tcpdump on a bridged interface without an
address assigned). If trafshow uses bpf that could be the cause
of the problem, likely.
cheers
luigi
--+-
Luigi RIZZO, [EMAIL PROTECTED] . ACIRI/ICSI (on leave from Univ. di
--+-
Luigi RIZZO, [EMAIL PROTECTED] . ACIRI/ICSI (on leave from Univ. di Pisa)
http://www.iet.unipi.it/~luigi/ . 1947 Center St, Berkeley CA 94704
Phone: (510) 666 2927
--+-
On Sat, 28
ne is used for scanning pty's).
cheers
luigi
--+-----
Luigi RIZZO, [EMAIL PROTECTED] . ACIRI/ICSI (on leave from Univ. di Pisa)
http://www.iet.unipi.it/~luigi/ . 1947 Center St, Berkeley CA 94704
Phone: (510
y their minor number ? But then
you cannot use the same name unless the entries are in different
directories. My suggestion was to use /dev/foo.00 /dev/foo.01 /dev/foo.02
and so on.
cheers
luigi
--+---------
Luigi RIZ
There seem to be a problem setting up bridge + ipfw using the fxp Intel Pro
100 cards. The problem doesn't exist on NE2000 cards. The same set of ipfw
rules and same configuration work on NE2000 cards. Does anybody know if there
is a problem with 100Mbit cards, the intel pro in particular or
The above doesn't explain why everything work under ne2000 cards but not intel
etherexpress pro 100. Same set of rules allow arp entries through ne2000 cards
but not intel. Also from /etc/rc.firewall that came with FreeBSD 4.2:
# If you're using 'options BRIDGE', uncomment the following line
ctl variables either.
Any hints ?
cheers
luigi
--+-
Luigi RIZZO, [EMAIL PROTECTED] . ACIRI/ICSI (on leave from Univ. di Pisa)
http://www.iet.unipi.it/~luigi/ . 1947 C
On Tuesday, 19 December 2000 at 16:01:52 -0800, David O'Brien wrote:
On Mon, Dec 18, 2000 at 01:11:12PM -0600, Jacques A. Vidrine wrote:
/* Case 1 */ /* Case 2 */
if (data) vs. free(data)
free(data);
Actually
Hello,
Some time a go I posted the same question to freebsd-questions, but uptill now
I didn't get an answer.
Currently I'm trying to move towards a statefull packet filter. When testing
without nat all seems to work fine. But when I added natd (as the first
rule) packets that were
Hey.
Did anybody suceed with fd1720 flopies ? I couldn't write any single
1720K image there.
you must fdformat /dev/fd0.1720 (check syntax) first, otherwise
the write fails when it hits the first sector (sec.19 track 0) which
is supposed to be there but is not
Note that almost surely you
On Fri, Dec 22, 2000 at 08:52:52AM -0800, Luigi Rizzo wrote:
Did anybody suceed with fd1720 flopies ? I couldn't write any single
1720K image there.
you must fdformat /dev/fd0.1720 (check syntax) first, otherwise
the write fails when it hits the first sector (sec.19 track 0) which
The Linux issue was actually more stupid than that; Linux won't run on a
CPU it doesn't recognise. FreeBSD will only refuse to run on a CPU it
recognises as incapable (since that is a much smaller set).
actually, back in 1.1.5 times, i had a kernel which did not have
cpu I586_CPU in the
Jesus Monroy Jr., i
am sure this will tell you something...
cheers
luigi
--+-
Luigi RIZZO, [EMAIL PROTECTED] . ACIRI/ICSI (on leave from Univ. di Pisa)
http://www.iet.unipi.it/~luigi/ . 1947 Center St
Note that almost surely you won't be able to boot from that disk.
Note also that if you have bad luck you can physically break the floppy drive
doing this :(
if so, that will also happen with the '1480' format, which uses the same
82 tracks. Fact is, any decent drive is not supposed to
I think this is a BIOS issue. I don't think any BIOS will let you
boot from arbitrarily-formatted floppies :)
the 1480 format works.
luigi
To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe freebsd-hackers" in the body of the message
On Sat, Jan 20, 2001 at 01:19:17PM -0800, Luigi Rizzo wrote:
I think this is a BIOS issue. I don't think any BIOS will let you
boot from arbitrarily-formatted floppies :)
the 1480 format works.
Have you got this working now - or was it the larger size that didn't
work?
1480
On Tue, Apr 06, 2004 at 08:26:00PM +0200, Jens Schweikhardt wrote:
Fellow hackers,
suppose you have a long list of files in a make variable V, exceeding
kern.argmax. This means there is no way you can write a rule where $(V)
is a command argument in any way shape or form. There is also no
On Wed, Jun 02, 2004 at 03:14:43PM -0700, Christian S.J. Peron wrote:
I understand what you are saying. The only real other choice
would be to copy out the entire cr_groups array. Do you know
if this copy would be more expensive then the mutex lock/unlock
associated with grabbing a
On Fri, Jun 11, 2004 at 04:07:40PM +0200, Jens Schweikhardt wrote:
On Thu, Jun 10, 2004 at 09:53:07PM -0500, Chip Norkus wrote:
...
# normalize the code a bit. In doing so I discovered a few deficencies in
# the stock FreeBSD (5.2-CURRENT) indent and decided to fix them, I
# thought these
On Fri, Jun 11, 2004 at 05:20:19PM +0200, Jens Schweikhardt wrote:
...
Sigh. A request for a little bit of QA and an emoticon as well and
I'm criticised. I remember when I was not yet a committer that the
better I could demonstrate that the code has no ill-effect the more
chances some
On Mon, Sep 06, 2004 at 12:52:49AM +0400, Gleb Smirnoff wrote:
Luigi,
I see that bridge callbacks are still living in if_ed.c
from FreeBSD 2.x times. See if_ed.c:2816. I think this is
not correct.
Bridge code is called from ether_input(), which is
indirectly called from if_ed.c:2836.
On Mon, Sep 06, 2004 at 03:01:00AM +0400, Gleb Smirnoff wrote:
...
L I'd rather not apply the patch unless you can show that
L the current code leads to incorrect behaviour.
I suspect that packets dropped by bridge_in() called from if_ed will
not be captured by bpf(4). This is incorrect.
if
On Sun, Sep 05, 2004 at 02:37:31PM -0700, Matthew Dillon wrote:
Well, wait a second... are we talking about a lot of packets being
discarded by the filter in 'normal' operation, or are we talking about
an attack? Because if we are takling about an attack the LAST ethernet
...
On Sat, Nov 06, 2004 at 11:21:23AM -0800, John-Mark Gurney wrote:
Devesh Shah wrote this message on Thu, Nov 04, 2004 at 15:22 -0800:
Based on the SYSINIT framework, I have made ULE scheduler as a loadable module but
have not quite
figured how to migrate from default 4bsd to newly loaded
hi,
i modified rc.diskless1 to use union fs like:
mount_md 1024 /conf/etc 0
mount -t union /conf/etc /etc
any reason why this might be problematic?
not sure, i think i tried this at some point and had problems with
bugs in the implementation of mount_union. If it works for you
--+-
Luigi RIZZO, [EMAIL PROTECTED] . ACIRI/ICSI (on leave from Univ. di Pisa)
http://www.iet.unipi.it/~luigi/ . 1947 Center St, Berkeley CA 94704
Phone: (510) 666 2927
Did you have opportunity to play with the soft interrupt
coalescing we discussed?
Did this message just leak to a mailing list, or would you
be able to expand this (or pass a pointer to mailing lists
where this was discussed) ?
thanks
luigi
I was able to remove a third of
there seems to be no problem with the chipset
in handling this ?
Bill, any comments ?
cheers
luigi
--+-
Luigi RIZZO, [EMAIL PROTECTED] . ACIRI/ICSI (on leave from Univ. di Pisa)
http://www.iet.unipi.it/~luigi
will
see the limitation in effect.
cheers
luigi
--+-
Luigi RIZZO, [EMAIL PROTECTED] . ACIRI/ICSI (on leave from Univ. di Pisa)
http://www.iet.unipi.it/~luigi/ . 1947 Center St, Berkeley CA 94704
Phone (510) 666
I probably missed some emails ?
In any case i was only concerned about the additional copy
done by m_devget when the controller can already DMA into
an mbuf, and there are no alignment constraints.
cheers
luigi
Andrew Gallatin wrote:
I disagree with this code; the elemenets
in fact one_pass does not work with bridging,
it might be as simple as changing one line in bridge.c
if (ip_fw_chk_ptr bdg_ipfw != 0 src != NULL) {
struct ip *ip ;
int i;
- if (rule != NULL) /* dummynet packet, already partially processed */
+ if (rule !=
Hi,
one problem you have to keep in mind with what you want to do
(and i am not talking about the implementation that you suggest,
just the delayed processing aspects) is that sometimes data passed
through modules have a limited lifetime and might have become stale
by the time the consumer is
--+-
Luigi RIZZO, [EMAIL PROTECTED] . ACIRI/ICSI (on leave from Univ. di Pisa)
http://www.iet.unipi.it/~luigi/ . 1947 Center St, Berkeley CA 94704
Phone: (510) 666 2927
--+-
To Unsubscribe: send mail to [EMAIL PROTECTED
), ../../conf/options);
and maybe more places like this.
Am I wrong ? And if not, is there any plan to make config
handle config files in other places than ${SYS}/${ARCH}/conf ?
cheers
luigi
--+-
Luigi RIZZO
On Thu, Oct 18, 2001 at 01:46:06PM -0400, Kenneth Wayne Culver wrote:
I was wondering if anyone had ever used altq to throttle people on an adsl
connection. Basically what I want to do make each user share bandwidth
evenly, but in such a way that they can use all the available bandwidth
--+-
Luigi RIZZO, [EMAIL PROTECTED] . ACIRI/ICSI (on leave from Univ. di Pisa)
http://www.iet.unipi.it/~luigi/ . 1947 Center St, Berkeley CA 94704
Phone: (510) 666 2927
/
they have a kernel version of Click for FreeBSD.
cheers
luigi
--+-
Luigi RIZZO, [EMAIL PROTECTED] . ACIRI/ICSI (on leave from Univ. di Pisa)
http://www.iet.unipi.it/~luigi/ . 1947 Center St, Berkeley CA
On Fri, Oct 26, 2001 at 10:22:48AM -0700, rick norman wrote:
Hi,
I seem to get inconsistent outputs from the same dummynet
stat query. Following is the output from two different queries :
bash-2.05$
bash-2.05$ ipfw pipe 3 show
3: unlimited0 ms 2048 B 0 queues (1 buckets)
On Tue, Oct 30, 2001 at 10:47:33AM -0800, rick norman wrote:
Hi,
I have enclosed a short piece of code that seems to
reproduce the problem after 5 to 10 minutes.
I am running 4.3 freebsd off the release cd's.
Pretty much the generic kernel except for the
addition of dummynet and ipfw. My
with
the routing code, not with dummynet, and it has to do with the
fact that you delete and reassign the address to the
loopback interface.
I am almost sure that 4.4 would cure the problem, because
that problem was fixed before 4.4.
cheers
luigi
Rick
Luigi Rizzo wrote:
On Tue
--+-
Luigi RIZZO, [EMAIL PROTECTED] . ACIRI/ICSI (on leave from Univ. di Pisa)
http://www.iet.unipi.it/~luigi/ . 1947 Center St, Berkeley CA 94704
Phone: (510) 666 2927
On Fri, Nov 30, 2001 at 02:11:00PM -0500, Leo Bicknell wrote:
...
* Many people use FreeBSD as a desktop OS. Think the same people
who use Win98, but only slightly smarter. These people are
'sysadmins' only in the sense that they have a root password.
When FreeBSD can't fill their DSL
On Fri, Nov 30, 2001 at 05:14:18PM -0500, Leo Bicknell wrote:
First off, apologies to Luigi, I was shooting off my mouth.
no problem, and no need for apologies :)
cheers
luigi
To Unsubscribe: send mail to [EMAIL PROTECTED]
with unsubscribe freebsd-hackers in the body of the
On Fri, Nov 30, 2001 at 05:19:18PM -0500, Mike Silbersack wrote:
On Fri, 30 Nov 2001, Leo Bicknell wrote:
* The logging at 90% usage should be investigated. I can probably
...
Luigi, Jonathan and I had already been discussing this idea before this
this thread even started. If you come
On Fri, Nov 30, 2001 at 08:39:05PM -0500, Leo Bicknell wrote:
On Fri, Nov 30, 2001 at 05:30:33PM -0800, Luigi Rizzo wrote:
I just committed to current (and soon to stable) some code to log
_failures_ in mbuf allocations, but that is only meant as an aid
to remove worse code in the drivers
On Sun, Dec 02, 2001 at 12:10:53AM -0800, Matthew Dillon wrote:
...
There are still a couple of unresolved issues. I noticed that when
connecting locally TCP is non-optimal... when sending a 4100 byte
data block it sends two 1460 byte packets (maxseg), then one
1176 byte
Hi,
while doing some timing measurements on our test boxes, i noticed
that if I compile a kernel with
options HZ=1000
I get a number of stray clock interrupts (i.e. occasionally a
clock interrupts comes way before its due time -- other measurements
showed that the two regular clock
On Mon, Dec 10, 2001 at 09:52:22AM -0800, Mike Smith wrote:
stick it there for you anyway. All PCI interrupts are shareable; you
can't ask for an unshared vector; you get the one you're given, and you
should be thankful for that much. Lots of people are going without these
days. 8(
On Sun, Dec 16, 2001 at 03:56:02AM +0300, .@babolo.ru wrote:
different results. btw, the if_dc driver is one of the drivers optimized for
the alpha (note the m_devget calls)..and can use a bit of tuning. my
this has been fixed recently in both stable and current.
luigi
To
Hi,
FreeBSD uses a single queue, but as long as you make sure that you
do not fill the queue with packets coming from a single interface,
you can still give some fairness to the system. Recent DEVICE_POLLING
code in -current (hopefully going into -stable at some point) does
exactly this -- an
also do
sorry, i forgot... have a look at http://www.iet.unipi.it/~luigi/polling/
cheers
luigi
cheers
s
Quoting Luigi Rizzo [EMAIL PROTECTED]:
Hi,
FreeBSD uses a single queue, but as long as you make
sure that you
do not fill the queue with packets coming from
Hi,
i need a bit of help from creative /bin/sh users...
I am writing a script to generate ipfw test cases, and as
part of the script i need to generate 'actions' which can be either
one or more, e.g.
a1=allow
a2=deny log
a3=pipe 10
Now, this works:
for act in $a1 $a2 $a3; do
hi,
i have the following questions:
* strange benchmark results! Given the description, I would expect
the |@ rsh and |@ ssh cases to give the same throughput, and
in any case | rsh to be faster than | ssh. How comes, instead,
that the times differ by an order of magnitude ? Can you
at 02:04:21PM +0300, Diomidis Spinellis wrote:
Luigi Rizzo wrote:
* strange benchmark results! Given the description, I would expect
the |@ rsh and |@ ssh cases to give the same throughput, and
in any case | rsh to be faster than | ssh. How comes, instead,
that the times differ
On Thu, Jul 24, 2003 at 10:36:41AM -0700, John-Mark Gurney wrote:
Diomidis Spinellis wrote this message on Thu, Jul 24, 2003 at 14:04 +0300:
separate command netpipe. Netpipe takes as arguments the originating
host, the socket port, the command to execute, and its arguments.
Netpipe
hi,
recently i have been bitten by a problem which might be already
known, but still...
quite a few apps (sendmail and ssh among them) seem to always
try an query if compiled with ipv6 support, and even if
the kernel does not support ipv6, tcpdump shows queries going out
to the
On Sat, Aug 02, 2003 at 09:59:18AM +0100, David Malone wrote:
On Fri, Aug 01, 2003 at 11:52:00PM -0700, Luigi Rizzo wrote:
My understanding is that there are multiple buggy components here:
my ISP's nameserver certainly shouldn't behave so badly on
requests, and the applications should
On Mon, Sep 22, 2003 at 08:07:13PM +0200, Uwe Klann wrote:
Hi All,
From the Log file IPFW:-
Sep 22 00:24:13 muc /kernel: ipfw: 3300 Accept TCP 217.10.213.30:4418
217.9.121.209:21 in via fxp0
How can I extend on FreeBSD 4.8 (ipfw2) the log contens to see the tranfered
data File and the
On Mon, Sep 22, 2003 at 02:43:40PM -0400, [EMAIL PROTECTED] wrote:
...
But now I noticed that my application is occassionally doing slower
iterations. Average iteration time used to be 0.2 ms without polling
enabled. With the device polling changes, the average time is still around
the same,
On Tue, Sep 23, 2003 at 12:28:07PM -0400, Matthew George wrote:
...
you can count the traffic with dynamic rules (but this does not go
to the logfile), not sure what you mean by 'see the transfered data file'
from ipf(5):
LOGGING
When a packet is logged, with either the log
on this is
appreciated.
Thanks,
-ansh
Original Message:
-
From: Mark Santcroos [EMAIL PROTECTED]
Date: Tue, 7 Oct 2003 19:16:14 +0200
To: [EMAIL PROTECTED]
Subject: Re: HZ = 1000 slows down application
On Mon, Sep 22, 2003 at 02:22:02PM -0700, Luigi Rizzo wrote
On Thu, Oct 16, 2003 at 11:17:50AM -0400, Michael Marchetti wrote:
Hi,
We have encountered a problem where the system hangs. We are running a 4.7
SMP kernel using kernel polling on a Dual Xeon with hyperthreading enabled
puzzled on what you mean by kernel polling ... DEVICE_POLLING,
if that
luigi
-Original Message-
From: Luigi Rizzo [mailto:[EMAIL PROTECTED]
Sent: Thursday, October 16, 2003 11:49 AM
To: Michael Marchetti
Cc: '[EMAIL PROTECTED]'; '[EMAIL PROTECTED]'
Subject: Re: hardclock interrupt deadlock
On Thu, Oct 16, 2003 at 11:17:50AM -0400, Michael Marchetti
Hi,
both -current and -stable have the following snippet of code in
sys/dev/syscons/syscons.c:scclose():
{
...
int s;
if (SC_VTY(dev) != SC_CONSOLECTL) {
...
s = spltty();
...
}
[Not sure what is the appropriate forum to discuss this, so
please redirect the discussion if you know where. I have Bcc-ed
a few /bin/sh committers]
I am trying to implement, in the most unintrusive way, something
resembliung associative arrays in /bin/sh. I am not interested in
syntactic
On Sun, Nov 30, 2003 at 06:53:10AM -, Antti Louko wrote:
Generally, I like the (Free)BSD way of doing things. But the IP
filtering modules available for FreeBSD lack one feature when compared
to Linux way (ipchains and iptables).
There is no call instruction by design in ipfw2. The reason
On Tue, Dec 23, 2003 at 03:17:12PM -0500, Leo Bicknell wrote:
...
I must not be clear on what in out recv and xmit mean, and
after reading the manual page 3 times I'm now even more confused.
The names are reasonably intuitive...
in matches packets on the INput path (basically,
On Wed, Dec 24, 2003 at 08:39:45AM -0500, Leo Bicknell wrote:
...
Now that I've used IPFW2 for something more complicated than simple
host filtering I see that the syntax and structure makes something
like a firewall/nat box for any moderately interesting config way
too complicated with way
On Sun, Jan 04, 2004 at 02:15:18AM +0700, Eugene Grosbein wrote:
Hi!
[EMAIL PROTECTED] wrote 8 years ago in src/lib/libc/gen/syslog.c:
p += sprintf(p, %.15s , ctime(now) + 4);
What is '+ 4' for?
quite likely it is to skip the 'day of week' field -- the ctime
manpage says
The
On Fri, Jan 23, 2004 at 06:09:20PM +0100, Andre Oppermann wrote:
...
send() for UDP should block if the socket is filled and the interface
can't drain the data fast enough.
It doesn't (at least I cannot make it block)
This stuff is rather complex. A send() on a UDP socket processes
On Sat, Jan 24, 2004 at 01:38:37PM -0500, Robert Watson wrote:
...
(2) Try the NDIS driver with the NDIS-u-lator on FreeBSD 5.x and see if
that also has the problem.
but going this way you have no idea on what the driver does,
including enabling hw checksums. This looks like a
useless test
On Sat, Jan 24, 2004 at 02:12:12PM -0500, Robert Watson wrote:
...
but going this way you have no idea on what the driver does, including
enabling hw checksums. This looks like a useless test at least for the
purpose of finding out what is going wrong
Actually, I'm more curious about
On Mon, Jan 26, 2004 at 10:53:54AM -0800, Julian Elischer wrote:
...
On Mon, 26 Jan 2004, Stuart Pook wrote:
On 23 Jan 2004, Don Lewis wrote:
the send does not give an error: the packet is just thrown away.
Which is the same result as you would get if the bottleneck is just one
hi,
browsing through the munmap() page, it says
Munmap() will fail if:
[EINVAL] The addr parameter was not page aligned, the len
...
now, i have verified that munmap works fine with any address returned
by mmap, even if not aligned, at least on a
On Wed, Mar 03, 2004 at 10:03:11AM -0500, Andrew Gallatin wrote:
Don Bowman writes:
I'm not sure what affect on fxp. fxp is inherently limited
by something internal to it, which prevents achieving
high packet rates. bge is the best chip, but doesn't
but you should not compare
On Wed, Mar 03, 2004 at 07:37:06AM +, Matt wrote:
Tried this on the ipfw list but didnt get any response.
Part of an app I am playing with needs to be able to add an ipfw
rule. I had though i got all of what i need from ipfw2.c and ip_fw.h
but I am painfully new to C and must be missing
reading also the continuation of this mail thread, I wonder if there
is any relationship with this issue i found a few days ago debugging
asterisk. It happens when linking the code with libc_r, but maybe
some of the bugs in libc_r were also imported in other thread
libraries.
cheers
I am afraid the existing code cannot help you.
The packets you see are encapsulated in 802.1q aka VLAN frames,
and since ipfw2 does not try to decapsulate the packets, you
don't get to see the IP headers.
Your most reasonable option would be to write a new ipufw2 opcode,
say something like
On Sat, Aug 13, 2005 at 12:49:56AM +0200, Jeremie Le Hen wrote:
Hi,
I am afraid the existing code cannot help you.
The packets you see are encapsulated in 802.1q aka VLAN frames,
and since ipfw2 does not try to decapsulate the packets, you
don't get to see the IP headers.
Your most
On Thu, Sep 15, 2005 at 06:45:27PM +0530, Pranav Peshwe wrote:
Hello,
Which is the I/O scheduler used by FBSD 5.4 ?
I googled in various ways but could not get an answer.
it is called FCFSUSIIABPIWCTTOIS, which stands for
First Come First Serve Unless Someone Is In A Better Position
On Thu, Sep 15, 2005 at 07:52:15PM +0530, Pranav Peshwe wrote:
...
Thank you very much for the name and the source
link.Is there any documentation available on this
topic(fbsd io schedulers) ?
Where is the io scheduler located in the
src code tree ?
see
On Mon, May 01, 2006 at 01:15:44PM +0300, Giorgos Keramidas wrote:
...
I'd certainly prefer it if the beep was turned *off* by default,
but I'm not sure if that's what everyone prefers. This is why I
opted for keeping the current behavior and making my personal
preference an option :)
i do
On Fri, Sep 06, 2002 at 11:59:05AM -0400, Dan Ellard wrote:
...
What's the gigabit ethernet NIC of choice these days? (I've had good
experiences with the NetGear G620T, but apparently this card is no
longer being sold.)
I'm looking for:
- Easy FreeBSD integration.
-
On Fri, Oct 11, 2002 at 12:46:36AM -0400, abe wrote:
...
Unfortunately, feedback sent while in good intentions did not help. However, in
further
tinkering with this issue I believe I've come to a conclusion. I run a rather
high-traffic
server so I had initially increased
from your patch i am a bit unclear, do you still depend on
having MD_ROOT_SIZE or you can get rid of it ?
cheers
luigi
On Fri, Oct 18, 2002 at 03:56:11PM -0700, David Yeske wrote:
I am writing an article about a replacement for write_mfs_in_kernel, and I wanted to
get some
On Fri, Oct 18, 2002 at 04:42:01PM -0700, David Yeske wrote:
MD_ROOT_SIZE is only needed for write_mfs_in_kernel. When write_mfs_in_kernel was
removed the
ok, sorry for the confusion, i misread the patch.
luigi
To Unsubscribe: send mail to [EMAIL PROTECTED]
with unsubscribe
known problem with watchdog handling on several network drivers
including the sis.
This has been fixed in some drivers (including the sis')
some time ago, surely in 4.7 and probably also in 4.6
cheers
luigi
On Fri, Oct 25, 2002 at 09:26:30AM +0100, Neil McGann wrote:
Hi All,
Strictly speaking it is not necessary to get rid of the ipintr()
code, it will just remain unused, so the relevant part of the patch is
the direct call of ip_input() instead of schednetisr().
This patch will not make any difference if you have device_polling
enabled, because polling already does
On Mon, Nov 18, 2002 at 05:12:56PM -0800, Terry Lambert wrote:
Luigi Rizzo wrote:
...
This patch will not make any difference if you have device_polling
enabled, because polling already does this -- queues a small number
of packets (default is max 5 per card) and calls ip_input on them
Very nice report, thanks :)
just wanted to mention that i am totally unrelated to the Torino
crew (at least, as far as i can tell... unless there was some
former student of mine!) and the credit for the cool stuff
they did is entirely to them.
cheers
luigi
On Tue, Nov 19, 2002
Hi,
I just got hit by a peculiar problem related to out-of-order
execution of instructions.
I was doing some low-level timing measurements using the rdtsc()
around selected pieces of code (the rdtsc() is included in
the TSTMP() functions that are in RELENG_4, source is in
sys/i386/isa/clock.c), as
thanks a lot for the pointer to CPUID
luigi
On Mon, Nov 25, 2002 at 05:15:06PM -0800, Nate Lawson wrote:
...
The Intel processor manual has an explicit example for this and recommends
you use cpuid as a serializing instruction before the call to rdtsc.
To Unsubscribe: send mail to
the diagnosis looks reasonable, though i do not remember changing
anything related to this between 4.6 and 4.7 so i wonder why the
error did not appear in earlier versions of the code.
icmp_error() consumes the mbuf so i believe it is ok to scramble it
but one should double check.
Note that
On Mon, Dec 16, 2002 at 11:10:42AM +0200, mika ruohotie wrote:
hello,
ipfw man page says:
buckets hash-table-size
Specifies the size of the hash table used for storing the various
queues. Default value is 64 controlled by the sysctl(8) variable
why don't you read the ipfw manpage, install IPFW2, and rewrite
the ruleset using ipfw2 features (specifically the new syntax to
specify address sets) and dynamic rules:
something like
hosts={4,6,44,52,12,99,130,21,244}
ports=22,25,80,443
allow proto tcp src-ip 1.2.3.${hosts}/24
On Fri, Mar 07, 2003 at 03:49:05PM -0600, Brandon D. Valentine wrote:
...
I have had good luck with the Adaptec Quartet 66 cards, under both Linux
and FreeBSD. YMMV, though. They come as 64-bit/66Mhz cards, which
...
controllers on it. Chances are if you really need a four-port card $300
is
On Wed, Mar 12, 2003 at 05:44:25PM +1100, Peter Jeremy wrote:
...
Are you sure you were generating wire speed packets - this is about
200,000 packets/sec at Fast speed. ping -f runs at whatever rate
148,800kpps
In order to get 200,000 pps, you're going to need 5-10 hosts
generating traffic,
(). With a high bandwidth-delay product, that chain
can get very long.
This topic came up on freebsd-net last July, and Luigi Rizzo provided
the following URL for a patch to cache the end of the mbuf chain, so
sbappend() stays O(1) instead of O(n).
the patch was only for UDP though. I think
it...
thanks
luigi
--+-
Luigi RIZZO, [EMAIL PROTECTED] . ICSI (on leave from Univ. di Pisa)
http://www.iet.unipi.it/~luigi/ . 1947 Center St, Berkeley CA 94704
Phone: (510) 666 2927
On Thu, Jan 31, 2002 at 05:33:28PM +, Mike Silbersack wrote:
On Thu, 31 Jan 2002, Storms of Perfection wrote:
I'm going to benchmark different network senarious with different options
to see what I can get, and what works best. If someone wants to help me
out, I could maybe write
101 - 200 of 331 matches
Mail list logo
