Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > comp.programming > #3787 > unrolled thread

About lockfree queues

Back to article view | Back to comp.programming

Contents

  About lockfree queues aminer <aminer@toto.net> - 2013-09-24 13:09 -0700
    Re: About lockfree queues "Chris M. Thomasson" <no@spam.invalid> - 2013-09-24 10:32 -0700

#3787 — About lockfree queues

Hello,


I have come to an interresting subject about lockfree queues,
if you take a look at those lockfree queues, like in transactional 
memory, if the data have changed those lockfree queue retries and loop 
again, but this (lockfree) mechanism generates a lot of cache-coherence 
traffic, so i will not advice this lockfree mechanism, so how
can we do it ? you can take a look at the MCS queue Lock , i
think they are doing it like a waitfree linklist that doesn't spin and
that reduces a lot the cache-coherence traffic, other than that
if your memory manager is not optimal and uses a lockfree mechanism and 
generates a lot cache-coherence traffic, so you have to use a freelist 
to lower the cache coherence traffic.


So be smart please and think about that.


Thank youi,
Amine Moulay Ramdane.

[toc] | [next] | [standalone]

#3788

> "aminer"  wrote in message news:l1sh13$krl$1@news.albasani.net... I have 
> come to an interresting subject about lockfree queues,
> if you take a look at those lockfree queues[...]

This MPMC queue one scales very good for a damn anti-pattern:

I think I will post the algorithm that uses eventcounts to get around 
spin-wait.

The code needs Relacy to run.


Some context:


https://groups.google.com/forum/#!searchin/comp.arch/random$20isa/comp.arch/aLVoxdQdRac/overview
(read all)

https://groups.google.com/forum/#!original/comp.arch/aLVoxdQdRac/9DtioMswSmUJ
(pseudo-code for spin-based algorithm) 

[toc] | [prev] | [standalone]

Back to top | Article view | comp.programming

csiph-web