Gentoo Archives: gentoo-amd64

From: Mark Knecht <markknecht@×××××.com>
To: gentoo-amd64@l.g.o
Subject: Re: [gentoo-amd64] Re: kernel.org vs. Gentoo-64 bit kernels (xruns)
Date: Tue, 20 Sep 2005 12:26:56
Message-Id: 5bdc1c8b050920052512a333d1@mail.gmail.com
In Reply to: [gentoo-amd64] Re: kernel.org vs. Gentoo-64 bit kernels (xruns) by Duncan <1i5t5.duncan@cox.net>
1 On 9/20/05, Duncan <1i5t5.duncan@×××.net> wrote:
2 > Mark Knecht posted <5bdc1c8b05091914554f0c7360@××××××××××.com>, excerpted
3 > below, on Mon, 19 Sep 2005 14:55:59 -0700:
4 >
5 > > It seems right now that a simple emerge sync is causing xruns on this
6 > > system implying to me some underlying problem with either hard drive
7 > > activity or networking. since the hard drive is SATA and the networking
8 > > option in the kernel marks the NIC driver as 'Reverse engineered -
9 > > experimental' I'm not confident of fixing this problem in the immediate
10 > > short term anyway.
11 > >
12 > > My thoughts right now:
13 > >
14 > > 1) kernel.org + rt patches
15 > > 2) ck-sources
16 > > 3) gentoo-sources-amd64 + rt patches not cleanly applied
17 > >
18 > > I may also investigate a different NIC. I have a email friend that
19 > > runs a studio in Sydney. I helped him move from FC2 to Gentoo. We had
20 > > xruns using some of the NIC stuff for his motherboard. When we found that
21 > > was the problem he never had another problem.
22 >
23 > I'm not familiar with the term "xrun", so this may be entirely off the
24 > wall, but have you confirmed the hard drive is running DMA? If your
25 > chipset or SATA drivers are wrong, and your hard drive is having to run in
26 > legacy interrupt mode instead of DMA mode, it *WILL* destroy latency and
27 > generally make the system unusable for any sort of real-time work at all,
28 > regardless of the other kernel patches applied. So... in addition to
29 > checking the network drivers, investigate the hard drive and chipset I/O
30 > drivers as well, and confirm you ARE running DMA mode.
31 >
32 Thanks, yes, DMA is running, as far as I can tell. hdparm -tT returns
33 numbers that are >50MB/S.
34
35 xruns are a term specific to the Jack server
36 (jack-audio-connection-kit) that tell us whether we've had and overrun
37 or an underrun. It's would be off topic to go deeply into how Jack
38 operates when talking to sound cards, but take it to mean something
39 bad has happened with real-time audio data.
40
41 Interestingly Jack runs from memory so hard drive performance should
42 not cause major problems unless it's not interruptable in a more or
43 less real-time way. On my Gentoo 32-bit machines (using Via and ATI
44 chipsets) I've not had to install any real-time patches and can still
45 run reliable at sub-2mS latencies. On those machines I can do pretty
46 much anything, browse the web with firefox, do and emerge sync, etc.,
47 and I get no xruns. On this AMD64/NForce4 machine and emerge sync
48 causes xruns immediately, indicating the sound card is getting starved
49 for data.
50
51 Anyway, thanks for the comments. DMA seems to be enabled on both the
52 hard drive and the CDRW and DVDRW drives.
53
54 Cheers,
55 Mark
56
57 --
58 gentoo-amd64@g.o mailing list

Replies