Re: [PATCH 1/3] Increase lockdep limits: MAX_STACK_TRACE_ENTRIES

From: Peter Zijlstra
Date: Tue Jul 07 2009 - 11:55:19 EST


On Tue, 2009-07-07 at 16:50 +0100, Joao Correia wrote:

> >> Yes. Anything 2.6.31 forward triggers this immediatly during init
> >> process, at random places.
> >
> > Not on my machines it doesn't.. so I suspect its something weird in
> > your .config or maybe due to some hardware you have that I don't that
> > triggers different drivers or somesuch.
>
> I am not the only one reporting this, and it happens, for example,
> with a stock .config from a Fedora 11 install.
>
> It may, of course, be a funny driver interaction yes, but other than
> stripping the box piece by piece, how would one go about debugging
> this otherwise?

One thing to do is stare (or share) at the output
of /proc/lockdep_chains and see if there's some particularly large
chains in there, or many of the same name or something.

/proc/lockdep_stats might also be interesting, mine reads like:

[root@opteron ~]# cat /proc/lockdep_stats
lock-classes: 641 [max: 8191]
direct dependencies: 3794 [max: 16384]
indirect dependencies: 7557
all direct dependencies: 73254
dependency chains: 3716 [max: 32768]
dependency chain hlocks: 10167 [max: 163840]
in-hardirq chains: 21
in-softirq chains: 353
in-process chains: 3342
stack-trace entries: 91035 [max: 262144]
combined max dependencies: 26035284
hardirq-safe locks: 28
hardirq-unsafe locks: 460
softirq-safe locks: 114
softirq-unsafe locks: 373
irq-safe locks: 123
irq-unsafe locks: 460
hardirq-read-safe locks: 0
hardirq-read-unsafe locks: 45
softirq-read-safe locks: 8
softirq-read-unsafe locks: 39
irq-read-safe locks: 8
irq-read-unsafe locks: 45
uncategorized locks: 106
unused locks: 1
max locking depth: 14
max recursion depth: 10
debug_locks: 1


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/