From f8665d43b8e1e33a92b7529d49e3e8c8b1c3c586 Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Thu, 17 May 2018 17:02:31 +0200 Subject: man: reformat all man pages - use .TP for option and example labels - use .BR for references to other manpages, also in description texts - highlight options using .B in description texts - misc. cleanups Signed-off-by: Tobias Klauser --- ifpps.8 | 103 ++++++++++++++++++++++++++++++++++------------------------------ 1 file changed, 55 insertions(+), 48 deletions(-) (limited to 'ifpps.8') diff --git a/ifpps.8 b/ifpps.8 index b60e7b8..f344cec 100644 --- a/ifpps.8 +++ b/ifpps.8 @@ -22,83 +22,90 @@ an Intel 82566DC-2 Gigabit Ethernet NIC are used for performance evaluation. One machine generates 64 byte network packets by using the kernel space packet generator pktgen with a maximum possible packet rate. The other machine displays statistics about incoming network packets by using i) -iptraf(8) and ii) ifpps. -.PP -iptraf which incorporates pcap(3) shows an average packet rate of -246,000 pps while on the other hand ifpps shows an average packet rate -of 1,378,000 pps. Hence, due to packet copies and deferring statistics -creation into user space, a measurement error of approximately 460 percent -occurs. Tools like iptraf might display much more information such as -TCP per flow statistics (hence the use of the pcap library). This is not -possible with ifpps, because overall networking statistics are its focus; -statistics, which are also fairly reliable under high packet load. +.BR iptraf (8) +and ii) ifpps. +.PP +iptraf which incorporates +.BR pcap (3) +shows an average packet rate of 246,000 pps while on the other hand ifpps shows +an average packet rate of 1,378,000 pps. Hence, due to packet copies and +deferring statistics creation into user space, a measurement error of +approximately 460 percent occurs. Tools like iptraf might display much more +information such as TCP per flow statistics (hence the use of the pcap library). +This is not possible with ifpps, because overall networking statistics are its +focus; statistics, which are also fairly reliable under high packet load. .PP ifpps also periodically displays CPU load, interrupt, software interrupt data per sample interval as well as total interrupts, all per CPU. In case the number of CPUs exceeds 5 or the number specified by the user with the -\[lq]\-n\[rq] command line option, ifpps will only display this number top +\fB-n\fP command line option, ifpps will only display this number top heavy hitters. The topmost heavy hitter CPU will be marked with \[lq]+\[rq]. The least heavy hitter will always be displayed and is marked with \[lq]-\[rq]. In addition, the average for all the above per-CPU data is -shown. Optionally the median values can be displayed using the \[lq]\-m\[rq] +shown. Optionally the median values can be displayed using the \fB-m\fP command line option. .PP -ifpps also supports directly the gnuplot(1) data sample format. This -facilitates creation of gnuplot figures from ifpps time series. +ifpps also supports directly the +.BR gnuplot (1) +data sample format. This facilitates creation of gnuplot figures from ifpps time +series. .PP .SH OPTIONS -.PP -.SS -d , --dev +.TP +.B -d , --dev Networking device to fetch statistics from, for example eth0, wlan0. -.PP -.SS -n, --num-cpus +.TP +.B -n, --num-cpus Set maximum number of top hitter CPUs (in terms of time spent in system/user mode) to display in ncurses mode, default is 10. -.PP -.SS -t