Date: Fri, 3 Feb 2006 17:47:32 -0500 (EST) From: Andrew Gallatin <gallatin@cs.duke.edu> To: freebsd-current@freebsd.org Subject: machdep.cpu_idle_hlt and SMP perf? Message-ID: <17379.56708.421007.613310@grasshopper.cs.duke.edu>
next in thread | raw e-mail | index | archive | help
Why dooes machdep.cpu_idle_hlt=1 drop my 10GbE network rx performance by a considerable amount (7.5Gbs -> 5.5Gbs)? I've (blindly) tried leaving machdep.cpu_idle_hlt=1 enabled and playing with the vast array of kern.sched.ipiwakeup.* sysctls, but receive performance remains limited to ~5.5Gb/sec or less. This is an 'AMD Athlon(tm) 64 X2 Dual Core Processor 3800+' running FreeBSD-current as of about one week ago. The interrupt load is about 22,000 device interrupts/sec (ithreaded). Interestingly, the more I decrease the interrupt load by increasing the interrupt coalescing timer, the worse the machdep.cpu_idle_hlt=1 case does. Is this just a case of the wakeup IPI taking a long time or blocking on some lock? Drew PS: Here is what I mean: rome% ssh venice-my netperf224 -Hrome-my -tTCP_SENDFILE -F /boot/vmlinuz-2.6.9-11.EL -- -S 131072 TCP SENDFILE TEST to rome-my Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 131072 65536 65536 10.00 5460.73 rome% sudo sysctl machdep.cpu_idle_hlt=0 machdep.cpu_idle_hlt: 1 -> 0 rome% ssh venice-my netperf224 -Hrome-my -tTCP_SENDFILE -F /boot/vmlinuz-2.6.9-11.EL -- -S 131072 TCP SENDFILE TEST to rome-my Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 131072 65536 65536 10.00 7842.41
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?17379.56708.421007.613310>