[lttng-dev] Alternative to signals/sys_membarrier() in liburcu

[Mathieu Desnoyers]

----- Original Message -----
> From: "Duncan Sands" <baldrick at free.fr>
> To: lttng-dev at lists.lttng.org
> Sent: Thursday, February 12, 2015 8:57:51 AM
> Subject: Re: [lttng-dev] Alternative to signals/sys_membarrier() in liburcu
> 
> Hi Michael,
> 
> On 11/02/15 01:03, Michael Sullivan wrote:
> > I've been looking at the RCU library (as part of gathering examples for my
> > research on weak memory models) and was thinking about ways to force other
> > threads to issue barriers. Since it seems like sys_membarrier() never made
> > it
> > into the kernel, I was pondering whether there was some other way to more
> > or
> > less get its effect; as it turns out, there is, but it is a hack:
> > mprotect(2).
> 
> is it clear that sys_membarrier is really dead?

There were no technical objections to sys_membarrier. The only objection
left was that only liburcu was needing it, and kernel maintainers were
concerned to introduce a kernel API for only a single user.

It would be good if we can come up with other uses of sys_membarrier.

Thoughts ?

Thanks,

Mathieu


> 
> Ciao, Duncan.
> 
> _______________________________________________
> lttng-dev mailing list
> lttng-dev at lists.lttng.org
> http://lists.lttng.org/cgi-bin/mailman/listinfo/lttng-dev
> 

-- 
Mathieu Desnoyers
EfficiOS Inc.
http://www.efficios.com