Re: [Asterisk-Users] Interrupt latency problems
On Wednesday 01 December 2004 20:31, Steven Critchfield wrote: I am glad it solved the problem. Now if only someone knew what it was about the stock RH or FC kernel that makes it happen you could get RH or FC to stop using that patch. That or maybe more people will be like me and always cast a weary eye upon a prepackaged kernel no matter what distro it came from. First thing when installing any distro is to bin the kernel and install a vanilla one - how else can you be sure of the state of possibly the most important part of your system. Jon ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [Asterisk-Users] Interrupt latency problems
Title: OpSign Have any of you tried to disable ACPI on the kernel? Rich Adamson wrote: On Wed, 2004-12-01 at 13:03 -0700, Michael Welter wrote: Steven Critchfield wrote: On Wed, 2004-12-01 at 13:36 -0600, Rich Adamson wrote: So, isn't the issue he/I are chasing after essentially 'why is cpu consumption jumping 30% (or 100%) every ten seconds when zaptel is running with no calls present? So where is that CPU time going? Is it in the system, or userspace? Have you tried changing to a non FC or RH kernel as suggested earlier? Yes, I've just completed the installation of 2.6.9, and the spikes have gone away. Thank you, Steven. Your welcome. I am glad it solved the problem. Now if only someone knew what it was about the stock RH or FC kernel that makes it happen you could get RH or FC to stop using that patch. That or maybe more people will be like me and always cast a weary eye upon a prepackaged kernel no matter what distro it came from. Looking at the Changlog for 2.6.9, it would appear a fair amount of work has been down in the pci stuff and the interrupt support areas. Since that seems to be an issue that keeps rearing its head with the digium analog cards, maybe there is something 'fixed' in that area. Not being a strong linux admin, how difficult would you say installing 2.6.9 is on top of a RHv9 system (2.4.20-31.9) should be for me? Any suggestions/hints on how to do it would be appreciated. Rich ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users -- __ AlessandroRen OpServices LucianadeAbreu,471-Sala403 PortoAlegre,RS-CEP90570-060 (phone55(51)3061-3588 4fax55(51)3061-3588 Qmobile55(51)9807-3255 :email[EMAIL PROTECTED] __ ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [Asterisk-Users] Interrupt latency problems
Alessandro Ren wrote: Have any of you tried to disable ACPI on the kernel? I turn-off the ACPI service, but I haven't removed it from the kernel. Is there a problem with ACPI holding an interrupt? Thanks, -- Michael Welter Introspect Telephony Corp. Denver, Colorado US +1.303.674.2575 [EMAIL PROTECTED] www.introspect.com ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [Asterisk-Users] Interrupt latency problems
Rich Adamson wrote: Is their an open Bug # that we can track against for those of us that watch the -cvs list and have a vested interest? I tried, see Bug 2901. Seems probable driver issues don't count as bugs. Reported it to support, who were aware of the issue, requested login to my machine and the last I heard from them as of last week was: We currently have all the data to begin fixing the problem at the software level we should have a patch for the zaptel driver soon. Thank you for all your help. Regards, Richard ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [Asterisk-Users] Interrupt latency problems
The problem of CPU spikes went away on the x86_64 machine with kernel-2.6.9. I have just installed 2.6.9 on an Athlon (K7) box and I'm getting CPU spikes again, this time every three seconds. :-( Unloading wcfxs causes CPU to stay at 0%. Mike Richard Scobie wrote: Rich Adamson wrote: Is their an open Bug # that we can track against for those of us that watch the -cvs list and have a vested interest? I tried, see Bug 2901. Seems probable driver issues don't count as bugs. Reported it to support, who were aware of the issue, requested login to my machine and the last I heard from them as of last week was: We currently have all the data to begin fixing the problem at the software level we should have a patch for the zaptel driver soon. Thank you for all your help. -- Michael Welter Introspect Telephony Corp. Denver, Colorado US +1.303.674.2575 [EMAIL PROTECTED] www.introspect.com ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [Asterisk-Users] Interrupt latency problems
So, isn't the issue he/I are chasing after essentially 'why is cpu consumption jumping 30% (or 100%) every ten seconds when zaptel is running with no calls present? So where is that CPU time going? Is it in the system, or userspace? Have you tried changing to a non FC or RH kernel as suggested earlier? Yes, I've just completed the installation of 2.6.9, and the spikes have gone away. Thank you, Steven. Your welcome. I am glad it solved the problem. Now if only someone knew what it was about the stock RH or FC kernel that makes it happen you could get RH or FC to stop using that patch. That or maybe more people will be like me and always cast a weary eye upon a prepackaged kernel no matter what distro it came from. See http://lists.digium.com/pipermail/asterisk-dev/2004-November/007329.html This has been brought to Digiums attention and they are currently working on it. Is their an open Bug # that we can track against for those of us that watch the -cvs list and have a vested interest? ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [Asterisk-Users] Interrupt latency problems
On December 1, 2004 02:48 pm, Juan J. Sierralta P. wrote: Maybe vmstat(8) could be of help instead of the so flamed top(1). vmstat only polls every 1 second, *but* it does give interrupt counts and context switches per period. -A. ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [Asterisk-Users] Interrupt latency problems
On Thursday 02 December 2004 16:25, Andrew Kohlsmith wrote: On December 1, 2004 02:48 pm, Juan J. Sierralta P. wrote: Maybe vmstat(8) could be of help instead of the so flamed top(1). vmstat only polls every 1 second, *but* it does give interrupt counts and context switches per period. You can give an interval time and count to vmstat. B ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [Asterisk-Users] Interrupt latency problems
On December 2, 2004 12:35 pm, Bob Goddard wrote: vmstat only polls every 1 second, *but* it does give interrupt counts and context switches per period. You can give an interval time and count to vmstat. from vmstat(8): delay is the delay between updates in seconds. Your granularity is still no better than 1s. :-) -A. ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [Asterisk-Users] Interrupt latency problems
On Thursday 02 December 2004 18:30, Andrew Kohlsmith wrote: On December 2, 2004 12:35 pm, Bob Goddard wrote: vmstat only polls every 1 second, *but* it does give interrupt counts and context switches per period. You can give an interval time and count to vmstat. from vmstat(8): delay is the delay between updates in seconds. Your granularity is still no better than 1s. :-) The smaller the granularity the more skewed the results. 10s may be better. Either way, it is not limited to 1s. B ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
[Asterisk-Users] Interrupt latency problems
I'm debugging a TxFax problem whereby the fax transmission fails. I suspect interrupt latency--some interrupt routine is holding its interrupt too long. I have all unnecessary services switched off and X is not running when I perform these tests. Some transmission are successful while others fail at random points. I've noticed that after I boot Linux, load zaptel, wcfxo, and wcfxs, and then run System Monitor, the CPU utilization spikes to 60% every 10 seconds. After I remove wcfxs the spikes stop, and system utilization stays at 0%. I have two TDM22B cards and get these spikes with either card in the system. This is an Athlon-64 3000+ CPU and Fedora Core 2. zaptel-1.0.2. Is there anyone who has a TDM card on a quiet system who can run System Monitor and observe CPU utilization? Thanks for your help. P.S. I do 'hdparm -u1 /dev/hdx' on the disks. -- Michael Welter Introspect Telephony Corp. Denver, Colorado US +1.303.674.2575 [EMAIL PROTECTED] www.introspect.com ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [Asterisk-Users] Interrupt latency problems
I'm debugging a TxFax problem whereby the fax transmission fails. I suspect interrupt latency--some interrupt routine is holding its interrupt too long. I have all unnecessary services switched off and X is not running when I perform these tests. Some transmission are successful while others fail at random points. I've noticed that after I boot Linux, load zaptel, wcfxo, and wcfxs, and then run System Monitor, the CPU utilization spikes to 60% every 10 seconds. After I remove wcfxs the spikes stop, and system utilization stays at 0%. I have two TDM22B cards and get these spikes with either card in the system. This is an Athlon-64 3000+ CPU and Fedora Core 2. zaptel-1.0.2. Is there anyone who has a TDM card on a quiet system who can run System Monitor and observe CPU utilization? FYI, I see the same thing on a RHv9 2.2ghz box with a single TDM04b and no calls being processed. Top indicates 30.6% every 10 seconds. Stopping * has no impact. Stopping zaptel makes that disappear. Starting zaptel only (no asterisk) brings it back to 30.6%. ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [Asterisk-Users] Interrupt latency problems
Michael Welter wrote: I'm debugging a TxFax problem whereby the fax transmission fails. I suspect interrupt latency--some interrupt routine is holding its interrupt too long. I have all unnecessary services switched off and X is not running when I perform these tests. Some transmission are successful while others fail at random points. I've noticed that after I boot Linux, load zaptel, wcfxo, and wcfxs, and then run System Monitor, the CPU utilization spikes to 60% every 10 seconds. After I remove wcfxs the spikes stop, and system utilization stays at 0%. I have two TDM22B cards and get these spikes with either card in the system. This is an Athlon-64 3000+ CPU and Fedora Core 2. zaptel-1.0.2. Is there anyone who has a TDM card on a quiet system who can run System Monitor and observe CPU utilization? Thanks for your help. P.S. I do 'hdparm -u1 /dev/hdx' on the disks. I have a athlon xp 1600 with a gig of memory a tdm40 with 2 fxs ports and a t100p t1 hooked to a audiocoded tp260 and see minimal cpu utilization when idle. run top and see what is using the cpu. -- They that give up essential liberty to obtain temporary safety, deserve neither liberty nor safety. (Ben Franklin) The course of history shows that as a government grows, liberty decreases. (Thomas Jefferson) ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [Asterisk-Users] Interrupt latency problems
Michael Welter wrote: I'm debugging a TxFax problem whereby the fax transmission fails. I suspect interrupt latency--some interrupt routine is holding its interrupt too long. I have all unnecessary services switched off and X is not running when I perform these tests. Some transmission are successful while others fail at random points. I've noticed that after I boot Linux, load zaptel, wcfxo, and wcfxs, and then run System Monitor, the CPU utilization spikes to 60% every 10 seconds. After I remove wcfxs the spikes stop, and system utilization stays at 0%. I have two TDM22B cards and get these spikes with either card in the system. This is an Athlon-64 3000+ CPU and Fedora Core 2. zaptel-1.0.2. Is there anyone who has a TDM card on a quiet system who can run System Monitor and observe CPU utilization? Thanks for your help. P.S. I do 'hdparm -u1 /dev/hdx' on the disks. Forget what I just posted - after watching top for a while about every 30 seconds I see irq% go to about 30%. Steve -- They that give up essential liberty to obtain temporary safety, deserve neither liberty nor safety. (Ben Franklin) The course of history shows that as a government grows, liberty decreases. (Thomas Jefferson) ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [Asterisk-Users] Interrupt latency problems
On Wed, 2004-12-01 at 13:12 -0500, Steve Clark wrote: Michael Welter wrote: I'm debugging a TxFax problem whereby the fax transmission fails. I suspect interrupt latency--some interrupt routine is holding its interrupt too long. I have all unnecessary services switched off and X is not running when I perform these tests. Some transmission are successful while others fail at random points. I've noticed that after I boot Linux, load zaptel, wcfxo, and wcfxs, and then run System Monitor, the CPU utilization spikes to 60% every 10 seconds. After I remove wcfxs the spikes stop, and system utilization stays at 0%. I have two TDM22B cards and get these spikes with either card in the system. This is an Athlon-64 3000+ CPU and Fedora Core 2. zaptel-1.0.2. Is there anyone who has a TDM card on a quiet system who can run System Monitor and observe CPU utilization? Thanks for your help. P.S. I do 'hdparm -u1 /dev/hdx' on the disks. I have a athlon xp 1600 with a gig of memory a tdm40 with 2 fxs ports and a t100p t1 hooked to a audiocoded tp260 and see minimal cpu utilization when idle. run top and see what is using the cpu. top will only report userspace problems, and to top it off, top only reports on snapshots of the system on as low as 1 second. With Zap hardware hitting the system 1000 times a second for service, you might happen to get an occasional hit time here top and the hardware hit pretty close to show extra load. top also has the problem of effecting the system it is watching. It is a lot like those pesky physics problems where what you use to measure changes the object your measuring. Basically all that is to say that top probably won't tell you what you want to know.About the only thing that would be of interest is if the percentage is viewed in the system or userspace portions. If in system, you will have to go debugging the kernel. Of course, it seems this is mostly being reported against RH and FC. I'll take a quick guess that it isn't bad users so it would leave you with bad kernels. My personal opinion is to not trust what the distros do to the kernels. Even in my beloved Debian I don't trust the default kernel. I suggest you download a stock vanila kernel from kernel.org and config it as minimally as possible for your hardware and try and see if it reproduces the problems you are seeing currently. -- Steven Critchfield [EMAIL PROTECTED] ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [Asterisk-Users] Interrupt latency problems
Steve Clark wrote: Forget what I just posted - after watching top for a while about every 30 seconds I see irq% go to about 30%. Steve What are your command line options? -- Michael Welter Introspect Telephony Corp. Denver, Colorado US +1.303.674.2575 [EMAIL PROTECTED] www.introspect.com ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [Asterisk-Users] Interrupt latency problems
I'm seeing a correlation between the fax transmission failure and the second hand on my watch. Failures occur at about :02, :12, :22, :32, :42, and :52. This is +/- the same time as the CPU spike. Can anyone from Digium help with this? Thanks, -- Michael Welter Introspect Telephony Corp. Denver, Colorado US +1.303.674.2575 [EMAIL PROTECTED] www.introspect.com ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [Asterisk-Users] Interrupt latency problems
Steven Critchfield wrote: top will only report userspace problems, and to top it off, top only reports on snapshots of the system on as low as 1 second. With Zap hardware hitting the system 1000 times a second for service, you might happen to get an occasional hit time here top and the hardware hit pretty close to show extra load. top also has the problem of effecting the system it is watching. It is a lot like those pesky physics problems where what you use to measure changes the object your measuring. Basically all that is to say that top probably won't tell you what you want to know.About the only thing that would be of interest is if the percentage is viewed in the system or userspace portions. If in system, you will have to go debugging the kernel. Of course, it seems this is mostly being reported against RH and FC. I'll take a quick guess that it isn't bad users so it would leave you with bad kernels. My personal opinion is to not trust what the distros do to the kernels. Even in my beloved Debian I don't trust the default kernel. I suggest you download a stock vanila kernel from kernel.org and config it as minimally as possible for your hardware and try and see if it reproduces the problems you are seeing currently. In line #3 (CPU) of top, I'm seeing idle time go from 100% to +/-30% every 10 seconds. I'll download 2.6.9 today and give it a try. Thanks, -- Michael Welter Introspect Telephony Corp. Denver, Colorado US +1.303.674.2575 [EMAIL PROTECTED] www.introspect.com ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [Asterisk-Users] Interrupt latency problems
On Wed, 2004-12-01 at 11:46 -0700, Michael Welter wrote: Steven Critchfield wrote: top will only report userspace problems, and to top it off, top only reports on snapshots of the system on as low as 1 second. With Zap hardware hitting the system 1000 times a second for service, you might happen to get an occasional hit time here top and the hardware hit pretty close to show extra load. top also has the problem of effecting the system it is watching. It is a lot like those pesky physics problems where what you use to measure changes the object your measuring. Basically all that is to say that top probably won't tell you what you want to know.About the only thing that would be of interest is if the percentage is viewed in the system or userspace portions. If in system, you will have to go debugging the kernel. Of course, it seems this is mostly being reported against RH and FC. I'll take a quick guess that it isn't bad users so it would leave you with bad kernels. My personal opinion is to not trust what the distros do to the kernels. Even in my beloved Debian I don't trust the default kernel. I suggest you download a stock vanila kernel from kernel.org and config it as minimally as possible for your hardware and try and see if it reproduces the problems you are seeing currently. In line #3 (CPU) of top, I'm seeing idle time go from 100% to +/-30% every 10 seconds. So again, idle isn't helpfull. Where that time is being spent is the important part of the details. If it is in system, then it is IO calls or something else inside the kernel itself. If it is in user, then it is a userspace app that is getting hit every so often doing damage. To give a bit more explicit example, if you have a perl app that wakes up every 10 seconds or so from a sleep to do some directory managment, then you would see user percentage spike at that point. However if you had something dump a large chunk of data to the drives, the kernel would slurp that data in really quick and then churn on it a moment trying to get it down to the filesystem. This would show itself as a system time. If your drive was particularly slow, it very well may hang the interupts for a moment as it tries to do something. Old S3 video cards under windows used to be really bad about holding interupts too long. Used to be if you wiggled the mouse you could hear the effects in any music you happened to be playing. -- Steven Critchfield [EMAIL PROTECTED] ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [Asterisk-Users] Interrupt latency problems
I'm debugging a TxFax problem whereby the fax transmission fails. I suspect interrupt latency--some interrupt routine is holding its interrupt too long. I have all unnecessary services switched off and X is not running when I perform these tests. Some transmission are successful while others fail at random points. I've noticed that after I boot Linux, load zaptel, wcfxo, and wcfxs, and then run System Monitor, the CPU utilization spikes to 60% every 10 seconds. After I remove wcfxs the spikes stop, and system utilization stays at 0%. I have two TDM22B cards and get these spikes with either card in the system. This is an Athlon-64 3000+ CPU and Fedora Core 2. zaptel-1.0.2. Is there anyone who has a TDM card on a quiet system who can run System Monitor and observe CPU utilization? Thanks for your help. P.S. I do 'hdparm -u1 /dev/hdx' on the disks. I have a athlon xp 1600 with a gig of memory a tdm40 with 2 fxs ports and a t100p t1 hooked to a audiocoded tp260 and see minimal cpu utilization when idle. run top and see what is using the cpu. top will only report userspace problems, and to top it off, top only reports on snapshots of the system on as low as 1 second. With Zap hardware hitting the system 1000 times a second for service, you might happen to get an occasional hit time here top and the hardware hit pretty close to show extra load. top also has the problem of effecting the system it is watching. It is a lot like those pesky physics problems where what you use to measure changes the object your measuring. Basically all that is to say that top probably won't tell you what you want to know.About the only thing that would be of interest is if the percentage is viewed in the system or userspace portions. If in system, you will have to go debugging the kernel. Of course, it seems this is mostly being reported against RH and FC. I'll take a quick guess that it isn't bad users so it would leave you with bad kernels. My personal opinion is to not trust what the distros do to the kernels. Even in my beloved Debian I don't trust the default kernel. I suggest you download a stock vanila kernel from kernel.org and config it as minimally as possible for your hardware and try and see if it reproduces the problems you are seeing currently. Critch, Help me understand the above. When running top without any parameters, I see the 30% cpu jump. Killing asterisk, I see the same. Killing zaptel, the 30% goes away. Restarting zaptel, the 30% comes back. That would suggest that zaptel (and wctdm in my case) are impacting the 30% cpu consumption (and the fax stuff for the original poster). The 1,000 interrupts are going on constantly, so should not have any impact on top's longer term sampling. If I change top to 1 second samples, I then see 100% utilization every ten seconds. That only implies that top is averaging the numbers over the sampling interval (for cpu utilization). So, isn't the issue he/I are chasing after essentially 'why is cpu consumption jumping 30% (or 100%) every ten seconds when zaptel is running with no calls present? Rich ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [Asterisk-Users] Interrupt latency problems
Hi, Maybe vmstat(8) could be of help instead of the so flamed top(1). Steven Critchfield wrote: top will only report userspace problems, and to top it off, top only reports on snapshots of the system on as low as 1 second. With Zap hardware hitting the system 1000 times a second for service, you might happen to get an occasional hit time here top and the hardware hit pretty close to show extra load. top also has the problem of effecting the system it is watching. It is a lot like those pesky physics problems where what you use to measure changes the object your measuring. Basically all that is to say that top probably won't tell you what you want to know.About the only thing that would be of interest is if the percentage is viewed in the system or userspace portions. If in system, you will have to go debugging the kernel. Of course, it seems this is mostly being reported against RH and FC. I'll take a quick guess that it isn't bad users so it would leave you with bad kernels. My personal opinion is to not trust what the distros do to the kernels. Even in my beloved Debian I don't trust the default kernel. I suggest you download a stock vanila kernel from kernel.org and config it as minimally as possible for your hardware and try and see if it reproduces the problems you are seeing currently. In line #3 (CPU) of top, I'm seeing idle time go from 100% to +/-30% every 10 seconds. So again, idle isn't helpfull. Where that time is being spent is the important part of the details. If it is in system, then it is IO calls or something else inside the kernel itself. If it is in user, then it is a userspace app that is getting hit every so often doing damage. To give a bit more explicit example, if you have a perl app that wakes up every 10 seconds or so from a sleep to do some directory managment, then you would see user percentage spike at that point. However if you had something dump a large chunk of data to the drives, the kernel would slurp that data in really quick and then churn on it a moment trying to get it down to the filesystem. This would show itself as a system time. If your drive was particularly slow, it very well may hang the interupts for a moment as it tries to do something. Old S3 video cards under windows used to be really bad about holding interupts too long. Used to be if you wiggled the mouse you could hear the effects in any music you happened to be playing. -- Steven Critchfield [EMAIL PROTECTED] -- Juanjo sin .sig :( ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [Asterisk-Users] Interrupt latency problems
On Wed, 2004-12-01 at 13:36 -0600, Rich Adamson wrote: So, isn't the issue he/I are chasing after essentially 'why is cpu consumption jumping 30% (or 100%) every ten seconds when zaptel is running with no calls present? So where is that CPU time going? Is it in the system, or userspace? Have you tried changing to a non FC or RH kernel as suggested earlier? -- Steven Critchfield [EMAIL PROTECTED] ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [Asterisk-Users] Interrupt latency problems
Steven Critchfield wrote: On Wed, 2004-12-01 at 13:36 -0600, Rich Adamson wrote: So, isn't the issue he/I are chasing after essentially 'why is cpu consumption jumping 30% (or 100%) every ten seconds when zaptel is running with no calls present? So where is that CPU time going? Is it in the system, or userspace? Have you tried changing to a non FC or RH kernel as suggested earlier? Yes, I've just completed the installation of 2.6.9, and the spikes have gone away. Thank you, Steven. -- Michael Welter Introspect Telephony Corp. Denver, Colorado US +1.303.674.2575 [EMAIL PROTECTED] www.introspect.com ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [Asterisk-Users] Interrupt latency problems
On Wed, 2004-12-01 at 13:03 -0700, Michael Welter wrote: Steven Critchfield wrote: On Wed, 2004-12-01 at 13:36 -0600, Rich Adamson wrote: So, isn't the issue he/I are chasing after essentially 'why is cpu consumption jumping 30% (or 100%) every ten seconds when zaptel is running with no calls present? So where is that CPU time going? Is it in the system, or userspace? Have you tried changing to a non FC or RH kernel as suggested earlier? Yes, I've just completed the installation of 2.6.9, and the spikes have gone away. Thank you, Steven. Your welcome. I am glad it solved the problem. Now if only someone knew what it was about the stock RH or FC kernel that makes it happen you could get RH or FC to stop using that patch. That or maybe more people will be like me and always cast a weary eye upon a prepackaged kernel no matter what distro it came from. -- Steven Critchfield [EMAIL PROTECTED] ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [Asterisk-Users] Interrupt latency problems
On Wed, 2004-12-01 at 13:03 -0700, Michael Welter wrote: Steven Critchfield wrote: On Wed, 2004-12-01 at 13:36 -0600, Rich Adamson wrote: So, isn't the issue he/I are chasing after essentially 'why is cpu consumption jumping 30% (or 100%) every ten seconds when zaptel is running with no calls present? So where is that CPU time going? Is it in the system, or userspace? Have you tried changing to a non FC or RH kernel as suggested earlier? Yes, I've just completed the installation of 2.6.9, and the spikes have gone away. Thank you, Steven. Your welcome. I am glad it solved the problem. Now if only someone knew what it was about the stock RH or FC kernel that makes it happen you could get RH or FC to stop using that patch. That or maybe more people will be like me and always cast a weary eye upon a prepackaged kernel no matter what distro it came from. Looking at the Changlog for 2.6.9, it would appear a fair amount of work has been down in the pci stuff and the interrupt support areas. Since that seems to be an issue that keeps rearing its head with the digium analog cards, maybe there is something 'fixed' in that area. Not being a strong linux admin, how difficult would you say installing 2.6.9 is on top of a RHv9 system (2.4.20-31.9) should be for me? Any suggestions/hints on how to do it would be appreciated. Rich ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [Asterisk-Users] Interrupt latency problems
It did not fix my spandsp/TxFax problems, however :-( ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [Asterisk-Users] Interrupt latency problems
Rich Adamson wrote: Looking at the Changlog for 2.6.9, it would appear a fair amount of work has been down in the pci stuff and the interrupt support areas. Since that seems to be an issue that keeps rearing its head with the digium analog cards, maybe there is something 'fixed' in that area. Not being a strong linux admin, how difficult would you say installing 2.6.9 is on top of a RHv9 system (2.4.20-31.9) should be for me? Any suggestions/hints on how to do it would be appreciated. I tried to update my RH9 system with Fedora Core 2 (fedora.redhat.com), and the resulting system was quite confused. I finally did a backup and installed FC2 fresh. I'm looking at my interrupt assignments, and I see my tdm card on 17 and my T100P on 19. Are these cascaded interrupts on vector 2? Will the cascaded interrupts conflict with one another? Thanks, -- Michael Welter Introspect Telephony Corp. Denver, Colorado US +1.303.674.2575 [EMAIL PROTECTED] www.introspect.com ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [Asterisk-Users] Interrupt latency problems
On Wed, 2004-12-01 at 14:47 -0600, Rich Adamson wrote: Looking at the Changlog for 2.6.9, it would appear a fair amount of work has been down in the pci stuff and the interrupt support areas. Since that seems to be an issue that keeps rearing its head with the digium analog cards, maybe there is something 'fixed' in that area. Not being a strong linux admin, how difficult would you say installing 2.6.9 is on top of a RHv9 system (2.4.20-31.9) should be for me? Any suggestions/hints on how to do it would be appreciated. Suggestions are basically, understand what hardware you have. Learn to use lspci so you can check while running what the PCI devices are. Make sure you have ncurses development package installed. Kernels untar into linux-2.6.x directories now, link /usr/src/linux to the source version you are wanting to compile. Edit the makefile to specify where to install the kernel when you tell it to install. This is probably /boot. export INSTALL_PATH=/boot Make sure it is unxcommented too, the current kernels have it commented out. Use 'make menuconfig', it is nice and doesn't require X nor will you pull your hair out when you skip an option and realize you need to go backwards. If a config option doesn't seem necessary for your deployment and is available as a module, don't compile it into the kernel. You can always compile more modules later. Make sure your root filesystem type and hardware is compiled in. My opinion is initrd is for broken installs and is a hack to avoid if possible. Make sure you make a backup of a good working kernel. And preferably m copy accessible from your boot menu. Also make sure you have a good rescue disk handy in case you blow up either the installed kernel or the boot loader. Once finished configing, 'make clean modules modules_install install'. This will make everything, copy the modules to the right places, copy the kernel to the path specified in INSTALL_PATH, update the symlinks to point to your kernel and run your bootloader app(maybe just lilo) to install a new bootloader. Take a deep breath, verify your rescue disk is close, and reboot. Hope you did it all well. -- Steven Critchfield [EMAIL PROTECTED] ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users
Re: [Asterisk-Users] Interrupt latency problems
Steven Critchfield wrote: On Wed, 2004-12-01 at 13:03 -0700, Michael Welter wrote: Steven Critchfield wrote: On Wed, 2004-12-01 at 13:36 -0600, Rich Adamson wrote: So, isn't the issue he/I are chasing after essentially 'why is cpu consumption jumping 30% (or 100%) every ten seconds when zaptel is running with no calls present? So where is that CPU time going? Is it in the system, or userspace? Have you tried changing to a non FC or RH kernel as suggested earlier? Yes, I've just completed the installation of 2.6.9, and the spikes have gone away. Thank you, Steven. Your welcome. I am glad it solved the problem. Now if only someone knew what it was about the stock RH or FC kernel that makes it happen you could get RH or FC to stop using that patch. That or maybe more people will be like me and always cast a weary eye upon a prepackaged kernel no matter what distro it came from. See http://lists.digium.com/pipermail/asterisk-dev/2004-November/007329.html This has been brought to Digiums attention and they are currently working on it. Regards, Richard ___ Asterisk-Users mailing list [EMAIL PROTECTED] http://lists.digium.com/mailman/listinfo/asterisk-users To UNSUBSCRIBE or update options visit: http://lists.digium.com/mailman/listinfo/asterisk-users