John Regehr wrote:
> I'm writing a paper for the FREENIX track at USENIX about a tool for
> measuring scheduling behavior under different operating systems, and
> I've run across a performance anomaly that I'd like to explain.
>
> It's this: for threads created with Linuxthreads, FreeBSD has
> co
On Thu, 4 Apr 2002, Zwane Mwaikambo wrote:
> On Wed, 3 Apr 2002, John Regehr wrote:
>
> > > > Have you tried benchmarking process to process context switch times to see
> > > > if the results are similar?
> >
> > No, that's a good idea. My infrastructure isn't set up to support
> > processes, t
Ramkumar Chinchani wrote:
> ==> Terry Lambert <[EMAIL PROTECTED]>/7:01pm/Apr 3, 2002 <==
> [Ramkumar Chinchani wrote:
> [> The requirement is that I have a theoretical framework where no process
> [> trusts the other. So they watch (trace) each process.
> [
> [Sure.
> [
> [All you have to do is pa
Peter Wemm wrote:
> > You will need to modify nfs_realign() to take a waitflag,
+++
> > as propagated from nfsrv_rcv()... and then pass it through
*
> Terry, if you spent half of the time reading the code as s
> > Have you tried benchmarking process to process context switch times to see
> > if the results are similar?
No, that's a good idea. My infrastructure isn't set up to support
processes, though, so it'll take a little time.
> Also:
> You should run both linuxthreads binaries compile on linux
How does make such a distinction inside the kernel? Is it possible to
identify trace events in a trace and just ignore them?
-Ram
==> Terry Lambert <[EMAIL PROTECTED]>/7:01pm/Apr 3, 2002 <==
[Ramkumar Chinchani wrote:
[> The requirement is that I have a theoretical framework where no process
[
David Greenman wrote:
> >#16 0xc0152220 in tsleep ()
> >#17 0xc016abfe in m_clalloc_wait ()
> >#18 0xc01c8b14 in nfs_realign ()
> >#19 0xc01c9653 in nfsrv_rcv ()
> >#20 0xc01701d0 in sowakeup ()
> >#21 0xc01abd7c in udp_input ()
> >#22 0xc01a1bfb in ip_input ()
> >#23 0xc01a1c5b in ipintr ()
>
>
Whats the current limint on how many concurrent connections the main ftp
site can chew on?
Trying to size up some hardware..and Id like to use what ya you use there
as a guide.
To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe freebsd-hackers" in the body of the message
>Fatal trap 12: page fault while in kernel mode
>fault virtual address = 0x70
>#12 0xc014f61d in panic ()
>#13 0xc025c02f in trap_fatal ()
>#14 0xc025bcdd in trap_pfault ()
>#15 0xc025b883 in trap ()
>#16 0xc0152220 in tsleep ()
>#17 0xc016abfe in m_clalloc_wait ()
>#18 0xc01c8b14 in nfs_realign
Will Froning wrote:
> #12 0xc014f61d in panic ()
> #13 0xc025c02f in trap_fatal ()
> #14 0xc025bcdd in trap_pfault ()
> #15 0xc025b883 in trap ()
> #16 0xc0152220 in tsleep ()
> #17 0xc016abfe in m_clalloc_wait ()
The tsleep tried to reference a page that wasn't there. This
supposedly can't happ
Ramkumar Chinchani wrote:
> The requirement is that I have a theoretical framework where no process
> trusts the other. So they watch (trace) each process.
Sure.
All you have to do is patch the OS to lie to you about not
seeing trace events in a trace...
-- Terry
To Unsubscribe: send mail to [
Alfred Perlstein wrote:
> * Ian <[EMAIL PROTECTED]> [020403 17:01] wrote:
> > What I found instead was that each of the problems I had found had already
> > been PR'd and patches were submitted with the PRs, so the problems and the
> > fixes have just been sitting there going stale for months. In
In message: <[EMAIL PROTECTED]>
Poul-Henning Kamp <[EMAIL PROTECTED]> writes:
: In message <[EMAIL PROTECTED]>, "Kreider, Carl" write
: s:
: >
: >I am working on an embedded project running FreeBSD, and my driver
: >for our custom card needs to load an FPGA with code. I know I can
: >c
Ramkumar Chinchani wrote:
>
> Can two processes track each other through the proc file system then?
>
> I want a scenario where process P1 and P2 track each others execution.
>
> Is this possible at all?
By definition, doing this must result in infinite mutual
recursion, as process B traces p
Tony,
The Mac OS X port of SGE is done. It starts jobs
nicely,
and it runs as root. Instead of using the big "hack",
you can reuse the code in the Mac OS X port.
Mac OS X uses FreeBSD (and the mach u-kernel), so I
think
from the user-level, it looks much like FreeBSD.
You can get the diff from:
I have a 4.5-RELEASE-p2 box that is my Firewall/NAT/NFS server. As a
NFS client I have a RH7.2 linux box. When I do massive NFS writes to
my FBSD (from RH7.2 box), I get a panic. I've attached the info I got
from my debug kernel.
If there is more info you need, just ask (this is all the FBSD f
May be the jobs run, but somehow SGE can't get the status, so it says
it can't find the job??
BTW, I like SGE better than PBS, nice to hear that SGE is beening
ported to FreeBSD :-)
Rayson
--- Tony Maher <[EMAIL PROTECTED]> wrote:
> I did a quick 'hack' (with large axe) the routines dealing wit
if you consider that each process can only do damage with system calls,
what you REALLY want is to use ktrace (or the truss equivalent syscalls)
but why do you want the untrusted client to watch the watcher?
it seems that you must end up in an infinite loop because it will see it
doing the watchin
On Wed, Apr 03, 2002 at 10:44:17AM -0500, John Baldwin wrote:
> Or load the firmware using kldload or from the loader using a type string
> similar to the way we do MFS root filesystems.
Or similar to the ISP (Qlogic SCSI) firmware.
To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscrib
The requirement is that I have a theoretical framework where no process
trusts the other. So they watch (trace) each process.
-Ram
==> Julian Elischer <[EMAIL PROTECTED]>/5:09pm/Apr 3, 2002 <==
[but I'm confused..
[to trace a program you need to be gdb
[(or similar) why would one gdb gdb when
but I'm confused..
to trace a program you need to be gdb
(or similar) why would one gdb gdb when it's gdbing you?
Maybe you need to explain WHY rather than WHAT.
On Wed, 3 Apr 2002, Ramkumar Chinchani wrote:
>
> Track means to basically trace the execution and watch the events that
> occur w
Track means to basically trace the execution and watch the events that
occur without any interprocess communication.
-Ram
==> Julian Elischer <[EMAIL PROTECTED]>/4:59pm/Apr 3, 2002 <==
[that depends on what you mean by "track"
[
[
[On Wed, 3 Apr 2002, Ramkumar Chinchani wrote:
[
[>
[> Can two
* Ian <[EMAIL PROTECTED]> [020403 17:01] wrote:
>
> Could you (or someone) expand on this a bit more? "Bring up..." in what
> sense? On which mailing list(s)?
>
> I recently ran into minor-ish problems with some tools and figured I'd
> contribute by submitting PRs along with patches to fix the
>
> My suggestion is to have a look at the problem report database,
> see if you can solve or help some of them and then bring the
> fix or suggestion you've made up on the mailing lists.
>
> http://www.freebsd.org/cgi/query-pr-summary.cgi
>
> I would also make sure to follow this list (freebsd
that depends on what you mean by "track"
On Wed, 3 Apr 2002, Ramkumar Chinchani wrote:
>
> Can two processes track each other through the proc file system then?
>
> I want a scenario where process P1 and P2 track each others execution.
>
> Is this possible at all?
>
> Thanks.
>
> -Ram
To
Can two processes track each other through the proc file system then?
I want a scenario where process P1 and P2 track each others execution.
Is this possible at all?
Thanks.
-Ram
==> Tim J. Robbins <[EMAIL PROTECTED]>/9:55am/Apr 4, 2002 <==
[On Wed, Apr 03, 2002 at 06:20:13PM -0500, Ramkuma
On Wed, Apr 03, 2002 at 06:20:13PM -0500, Ramkumar Chinchani wrote:
> What are the pitfalls in two processes ptracing each other?
>
> Are there possibilities of deadlocks?
Yes.
http://www.freebsd.org/cgi/query-pr.cgi?pr=kern/29741
Last time I checked, both -STABLE and -CURRENT are affected by t
Hello,
> Someone also started the SGE port to FreeBSD (which
> means duplicated work), so you are interested, or if
> you want to be the maintainer of the ports (currently,
> we have FreeBSD, NetBSD, OpenBSD, Darwin/MacOSX),
> please contact me.
I started a port a few months ago and recently sta
What are the pitfalls in two processes ptracing each other?
Are there possibilities of deadlocks?
-Ram
To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe freebsd-hackers" in the body of the message
On Fri, Mar 29, 2002 at 09:21:03PM +0500, Ilia Chipitsine wrote:
> Dear Sirs,
>
> I'm currently implementing a program which will run thousands and
> thousands times. It uses regular expressions.
hi
Port: re2c-0.9.1
Path: /usr/ports/devel/re2c
Info: Compile regular expression to C (much f
http://rr.sans.org/firewall/IPSec_VPN.php
can someone add it to the "Press" page and whereever it might be useful?
(e.g. handbook or whatever)
To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe freebsd-hackers" in the body of the message
On Wed, 3 Apr 2002, Mike Silbersack wrote:
>
> On Wed, 3 Apr 2002, John Regehr wrote:
>
> > Anyway, I was speculating that the higher cost is either due to (1) a
> > failure, in FreeBSD, to avoid page table operations when switching
> > between threads in the same addres space, or (2) some ot
"Kreider, Carl" wrote:
> I am working on an embedded project running FreeBSD, and my driver
> for our custom card needs to load an FPGA with code. I know I can
> compile the code in as data, but for ease of development, I would
> rather fetch the FPGA code from a file. With a driver in kernel
> sp
* digital <[EMAIL PROTECTED]> [020403 09:15] wrote:
> Hi I'm from Serbia and I love most computers and programming.I am very
> familiar with FreeBSD operating system and I know to programme in
> language C, and if it is necessarirly I can learn C++.I would be very
> happy if I could help in som
On Wed, 3 Apr 2002, John Regehr wrote:
> Anyway, I was speculating that the higher cost is either due to (1) a
> failure, in FreeBSD, to avoid page table operations when switching
> between threads in the same addres space, or (2) some other kind of
> semantic mismatch between Linuxthreads and r
Hi all,
I'm writing a paper for the FREENIX track at USENIX about a tool for
measuring scheduling behavior under different operating systems, and
I've run across a performance anomaly that I'd like to explain.
It's this: for threads created with Linuxthreads, FreeBSD has
considerably slower cont
FreeBSD hackers and Beowulf users,
I am porting SGE (a software for the compute farms, or
the so-called batch systems) to *BSDs, and I am
wondering if someone can take over some of the ports.
I just started porting the code to *BSDs. Currently, I
can get the code compiled on *BSDs with "#ifdef BS
In message <[EMAIL PROTECTED]>, Josef Karthauser writes:
>We're not talking too high intervals here, probably the maximum timing
>speed is around 13k rpm, so that's still in the ms range of things.
>
>What I'd like to do is use the printer port to sample timing signals and
>to drive the fuel inje
generally the answer is "You can't do that"
BUT
you could make a loadable module with the firmware,
and load both the module and the driver before booting from
the boot blocks..
then you can unload the firmware module after booting
(or whenever)
On Wed, 3 Apr 2002, Kreider, Carl wrote:
>
>
Dear Expert Hackers,
I've been tasked with knocking up an engine management system. There
are two parts, one is going to be running on a pic chip embedded
processor on the motorbike, and the other is for tuning in the workshop
via a laptop. I'd really love to knock together the workshop part vi
On Wed, Apr 03, 2002 at 07:14:59PM +0200, digital wrote:
> Hi I'm from Serbia and I love most computers and programming.I am very
> familiar with FreeBSD operating system and I know to programme in
> language C, and if it is necessarirly I can learn C++.I would be very
> happy if I could help
On Thu, 4 Apr 2002, Semen A. Ustimenko wrote:
> crashump and any details are available, ask for them.
>
Sorry for not mentioning this first time, I though of the usual ``This
particular panic will have a delayed effect, so the trace probably isn't
the problem'' answer from Matt. But the trace m
Hi!
Here is what we have got once with 4.4-RELEASE:
vm_page_free: pindex(747), busy(0), PG_BUSY(1), hold(0)
panic: vm_page_free: freeing free page
crashump and any details are available, ask for them.
Bye!
To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe freebsd-hackers" in t
Hi I'm from Serbia and I love most computers and programming.I am very
familiar with FreeBSD operating system and I know to programme in
language C, and if it is necessarirly I can learn C++.I would be very
happy if I could help in some way in development of FreeBSD operating
system (maybe Soc
On 03-Apr-2002 Poul-Henning Kamp wrote:
> In message <[EMAIL PROTECTED]>, "Kreider, Carl"
> write
> s:
>>
>>I am working on an embedded project running FreeBSD, and my driver
>>for our custom card needs to load an FPGA with code. I know I can
>>compile the code in as data, but for ease of develop
On Wed, 3 Apr 2002, Kreider, Carl wrote:
> I am working on an embedded project running FreeBSD, and my driver
> for our custom card needs to load an FPGA with code. I know I can
> compile the code in as data, but for ease of development, I would
> rather fetch the FPGA code from a file. With a dri
In message <[EMAIL PROTECTED]>, "Kreider, Carl" write
s:
>
>I am working on an embedded project running FreeBSD, and my driver
>for our custom card needs to load an FPGA with code. I know I can
>compile the code in as data, but for ease of development, I would
>rather fetch the FPGA code from a fi
I am working on an embedded project running FreeBSD, and my driver
for our custom card needs to load an FPGA with code. I know I can
compile the code in as data, but for ease of development, I would
rather fetch the FPGA code from a file. With a driver in kernel
space. Really.
Can it be done? If
In which version will it be/ or is it possible to use ipv6 adressen for a jail?
regards,
oPr
To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe freebsd-hackers" in the body of the message
49 matches
Mail list logo
