:
a) "current" is not bigger than hwm
or
b) It successfully performs Load and then CompareAndSwap without another thread in the middle

Design pattern for asynchronous while loop

I have a function that boils down to:
while(doWork)
{
config = generateConfigurationForTesting();
result = executeWork(config);
doWork = isDone(result);
}
How can I rewrite this for efficient asynchronous execution, assuming all functions are thread safe, independent of previous iterations, and probably require more iterations than the maximum number of allowable threads ?
The problem here is we don't know how many iterations are required in advance so we can't make a dispatch_group or use dispatch_apply.
This is my first attempt, but it looks a bit ugly to me because of arbitrarily chosen values and sleeping;
int thread_count = 0;
bool doWork = true;
int max_threads = 20; // arbitrarily chosen number
dispatch_queue_t queue =
dispatch_get_global_queue(DISPATCH_QUEUE_PRIORITY_DEFAULT, 0);
while(doWork)
{
if(thread_count < max_threads)
{
dispatch_async(queue, ^{ Config myconfig = generateConfigurationForTesting();
Result myresult = executeWork();
dispatch_async(queue, checkResult(myresult)); });
thread_count++;
}
else
usleep(100); // don't consume too much CPU
}
void checkResult(Result value)
{
if(value == good) doWork = false;
thread_count--;
}
Based on your description, it looks like generateConfigurationForTesting is some kind of randomization technique or otherwise a generator which can make a near-infinite number of configuration (hence your comment that you don't know ahead of time how many iterations you will need). With that as an assumption, you are basically stuck with the model that you've created, since your executor needs to be limited by some reasonable assumptions about the queue and you don't want to over-generate, as that would just extend the length of the run after you have succeeded in finding value ==good measurements.
I would suggest you consider using a queue (or OSAtomicIncrement* and OSAtomicDecrement*) to protect access to thread_count and doWork. As it stands, the thread_count increment and decrement will happen in two different queues (main_queue for the main thread and the default queue for the background task) and thus could simultaneously increment and decrement the thread count. This could lead to an undercount (which would cause more threads to be created than you expect) or an overcount (which would cause you to never complete your task).
Another option to making this look a little nicer would be to have checkResult add new elements into the queue if value!=good. This way, you load up the initial elements of the queue using dispatch_apply( 20, queue, ^{ ... }) and you don't need the thread_count at all. The first 20 will be added using dispatch_apply (or an amount that dispatch_apply feels is appropriate for your configuration) and then each time checkResult is called you can either set doWork=false or add another operation to queue.
dispatch_apply() works for this, just pass ncpu as the number of iterations (apply never uses more than ncpu worker threads) and keep each instance of your worker block running for as long as there is more work to do (i.e. loop back to generateConfigurationForTesting() unless !doWork).

Looking for a lock-free RT-safe single-reader single-writer structure

I'm looking for a lock-free design conforming to these requisites:
a single writer writes into a structure and a single reader reads from this structure (this structure exists already and is safe for simultaneous read/write)
but at some time, the structure needs to be changed by the writer, which then initialises, switches and writes into a new structure (of the same type but with new content)
and at the next time the reader reads, it switches to this new structure (if the writer multiply switches to a new lock-free structure, the reader discards these structures, ignoring their data).
The structures must be reused, i.e. no heap memory allocation/free is allowed during write/read/switch operation, for RT purposes.
I have currently implemented a ringbuffer containing multiple instances of these structures; but this implementation suffers from the fact that when the writer has used all the structures present in the ringbuffer, there is no more place to change from structure... But the rest of the ringbuffer contains some data which don't have to be read by the reader but can't be re-used by the writer. As a consequence, the ringbuffer does not fit this purpose.
Any idea (name or pseudo-implementation) of a lock-free design? Thanks for having considered this problem.
Here's one. The keys are that there are three buffers and the reader reserves the buffer it is reading from. The writer writes to one of the other two buffers. The risk of collision is minimal. Plus, this expands. Just make your member arrays one element longer than the number of readers plus the number of writers.
class RingBuffer
{
RingBuffer():lastFullWrite(0)
{
//Initialize the elements of dataBeingRead to false
for(unsigned int i=0; i<DATA_COUNT; i++)
{
dataBeingRead[i] = false;
}
}
Data read()
{
// You may want to check to make sure write has been called once here
// to prevent read from grabbing junk data. Else, initialize the elements
// of dataArray to something valid.
unsigned int indexToRead = lastFullWriteIndex;
Data dataCopy;
dataBeingRead[indexToRead] = true;
dataCopy = dataArray[indexToRead];
dataBeingRead[indexToRead] = false;
return dataCopy;
}
void write( const Data& dataArg )
{
unsigned int writeIndex(0);
//Search for an unused piece of data.
// It's O(n), but plenty fast enough for small arrays.
while( true == dataBeingRead[writeIndex] && writeIndex < DATA_COUNT )
{
writeIndex++;
}
dataArray[writeIndex] = dataArg;
lastFullWrite = &dataArray[writeIndex];
}
private:
static const unsigned int DATA_COUNT;
unsigned int lastFullWrite;
Data dataArray[DATA_COUNT];
bool dataBeingRead[DATA_COUNT];
};
Note: The way it's written here, there are two copies to read your data. If you pass your data out of the read function through a reference argument, you can cut that down to one copy.
You're on the right track.
Lock free communication of fixed messages between threads/processes/processors
fixed size ring buffers can be used in lock free communications between threads, processes or processors if there is one producer and one consumer. Some checks to perform:
head variable is written only by producer (as an atomic action after writing)
tail variable is written only by consumer (as an atomic action after reading)
Pitfall: introduction of a size variable or buffer full/empty flag; these are typically written by both producer and consumer and hence will give you an issue.
I generally use ring buffers for this purpoee. Most important lesson I've learned is that a ring buffer of can never contain more than elements. This way a head and tail variable are written by producer respectively consumer.
Extension for large/variable size blocks
To use buffers in a real time environment, you can either use memory pools (often available in optimized form in real time operating systems) or decouple allocation from usage. The latter fits to the question, I believe.
If you need to exchange large blocks, I suggest to use a pool with buffer blocks and communicate pointers to buffers using a queue. So use a 3rd queue with buffer pointers. This way the allocates can be done in application (background) and you real time portion has access to a variable amount of memory.
Application
while (blockQueue.full != true)
{
buf = allocate block of memory from heap or buffer pool
msg = { .... , buf };
blockQueue.Put(msg)
}
Producer:
pBuf = blockQueue.Get()
pQueue.Put()
Consumer
if (pQueue.Empty == false)
{
msg=pQueue.Get()
// use info in msg, with buf pointer
// optionally indicate that buf is no longer used
}

Resources