https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=256594
--- Comment #17 from Mark Johnston ---
(In reply to Andriy Gapon from comment #16)
Yes, I've observed this too when measuring TCP ping-pong latency over loopback
- latency is higher if the core was recently idle, I guess because autonomous
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=256594
--- Comment #16 from Andriy Gapon ---
Just in case, I want to share an old discovery of mine:
https://forums.FreeBSD.org/threads/variable-ping-latency-on-ryzen-setup.82791/post-547552
The point is that not all "micro-stutter" can be attrib
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=256594
Mark Johnston changed:
What|Removed |Added
Resolution|--- |FIXED
Status|Open
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=256594
--- Comment #14 from Jack ---
It looks like the stuttering is gone with the hacks removed now. Will reply if
issue comes back, thanks!
--
You are receiving this mail because:
You are the assignee for the bug.
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=256594
Mark Johnston changed:
What|Removed |Added
Status|New |Open
CC|
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=256594
--- Comment #12 from simony...@gmail.com ---
Actually, sorry, I just discovered this might be a different bug altogether for
the following reasons:
1. I tried setting kern.sched.steal_thresh=0 as per cr...@rlwinm.de directions.
There is no
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=256594
--- Comment #11 from cr...@rlwinm.de ---
If you're still stuck try breakout out into the loader prompt by pressing
escape during the 10 second countdown in the bootloader menu. On the loader
prompt type:
set kern.sched.steal_thresh=0
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=256594
simony...@gmail.com changed:
What|Removed |Added
CC||simony...@gmail.com
--- Comm
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=256594
lucenera changed:
What|Removed |Added
CC||ooo...@gmail.com
--- Comment #9 from lu
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=256594
Jack changed:
What|Removed |Added
CC||xxjack1...@gmail.com
--- Comment #8 from Ja
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=256594
--- Comment #7 from Bob Frazier ---
(In reply to Andriy Gapon from comment #4)
can you also try kern.eventtimer.timer=HPET ?
(this seems to make the most difference, especially if you have LAPIC assigned
which I think is the default, and
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=256594
Bob Frazier changed:
What|Removed |Added
CC||b...@mrp3.com
--- Comment #6 from Bo
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=256594
--- Comment #5 from cr...@rlwinm.de ---
(In reply to Jack from comment #0)
I still require the same workaround on my Ryzen 3950X system as well.
--
You are receiving this mail because:
You are the assignee for the bug.
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=256594
--- Comment #4 from Andriy Gapon ---
On my setup, also with a Zen 3 CPU, machdep.idle=mwait seems to improve the
situation.
--
You are receiving this mail because:
You are the assignee for the bug.
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=256594
Alan Somers changed:
What|Removed |Added
CC||asom...@freebsd.org,
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=256594
cr...@rlwinm.de changed:
What|Removed |Added
CC||cr...@rlwinm.de
--- Comment #2 fr
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=256594
Mark Linimon changed:
What|Removed |Added
Keywords||performance
Summary|AMD
17 matches
Mail list logo
