Dear colleagues,
for last couple of hours I've encountered random TCP packets drops (most
visible as ssh sessions lockups) and random kernel messages about "pullup
failed"
marck@gw-f:~> netstat -m
1051/1584/32768 mbufs in use (current/peak/max):
1050 mbufs allocated to data
1 mbufs allocated to packet headers
1047/1582/16384 mbuf clusters in use (current/peak/max)
3560 Kbytes allocated to network (8% of mb_map in use)
0 requests for memory denied
0 requests for memory delayed
0 calls to protocol drain routines
Quick googling shows me
http://www.mail-archive.com/freebsd-net@freebsd.org/msg10291.html which has not
been answered by luigi
Any thoughts?
Sincerely,
D.Marck [DM5020, MCK-RIPE, DM3-RIPN]
------------------------------------------------------------------------
*** Dmitry Morozovsky --- D.Marck --- Wild Woozle --- marck@rinet.ru ***
------------------------------------------------------------------------
On Tue, 13 Jan 2004, 18:19+0300, Dmitry Morozovsky wrote:> Dear colleagues, > > for last couple of hours I've encountered random TCP packets drops (most > visible as ssh sessions lockups) and random kernel messages about "pullup > failed"tcpdump of these sessions would be helpful.> marck@gw-f:~> netstat -m > 1051/1584/32768 mbufs in use (current/peak/max): > 1050 mbufs allocated to data > 1 mbufs allocated to packet headers > 1047/1582/16384 mbuf clusters in use (current/peak/max) > 3560 Kbytes allocated to network (8% of mb_map in use) > 0 requests for memory denied > 0 requests for memory delayed > 0 calls to protocol drain routines > > Quick googling shows me > http://www.mail-archive.com/freebsd-net@freebsd.org/msg10291.html which has not > been answered by luigiThe patch is incorrect. -- Maxim Konovalov, maxim@macomnet.ru, maxim@FreeBSD.org
What is the output of
sysctl net.inet.ip | grep queue
Do you have any errors on your ethernet ? what does netstat -ni show ?
---Mike
At 10:19 AM 13/01/2004, Dmitry Morozovsky wrote:>Dear colleagues,
>
>for last couple of hours I've encountered random TCP packets drops (most
>visible as ssh sessions lockups) and random kernel messages about
"pullup
>failed"
>
>marck@gw-f:~> netstat -m
>1051/1584/32768 mbufs in use (current/peak/max):
> 1050 mbufs allocated to data
> 1 mbufs allocated to packet headers
>1047/1582/16384 mbuf clusters in use (current/peak/max)
>3560 Kbytes allocated to network (8% of mb_map in use)
>0 requests for memory denied
>0 requests for memory delayed
>0 calls to protocol drain routines
>
>Quick googling shows me
>http://www.mail-archive.com/freebsd-net@freebsd.org/msg10291.html which
>has not
>been answered by luigi
>
>
>Any thoughts?
>
>Sincerely,
>D.Marck [DM5020, MCK-RIPE, DM3-RIPN]
>------------------------------------------------------------------------
>*** Dmitry Morozovsky --- D.Marck --- Wild Woozle --- marck@rinet.ru ***
>------------------------------------------------------------------------
>_______________________________________________
>freebsd-stable@freebsd.org mailing list
>http://lists.freebsd.org/mailman/listinfo/freebsd-stable
>To unsubscribe, send any mail to
"freebsd-stable-unsubscribe@freebsd.org"
On Tue, 13 Jan 2004, Dmitry Morozovsky wrote: DM> for last couple of hours I've encountered random TCP packets drops (most DM> visible as ssh sessions lockups) and random kernel messages about "pullup DM> failed" False (or, more precisely, coincident) alarm: real problem lies somewhere under hardware and software driving rl 8139 (planned to be replaced by fxp ;-) Sincerely, D.Marck [DM5020, MCK-RIPE, DM3-RIPN] ------------------------------------------------------------------------ *** Dmitry Morozovsky --- D.Marck --- Wild Woozle --- marck@rinet.ru *** ------------------------------------------------------------------------
At 02:19 AM 14/01/2004, Dmitry Morozovsky wrote:>Dear colleagues, > >for last couple of hours I've encountered random TCP packets drops (most >visible as ssh sessions lockups) and random kernel messages about "pullup >failed" > >marck@gw-f:~> netstat -m >1051/1584/32768 mbufs in use (current/peak/max): > 1050 mbufs allocated to data > 1 mbufs allocated to packet headers >1047/1582/16384 mbuf clusters in use (current/peak/max) >3560 Kbytes allocated to network (8% of mb_map in use) >0 requests for memory denied >0 requests for memory delayed >0 calls to protocol drain routines > >Quick googling shows me >http://www.mail-archive.com/freebsd-net@freebsd.org/msg10291.html which >has not >been answered by luigiI've seen this happening as well, since you don't appeaer to be low on mbufs ... (from the ipfw man page:) "There are circumstances where fragmented datagrams are uncondition- ally dropped. TCP packets are dropped if they do not contain at least 20 bytes of TCP header, UDP packets are dropped if they do not contain a full 8 byte UDP header, and ICMP packets are dropped if they do not contain 4 bytes of ICMP header, enough to specify the ICMP type, code, and checksum. These packets are simply logged as ``pullup failed'' since there may not be enough good data in the packet to produce a meaningful log entry." Cheers, Rob -- He lived in such a low room he could only eat pancakes. This is random quote 549 of 1254. Distance from the centre of the brewing universe [15200.8 km (8207.8 mi), 262.8 deg](Apparent) Rennerian Public Key fingerprint = 6219 33BD A37B 368D 29F5 19FB 945D C4D7 1F66 D9C5