Problem with timecounters and memory model
Poul-Henning Kamp
phk at phk.freebsd.dk
Fri May 29 13:36:26 UTC 2015
--------
In message <55686300.3080100 at embedded-brains.de>, Sebastian Huber writes:
>This version seems to work at least on uni-processor systems. Shouldn't
>there be real memory barriers the synchronize the reads/writes to
>th_generation for SMP machines?
yes, there should.
(I must admit that I havn't looked at that code for about five or ten years.)
--
Poul-Henning Kamp | UNIX since Zilog Zeus 3.20
phk at FreeBSD.ORG | TCP/IP since RFC 956
FreeBSD committer | BSD since 4.3-tahoe
Never attribute to malice what can adequately be explained by incompetence.
More information about the freebsd-hackers
mailing list