Date: Thu, 30 May 1996 16:54:47 +0000 () From: Werner Griessl <croot@btp1da.phy.uni-bayreuth.de> To: robmel@nadt.org.uk (Robin Melville) Cc: questions@freebsd.org Subject: Re: Excessive interrupts question Message-ID: <199605301654.QAA16142@btp1da.phy.uni-bayreuth.de> In-Reply-To: <v01530501add360498bbb@[194.155.224.204]> from Robin Melville at "May 30, 96 03:31:26 pm"
next in thread | previous in thread | raw e-mail | index | archive | help
> > > >> I have 2.1 running on a Hewlett Packard NetServer with a NE2000 clone ether > >> card and HP-doctored Adaptech 7770 on-board scsi with one 2Gb disk. > >> > >> It runs ok but very sluggishly. Checking with xperfmon++ I discover that > >> something's generating 20k+ interrupts per second. Can anyone suggest what > >> I should do to solve this? > > > > >Try "vmstat -i" to identify the interrupt source > > > >Werner > > >I'd immediately suspect the NE2000. This is a well-known CPU hog in > >Novell servers. > > > >[ Michael ] > > vmstat -i shows: > > interrupt total rate > clk0 irq0 95305809 99 > rtc0 irq8 104534 0 > fdc0 irq6 1 0 > ahc1 irq11 9696467 10 > sc0 irq1 5 0 > sio0 irq4 2 0 > sio1 irq3 2 0 > ed1 irq5 7469608 7 > Total 112576428 118 > > This is a different picture from that supplied by xperfmon (?). Are these > interrupts excessive? > > Thanx again .... > > Robin. > > ----------------------------------------------- Looks very normal except the rtc0 . Here is my "vmstat -i": interrupt total rate clk0 irq0 9169027 100 rtc0 irq8 11734233 127 fdc0 irq6 1 0 wdc0 irq14 3465496 37 sio0 irq4 9 0 vt0 irq1 259 0 ed0 irq5 3211171 35 Total 27580196 300 Werner
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199605301654.QAA16142>