... My computer suffers from high load average when the system is idle, >> introduced by commit ... also works fine. >> >> This fixes the problem: >> >> -------------------------- fs/jbd/transaction.c ----------------------------- >> index cceaf57.. ...

linux-kernel - Anders - Oct 3 2007 - 14:34

... suffers from high load average when the system is idle, > introduced ... to be the too high load average. All versions up to ... works fine. > > This fixes the problem: > > -------------------------- fs/jbd/transaction.c ----------------------------- > index ...

linux-kernel - Andrew Morton - Oct 2 2007 - 18:07

... suffers from high load average when the system is idle, >> introduced ... including 2.6.21 and >> 2.6.22, make the load ... works fine. >> >> This fixes the problem: >> >> -------------------------- fs/jbd/transaction.c ----------------------------- >> index ...

linux-kernel - Chuck Ebbert - Oct 2 2007 - 18:33

... suffers from high load average when the system is idle, introduced ... works fine. This fixes the problem: -------------------------- fs/jbd/transaction.c ----------------------------- index ... don't suffer from this problem. However, all other computers I ...

linux-kernel - Anders - Oct 2 2007 - 17:37

... computer suffers from high load average when the system is idle, > introduced by ... when the computer is totally > idle (I've tested in single user mode), the load average end up > at ~0.30 ... and don't suffer from the problem. > can you tell me if you ...

linux-kernel - Arjan van de Ven - Oct 2 2007 - 19:13

... computer suffers from high load average when the system is idle, >> introduced by ... when the computer is totally >> idle (I've tested in single user mode), the load average end up >> at ~0.30 ... and don't suffer from the problem. AvdV> can you tell me ...

linux-kernel - Anders - Oct 3 2007 - 03:04

... > My computer suffers from high load average when the system is idle, > introduced by commit ... :43 up 13 min, 18 users, load average: 0.65, 0.64, 0. ... any investigation, yet ;-) > This fixes the problem: I'll check this evening. Bye, ...

linux-kernel - Thorsten Kranzkowski - Oct 3 2007 - 05:40

... because some ticks just never >> happen when the timers get rounded: >> >> No rounding ... have something here! Why does this problem only show up on my computer ... ,7 @@ extern unsigned long avenrun[]; /* Load averages */ LT> #define FSHIFT 11 ...

linux-kernel - Anders - Oct 3 2007 - 16:15

... some ticks just never > happen when the timers get rounded: > > No ... In the first case the average is 1, but it's ... to try to round to an even second, and the load ... 7 @@ extern unsigned long avenrun[]; /* Load averages */ #define FSHIFT 11 /* nr ...

linux-kernel - Linus Torvalds - Oct 3 2007 - 14:02

... Morton wrote: > > This is unexpected. High load average is due to either a ... uninterruptible sleep. Not necessarily. We saw high loadaverages with the timer bogosity with ... select(.. , timeout = ) and when "date" wasn't taking the ...

linux-kernel - Linus Torvalds - Oct 2 2007 - 18:32

... Morton wrote: >> This is unexpected. High load average is due to either a ... uninterruptible sleep. > > Not necessarily. > > We saw high loadaverages with the timer bogosity ... select(.. , timeout = ) > > and when "date" wasn't taking the ...

linux-kernel - Mark Lord - Oct 2 2007 - 18:46

... round to an even second, and the load-average code generally also runs at > ... 7 +113,7 @@ extern unsigned long avenrun[]; /* Load averages */ > > #define FSHIFT 11 /* nr of bits ... is going to help; I mean, the load gets only updated in actual timer ...

linux-kernel - Arjan van de Ven - Oct 3 2007 - 14:20

... >> Or, everybody wakes up at once right when we are taking a sample. :) > ... of samples because some ticks just never happen when the timers get rounded: No rounding: tick ... 2 running In the first case the average is 1, but it's 2 in the ...

linux-kernel - Chuck Ebbert - Oct 3 2007 - 13:32

... > > not sure this is going to help; I mean, the load gets only updated in actual > timer interrupts... and on a tickless ... of other timers going on, hiding the issue. Hmm. Maybe Anders' problem stems partly from the fact that he really is using the ...

linux-kernel - Linus Torvalds - Oct 3 2007 - 14:28

... wrote: >> not sure this is going to help; I mean, the load gets only updated in actual >> timer interrupts... and on a tickless ... on a tuned one you have 2 or less. > > Hmm. Maybe Anders' problem stems partly from the fact that he really is > using ...

linux-kernel - Arjan van de Ven - Oct 3 2007 - 14:29

... "bunches" per CPU should really be done by > setting a flag on the timer itself - so that we could do that rounding > when the timer is actually added to the per-cpu queues! it's pretty much the same thing though - To unsubscribe from this list: ...

linux-kernel - Arjan van de Ven - Oct 2 2007 - 18:39

On Tue, 02 Oct 2007 18:33:58 -0400 > Or, everybody wakes up at once right when we are taking a sample. :) nice try but we sample every timer tick; this code being timer driven makes it what you say it is regardless of *which* timer tick it happens ...

linux-kernel - Arjan van de Ven - Oct 2 2007 - 19:26

On Tue, 2 Oct 2007 15:32:53 -0700 (PDT) > And I wonder if the same kind thing is effectively happening here: > the code is written so that it *tries* to sleep, but the rounding of > the clock basically means that it's trying to sleep using a

linux-kernel - Arjan van de Ven - Oct 2 2007 - 19:19

On Tue, 02 Oct 2007 18:46:18 -0400 > > On a related note, {set/get}itimer() currently are buggy (since > 2.6.11 or so), also due to this round_jiffies() thing I believe. I very much believe that it is totally unrelated... most of all since

linux-kernel - Arjan van de Ven - Oct 2 2007 - 19:22

Arjan van de Ven wrote: > On Tue, 02 Oct 2007 18:46:18 -0400 >> On a related note, {set/get}itimer() currently are buggy (since >> 2.6.11 or so), also due to this round_jiffies() thing I believe. > > I very much believe that it is totally unrelated

linux-kernel - Mark Lord - Oct 2 2007 - 19:40