Fix data race in SamplingCircularQueue

Fix data race in SamplingCircularQueue

This change fixes data race described in the bug by adding Acquire_Load to SamplingCircularQueue::StartDequeue and Acquire_Store to SamplingCircularQueue::Enqueue.

Also the queue implementation imposed a constraint on the records it stored: the first AtomicWord in each record was a marker. For that purpose TickSampleEventRecord had filter field of type int. This approach is error prone, e.g. on x64 sizeof(AtomicWord) is 8 while sizeof(int) is 4. Moreover the queue needs such marker only at the beginning of chunk. I changed the queue so that it stores the marker explicitly as the first Cell in chunk and removed the filter field.

BUG=251218
R=loislo@chromium.org, yangguo@chromium.org

Committed: https://code.google.com/p/v8/source/detail?r=15750

[loislo, 2013-07-18 12:28:42]

LGTM

This approach looks simpler than the previous but still complicated. I'd say
that we could align the chunk size to the cache line size and use 1 chunk size
distance.

Also we could simplify the size calculation for the positions buffer. It could
be sizeof(producer_pos) + kCacheLineSize + sizeof(consumer_pos).

[yurys, 2013-07-18 12:56:32]

On 2013/07/18 12:28:42, loislo wrote:
> LGTM
> 
> This approach looks simpler than the previous but still complicated. I'd say
> that we could align the chunk size to the cache line size and use 1 chunk size
> distance.
> 
I don't think there is much sense in having the chunks. It seems that we could
simply align records by cache line boundaries and poll current_record + 2 in the
consumer.

> Also we could simplify the size calculation for the positions buffer. It could
> be sizeof(producer_pos) + kCacheLineSize + sizeof(consumer_pos).
I'll do this in a separate patch.

[yurys, 2013-07-18 12:57:10]

Yang or Jakob, can you do OWNER review please?

[Yang, 2013-07-18 13:12:54]

On 2013/07/18 12:57:10, Yury Semikhatsky wrote:
> Yang or Jakob, can you do OWNER review please?

LGTM.

[yurys, 2013-07-18 13:42:13]

Committed patchset #2 manually as r15750 (presubmit successful).