Date: Mon, 13 Nov 2023 14:36:29 +0000 From: bugzilla-noreply@freebsd.org To: net@FreeBSD.org Subject: [Bug 274994] Regression of iperf3 network throughput tests with erms "rep movsb" copyto loops Message-ID: <bug-274994-7501-6mcFMQ4Oqp@https.bugs.freebsd.org/bugzilla/> In-Reply-To: <bug-274994-7501@https.bugs.freebsd.org/bugzilla/> References: <bug-274994-7501@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=3D274994 Richard Scheffenegger <rscheff@freebsd.org> changed: What |Removed |Added ---------------------------------------------------------------------------- Status|New |Closed Resolution|--- |Not A Bug --- Comment #3 from Richard Scheffenegger <rscheff@freebsd.org> --- Seems like a number of anciliary changes in the kernel behavior (core selection, NUMA etc) cause these more modern x86_64 instructions to be suboptimal in the local code; testing with upstream kernel code does not sh= ow similar performance degradations. Closing this bug therefore as it needs to= be addressed locally by making sure these instructions live up to the expectations. --=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-274994-7501-6mcFMQ4Oqp>