Re: BUG in 2.6.20-rt8

2007-02-25 Thread Nick Piggin
David Miller wrote: From: "Paul E. McKenney" <[EMAIL PROTECTED]> Date: Sun, 25 Feb 2007 17:52:30 -0800 Why doesn't the traditional hash table of locks work here? Use the cache-line address as input to the hash function, take the corresponding lock, do the compare-and-exchange by hand, and

Re: BUG in 2.6.20-rt8

2007-02-25 Thread David Miller
From: "Paul E. McKenney" <[EMAIL PROTECTED]> Date: Sun, 25 Feb 2007 17:52:30 -0800 > Why doesn't the traditional hash table of locks work here? Use the > cache-line address as input to the hash function, take the corresponding > lock, do the compare-and-exchange by hand, and then release the

Re: BUG in 2.6.20-rt8

2007-02-25 Thread Paul E. McKenney
On Sat, Feb 24, 2007 at 10:37:44PM -0800, David Miller wrote: > From: Ingo Molnar <[EMAIL PROTECTED]> > Date: Sun, 25 Feb 2007 07:27:47 +0100 > > > > > * Paul E. McKenney <[EMAIL PROTECTED]> wrote: > > > > > I got the following running stock 2.6.20-rt8 on an 4-CPU 1.8GHz > > > Opteron box.

Re: BUG in 2.6.20-rt8

2007-02-25 Thread Paul E. McKenney
On Sun, Feb 25, 2007 at 07:27:47AM +0100, Ingo Molnar wrote: > > * Paul E. McKenney <[EMAIL PROTECTED]> wrote: > > > I got the following running stock 2.6.20-rt8 on an 4-CPU 1.8GHz > > Opteron box. The machine continued to run a few rounds of kernbench > > and LTP. Looks a bit scary -- a

Re: BUG in 2.6.20-rt8

2007-02-25 Thread Paul E. McKenney
On Sun, Feb 25, 2007 at 07:27:47AM +0100, Ingo Molnar wrote: * Paul E. McKenney [EMAIL PROTECTED] wrote: I got the following running stock 2.6.20-rt8 on an 4-CPU 1.8GHz Opteron box. The machine continued to run a few rounds of kernbench and LTP. Looks a bit scary -- a tasklet was

Re: BUG in 2.6.20-rt8

2007-02-25 Thread Paul E. McKenney
On Sat, Feb 24, 2007 at 10:37:44PM -0800, David Miller wrote: From: Ingo Molnar [EMAIL PROTECTED] Date: Sun, 25 Feb 2007 07:27:47 +0100 * Paul E. McKenney [EMAIL PROTECTED] wrote: I got the following running stock 2.6.20-rt8 on an 4-CPU 1.8GHz Opteron box. The machine continued

Re: BUG in 2.6.20-rt8

2007-02-25 Thread David Miller
From: Paul E. McKenney [EMAIL PROTECTED] Date: Sun, 25 Feb 2007 17:52:30 -0800 Why doesn't the traditional hash table of locks work here? Use the cache-line address as input to the hash function, take the corresponding lock, do the compare-and-exchange by hand, and then release the lock.

Re: BUG in 2.6.20-rt8

2007-02-25 Thread Nick Piggin
David Miller wrote: From: Paul E. McKenney [EMAIL PROTECTED] Date: Sun, 25 Feb 2007 17:52:30 -0800 Why doesn't the traditional hash table of locks work here? Use the cache-line address as input to the hash function, take the corresponding lock, do the compare-and-exchange by hand, and then

Re: BUG in 2.6.20-rt8

2007-02-24 Thread David Miller
From: Ingo Molnar <[EMAIL PROTECTED]> Date: Sun, 25 Feb 2007 07:27:47 +0100 > > * Paul E. McKenney <[EMAIL PROTECTED]> wrote: > > > I got the following running stock 2.6.20-rt8 on an 4-CPU 1.8GHz > > Opteron box. The machine continued to run a few rounds of kernbench > > and LTP. Looks a bit

Re: BUG in 2.6.20-rt8

2007-02-24 Thread Ingo Molnar
* Paul E. McKenney <[EMAIL PROTECTED]> wrote: > I got the following running stock 2.6.20-rt8 on an 4-CPU 1.8GHz > Opteron box. The machine continued to run a few rounds of kernbench > and LTP. Looks a bit scary -- a tasklet was "stolen" from > __tasklet_action(). > > Thoughts? In the

Re: BUG in 2.6.20-rt8

2007-02-24 Thread Paul E. McKenney
On Sat, Feb 24, 2007 at 09:02:12PM -0800, Paul E. McKenney wrote: > Hello! > > I got the following running stock 2.6.20-rt8 on an 4-CPU 1.8GHz Opteron > box. The machine continued to run a few rounds of kernbench and LTP. > Looks a bit scary -- a tasklet was "stolen" from __tasklet_action(). >

BUG in 2.6.20-rt8

2007-02-24 Thread Paul E. McKenney
Hello! I got the following running stock 2.6.20-rt8 on an 4-CPU 1.8GHz Opteron box. The machine continued to run a few rounds of kernbench and LTP. Looks a bit scary -- a tasklet was "stolen" from __tasklet_action(). Thoughts? In the meantime, kicking it off again to see if it repeats.

BUG in 2.6.20-rt8

2007-02-24 Thread Paul E. McKenney
Hello! I got the following running stock 2.6.20-rt8 on an 4-CPU 1.8GHz Opteron box. The machine continued to run a few rounds of kernbench and LTP. Looks a bit scary -- a tasklet was stolen from __tasklet_action(). Thoughts? In the meantime, kicking it off again to see if it repeats.

Re: BUG in 2.6.20-rt8

2007-02-24 Thread Paul E. McKenney
On Sat, Feb 24, 2007 at 09:02:12PM -0800, Paul E. McKenney wrote: Hello! I got the following running stock 2.6.20-rt8 on an 4-CPU 1.8GHz Opteron box. The machine continued to run a few rounds of kernbench and LTP. Looks a bit scary -- a tasklet was stolen from __tasklet_action().

Re: BUG in 2.6.20-rt8

2007-02-24 Thread Ingo Molnar
* Paul E. McKenney [EMAIL PROTECTED] wrote: I got the following running stock 2.6.20-rt8 on an 4-CPU 1.8GHz Opteron box. The machine continued to run a few rounds of kernbench and LTP. Looks a bit scary -- a tasklet was stolen from __tasklet_action(). Thoughts? In the meantime,

Re: BUG in 2.6.20-rt8

2007-02-24 Thread David Miller
From: Ingo Molnar [EMAIL PROTECTED] Date: Sun, 25 Feb 2007 07:27:47 +0100 * Paul E. McKenney [EMAIL PROTECTED] wrote: I got the following running stock 2.6.20-rt8 on an 4-CPU 1.8GHz Opteron box. The machine continued to run a few rounds of kernbench and LTP. Looks a bit scary -- a