Re: MBuf clusters - what uses them?

["Niels Dettenbach (Syndicat IT&Internet)" <nd%syndicat.com@localhost>]

>On Sat, 5 Apr 2014, Greg Troxel wrote:
>
>> <snip>
>>
>> I see no fails counted.  Why do you think you are out of clusters? 
>Are
>> you seeing that in dmesg?  Or is it just a possible lockup
>explanation?
>
>The mbuf/mbufcluster "explanation" was offered when I first reported 
>this several months ago.
>
>> Please describe the lockup symptoms more precisely.
>
>Most obvious symptom is sudden lack of network connectivity.  A ping to
>
>another host on the local network fails with a "no buffer space" error.
>
>> Also, look in vmstat -m for anything with fail != 0.
>
>No failures ever appear.
>
>However, I have tracked mbuf usage via netstat and vmstat, and shortly 
>before the lockup, both numbers showed a sudden increase in
>utilization.
>
>> you might also save vmstat -m to a file every 5 minutes, and look
>> before/after the next lockup.
>
>Yeah, I was doing this every 1 minute...
>
>
>Someone at that time suggested that bit-torrent could have been doing 
>something nasty, so I stopped my "transmission" server.  The frequency 
>of lockup has dropped dramatically, but not to zero.
>
>
>Another symptom is with postfix...  It receives incoming mail from the 
>network, but fails to forward the mail through my local dspam - mailq 
>shows lots of messages in the "deferred" state due to "resources 

>
>
>
>
>
>-------------------------------------------------------------------------
>| Paul Goyette     | PGP Key fingerprint:     | E-mail addresses:      
>|
>| Customer Service | FA29 0E3B 35AF E8AE 6651 | paul at whooppee.com   
>|
>| Network Engineer | 0786 F758 55DE 53BA 7731 | pgoyette at juniper.net
>|
>| Kernel Developer |                          | pgoyette at netbsd.org 
>|
>-------------------------------------------------------------------------

On 6. April 2014 18:50:28 MESZ, Paul Goyette <paul%whooppee.com@localhost> 
wrote:

>temporarily unavailable" errors.  (As near as I can tell, postfix uses 
>unix-family sockets for this...)
...i can notice the same scenario with the same error msgs in timeframes of 
weeks on a xen virtualized machine (seems only a NetBSD over 6.x is affected) 
with several TCP services plus DNS plus local unix sockets - but i have no 
"blocked" unix sockets before and even when the net "goes down" seconds or 
minutes before the os locks completely.

On xen i had an additional effect - if i tried to define a second network 
interface for local (host internal) LAN TCP connections to the local LAN 
brought down the other interface traffic too. Not shure if this is related - 
the behaviours are very similiar to the mbuf network slowdown/lock before 
system lock.

I do not understand in detail why the whole OS is locking in a case where mbufs 
are going out - if a system i.e. goes out of file descriptors the os byself is 
still reacting. So is this a bug or feature? ß)


hth
cheerioh,


Niels.
-- 
Niels Dettenbach
Syndicat IT&Internet
http://www.syndicat.com