Date: Thu, 17 Mar 2016 23:50:46 +0700 From: Eugene Grosbein <eugen@grosbein.net> To: Eric van Gyzen <vangyzen@FreeBSD.org>, Alan Somers <asomers@freebsd.org>, "Pieper, Jeffrey E" <jeffrey.e.pieper@intel.com> Cc: FreeBSD Net <freebsd-net@freebsd.org>, Jack Vogel <jfvogel@gmail.com> Subject: Re: TSO test Message-ID: <56EAE066.1010108@grosbein.net> In-Reply-To: <56EACBCF.5020109@FreeBSD.org> References: <CAFOYbcn9XTaLrtZhkS1X69qhf2aOe0iOSirCTA=LfGsZDTqbeg@mail.gmail.com> <2A35EA60C3C77D438915767F458D656880953A88@ORSMSX111.amr.corp.intel.com> <CAOtMX2g7NzquGC17Gz5dXHEOy7nQFGEhb7FrBPO0zrXDwH=d6g@mail.gmail.com> <56EACBCF.5020109@FreeBSD.org>
next in thread | previous in thread | raw e-mail | index | archive | help
17.03.2016 22:22, Eric van Gyzen пишет:
> Alan,
>
> That does sound useful. As one complication, "vmstat -i" shows the
> interrupt rate since boot. Either the test would need to reboot between
> each iteration, or vmstat would need to be improved to show the "recent"
> rate. The latter would be a much welcome improvement, in my humble opinion.
vmstat with "-i" option shows interrupts since reboot
and without "-i" shows interrupts per interval,
look for "in" column under "faults":
$ vmstat 1 3
procs memory page disks faults cpu
r b w avm fre flt re pi po fr sr ad0 ad1 in sy cs us sy id
0 1 17 9221M 1525M 197 0 0 0 215 119 0 0 1107 106 813 4 3 94
0 1 17 9221M 1525M 0 0 0 0 0 47 0 0 1078 544 2505 0 2 98
0 1 17 9221M 1525M 0 0 0 0 0 47 0 0 1082 509 2468 0 2 97
In this example, there were 107, 87 and 82 interrupts per each of last 3 seconds
excluding 1000 clock ("HZ") interrupts.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?56EAE066.1010108>