http://bugzilla.suse.com/show_bug.cgi?id=1131330 http://bugzilla.suse.com/show_bug.cgi?id=1131330#c4 Michael Matz <matz@suse.com> changed: What |Removed |Added ---------------------------------------------------------------------------- CC| |matz@suse.com Flags| |needinfo?(asbeer@gmail.com) --- Comment #4 from Michael Matz <matz@suse.com> --- 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.