requests for mbufs denied increasing

2006-05-31 Thread Alexandre Biancalana
Hi list, I've a NFS/FTP server used as backup server, receiving few connections with high volume of data (100GB/Day). During this period the "requests for mbufs denied (mbufs/clusters/mbuf+clusters)" of netstat -m is increasing constantly, now is: 151/404/555 mbufs in use (current/cache

Re: requests for mbufs denied increasing

2006-05-31 Thread Maxim Konovalov
On Wed, 31 May 2006, 10:29-0300, Alexandre Biancalana wrote: > Hi list, > >I've a NFS/FTP server used as backup server, receiving few > connections with high volume of data (100GB/Day). During this period > the "requests for mbufs denied (mbufs/clusters/mbuf+clusters)" of > netstat -m is incre

RE: requests for mbufs denied increasing

2006-05-31 Thread Peter Blok
This will indeed fix the false mbufs denied counts as part of the uma_reclaim and mb_reclaim functionality. If you still see mbuf denied counts after implementing this fix, it might be your problem. If the counts stay at 0 and your system still stops accepting network connections, you have a diffe

Re: requests for mbufs denied increasing

2006-05-31 Thread Alexandre Biancalana
Thanks for all replies ! After apply the patch, I must rebuild just the kernel... right ?! Regards, Alexandre Peter Blok wrote: This will indeed fix the false mbufs denied counts as part of the uma_reclaim and mb_reclaim functionality. If you still see mbuf denied counts after implementin

Re: requests for mbufs denied increasing

2006-05-31 Thread Maxim Konovalov
On Wed, 31 May 2006, 15:21-0300, Alexandre Biancalana wrote: > Thanks for all replies ! > > After apply the patch, I must rebuild just the kernel... right ?! Correct. -- Maxim Konovalov ___ freebsd-net@freebsd.org mailing list http://lists.freebsd.org

Question about netinet/ip.h

2006-05-31 Thread Emil Kondayan
Can someone tell me why "ip_hl" and "ip_v" are of type "u_int" when the structure is packed and they only fill a byte? And my second question:do these "#define ..." directives allocate space in the structure? struct ip { #if BYTE_ORDER == LITTLE_ENDIAN u_int ip_hl:4, /* header length */ ip_v:4;

Re: Question about netinet/ip.h

2006-05-31 Thread Rui Paulo
At Wed, 31 May 2006 21:57:03 -0700, Emil Kondayan wrote: > > Can someone tell me why "ip_hl" and "ip_v" are of type "u_int" when the > structure is packed and they only fill a byte? u_int means unsigned int and they only fill a byte because 4 + 4 = 8 bits (a byte) (I'm not going into the "Why is

Re: Question about netinet/ip.h

2006-05-31 Thread Charles Swiger
On Jun 1, 2006, at 12:57 AM, Emil Kondayan wrote: Can someone tell me why "ip_hl" and "ip_v" are of type "u_int" when the structure is packed and they only fill a byte? Well, that struct definition is relying on the compiler to squeeze the bitfields into the smallest space required. Some p

Re: Question about netinet/ip.h

2006-05-31 Thread Bruce Evans
On Wed, 31 May 2006, Emil Kondayan wrote: Can someone tell me why "ip_hl" and "ip_v" are of type "u_int" when the structure is packed and they only fill a byte? Because ip.h is mostly written in C (!= Gnu C) and bit-fields cannot have type u_char in C. From an old draft of C99 (n689.txt): %

performance graphs with netgraph

2006-05-31 Thread Iantcho Vassilev
Hello everyone, Does anyone knows how to implement(make graphs of the traffic) via the Netgraph framework? Maybe RRD? or something? ___ freebsd-net@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-net To unsubscribe, send any

Re: How to force full sync using pfsync?

2006-05-31 Thread David DeSimone
David DeSimone <[EMAIL PROTECTED]> wrote: > > When I reboot one of the cluster members, the state tables do > synchronize and populate with some of the same connection states, but > not all of them. I still have not figured out why this condition comes about. > In particular, long-lived, extant c

Trouble booting NFS root

2006-05-31 Thread lukem . freebsd
I'm trying to set up a small cluster of diskless boxes using FreeBSD 6.1. So Far, PXE loads pxeboot which loads the kernel. But the kernel stops in the middle of booting for no apparent reason. The last thing on the console is "Timecounters tick every 1.000 msec", which usually occurs just bef