Date: Mon, 08 Oct 2007 13:26:52 -0600 From: Scott Long <scottl@samsco.org> To: Jeff Kramer <jeffk@well.com> Cc: freebsd-stable@freebsd.org, Ivan Voras <ivoras@freebsd.org> Subject: Re: PAE Slowdown Message-ID: <470A847C.6040409@samsco.org> In-Reply-To: <p06002007c330182a41ec@[192.168.0.5]> References: <p06002004c33006420f72@[192.168.0.5]> <fedngm$aa4$1@sea.gmane.org> <p06002007c330182a41ec@[192.168.0.5]>
next in thread | previous in thread | raw e-mail | index | archive | help
Jeff Kramer wrote: > At 6:56 PM +0200 10/8/07, Ivan Voras wrote: >> Jeff Kramer wrote: >>> Hey all, >>> >>> I know that AMD64's the preferred way to run >4 gig systems, but I'm >>> having a weird situation with 6.2-RELEASE-p8 and 6-STABLE as of last >>> night. When I compile the PAE kernel, my system performance drops like >>> a rock. It still boots and everything still runs, but for instance, >>> running the Flops port my megaflops drop from the 950 MFLOPS range to 4 >>> MFLOPS. It feels about as fast as a 486. >> >> Does vmstat -i show unusually high interrupt rates? > > When it's running ok at idle (4 gig of ram): > > interrupt total rate > irq1: atkbd0 77 0 > irq16: twa0 1084 3 > irq17: atapci0 1 0 > irq19: fwohci0++ 3 0 > irq20: em0 161 0 > cpu0: timer 549165 1920 > Total 550491 1924 > > When it's slow at idle (8 gig of ram): > > interrupt total rate > irq1: atkbd0 48 0 > irq16: twa0 1093 8 > irq17: atapci0 1 0 > irq19: fwohci0++ 3 0 > irq20: em0 179 1 > cpu0: timer 241862 1950 > Total 243186 1961 > > > The culprit could be the twa driver. Are you really generating that much I/O? Scott
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?470A847C.6040409>