On Fri, Mar 23, 2001 at 03:03:28PM +0800, David Xu wrote:
> Linux 2.2 is known slow at TCP/IP throughput,
> but did you test Linux 2.4? it is very different.
> while Linux and FreeBSD are being improved, some guys here
> are still comparing FreeBSD with Linux 2.2, it's unfair, useless
> and wast
On Thu, Mar 22, 2001 at 09:45:12PM +0100, Peter Blok wrote:
> Hi,
>
> I'm having a strange problem. I have a block public ip addresses at
> X.Y.Z.128/28. My FreeBSD 4.3-BETA system has assigned IP address X.Y.Z.140
> netmask 255.255.255.240, broadcast X.Y.Z.143.
>
> I don't use routed. I have on
David Xu wrote:
>
> Linux 2.2 is known slow at TCP/IP throughput,
> but did you test Linux 2.4? it is very different.
> while Linux and FreeBSD are being improved, some guys here
> are still comparing FreeBSD with Linux 2.2, it's unfair, useless
> and waste time. please stop doing such a stupid
ALC> Yes, we do. In fact, the difference between FreeBSD and Linux is
ALC> greater
ALC> than 2x. On equivalent processors, we demonstrated 1900 polygraph
ALC> req/sec
ALC> on FreeBSD 4.2 and 720 polygraph req/sec on a 2.2.14 Linux kernel. It's
ALC> also worth mentioning that the response time
On Thu, Mar 22, 2001 at 11:43:33AM -0500, Garrett Wollman wrote:
> <
>said:
> > RTM_LOSING: Kernel Suspects Partitioning: len 124, pid: 0, seq 0, errno 0,
>flags:
> > locks: inits:
> > sockaddrs:
> > ftp.de.cw.net 62.236.255.201
>
> This is perfectly natural. TCP will generate these message
> Note that iMimic claims to run on a standard FreeBSD platform, which
> would also imply they use kqueue; this alone can probably provide the
> 2x performance boost you see on polygraph.
Yes, we do. In fact, the difference between FreeBSD and Linux is
greater
than 2x. On equivalent processors,
Jonathan Graehl wrote:
>
> Interesting topic in the linux kernel mailing list (Linux is "a lot" faster than
> FreeBSD):
> http://kt.zork.net/kernel-traffic/latest.html#2
>
> I came to use FreeBSD from Linux for servers because of kqueue. I stayed
> because I liked the entire system. I'm sure t
On Thu, 22 Mar 2001, Jonathan Lemon wrote:
> Yeah, I read this; it basically ended with the author of the GigE card
> making unsubstantiated claims that Linux is "much" faster than FreeBSD.
>
> Without more solid information, this is basically FUD. I'm sure that
> by picking the appropriate ben
> I'm connected through cable to the 'Net, and the provider I go
> through, it appears, somehow has it setup that if I change nics, I hvae a
> bugger of a time re-acquiring a lease ...
I presume dhclient is what you use to get your IP address.
I've seen ISPs that record the MAC address of the in
Hello Jonathan,
Friday, March 23, 2001, 3:12:19 AM, you wrote:
JG> Interesting topic in the linux kernel mailing list (Linux is "a lot" faster than
JG> FreeBSD):
JG> http://kt.zork.net/kernel-traffic/latest.html#2
JG> I came to use FreeBSD from Linux for servers because of kqueue. I stayed
JG>
Morning ...
I'm connected through cable to the 'Net, and the provider I go
through, it appears, somehow has it setup that if I change nics, I hvae a
bugger of a time re-acquiring a lease ...
a tcpdump of the interface, shows:
Script started on Thu Mar 22 15:21:54 2001
You have
< said:
> /kernel: arplookup A.B.C.D failed: host is not on local network
> /kernel: arpresolve: can't allocate llinfo A.B.C.Drt
Show us the output of `route -nv get A.B.C.D'.
-GAWollman
To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe freebsd-net" in the body of the message
Why is routing done via the ::1 and 127.0.0.1 network addresses? I notice
for "normal" interfaces it is bound directly to "link#2" and such.
I realize I don't really know what I am talking about here, but, it
seems that binding it to the link is more efficient than having it go
through the loop
Hi,
I'm having a strange problem. I have a block public ip addresses at
X.Y.Z.128/28. My FreeBSD 4.3-BETA system has assigned IP address X.Y.Z.140
netmask 255.255.255.240, broadcast X.Y.Z.143.
I don't use routed. I have one static host route to a particular host.
Here's the problem when somebod
-On [20010322 21:08], Hajimu UMEMOTO ([EMAIL PROTECTED]) wrote:
>Since routing info to ::1 is allocated in IPv6 case, I think it should
>be alloacated to 127.0.0.1 also in IPv4 case.
Seems to make sense, since a lot of the tunnels will be IPv4 ones as
well.
--
Jeroen Ruigrok van der
>>>>> On Thu, 22 Mar 2001 11:17:58 +0100
>>>>> Jeroen Ruigrok/Asmodai <[EMAIL PROTECTED]> said:
asmodai> [This question is more appropriate for -net IMHO]
asmodai> -On [20010322 03:00], David E. Cross ([EMAIL PROTECTED]) wrote:
>I recently tried
In article <[EMAIL PROTECTED]> you write:
>Interesting topic in the linux kernel mailing list (Linux is "a lot"
>faster than
>FreeBSD):
>http://kt.zork.net/kernel-traffic/latest.html#2
Yeah, I read this; it basically ended with the author of the GigE card
making unsubstantiated claims that Linux
* Jonathan Graehl <[EMAIL PROTECTED]> [010322 11:13] wrote:
> Interesting topic in the linux kernel mailing list (Linux is "a lot" faster than
> FreeBSD):
> http://kt.zork.net/kernel-traffic/latest.html#2
>
> I came to use FreeBSD from Linux for servers because of kqueue. I stayed
> because I li
Interesting topic in the linux kernel mailing list (Linux is "a lot" faster than
FreeBSD):
http://kt.zork.net/kernel-traffic/latest.html#2
I came to use FreeBSD from Linux for servers because of kqueue. I stayed
because I liked the entire system. I'm sure that Linux does TCP processing as
fast
< said:
> RTM_LOSING: Kernel Suspects Partitioning: len 124, pid: 0, seq 0, errno 0,
>flags:
> locks: inits:
> sockaddrs:
> ftp.de.cw.net 62.236.255.201
This is perfectly natural. TCP will generate these messages whenever
its retransmission timer goes off; they should correlate with packet
Jean-Christophe Varaillon wrote:
You have to get non empty netstat.
Try to compile it from /usr/src or get from ftp.freebsd.org
>
> On Thu, 22 Mar 2001, Dmitry Samersoff wrote:
>
> > Jean-Christophe Varaillon wrote:
> > >
> > > Hi,
> > >
> > > The netstat command is not working any more on m
On Thu, 22 Mar 2001, Ruslan Ermilov wrote:
> I wrote:
> >
> > Unless someone has a good motivation for not doing this, I am going
> > to commit the attached patch that disallows indirect routes with
> > indirect gateways.
> >
> Okay, I will rephrase this. Can you give me at least one example w
On Thu, 22 Mar 2001, Dmitry Samersoff wrote:
> Jean-Christophe Varaillon wrote:
> >
> > Hi,
> >
> > The netstat command is not working any more on my machine:
> >
> > ---
> > % ls -l /bin/netstat
> > -rwxr-xr-x 1 root wheel 0 Mar 16 14:08 /bin/netstat
>
> Try to use /usr/bin/netstat
>
Jean-Christophe Varaillon wrote:
>
> Hi,
>
> The netstat command is not working any more on my machine:
>
> ---
> % ls -l /bin/netstat
> -rwxr-xr-x 1 root wheel 0 Mar 16 14:08 /bin/netstat
Try to use /usr/bin/netstat
(or any other one having not zero size ;-)) )
# ls -l /usr/bin/net
I recently tried (for the first time) to get gif running under FreeBSD
4.3-BETA (cvsup-ed yesterday). I noticed the following:
gifconfig gif0 inet 10.1.1.1 10.1.2.1
ifconfig gif0 192.168.1.1 192.168.1.2 netmask 0xff00
and then I 'ping 192.168.1.1' it will try to route the packet instead of
Hi,
The netstat command is not working any more on my machine:
---
% ls -l /bin/netstat
-rwxr-xr-x 1 root wheel 0 Mar 16 14:08 /bin/netstat
%
---
How can I make it working ?
Thanks,
Jean-Christophe.
To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe freebsd-net" in the body
I'm gettin these error messages on `route monitor` when trying to ftp/cvsup/eg. to
other hosts from my box
got message of size 124 on Thu Mar 22 10:24:12 2001
RTM_LOSING: Kernel Suspects Partitioning: len 124, pid: 0, seq 0, errno 0,
flags:
locks: inits:
sockaddrs:
ftp.de.cw.net 62.236.255.
[This question is more appropriate for -net IMHO]
-On [20010322 03:00], David E. Cross ([EMAIL PROTECTED]) wrote:
>I recently tried (for the first time) to get gif running under FreeBSD
>4.3-BETA (cvsup-ed yesterday). I noticed the following:
>
>gifconfig gif0 inet 10.1.1.1 10.1.2
I have server under FreeBSD 4.2 with apache fired simple C++ CGI for
each connection.
Aproximately every 12H uptime server stop responding.
Kernel answers to ping, establish TCP connection but no process forking.
This is statisitics (netstat -nm & top ) immediately before crash.
Any ideas?
T
29 matches
Mail list logo