[gentoo-user] Re: Constant Load 1.00+ on new Toshiba laptop
podgeweb.com> writes: > > I was wondering if anyone might have any idea's as to what is causing my > > new Toshiba A300 Satelite to idle at a load of 1.00 when not in use. Right > > after boot up it settles at 1.00 when I do nothing. I'm not seeing anything > > out of ordinary in dmesg ( asside from an non issue with legacy usb and sd > > and sr drivers in the kernel ). Ah, I have had a similar problem a few months ago on one system (AMD 64 X2). I never figured it out, but I suspect that rebuilding X, KDE and many other utilities over time, fixed it. X seems to use more resources than it should. But, in reality, after a while, it just went away. None of the other AMD 64 X2 systems I manage, had the problem. The load was always 1.0 or higher. I think I even posted to this list and we discussed the meaning of "load" too. Here's some good reading on "load average" http://www.teamquest.com/resources/gunther/display/5/
Re: [gentoo-user] Re: Constant Load 1.00+ on new Toshiba laptop
On Thu, Feb 19, 2009 at 1:18 AM, James wrote: > podgeweb.com> writes: > > > > > I was wondering if anyone might have any idea's as to what is causing > my > > > new Toshiba A300 Satelite to idle at a load of 1.00 when not in use. > Right > > > after boot up it settles at 1.00 when I do nothing. I'm not seeing > anything > > > out of ordinary in dmesg ( asside from an non issue with legacy usb and > sd > > > and sr drivers in the kernel ). > > Ah, > > I have had a similar problem a few months ago on one system (AMD 64 X2). > I never figured it out, but I suspect that rebuilding X, KDE and many > other utilities over time, fixed it. X seems to use more resources than > it should. But, in reality, after a while, it just went away. None of the > other AMD 64 X2 systems I manage, had the problem. The load was always 1.0 > or higher. > > > I think I even posted to this list and we discussed the meaning of "load" > too. > > Here's some good reading on "load average" > > http://www.teamquest.com/resources/gunther/display/5/ > > > Hey, I'm fairly comfortable with the definition of load average, that's not something I need clarification on, but thanks to all whom have offered. I'll fire up htop today and see if its able to identify anything that top or ps hasn't as yet. I'm relatively certain the issue isn't related to X or gnome as the load shoots up immediately after boot up and the load issue happens even without firing up startx. -- Beau Dylan Henderson "No human being should be denied the fundamental right to educate themselves or indulge their curiosities. To deny any person the right to do so, for whatever reason, is nothing more than the safeguarding of ignorance to ensure that enlightenment does not become a threat. For nothing in this world is more dangerous than an open mind." -- Matthew Good
Re: [gentoo-user] Re: Constant Load 1.00+ on new Toshiba laptop
On Wed, Feb 18, 2009 at 4:57 PM, Beau Henderson wrote: > > > On Thu, Feb 19, 2009 at 1:18 AM, James wrote: >> >> podgeweb.com> writes: >> >> >> > > I was wondering if anyone might have any idea's as to what is causing >> > > my >> > > new Toshiba A300 Satelite to idle at a load of 1.00 when not in use. >> > > Right >> > > after boot up it settles at 1.00 when I do nothing. I'm not seeing >> > > anything >> > > out of ordinary in dmesg ( asside from an non issue with legacy usb >> > > and sd >> > > and sr drivers in the kernel ). >> >> Ah, >> >> I have had a similar problem a few months ago on one system (AMD 64 X2). >> I never figured it out, but I suspect that rebuilding X, KDE and many >> other utilities over time, fixed it. X seems to use more resources than >> it should. But, in reality, after a while, it just went away. None of the >> other AMD 64 X2 systems I manage, had the problem. The load was always 1.0 >> or higher. >> >> >> I think I even posted to this list and we discussed the meaning of "load" >> too. >> >> Here's some good reading on "load average" >> >> http://www.teamquest.com/resources/gunther/display/5/ >> >> > > Hey, > > I'm fairly comfortable with the definition of load average, that's not > something I need clarification on, but thanks to all whom have offered. > > I'll fire up htop today and see if its able to identify anything that top or > ps hasn't as yet. > > I'm relatively certain the issue isn't related to X or gnome as the load > shoots up immediately after boot up and the load issue happens even without > firing up startx. I wonder if the laptop could be going into some low-speed, low-power mode, causing it to seem "slow" and thus making the load seem artificially high? (assuming you're using CPU frequency scaling at all)
Re: [gentoo-user] Re: Constant Load 1.00+ on new Toshiba laptop
On Thu, Feb 19, 2009 at 9:20 AM, Paul Hartman > wrote: > On Wed, Feb 18, 2009 at 4:57 PM, Beau Henderson > wrote: > > > > > > On Thu, Feb 19, 2009 at 1:18 AM, James wrote: > >> > >> podgeweb.com> writes: > >> > >> > >> > > I was wondering if anyone might have any idea's as to what is > causing > >> > > my > >> > > new Toshiba A300 Satelite to idle at a load of 1.00 when not in use. > >> > > Right > >> > > after boot up it settles at 1.00 when I do nothing. I'm not seeing > >> > > anything > >> > > out of ordinary in dmesg ( asside from an non issue with legacy usb > >> > > and sd > >> > > and sr drivers in the kernel ). > >> > >> Ah, > >> > >> I have had a similar problem a few months ago on one system (AMD 64 X2). > >> I never figured it out, but I suspect that rebuilding X, KDE and many > >> other utilities over time, fixed it. X seems to use more resources than > >> it should. But, in reality, after a while, it just went away. None of > the > >> other AMD 64 X2 systems I manage, had the problem. The load was always > 1.0 > >> or higher. > >> > >> > >> I think I even posted to this list and we discussed the meaning of > "load" > >> too. > >> > >> Here's some good reading on "load average" > >> > >> http://www.teamquest.com/resources/gunther/display/5/ > >> > >> > > > > Hey, > > > > I'm fairly comfortable with the definition of load average, that's not > > something I need clarification on, but thanks to all whom have offered. > > > > I'll fire up htop today and see if its able to identify anything that top > or > > ps hasn't as yet. > > > > I'm relatively certain the issue isn't related to X or gnome as the load > > shoots up immediately after boot up and the load issue happens even > without > > firing up startx. > > I wonder if the laptop could be going into some low-speed, low-power > mode, causing it to seem "slow" and thus making the load seem > artificially high? (assuming you're using CPU frequency scaling at > all) > > I've tried manually altering the governor to performance but its the same story. The system doesn't appear sluggish, I'm really more concerned that something is causing the load and this might lead to shorter battery life and and more heat. htop doesn't seem to show anything either. Just for shits n giggles I fired up powertop and implemented its suggestions. No luck with that either unfortunately. This has me completely baffled. -- Beau Dylan Henderson "No human being should be denied the fundamental right to educate themselves or indulge their curiosities. To deny any person the right to do so, for whatever reason, is nothing more than the safeguarding of ignorance to ensure that enlightenment does not become a threat. For nothing in this world is more dangerous than an open mind." -- Matthew Good
Re: [gentoo-user] Re: Constant Load 1.00+ on new Toshiba laptop
On Thursday 19 February 2009 01:38:39 Beau Henderson wrote: > I've tried manually altering the governor to performance but its the same > story. > > The system doesn't appear sluggish, I'm really more concerned that > something is causing the load and this might lead to shorter battery life > and and more heat. Right in the beginning you said the load was *exactly* 1.00. Now, load is defined as "the _number_ of processes on average waiting for the cpu in the last 1, 5, 15 minutes" So it does not mean that the cpu is necessarily working hard (but usually does) if the load is high. Yours is _exactly_ 1.00 (very suspicious) This is almost certainly one of two things: 1. A stupid kernel config that you should not have done :-) 2. Some app is blocking hard on IO I guess #2 - something waits for IO, it is not available, so immediately goes back to sleep waiting for it's next time slice. This happens many times a second and averaged over a minute looks like the cpu is constantly busy. Thus, no real extra cpu load is happening, the machine does not appear at all sluggish and the only harm is that it is annoying as hell. -- alan dot mckinnon at gmail dot com
Re: [gentoo-user] Re: Constant Load 1.00+ on new Toshiba laptop
On Thu, Feb 19, 2009 at 9:53 AM, Alan McKinnon wrote: > On Thursday 19 February 2009 01:38:39 Beau Henderson wrote: > > I've tried manually altering the governor to performance but its the same > > story. > > > > The system doesn't appear sluggish, I'm really more concerned that > > something is causing the load and this might lead to shorter battery life > > and and more heat. > > Right in the beginning you said the load was *exactly* 1.00. Now, load is > defined as > > "the _number_ of processes on average waiting for the cpu in the last 1, 5, > 15 > minutes" > > So it does not mean that the cpu is necessarily working hard (but usually > does) if the load is high. Yours is _exactly_ 1.00 (very suspicious) > > This is almost certainly one of two things: > > 1. A stupid kernel config that you should not have done :-) > 2. Some app is blocking hard on IO > > I guess #2 - something waits for IO, it is not available, so immediately > goes > back to sleep waiting for it's next time slice. This happens many times a > second and averaged over a minute looks like the cpu is constantly busy. > Thus, > no real extra cpu load is happening, the machine does not appear at all > sluggish and the only harm is that it is annoying as hell. > > -- > alan dot mckinnon at gmail dot com > > > Woah, now were getting somewhere. After reading that, I had another look at the top output and noticed that a single hald process was in D state. /etc/init.d/hald stop and the load is lowering as I type. I'm going to have to dig into this deeper as time permits. Thanks everyone :) -- Beau Dylan Henderson "No human being should be denied the fundamental right to educate themselves or indulge their curiosities. To deny any person the right to do so, for whatever reason, is nothing more than the safeguarding of ignorance to ensure that enlightenment does not become a threat. For nothing in this world is more dangerous than an open mind." -- Matthew Good
Re: [gentoo-user] Re: Constant Load 1.00+ on new Toshiba laptop
On Thu, Feb 19, 2009 at 10:04 AM, Beau Henderson wrote: > > > On Thu, Feb 19, 2009 at 9:53 AM, Alan McKinnon wrote: > >> On Thursday 19 February 2009 01:38:39 Beau Henderson wrote: >> > I've tried manually altering the governor to performance but its the >> same >> > story. >> > >> > The system doesn't appear sluggish, I'm really more concerned that >> > something is causing the load and this might lead to shorter battery >> life >> > and and more heat. >> >> Right in the beginning you said the load was *exactly* 1.00. Now, load is >> defined as >> >> "the _number_ of processes on average waiting for the cpu in the last 1, >> 5, 15 >> minutes" >> >> So it does not mean that the cpu is necessarily working hard (but usually >> does) if the load is high. Yours is _exactly_ 1.00 (very suspicious) >> >> This is almost certainly one of two things: >> >> 1. A stupid kernel config that you should not have done :-) >> 2. Some app is blocking hard on IO >> >> I guess #2 - something waits for IO, it is not available, so immediately >> goes >> back to sleep waiting for it's next time slice. This happens many times a >> second and averaged over a minute looks like the cpu is constantly busy. >> Thus, >> no real extra cpu load is happening, the machine does not appear at all >> sluggish and the only harm is that it is annoying as hell. >> >> -- >> alan dot mckinnon at gmail dot com >> >> >> > Woah, now were getting somewhere. > > After reading that, I had another look at the top output and noticed that a > single hald process was in D state. /etc/init.d/hald stop and the load is > lowering as I type. I'm going to have to dig into this deeper as time > permits. > > Thanks everyone :) > > > -- > Beau Dylan Henderson > > "No human being should be denied the fundamental right to educate > themselves or indulge their curiosities. To deny any person the right to do > so, for whatever reason, is nothing more than the safeguarding of ignorance > to ensure that enlightenment does not become a threat. For nothing in this > world is more dangerous than an open mind." -- Matthew Good > The culprit: Hals cdrom polling. Interestingly, the load shot down as soon as I stuck a disk. The fix: hal-disable-polling --device /dev/scd0 'hal' -- Beau Dylan Henderson "No human being should be denied the fundamental right to educate themselves or indulge their curiosities. To deny any person the right to do so, for whatever reason, is nothing more than the safeguarding of ignorance to ensure that enlightenment does not become a threat. For nothing in this world is more dangerous than an open mind." -- Matthew Good
Re: [gentoo-user] Re: Constant Load 1.00+ on new Toshiba laptop
Beau Henderson wrote: > > > On Thu, Feb 19, 2009 at 10:04 AM, Beau Henderson > mailto:b...@thehenderson.com>> wrote: > > > > On Thu, Feb 19, 2009 at 9:53 AM, Alan McKinnon > mailto:alan.mckin...@gmail.com>> wrote: > > On Thursday 19 February 2009 01:38:39 Beau Henderson wrote: > > I've tried manually altering the governor to performance but > its the same > > story. > > > > The system doesn't appear sluggish, I'm really more > concerned that > > something is causing the load and this might lead to shorter > battery life > > and and more heat. > > Right in the beginning you said the load was *exactly* 1.00. > Now, load is > defined as > > "the _number_ of processes on average waiting for the cpu in > the last 1, 5, 15 > minutes" > > So it does not mean that the cpu is necessarily working hard > (but usually > does) if the load is high. Yours is _exactly_ 1.00 (very > suspicious) > > This is almost certainly one of two things: > > 1. A stupid kernel config that you should not have done :-) > 2. Some app is blocking hard on IO > > I guess #2 - something waits for IO, it is not available, so > immediately goes > back to sleep waiting for it's next time slice. This happens > many times a > second and averaged over a minute looks like the cpu is > constantly busy. Thus, > no real extra cpu load is happening, the machine does not > appear at all > sluggish and the only harm is that it is annoying as hell. > > -- > alan dot mckinnon at gmail dot com > > > > Woah, now were getting somewhere. > > After reading that, I had another look at the top output and > noticed that a single hald process was in D state. > /etc/init.d/hald stop and the load is lowering as I type. I'm > going to have to dig into this deeper as time permits. > > Thanks everyone :) > > > -- > Beau Dylan Henderson > > "No human being should be denied the fundamental right to educate > themselves or indulge their curiosities. To deny any person the > right to do so, for whatever reason, is nothing more than the > safeguarding of ignorance to ensure that enlightenment does not > become a threat. For nothing in this world is more dangerous than > an open mind." -- Matthew Good > > > > The culprit: Hals cdrom polling. Interestingly, the load shot down as > soon as I stuck a disk. > > The fix: hal-disable-polling --device /dev/scd0 'hal' > -- > Beau Dylan Henderson > > "No human being should be denied the fundamental right to educate > themselves or indulge their curiosities. To deny any person the right > to do so, for whatever reason, is nothing more than the safeguarding > of ignorance to ensure that enlightenment does not become a threat. > For nothing in this world is more dangerous than an open mind." -- > Matthew Good I would never have guessed this was your problem but I had the same thing happen on my DESKTOP puter a while back. I hit the eject button, closed the tray again, restarted hald and it went back to normal. I also had a TON of errors in messages too. I have cron set up to rotate messages so I may not have those now. This may be a different cause but does make one wonder. Also, it hasn't done it since. Dale :-) :-)