Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
Ariff Abdullah wrote: On Sat, 27 Aug 2005 13:38:00 -0500 Mark Kane [EMAIL PROTECTED] wrote: Mark Kane wrote: I do notice that when doing some things like using unrar to extract a file or loading a video into video encoding software I do get some of the same little crackles and static in the audio. I didn't notice this static/crackling ever before applying that first patch. I am still skip/stutter free though :). Might the second patch help the crackling/static? Perhaps. You should give it a try. There is another issue as well (such as PCI latency timer), but only after you applied all those suggested patches. Okay I applied the second patch. Still whenever unrarring a file or loading big files from a drive I do hear little static in the audio, but it's not bad at all. But the initial problem of the skipping and stuttering is fixed so I am very happy :). Thanks again for the help. -Mark ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
On Mon, 29 Aug 2005 19:38:41 -0500 Mark Kane [EMAIL PROTECTED] wrote: Ariff Abdullah wrote: On Sat, 27 Aug 2005 13:38:00 -0500 Mark Kane [EMAIL PROTECTED] wrote: Mark Kane wrote: I do notice that when doing some things like using unrar to extract a file or loading a video into video encoding software I do get some of the same little crackles and static in the audio. I didn't notice this static/crackling ever before applying that first patch. I am still skip/stutter free though :). Might the second patch help the crackling/static? Perhaps. You should give it a try. There is another issue as well (such as PCI latency timer), but only after you applied all those suggested patches. Okay I applied the second patch. Still whenever unrarring a file or loading big files from a drive I do hear little static in the audio, but it's not bad at all. But the initial problem of the skipping and stuttering is fixed so I am very happy :). PCI latency issue comes in mind (which pretty common within VIA universe). http://staff.mybsd.org.my/skywizard/FreeBSD/sound/pcmutils/pcilattimer Play around with its latency timer value (increase) and see whether that could make things better. -- Ariff Abdullah MyBSD http://www.MyBSD.org.my (IPv6/IPv4) http://staff.MyBSD.org.my (IPv6/IPv4) http://tomoyo.MyBSD.org.my (IPv6/IPv4) ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
Ariff Abdullah wrote: On Mon, 29 Aug 2005 19:38:41 -0500 Mark Kane [EMAIL PROTECTED] wrote: Ariff Abdullah wrote: On Sat, 27 Aug 2005 13:38:00 -0500 Mark Kane [EMAIL PROTECTED] wrote: Mark Kane wrote: I do notice that when doing some things like using unrar to extract a file or loading a video into video encoding software I do get some of the same little crackles and static in the audio. I didn't notice this static/crackling ever before applying that first patch. I am still skip/stutter free though :). Might the second patch help the crackling/static? Perhaps. You should give it a try. There is another issue as well (such as PCI latency timer), but only after you applied all those suggested patches. Okay I applied the second patch. Still whenever unrarring a file or loading big files from a drive I do hear little static in the audio, but it's not bad at all. But the initial problem of the skipping and stuttering is fixed so I am very happy :). PCI latency issue comes in mind (which pretty common within VIA universe). http://staff.mybsd.org.my/skywizard/FreeBSD/sound/pcmutils/pcilattimer Play around with its latency timer value (increase) and see whether that could make things better. Well this is an nForce3 chipset, but I will look into the script. Thanks -Mark ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
Ariff Abdullah wrote: These are my suggestions: 1) enable 'options PREEMPTION'. This is a MUST. 2) use SCHED_ULE instead of SCHED_4BSD. ULE is pretty stable on me, but I can't guarantee (especially combining with PREEMPTION). It doesn't hurt to give it a try. 3) Apply these patches: http://staff.mybsd.org.my/skywizard/FreeBSD/sound/jroberson_flushbuf_RELENG_5.diff http://staff.mybsd.org.my/skywizard/FreeBSD/sound/snd_RELENG_5_20050825_035.diff Well I added PREEMPTION to the kernel yesterday as well as the first patch by Jeff Robertson. Immediately upon kernelinstall and reboot I tried untarring Firefox and Thunderbird, as well as tarring them both back up. Not a single skip, stutter, or freezing of the mouse/display! I did more testing last night like listening to audio with downloads open and encoding video, and I didn't hear one skip at all. The only time I heard a little static was when I was burning a DVD and listening to audio at the same time, but I can understand that. Thanks to everyone who replied, this seems to be fixed for now. :) -Mark ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
Mark Kane wrote: Ariff Abdullah wrote: These are my suggestions: 1) enable 'options PREEMPTION'. This is a MUST. 2) use SCHED_ULE instead of SCHED_4BSD. ULE is pretty stable on me, but I can't guarantee (especially combining with PREEMPTION). It doesn't hurt to give it a try. 3) Apply these patches: http://staff.mybsd.org.my/skywizard/FreeBSD/sound/jroberson_flushbuf_RELENG_5.diff http://staff.mybsd.org.my/skywizard/FreeBSD/sound/snd_RELENG_5_20050825_035.diff Well I added PREEMPTION to the kernel yesterday as well as the first patch by Jeff Robertson. Immediately upon kernelinstall and reboot I tried untarring Firefox and Thunderbird, as well as tarring them both back up. Not a single skip, stutter, or freezing of the mouse/display! I did more testing last night like listening to audio with downloads open and encoding video, and I didn't hear one skip at all. The only time I heard a little static was when I was burning a DVD and listening to audio at the same time, but I can understand that. Thanks to everyone who replied, this seems to be fixed for now. :) -Mark I do notice that when doing some things like using unrar to extract a file or loading a video into video encoding software I do get some of the same little crackles and static in the audio. I didn't notice this static/crackling ever before applying that first patch. I am still skip/stutter free though :). Might the second patch help the crackling/static? Thanks -Mark ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
On Sat, 27 Aug 2005 13:38:00 -0500 Mark Kane [EMAIL PROTECTED] wrote: Mark Kane wrote: Ariff Abdullah wrote: These are my suggestions: 1) enable 'options PREEMPTION'. This is a MUST. 2) use SCHED_ULE instead of SCHED_4BSD. ULE is pretty stable on me, but I can't guarantee (especially combining with PREEMPTION). It doesn't hurt to give it a try. 3) Apply these patches: http://staff.mybsd.org.my/skywizard/FreeBSD/sound/jroberson_flushb uf_RELENG_5.diff http://staff.mybsd.org.my/skywizard/FreeBSD/sound/snd_RELENG_5_200 50825_035.diff Well I added PREEMPTION to the kernel yesterday as well as the first patch by Jeff Robertson. Immediately upon kernelinstall and reboot I tried untarring Firefox and Thunderbird, as well as tarring them both back up. Not a single skip, stutter, or freezing of the mouse/display! I did more testing last night like listening to audio with downloads open and encoding video, and I didn't hear one skip at all. The only time I heard a little static was when I was burning a DVD and listening to audio at the same time, but I can understand that. Thanks to everyone who replied, this seems to be fixed for now. :) -Mark I do notice that when doing some things like using unrar to extract a file or loading a video into video encoding software I do get some of the same little crackles and static in the audio. I didn't notice this static/crackling ever before applying that first patch. I am still skip/stutter free though :). Might the second patch help the crackling/static? Perhaps. You should give it a try. There is another issue as well (such as PCI latency timer), but only after you applied all those suggested patches. -- Ariff Abdullah MyBSD http://www.MyBSD.org.my (IPv6/IPv4) http://staff.MyBSD.org.my (IPv6/IPv4) http://tomoyo.MyBSD.org.my (IPv6/IPv4) ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
On 26/08/05, Mark Kane [EMAIL PROTECTED] wrote: Roland Smith wrote: On Thu, Aug 25, 2005 at 04:44:59PM -0500, Mark Kane wrote: Okay, I may try that later then. STABLE is just about done on that Athlon XP 2000+ machine. Fingers crossed :-) Well Hmmm I've got -STABLE running on the 5.4-RELEASE i386 AMD Athlon XP 2000+ machine with 256MB RAM. I untar Firefox sources, and the improvement is noticeable within 3 seconds. When doing the same operation before or here on my amd64 (5.4-RELEASE) it starts freezing the screen, sound, and other things (Hard to describe the sound noise, but it sounds like a ERRR-R-R-R-R- stutter). I increased the XMMS buffer from 3000 to the value on your site (haven't done the sysctl one yet) and it made the skips that were happening during untarring reduce greatly. There are still a few skips and slight stuttering, but before when doing the same operation it was completely un-listenable and unresponsive. I'm even tarring the Firefox source back up with bzip2 now to try. It's going quite slowly, but that's probably due to low RAM, as well as an older, slower, UDMA66 hard drive. 608K of real mem free and using up 50MB of swap, it's still sounding pretty good with minimal skips. I'm listening to a stream from my Athlon XP 2000+ in my left ear (via a headphone) and the same stream on the speakers here from my amd64. I hear occasional skips in the audio from the amd64 5.4-RELEASE box as I'm just typing this email, but while the other -STABLE box is semi-idle (X, Xfce, Firefox with 40 tabs open) I don't hear many skips at all. It's not perfect, but a huge improvement. I'm wondering what changed in 5-STABLE to make this so much better. I thought the fix was in 6 (Unless it was MFC)? This much improvement almost makes me want to just upgrade this amd64 box to -STABLE and start using it now. I just want to be sure it's stable enough for my use. Thanks again for all the input :). -Mark ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED] Try these in kernel OPTIONS DIRECTIO OPTIONS NO_ADAPTIVE_MUTEXES and commenting optionsADAPTIVE_GIANT and disable apic. Tell me if that imporves or makes worse. Chris ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
Chris wrote: Try these in kernel OPTIONS DIRECTIO OPTIONS NO_ADAPTIVE_MUTEXES and commenting optionsADAPTIVE_GIANT and disable apic. Tell me if that imporves or makes worse. Well I did the kernel part, but wasn't sure how you wanted me to disable APIC. I looked in the BIOS but don't see any setting like APIC On/Off, but there is a few settings for a few IRQ's, and they are set to Auto. If I go to those options, it shows on one of the IRQ's the network controller and one of the ata controllers, but only gives me the option to change the IRQ for both of them. After doing the kernel and rebooting, I tried again. From what I can tell, there is no change. I untarred a large source file again while playing audio, and about the same result. The mouse also froze several times when the audio was stuttering too, however most of the time I just sat back and listened and watched it untar. I tried to make an audio clip of the stuttering, but for some reason in the clip it doesn't sound half as bad as it did when coming out. I am not sure why, since I took the exact output of the sound card, ran it through a mixer here, and then back in. It should sound equally bad if not worse, but here is a link to the 45 second clip: http://www.tntpowerhost.com/mixx941/samples/SoundCardExample1.ogg I took the last 45 seconds or so of the untar because when recording it, it sounded the worst. However it's not terrible in this clip...the last 10 seconds or so is right when it finished and is playing normal. -Mark ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
On Thu, Aug 25, 2005 at 12:48:17PM -0500, Mark Kane wrote: Roland Smith wrote: Another thing to look at might be the scheduler. I'm using SCHED_4BSD. Hmm, I'm using just a GENERIC kernel with support added in for my sound driver and atapicam for K3b. SCHED_4BSD looks default in GENERIC: options SCHED_4BSD # 4BSD scheduler I've been trying this morning with no real disk I/O and just XMMS open. It's much better than if I did have a download/upload going using disk I/O or trying to read from a file on the drive, but still nowhere near perfect. Every minute I'll still hear a little skip or stutter in the audio, and still notice the mouse locking up a bit at the exact moment that happens. Did you not read my mail? I explained this and the solution. Kris pgpd6WzMwyTBS.pgp Description: PGP signature
Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
Kris Kennaway wrote: On Thu, Aug 25, 2005 at 12:48:17PM -0500, Mark Kane wrote: Roland Smith wrote: Another thing to look at might be the scheduler. I'm using SCHED_4BSD. Hmm, I'm using just a GENERIC kernel with support added in for my sound driver and atapicam for K3b. SCHED_4BSD looks default in GENERIC: options SCHED_4BSD # 4BSD scheduler I've been trying this morning with no real disk I/O and just XMMS open. It's much better than if I did have a download/upload going using disk I/O or trying to read from a file on the drive, but still nowhere near perfect. Every minute I'll still hear a little skip or stutter in the audio, and still notice the mouse locking up a bit at the exact moment that happens. Did you not read my mail? I explained this and the solution. Kris Yes, I read your email and responded to it yesterday. I said: - I found the sound skipping thread by Jeff. Looks like a great explanation, however my problem even occurs even with light disk I/O such as reading an mp3/Ogg/video file off any of the drives. I did some more testing with actual files off the drives last night instead of streams, and it seems worse with actual files. I'm not sure if the proposed patch will fix it or not, and trying 6.0-BETA2 for my other hardware/hard drive problem just introduced new problems (panics, network stuff not recognized, etc). I do have a spare hard drive where I could put test anything though if you think trying -CURRENT or another BETA would be worthwhile. - So, in other words, even when there is NOT heavy disk I/O it still has problems, although they do get worse with more disk I/O. I don't know if you saw my previous replies, but trying 5.4-STABLE on my Athlon XP 2000+ instead of 5.4-RELEASE seemed to make it much better on that machine (however still not perfect). I was wondering if the code that fixed it in 6 was merged to 5-STABLE or if the patch was already committed to 5-STABLE? I haven't tried -STABLE on my amd64 yet though. -Mark ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
On Thu, Aug 25, 2005 at 06:36:04PM -0500, Mark Kane wrote: This much improvement almost makes me want to just upgrade this amd64 box to -STABLE and start using it now. I just want to be sure it's stable enough for my use. My amd64 workstation has been running -STABLE since 5.3 without problems. Roland -- R.F.Smith (http://www.xs4all.nl/~rsmith/) Please send e-mail as plain text. public key: http://www.xs4all.nl/~rsmith/pubkey.txt pgpp1YDRh3wDA.pgp Description: PGP signature
Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
On Fri, 26 Aug 2005 13:14:35 -0500 Mark Kane [EMAIL PROTECTED] wrote: Kris Kennaway wrote: On Thu, Aug 25, 2005 at 12:48:17PM -0500, Mark Kane wrote: Roland Smith wrote: Another thing to look at might be the scheduler. I'm using SCHED_4BSD. Hmm, I'm using just a GENERIC kernel with support added in for my sound driver and atapicam for K3b. SCHED_4BSD looks default in GENERIC: options SCHED_4BSD # 4BSD scheduler I've been trying this morning with no real disk I/O and just XMMS open. It's much better than if I did have a download/upload going using disk I/O or trying to read from a file on the drive, but still nowhere near perfect. Every minute I'll still hear a little skip or stutter in the audio, and still notice the mouse locking up a bit at the exact moment that happens. Did you not read my mail? I explained this and the solution. Kris Yes, I read your email and responded to it yesterday. I said: - I found the sound skipping thread by Jeff. Looks like a great explanation, however my problem even occurs even with light disk I/O such as reading an mp3/Ogg/video file off any of the drives. I did some more testing with actual files off the drives last night instead of streams, and it seems worse with actual files. I'm not sure if the proposed patch will fix it or not, and trying 6.0-BETA2 for my other hardware/hard drive problem just introduced new problems (panics, network stuff not recognized, etc). I do have a spare hard drive where I could put test anything though if you think trying -CURRENT or another BETA would be worthwhile. - So, in other words, even when there is NOT heavy disk I/O it still has problems, although they do get worse with more disk I/O. I don't know if you saw my previous replies, but trying 5.4-STABLE on my Athlon XP 2000+ instead of 5.4-RELEASE seemed to make it much better on that machine (however still not perfect). I was wondering if the code that fixed it in 6 was merged to 5-STABLE or if the patch was already committed to 5-STABLE? I haven't tried -STABLE on my amd64 yet though. [EMAIL PROTECTED] I've been following this thread, yet I still don't know what is your soundcard. To tell you the truth, much of these issues relies heavily on your spesific sound driver, whether it has been freed from Giant or not. At least: 1) What is your soundcard? 2) What type of scheduler you use? (I can see that is SCHED_4BSD) 3) Is PREEMPTION enabled? -- Ariff Abdullah MyBSD http://www.MyBSD.org.my (IPv6/IPv4) http://staff.MyBSD.org.my (IPv6/IPv4) http://tomoyo.MyBSD.org.my (IPv6/IPv4) ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
Ariff Abdullah wrote: I've been following this thread, yet I still don't know what is your soundcard. To tell you the truth, much of these issues relies heavily on your spesific sound driver, whether it has been freed from Giant or not. At least: Well the thing that makes me think it's not entirely related to sound is because when the sound problem happens, other things happen as well. As I have said, the mouse locks up and freezes at the precise time that the audio starts stuttering. If I was playing video, it would freeze/stutter at the same time too. 1) What is your soundcard? Sound Blaster Augidy 2 Platinum with the emu10k1 driver compiled into the kernel. 2) What type of scheduler you use? (I can see that is SCHED_4BSD) Right, SCHED_4BSD in the GENERIC kernel. 3) Is PREEMPTION enabled? No, not that I know of. I don't see it in GENERIC, and I haven't added it. Thanks -Mark ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
On Fri, Aug 26, 2005 at 01:14:35PM -0500, Mark Kane wrote: Kris Kennaway wrote: On Thu, Aug 25, 2005 at 12:48:17PM -0500, Mark Kane wrote: Roland Smith wrote: Another thing to look at might be the scheduler. I'm using SCHED_4BSD. Hmm, I'm using just a GENERIC kernel with support added in for my sound driver and atapicam for K3b. SCHED_4BSD looks default in GENERIC: options SCHED_4BSD # 4BSD scheduler I've been trying this morning with no real disk I/O and just XMMS open. It's much better than if I did have a download/upload going using disk I/O or trying to read from a file on the drive, but still nowhere near perfect. Every minute I'll still hear a little skip or stutter in the audio, and still notice the mouse locking up a bit at the exact moment that happens. Did you not read my mail? I explained this and the solution. Kris Yes, I read your email and responded to it yesterday. I said: - I found the sound skipping thread by Jeff. Looks like a great explanation, however my problem even occurs even with light disk I/O such as reading an mp3/Ogg/video file off any of the drives. I did some more testing with actual files off the drives last night instead of streams, and it seems worse with actual files. I'm not sure if the proposed patch will fix it or not, and trying 6.0-BETA2 for my other hardware/hard drive problem just introduced new problems (panics, network stuff not recognized, etc). I do have a spare hard drive where I could put test anything though if you think trying -CURRENT or another BETA would be worthwhile. - So, in other words, even when there is NOT heavy disk I/O it still has problems, although they do get worse with more disk I/O. I don't know if you saw my previous replies, but trying 5.4-STABLE on my Athlon XP 2000+ instead of 5.4-RELEASE seemed to make it much better on that machine (however still not perfect). I was wondering if the code that fixed it in 6 was merged to 5-STABLE or if the patch was already committed to 5-STABLE? I haven't tried -STABLE on my amd64 yet though. The patch is in 6.0 only and has not yet been merged to 5.x. Kris pgpYw2d5361zw.pgp Description: PGP signature
Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
On Wed, Aug 24, 2005 at 10:16:51PM -0500, Mark Kane wrote: Hi everyone. Last night I finally worked out some issues with my AMD64 machine and got it up and operational. It's an AMD64 3000+ with 1.5GB RAM, and five 7200RPM hard drives (total of 720 gigs) running FreeBSD 5.4-RELEASE (amd64). When doing testing and initial install/configuration of this machine (compiling apps and such) I didn't notice this too much, but now that I'm actually using it this is starting to be noticeable. The issue I'm having is that every minute or two, I will hear some stuttering in any audio/video playback (will see the video freeze if video), and my mouse will freeze for a few seconds as well while this happens. It seems to happen more frequently if I have something doing disk I/O, such as downloads running, untarring files, or torrents. Right now, I have the following applications open: This is a known bug in FreeBSD. It is fixed in 6.0, and there is a patch for 5.4 (search on -current from Jeff Roberson), which will be committed at some point. Kris pgpoqytndDLmi.pgp Description: PGP signature
Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
Daniel Marsh wrote: To get the CD device in dma try setting hw.ata.atapi_dma to 1 with sysctl (may need to go into loader) Only reason I didn't put the DVD burner in DMA is because a K3b howto guide recommended PIO mode. I no longer use K3b (but growisofs) so I guess I could try it but I'm not sure how that would affect this particular problem. In note of the problem of having multiple drives per channel, have you tried running one hard drive and seeing if you have any of the discussed problems? Have you tried disconnecting the raid totally (pulling out the promise raid) Well I started initially with one hard drive when I was rebuilding the system. It didn't seem to have any issues on it's own because it's when transferring data to one of the other drives on the same channel that the errors occurred. I also started without the Promise totally because at that point I didn't know what the problem was. I was downgrading the speeds on some of the drives via atacontrol to udma100 and it seemed to work then with two drives on the same channel, but after more testing it failed as well. Kris Kennaway wrote: This is a known bug in FreeBSD. It is fixed in 6.0, and there is a patch for 5.4 (search on -current from Jeff Roberson), which will be committed at some point. I found the sound skipping thread by Jeff. Looks like a great explanation, however my problem even occurs even with light disk I/O such as reading an mp3/Ogg/video file off any of the drives. I did some more testing with actual files off the drives last night instead of streams, and it seems worse with actual files. I'm not sure if the proposed patch will fix it or not, and trying 6.0-BETA2 for my other hardware/hard drive problem just introduced new problems (panics, network stuff not recognized, etc). I do have a spare hard drive where I could put test anything though if you think trying -CURRENT or another BETA would be worthwhile. Thanks. -Mark ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
On Wed, Aug 24, 2005 at 10:16:51PM -0500, Mark Kane wrote: The issue I'm having is that every minute or two, I will hear some stuttering in any audio/video playback (will see the video freeze if video), and my mouse will freeze for a few seconds as well while this happens. It seems to happen more frequently if I have something doing disk I/O, such as downloads running, untarring files, or torrents. Right now, I have the following applications open: My amd64 machine does not have this problem. I'm running 5.4-STABLE: FreeBSD slackbox.xs4all.nl 5.4-STABLE FreeBSD 5.4-STABLE #0: Wed Aug 10 20:25:45 CEST 2005 [EMAIL PROTECTED]:/usr/obj/usr/src/sys/RFS amd64 One thing I did do was enlarge the soundcard's DMA buffer in /boot/device.hints: # Larger DMA buffer for the soundcard, for better sound quality. hint.pcm.0.buffersize=16384 Roland -- R.F.Smith (http://www.xs4all.nl/~rsmith/) Please send e-mail as plain text. public key: http://www.xs4all.nl/~rsmith/pubkey.txt pgpCLIcV3uiQQ.pgp Description: PGP signature
Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
Roland Smith wrote: My amd64 machine does not have this problem. I'm running 5.4-STABLE: FreeBSD slackbox.xs4all.nl 5.4-STABLE FreeBSD 5.4-STABLE #0: Wed Aug 10 20:25:45 CEST 2005 [EMAIL PROTECTED]:/usr/obj/usr/src/sys/RFS amd64 One thing I did do was enlarge the soundcard's DMA buffer in /boot/device.hints: # Larger DMA buffer for the soundcard, for better sound quality. hint.pcm.0.buffersize=16384 Hey Roland. Yeah, back when I was looking into amd64 vs i386 version and had a thread going that you replied to, I checked out your website and saw your FreeBSD settings. :) I tried that device.hints setting on my backup Athlon XP 2000+ machine with just onboard sound and that seemed to make it worse. Maybe because it was crummy onboard. This machine runs an Audigy 2 Platinum. If it was just the sound doing this and not the mouse and display freezing as well as any video playing then I think it would be much easier to troubleshoot and pinpoint. I could try -STABLE on that spare hard drive though. Thanks. -Mark P.S. On an unrelated note, is there any changelog or anything for -STABLE to see what changes have been made? ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
On Thu, Aug 25, 2005 at 11:21:41AM -0500, Mark Kane wrote: /boot/device.hints: # Larger DMA buffer for the soundcard, for better sound quality. hint.pcm.0.buffersize=16384 Hey Roland. Yeah, back when I was looking into amd64 vs i386 version and had a thread going that you replied to, I checked out your website and saw your FreeBSD settings. :) I tried that device.hints setting on my backup Athlon XP 2000+ machine with just onboard sound and that seemed to make it worse. Maybe because it was crummy onboard. This machine runs an Audigy 2 Platinum. If it was just the sound doing this and not the mouse and display freezing as well as any video playing then I think it would be much easier to troubleshoot and pinpoint. I could try -STABLE on that spare hard drive though. Another thing to look at might be the scheduler. I'm using SCHED_4BSD. P.S. On an unrelated note, is there any changelog or anything for -STABLE to see what changes have been made? Hmm. /usr/src/UPDATING is one source of information. If you want to look at the change history of individual files, check out the CVS web interface: http://www.freebsd.org/cgi/cvsweb.cgi/ Roland -- R.F.Smith (http://www.xs4all.nl/~rsmith/) Please send e-mail as plain text. public key: http://www.xs4all.nl/~rsmith/pubkey.txt pgpePeGt1MOSb.pgp Description: PGP signature
Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
Roland Smith wrote: Another thing to look at might be the scheduler. I'm using SCHED_4BSD. Hmm, I'm using just a GENERIC kernel with support added in for my sound driver and atapicam for K3b. SCHED_4BSD looks default in GENERIC: options SCHED_4BSD # 4BSD scheduler I've been trying this morning with no real disk I/O and just XMMS open. It's much better than if I did have a download/upload going using disk I/O or trying to read from a file on the drive, but still nowhere near perfect. Every minute I'll still hear a little skip or stutter in the audio, and still notice the mouse locking up a bit at the exact moment that happens. So you have no similar problems in -STABLE? How about when untarring a bigger file and playing audio? If not, then maybe trying STABLE on that other drive might be a good idea. The reason I wanted to see any changelog was to see if there is any changes to this part of the code at all before trying it, but file by file I would probably be lost since I am not a programmer. Thanks. -Mark ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
On Thu, Aug 25, 2005 at 12:48:17PM -0500, Mark Kane wrote: Roland Smith wrote: Another thing to look at might be the scheduler. I'm using SCHED_4BSD. Hmm, I'm using just a GENERIC kernel with support added in for my sound driver and atapicam for K3b. SCHED_4BSD looks default in GENERIC: options SCHED_4BSD # 4BSD scheduler Yes it is. snip So you have no similar problems in -STABLE? How about when untarring a bigger file and playing audio? If not, then maybe trying STABLE on that other drive might be a good idea. Yesterday I was making a level 0 dump of my /usr partition (32429 MB) to another drive, which was being compressed with bzip2. CPU usage was around 97% [for bzip2], but I didn't notice anything. While the dump was underway, I was browsing with Firefox, and writing in emacs. The reason I wanted to see any changelog was to see if there is any changes to this part of the code at all before trying it, but file by file I would probably be lost since I am not a programmer. The file is the most usual way to partition code. How else would you know where to look? Some other thing you might look at is if too many devices are sharing an interrupt. Try ps -xa|grep '\[irq.*\]' If so, that might give problems, I think. Anything in the logfiles? Roland -- R.F.Smith (http://www.xs4all.nl/~rsmith/) Please send e-mail as plain text. public key: http://www.xs4all.nl/~rsmith/pubkey.txt pgpgzxp5JfUMo.pgp Description: PGP signature
Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
Roland Smith wrote: So you have no similar problems in -STABLE? How about when untarring a bigger file and playing audio? If not, then maybe trying STABLE on that other drive might be a good idea. Yesterday I was making a level 0 dump of my /usr partition (32429 MB) to another drive, which was being compressed with bzip2. CPU usage was around 97% [for bzip2], but I didn't notice anything. While the dump was underway, I was browsing with Firefox, and writing in emacs. Wow, that would be really nice. I notice whenever I compress something like a backup of my Thunderbird Inbox files (several hundred megs) in bzip2 format it goes nowhere near 100% or even 90% CPU usage. The problems I am talking about occur even when CPU usage is real low as well. :-\ The reason I wanted to see any changelog was to see if there is any changes to this part of the code at all before trying it, but file by file I would probably be lost since I am not a programmer. The file is the most usual way to partition code. How else would you know where to look? True. I meant I wouldn't know what files to look at since I don't know really anything about programming or how things are done internally. I'm kind of used to the subversion approach of revisions for everything instead of file by file. Then it would have one log showing all the changes of that revision all in one place. I see how the other way makes sense though. Some other thing you might look at is if too many devices are sharing an interrupt. Try ps -xa|grep '\[irq.*\]' If so, that might give problems, I think. Anything in the logfiles? [EMAIL PROTECTED]:~]% ps -xa|grep '\[irq.*\]' 12 ?? WL 0:05.59 [irq1: atkbd0] 13 ?? WL 0:00.00 [irq3: sio1] 14 ?? WL 0:00.00 [irq4: sio0] 15 ?? WL 0:00.00 [irq5:] 16 ?? WL 0:00.00 [irq6: fdc0] 17 ?? WL 0:00.00 [irq7: ppc0] 18 ?? WL 0:00.00 [irq8: rtc] 19 ?? WL 0:00.00 [irq9: acpi0] 20 ?? WL 0:00.00 [irq10:] 21 ?? WL 0:00.00 [irq11:] 22 ?? WL 1:03.19 [irq12: psm0] 23 ?? WL 0:00.00 [irq13:] 24 ?? WL 0:01.84 [irq14: ata0] 25 ?? WL 0:00.00 [irq15: ata1] 26 ?? WL 0:04.11 [irq16: atapci3] 27 ?? WL 1:13.49 [irq17: pcm0] 28 ?? WL 0:00.00 [irq18: fwohci0+] 29 ?? WL 1:35.00 [irq19: skc0 atapci2] 30 ?? WL 0:00.00 [irq20:] 31 ?? WL 0:00.00 [irq21: ohci1] 32 ?? WL 0:00.00 [irq22: ohci0+] 33 ?? WL 0:00.00 [irq23:] 34 ?? WL 0:00.00 [irq0: clk] I don't see anything in /var/log/messages or any errors in dmesg. -Mark ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
On Thu, Aug 25, 2005 at 01:39:25PM -0500, Mark Kane wrote: Wow, that would be really nice. I notice whenever I compress something like a backup of my Thunderbird Inbox files (several hundred megs) in bzip2 format it goes nowhere near 100% or even 90% CPU usage. The problems I am talking about occur even when CPU usage is real low as well. :-\ Hmm, if bzip2 can't saturate the CPU, I would say it's probably waiting for disk reads/writes. The file is the most usual way to partition code. How else would you know where to look? True. I meant I wouldn't know what files to look at since I don't know really anything about programming or how things are done internally. I'm kind of used to the subversion approach of revisions for everything instead of file by file. Then it would have one log showing all the changes of that revision all in one place. I see how the other way makes sense though. FreeBSD uses CVS, which can also produce such a logfile. But I think that you would have to install the complete CVS repository to generate such a changelog. Besides, if you are not a programmer, would the checkin comments really mean anything to you? snip 29 ?? WL 1:35.00 [irq19: skc0 atapci2] It looks like one of your disk controllers is sharing an interrupt with another device (network card? can't find a skc device, only sk). That might have something to do with your problem. Try disabling that device, and see if your troubles disappear. If so, you could try to add a device hint to have the skc device use another free interrupt line. See device.hints(5). Roland -- R.F.Smith (http://www.xs4all.nl/~rsmith/) Please send e-mail as plain text. public key: http://www.xs4all.nl/~rsmith/pubkey.txt pgpJBIlpSvtwe.pgp Description: PGP signature
Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
Roland Smith wrote: On Thu, Aug 25, 2005 at 01:39:25PM -0500, Mark Kane wrote: Wow, that would be really nice. I notice whenever I compress something like a backup of my Thunderbird Inbox files (several hundred megs) in bzip2 format it goes nowhere near 100% or even 90% CPU usage. The problems I am talking about occur even when CPU usage is real low as well. :-\ Hmm, if bzip2 can't saturate the CPU, I would say it's probably waiting for disk reads/writes. The drives I was trying to compress from/to are both brand new 200GB Maxtor 7200RPM ATA133 drives. Maybe that has something to do with the bad controller on this series of boards. snip 29 ?? WL 1:35.00 [irq19: skc0 atapci2] It looks like one of your disk controllers is sharing an interrupt with another device (network card? can't find a skc device, only sk). That might have something to do with your problem. Try disabling that device, and see if your troubles disappear. If so, you could try to add a device hint to have the skc device use another free interrupt line. See device.hints(5). Looks like it is the network card. Would disabling that in the BIOS mess anything up in FreeBSD? With it disabled I couldn't test the streaming, but could try playing files. [EMAIL PROTECTED]:~]% dmesg | grep sk skc0: Marvell Gigabit Ethernet port 0x9c00-0x9cff mem 0xfb008000-0xfb00bfff irq 19 at device 11.0 on pci2 skc0: Marvell Yukon Lite Gigabit Ethernet rev. A3(0x7) sk0: Marvell Semiconductor, Inc. Yukon on skc0 sk0: Ethernet address: 00:0f:ea:4f:83:8b I'm also compiling STABLE on that other 5.4-RELEASE i386 machine that had the same problems while I was using it for that month. I'm going to see if that helps that machine out any. Here is the IRQ output from that machine: 12 ?? WL 0:00.00 [irq1: atkbd0] 13 ?? WL 0:00.00 [irq3: sio1] 14 ?? WL 0:00.00 [irq4: sio0] 15 ?? WL 0:00.00 [irq5:] 16 ?? WL 0:00.00 [irq6: fdc0] 17 ?? WL 0:00.00 [irq7: ppc0] 18 ?? WL 0:00.00 [irq8: rtc] 19 ?? WL 0:00.00 [irq9: acpi0] 20 ?? WL 0:00.00 [irq10:] 21 ?? WL 0:00.00 [irq11:] 22 ?? WL 0:00.00 [irq12: psm0] 23 ?? WL 0:00.00 [irq13:] 24 ?? WL 0:01.94 [irq14: ata0] 25 ?? WL 0:00.00 [irq15: ata1] 26 ?? WL 0:00.00 [irq16:] 27 ?? WL 0:00.00 [irq17:] 28 ?? WL 0:19.72 [irq18: rl0] 29 ?? WL 0:00.00 [irq19:] 30 ?? WL 0:00.00 [irq20:] 31 ?? WL 0:00.00 [irq21: uhci0 uhci1+] 32 ?? WL 0:00.00 [irq22: pcm0] 33 ?? WL 0:00.00 [irq23:] 34 ?? WL 0:00.00 [irq0: clk] -Mark ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
On Thu, 25 Aug 2005, Mark Kane wrote: Hmm, if bzip2 can't saturate the CPU, I would say it's probably waiting for disk reads/writes. The drives I was trying to compress from/to are both brand new 200GB Maxtor 7200RPM ATA133 drives. Maybe that has something to do with the bad controller on this series of boards. Are both of these drives on the same channel? If so, remember that ATA cannot read/write to two drives on the same channel at the same time. ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
Laurence Sanford wrote: On Thu, 25 Aug 2005, Mark Kane wrote: Hmm, if bzip2 can't saturate the CPU, I would say it's probably waiting for disk reads/writes. The drives I was trying to compress from/to are both brand new 200GB Maxtor 7200RPM ATA133 drives. Maybe that has something to do with the bad controller on this series of boards. Are both of these drives on the same channel? If so, remember that ATA cannot read/write to two drives on the same channel at the same time. Nope, my board does not allow them to be on the same channel or I get UDMA ICRC READ and WRITE errors (had a thread going about that here as well). All drives are on their own channel. -Mark ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
On Thu, Aug 25, 2005 at 03:25:48PM -0500, Mark Kane wrote: Hmm, if bzip2 can't saturate the CPU, I would say it's probably waiting for disk reads/writes. The drives I was trying to compress from/to are both brand new 200GB Maxtor 7200RPM ATA133 drives. Maybe that has something to do with the bad controller on this series of boards. Have you checked (with 'atacontrol mode channel') that both drives are indeed using DMA? Looks like it is the network card. Would disabling that in the BIOS mess anything up in FreeBSD? With it disabled I couldn't test the streaming, but could try playing files. I don't really see how, other than having no network. :-) If you have a spare machine, you could even try the 6.0 beta release, and see if that solves the problem. Roland -- R.F.Smith (http://www.xs4all.nl/~rsmith/) Please send e-mail as plain text. public key: http://www.xs4all.nl/~rsmith/pubkey.txt pgpcft3kbNbby.pgp Description: PGP signature
Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
Roland Smith wrote: Have you checked (with 'atacontrol mode channel') that both drives are indeed using DMA? amd64# atacontrol mode 0 Master = UDMA133 [200GB w/ FreeBSD] Slave = BIOSPIO amd64# atacontrol mode 1 Master = BIOSPIO Slave = PIO4 [Sony DRU500A DVD+RW] amd64# atacontrol mode 4 Master = UDMA133 [200GB Storage] Slave = BIOSPIO amd64# atacontrol mode 5 Master = UDMA133 [160GB Storage] Slave = BIOSPIO amd64# atacontrol mode 6 Master = UDMA133 [80GB Storage] Slave = BIOSPIO amd64# atacontrol mode 7 Master = UDMA133 [80GB Storage] Slave = BIOSPIO Looks like it is the network card. Would disabling that in the BIOS mess anything up in FreeBSD? With it disabled I couldn't test the streaming, but could try playing files. I don't really see how, other than having no network. :-) If you have a spare machine, you could even try the 6.0 beta release, and see if that solves the problem. Okay, I may try that later then. STABLE is just about done on that Athlon XP 2000+ machine. As for 6.0, I did try it on another drive when I was still troubleshooting the DMA stuff. It however introduced new problems such as panics and my ethernet controller was no longer recognized. -Mark ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
Roland Smith wrote: On Thu, Aug 25, 2005 at 04:44:59PM -0500, Mark Kane wrote: Okay, I may try that later then. STABLE is just about done on that Athlon XP 2000+ machine. Fingers crossed :-) Well Hmmm I've got -STABLE running on the 5.4-RELEASE i386 AMD Athlon XP 2000+ machine with 256MB RAM. I untar Firefox sources, and the improvement is noticeable within 3 seconds. When doing the same operation before or here on my amd64 (5.4-RELEASE) it starts freezing the screen, sound, and other things (Hard to describe the sound noise, but it sounds like a ERRR-R-R-R-R- stutter). I increased the XMMS buffer from 3000 to the value on your site (haven't done the sysctl one yet) and it made the skips that were happening during untarring reduce greatly. There are still a few skips and slight stuttering, but before when doing the same operation it was completely un-listenable and unresponsive. I'm even tarring the Firefox source back up with bzip2 now to try. It's going quite slowly, but that's probably due to low RAM, as well as an older, slower, UDMA66 hard drive. 608K of real mem free and using up 50MB of swap, it's still sounding pretty good with minimal skips. I'm listening to a stream from my Athlon XP 2000+ in my left ear (via a headphone) and the same stream on the speakers here from my amd64. I hear occasional skips in the audio from the amd64 5.4-RELEASE box as I'm just typing this email, but while the other -STABLE box is semi-idle (X, Xfce, Firefox with 40 tabs open) I don't hear many skips at all. It's not perfect, but a huge improvement. I'm wondering what changed in 5-STABLE to make this so much better. I thought the fix was in 6 (Unless it was MFC)? This much improvement almost makes me want to just upgrade this amd64 box to -STABLE and start using it now. I just want to be sure it's stable enough for my use. Thanks again for all the input :). -Mark ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
Hi everyone. Last night I finally worked out some issues with my AMD64 machine and got it up and operational. It's an AMD64 3000+ with 1.5GB RAM, and five 7200RPM hard drives (total of 720 gigs) running FreeBSD 5.4-RELEASE (amd64). When doing testing and initial install/configuration of this machine (compiling apps and such) I didn't notice this too much, but now that I'm actually using it this is starting to be noticeable. The issue I'm having is that every minute or two, I will hear some stuttering in any audio/video playback (will see the video freeze if video), and my mouse will freeze for a few seconds as well while this happens. It seems to happen more frequently if I have something doing disk I/O, such as downloads running, untarring files, or torrents. Right now, I have the following applications open: Xorg Xfce X-Chat Mozilla Firefox (Only about 10 tabs, as opposed to my normal 40-50 tabs) Terminal XMMS Mozilla Thunderbird rtorrent I initially noticed it on this machine when untarring a 20MB tar.bz2 file, and I figured with it untarring that a little audio stuttering would be expected. Then today, I started noticing it when doing normal things. All I'm doing now is just light browsing with XMMS and X-Chat open, and maybe one download going. While my AMD64 was out of commission, I was using an Athlon XP 2000+ with 1GB of RAM and an old slower hard drive. It ran FreeBSD 5.4-RELEASE as well. I noticed the same stutters in audio/video playback and freezing of the mouse there, although it was much more frequent. Here is a top output from just now: last pid: 59025; load averages: 0.07, 0.08, 0.12 59 processes: 1 running, 58 sleeping CPU states: 4.3% user, 0.0% nice, 2.3% system, 1.6% interrupt, 91.8% idle Mem: 841M Active, 245M Inact, 194M Wired, 72M Cache, 162M Buf, 2300K Free Swap: 3045M Total, 96K Used, 3045M Free So basically I'm wondering if there are any OS optimizations or anything I am missing to reduce this? I'm not sure why on this type of hardware with not even using half of what I normally would have open (at least Firefox tabs wise) it would cause so many hiccups like this. Thanks in advance for any opinions or suggestions. -Mark ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
On Wed, 24 Aug 2005, Mark Kane wrote: Hi everyone. Last night I finally worked out some issues with my AMD64 machine and got it up and operational. It's an AMD64 3000+ with 1.5GB RAM, and five 7200RPM hard drives (total of 720 gigs) running FreeBSD 5.4-RELEASE (amd64). When doing testing and initial install/configuration of this machine (compiling apps and such) I didn't notice this too much, but now that I'm actually using it this is starting to be noticeable. The issue I'm having is that every minute or two, I will hear some stuttering in any audio/video playback (will see the video freeze if video), and my mouse will freeze for a few seconds as well while this happens. It seems to happen more frequently if I have something doing disk I/O, such as downloads running, untarring files, or torrents. Right now, I have the following applications open: Xorg Xfce X-Chat Mozilla Firefox (Only about 10 tabs, as opposed to my normal 40-50 tabs) Terminal XMMS Mozilla Thunderbird rtorrent I initially noticed it on this machine when untarring a 20MB tar.bz2 file, and I figured with it untarring that a little audio stuttering would be expected. Then today, I started noticing it when doing normal things. All I'm doing now is just light browsing with XMMS and X-Chat open, and maybe one download going. While my AMD64 was out of commission, I was using an Athlon XP 2000+ with 1GB of RAM and an old slower hard drive. It ran FreeBSD 5.4-RELEASE as well. I noticed the same stutters in audio/video playback and freezing of the mouse there, although it was much more frequent. Here is a top output from just now: last pid: 59025; load averages: 0.07, 0.08, 0.12 59 processes: 1 running, 58 sleeping CPU states: 4.3% user, 0.0% nice, 2.3% system, 1.6% interrupt, 91.8% idle Mem: 841M Active, 245M Inact, 194M Wired, 72M Cache, 162M Buf, 2300K Free Swap: 3045M Total, 96K Used, 3045M Free So basically I'm wondering if there are any OS optimizations or anything I am missing to reduce this? I'm not sure why on this type of hardware with not even using half of what I normally would have open (at least Firefox tabs wise) it would cause so many hiccups like this. Thanks in advance for any opinions or suggestions. -Mark Mark, I to am having similar problems with SATA drives, to the point where the audio coming from XMMS sounds just TRIPPING! One thing that helped me was to INSURE that the dma for the hw.ata.atapi_dma and hw.ata.ata_dma where both set to 1. Also, staying STABLE for me has been advantageous. T. ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
TRODAT wrote: Mark, I to am having similar problems with SATA drives, to the point where the audio coming from XMMS sounds just TRIPPING! Well while all my drives are PATA, I should mention that I'm not even trying to play mp3s/Ogg files from any of my five drives most of the time. I run a group of Internet radio stations so most times I am listening to them. It's not the server skipping, it's for sure some kind of few second freeze of the mouse/display and the sound stutters at the same time. It's also not just audio in XMMS. I could be watching a video clip in VLC or mplayer and have some of the same results. The picture would freeze for a moment and the audio would stutter for a few seconds, then resume normal playback...and that's even with NOTHING else running but X, Xfce, and VLC. I can manually make it worse. As I said before, if I untar an archive like Mozilla or something it gets almost unlistenable and the mouse is constantly freezing as I move it around. One thing that helped me was to INSURE that the dma for the hw.ata.atapi_dma and hw.ata.ata_dma where both set to 1. DMA is for sure enabled on all the hard drives, but the optical drive remains in PIO mode. I haven't attempted to play anything from that yet, however. Also, staying STABLE for me has been advantageous. I have not tried STABLE yet, but if it would help this and wouldn't introduce any new problems I would be happy to give it a try. -Mark ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Performance Issues with AMD64 3000+, 1.5GB RAM, FreeBSD 5.4-RELEASE
Daniel Marsh wrote: Could you post your dmesg to the list? I have had a similar problem with SATA hard drives on an Intel PNSLK 945 chipset motherboard with a Pentium D 3ghz. The SATA drives simply would not recognize as DMA, only PIO, in the BIOS there was a setting for ATA/IDE Mode, the options were Enhanced or Legacy (defaulted to Enhanced), once set to Legacy all disk drives are now working in UDMA 5 mode. Even though you have stated your drives are PATA, it could be a related issue. Did you check the sysctl variables listed above, what are their values? You say you have 5 disk drives, have you got an add-on IDE card for the extra hard drives (most mobo's I've seen only have one IDE port and 4 SATA ports these days) or does the mobo have onboard RAID controllers which you aren't using for RAID (could lead to driver incompatibilites for those controllers)? Thank you Daniel Thanks for the response, dmesg is included below. Before getting this system up and running, I had two weeks of hell getting DMA to properly work with this series of motherboards. They have some controller issues or something, because more than one drive cannot reside on the same cable or there are UDMA ICRC READ and WRITE errors. I know it's not this particular board because this is the second brand new board of the same model (Giga-Byte K8NS Pro) I've had with similar DMA problems. I had a thread going here about that also. The end solution to that was to have each drive on it's own dedicated channel, and I have a Promise ATA card in here in addition to the motherboard's 4 channels (2 IDE + 2 RAID which function as IDE). I don't think it is due to this particular problem with the controllers though since I used that other 5.4 machine for a month and a half and it did the exact same things. hw.ata.atapi_dma: 0 hw.ata.ata_dma: 1 - FreeBSD 5.4-RELEASE #1: Fri Aug 19 10:07:40 CDT 2005 [EMAIL PROTECTED]:/usr/obj/usr/src/sys/AMD643000 ACPI APIC Table: Nvidia AWRDACPI Timecounter i8254 frequency 1193182 Hz quality 0 CPU: AMD Athlon(tm) 64 Processor 3000+ (2009.79-MHz K8-class CPU) Origin = AuthenticAMD Id = 0xfc0 Stepping = 0 Features=0x78bfbffFPU,VME,DE,PSE,TSC,MSR,PAE,MCE,CX8,APIC,SEP,MTRR,PGE,MCA,CMOV,PAT,PSE36,CLFLUSH,MMX,FXSR,SSE,SSE2 AMD Features=0xe0500800SYSCALL,NX,MMX+,LM,3DNow+,3DNow real memory = 1610547200 (1535 MB) avail memory = 1542995968 (1471 MB) ioapic0 Version 1.1 irqs 0-23 on motherboard acpi0: Nvidia AWRDACPI on motherboard acpi0: Power Button (fixed) Timecounter ACPI-fast frequency 3579545 Hz quality 1000 acpi_timer0: 24-bit timer at 3.579545MHz port 0x1008-0x100b on acpi0 cpu0: ACPI CPU on acpi0 acpi_button0: Power Button on acpi0 pcib0: ACPI Host-PCI bridge port 0xcf0-0xcf3,0xcf8-0xcff on acpi0 pci0: ACPI PCI bus on pcib0 isab0: PCI-ISA bridge at device 1.0 on pci0 isa0: ISA bus on isab0 pci0: serial bus, SMBus at device 1.1 (no driver attached) ohci0: OHCI (generic) USB controller mem 0xfc002000-0xfc002fff irq 22 at device 2.0 on pci0 usb0: OHCI version 1.0, legacy support usb0: OHCI (generic) USB controller on ohci0 usb0: USB revision 1.0 uhub0: nVidia OHCI root hub, class 9/0, rev 1.00/1.00, addr 1 uhub0: 4 ports with 4 removable, self powered ohci1: OHCI (generic) USB controller mem 0xfc003000-0xfc003fff irq 21 at device 2.1 on pci0 usb1: OHCI version 1.0, legacy support usb1: OHCI (generic) USB controller on ohci1 usb1: USB revision 1.0 uhub1: nVidia OHCI root hub, class 9/0, rev 1.00/1.00, addr 1 uhub1: 4 ports with 4 removable, self powered pci0: serial bus, USB at device 2.2 (no driver attached) atapci0: nVidia nForce3 Pro UDMA133 controller port 0xf000-0xf00f,0x376,0x170-0x177,0x3f6,0x1f0-0x1f7 at device 8.0 on pci0 ata0: channel #0 on atapci0 ata1: channel #1 on atapci0 atapci1: GENERIC ATA controller port 0xe400-0xe40f,0xb70-0xb73,0x970-0x977,0xbf0-0xbf3,0x9f0-0x9f7 irq 22 at device 10.0 on pci0 ata2: channel #0 on atapci1 ata3: channel #1 on atapci1 pcib1: ACPI PCI-PCI bridge at device 11.0 on pci0 pci1: ACPI PCI bus on pcib1 pci1: display, VGA at device 0.0 (no driver attached) pcib2: ACPI PCI-PCI bridge at device 14.0 on pci0 pci2: ACPI PCI bus on pcib2 atapci2: Promise PDC20269 UDMA133 controller port 0x9000-0x900f,0x8c00-0x8c03,0x8800-0x8807,0x8400-0x8403,0x8000-0x8007 mem 0xfb00-0xfb003fff irq 19 at device 7.0 on pci2 ata4: channel #0 on atapci2 ata5: channel #1 on atapci2 pcm0: Creative Audigy 2 (EMU10K2) port 0x9400-0x943f irq 17 at device 9.0 on pci2 pcm0: SigmaTel STAC9721/23 AC97 Codec fwohci0: 1394 Open Host Controller Interface mem 0xfb004000-0xfb007fff,0xfb011000-0xfb0117ff irq 18 at device 9.2 on pci2 fwohci0: OHCI version 1.10 (ROM=0) fwohci0: No. of Isochronous channels is 4. fwohci0: EUI64 00:02:3c:00:91:01:6c:20 fwohci0: Phy 1394a available S400, 2 ports. fwohci0: Link S400, max_rec 2048 bytes. firewire0: IEEE1394(FireWire) bus on fwohci0 fwe0: Ethernet over