HEADS UP: inpcb/inpcbinfo rwlocking: coming to a 7-STABLE branch near you

[Robert Watson]

On Wed, 13 Aug 2008, Mike Tancsa wrote:

> At 04:41 PM 8/13/2008, Robert Watson wrote:
>
>> Well, it shouldn't be related, but sometimes things get tricky with locking 
>> if it turns out that extra locking at one layer was masking a lack of 
>> locking at another.  Let's try to diagnose this one a bit more before 
>> concluding that is the case, though.  I take that the same problems don't 
>> happen if you boot a vanilla version of the same rev of the kernel?  What 
>> command did you use to generate the list at the bottom of your e-mail?
>
>        the arp messages were a snippet from just arp -na. All of those IP 
> addresses are local to the box.  I am just doing a cvsup to the same point 
> in time and am rebuilding the kernel.
>
> Also odd, is that if I do a arp -nda it seems to want to delete more than it 
> should. Here is a snippet

It's concerning also that there is more than one entry for any particular IP 
address.  I'll have to go reread the ARP code.  Confirming that this doesn't 
happen with vanilla head is definitely the next step.  I'll be fairly busy for 
the next few days with things in Cambridge; if we can't rule out the inpcb 
patches as the source of the problem, I'll defer committing them until next 
week when I have a chance to work through this more.

Robert N M Watson
Computer Laboratory
University of Cambridge

>
>
> 199.212.134.2 (199.212.134.2) deleted
> delete: cannot locate 199.212.134.2
> delete: cannot locate 199.212.134.2
> delete: cannot locate 199.212.134.2
> delete: cannot locate 199.212.134.2
> delete: cannot locate 199.212.134.2
> delete: cannot locate 199.212.134.2
> delete: cannot locate 199.212.134.2
> delete: cannot locate 199.212.134.2
> delete: cannot locate 199.212.134.2
> delete: cannot locate 199.212.134.2
> delete: cannot locate 199.212.134.2
> delete: cannot locate 199.212.134.2
> delete: cannot locate 199.212.134.2
> delete: cannot locate 199.212.134.2
>
>
> After doing arp -nda, I am back to a very large arp cache again right away
>
> 0[smtp2]# arp -na | wc
>   27818  228335 1679120
> 0[smtp2]#
>
> 0[smtp2]# netstat -na | wc
>     762    4920   59057
> 0[smtp2]# netstat -nr | wc
>   27853  167097 1893894
> 0[smtp2]#
>
>
>
>
>
>> Robert N M Watson
>> Computer Laboratory
>> University of Cambridge
>> 
>>> 
>>> 0[smtp2]# sysctl -a | grep prox
>>> net.link.ether.inet.proxyall: 0
>>> 0[smtp2]#
>>> 
>>> 
>>> 0[smtp2]# arp -na | wc
>>>   27665  227053 1669734
>>> 0[smtp2]#
>>> 
>>> ? (199.212.134.1) at (incomplete) on em0 [ethernet]
>>> ? (199.212.134.1) at (incomplete) on em0 [ethernet]
>>> ? (199.212.134.1) at (incomplete) on em0 [ethernet]
>>> ? (199.212.134.1) at (incomplete) on em0 [ethernet]
>>> ? (199.212.134.1) at (incomplete) on em0 [ethernet]
>>> ? (199.212.134.1) at (incomplete) on em0 [ethernet]
>>> ? (199.212.134.1) at (incomplete) on em0 [ethernet]
>>> ? (199.212.134.1) at (incomplete) on em0 [ethernet]
>>> ? (199.212.134.1) at (incomplete) on em0 [ethernet]
>>> ? (199.212.134.1) at (incomplete) on em0 [ethernet]
>>> ? (199.212.134.1) at (incomplete) on em0 [ethernet]
>>> ? (199.212.134.1) at (incomplete) on em0 published (proxy only) [ethernet]
>>> ? (199.212.134.2) at 00:30:48:8f:3e:8a on em0 [ethernet]
>>> ? (199.212.134.2) at (incomplete) on em0 [ethernet]
>>> ? (199.212.134.2) at (incomplete) on em0 [ethernet]
>>> ? (199.212.134.2) at (incomplete) on em0 [ethernet]
>>> ? (199.212.134.2) at (incomplete) on em0 [ethernet]
>>> ? (199.212.134.2) at (incomplete) on em0 [ethernet]
>>> ? (199.212.134.2) at (incomplete) on em0 [ethernet]
>>> ? (199.212.134.2) at (incomplete) on em0 [ethernet]
>>> ? (199.212.134.2) at (incomplete) on em0 published (proxy only) [ethernet]
>>> ? (199.212.134.2) at (incomplete) on em0 published (proxy only) [ethernet]
>>> ? (199.212.134.2) at (incomplete) on em0 [ethernet]
>>> ? (199.212.134.2) at (incomplete) on em0 published (proxy only) [ethernet]
>>> ? (199.212.134.2) at (incomplete) on em0 [ethernet]
>>> ? (199.212.134.2) at (incomplete) on em0 [ethernet]
>>> ? (199.212.134.2) at (incomplete) on em0 [ethernet]
>
>