http://bugzilla.suse.com/show_bug.cgi?id=1131330
http://bugzilla.suse.com/show_bug.cgi?id=1131330#c4
Michael Matz changed:
What |Removed |Added
----------------------------------------------------------------------------
CC| |matz@suse.com
Flags| |needinfo?(asbeer@gmail.com)
--- Comment #4 from Michael Matz ---
Have any of you per chance CPUs capable of hardware lock elision? I can't
reproduce the problem with any glibc I find (e.g.
glibc-2.26-lp150.10.13.x86_64 (Leap 15)
glibc-2.26-lp150.11.17.1.x86_64 (Leap 15)
glibc-2.26-18.3.x86_64 (SLE 15 SP1)) on any machine I can find. But those
machines are all either AMD CPUs or Intel CPUs without HLE.
The code path using HLE for the low-level-locks in glibc is behaving different
from the traditional code path, including different behavious in error cases.
So it might be that, but can you please confirm the hardware details? lscpu
output from one machine where you can reproduce it would be good.
--
You are receiving this mail because:
You are on the CC list for the bug.