Date: Sun, 16 Apr 2023 08:50:51 +0000 From: bugzilla-noreply@freebsd.org To: threads@FreeBSD.org Subject: [Bug 270785] Performance and power efficiency regression due to pthread_cond_timedwait() changes Message-ID: <bug-270785-13406-WMxsXFjD3i@https.bugs.freebsd.org/bugzilla/> In-Reply-To: <bug-270785-13406@https.bugs.freebsd.org/bugzilla/> References: <bug-270785-13406@https.bugs.freebsd.org/bugzilla/>
next in thread | previous in thread | raw e-mail | index | archive | help
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=3D270785 --- Comment #10 from bllcha013@myuct.ac.za --- Thank you, I applied the diff on a clean git clone on releng/13.2 and teste= d, but unfortunately it doesn't appear to have any effect. The sysctl is visib= le as kern.ipc.umtx_min_timeout. I set it to 10ms (10000000ns) by issuing "sys= ctl kern.ipc.umtx_min_timeout=3D10000000" but unfortunately there doesn't seem = to be any effect. CPU usage stays the same. Here's the truss and dtrace output: syscall seconds calls errors __sysctlbyname 0.000986089 6 0 getrusage 0.008186177 106 0 sched_yield 1.172105081 28475 0 _umtx_op 30.594233465 28659 28654 ------------- ------- ------- 31.775510812 57246 28654 dtrace: description 'fbt::do_wait:entry ' matched 1 probe CPU ID FUNCTION:NAME 5 18113 do_wait:entry struct _umtx_time { struct timespec _timeout =3D { time_t tv_sec =3D 0x16a long tv_nsec =3D 0x279c2e2a } __uint32_t _flags =3D 0x1 __uint32_t _clockid =3D 0x4 } 6 18113 do_wait:entry struct _umtx_time { struct timespec _timeout =3D { time_t tv_sec =3D 0x16a long tv_nsec =3D 0x279dd9fd } __uint32_t _flags =3D 0x1 __uint32_t _clockid =3D 0x4 } It seems the high volume of syscalls stayed the same, with the same short 0= .1ms delay. Assuming this can be made to work though, this tunable would be really grea= tly appreciated. --=20 You are receiving this mail because: You are the assignee for the bug.=
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?bug-270785-13406-WMxsXFjD3i>