At 05:53 AM 23/05/2006, Daniel O'Connor wrote:
On Saturday 13 May 2006 22:00, Holger Kipp wrote:
If you encounter silo overflows, you might need to increase
cp4ticks in sio.c, eg
- cp4ticks = speed / 10 / hz * 4;
+ cp4ticks = speed / 10 / hz * 40;
and/or you might want to change hz from
Any chance someone could look at
http://www.freebsd.org/cgi/query-pr.cgi?pr=86598
for the next release of 6.2 ?
---Mike
Mike Tancsa, tel +1 519 651 3400
Sentex Communications
At 07:55 AM 26/06/2006, Marc G. Fournier wrote:
For the server that I'm fighting with right now, where Dmitry
pointed out that it looks like a deadlock issue ... I have
dumpdev/savecore enabled, is there some way of forcing it to panic
when I know I actually have the deadlock, so that it will
At 01:20 PM 08/07/2006, Ruslan Ermilov wrote:
Ah, I see. Thanks for the insight.
How about the attached patch?
I've been working on this problem for Mike Tancsa about a year ago,
and my fix was naive. I ended up not committing it because I found
that it broke something else, but I don't
At 12:06 AM 10/07/2006, User Freebsd wrote:
Not sure what STP is
Spanning Tree Protocol. Having the link go up and down would cause
the switch port to block traffic for a period of time.
---Mike
___
freebsd-stable@freebsd.org mailing
At 03:09 AM 10/07/2006, Patrick M. Hausen wrote:
Of course, any reasonable administrator would configure
interface FastEthernet0/1
spanning-tree portfast
for all ports connected to hosts. (shown syntax is Cisco's).
Yes, its great if you have access to the cisco... Not always
At 04:55 PM 10/07/2006, User Freebsd wrote:
'k, I know nothing about Cisco but do have access to change my
configs (knowing nothing tends to keep me from doing too much
playing) ... what does the above do, exactly?
Spanning tree is there to prevent switch loops as well as allow for
At 03:02 PM 14/07/2006, Miroslav Lachman wrote:
After reboot (command reboot), system boot up with both disks
attached and start autosynchronization. I do not know, if this is hw
or sw error, I got
Install the smartmontools from
/usr/ports/sysutils/smartmontools/
and post the output of
At 05:59 AM 17/07/2006, Johan Ström wrote:
On 17 jul 2006, at 00.53, Mike Tancsa wrote:
At 03:02 PM 14/07/2006, Miroslav Lachman wrote:
After reboot (command reboot), system boot up with both disks
attached and start autosynchronization. I do not know, if this is
hw or sw error, I got
At 11:02 AM 17/07/2006, Johan Ström wrote:
On 17 jul 2006, at 16.51, Mike Tancsa wrote:
This at least rules out the disks being bad for the most part. It
still could be bad cables, but if you changed those out than its
doubtful. Perhaps try updating to RELENG_6 ? If its a gmirror
issue, I
At 07:13 AM 30/07/2006, Nikolas Britton wrote:
On 7/29/06, Nikolas Britton [EMAIL PROTECTED] wrote:
Anyone know why the giant is in arcmsr(4) or how to kill him?
I did some work on the arcmsr(4) driver:
http://www.freebsd.org/cgi/query-pr.cgi?pr=101045
Is not the driver from the Areca
At 06:45 AM 14/08/2006, Gleb Smirnoff wrote:
The patch for RELENG_6 is available here:
http://people.freebsd.org/~glebius/em-RELENG_6.patch
Currently there is also a known problem - a race condition,
that occurs on SMP triggering a fake watchdog event, that
leads to unwanted NIC reset.
Hi,
At 10:15 AM 9/12/2006, Karl Denninger wrote:
On Tue, Sep 12, 2006 at 09:06:15AM +0200, Bj?rn K?nig wrote:
Karl Denninger schrieb:
This is not cool folks.
I think you misunderstood what -STABLE means. (Or maybe I do?)
-STABLE is still a development branch without guarantee of a stable and
At 01:27 PM 9/13/2006, Robert Watson wrote:
The other common optimization advice that you may already have
received is to check which time counter FreeBSD has selected. Right
now, 6.x/7.x err on the side of accurate over fast. There's been
quite a bit of debate about this approach, and it's
At 10:20 PM 9/13/2006, David Myers wrote:
Sep 5 11:55:12 ronald kernel: em0: watchdog timeout -- resetting
I got a bazillion of these, and a completely unusable machine, when
I upgraded to 6.1-stable sources as of two days ago. The machine
would simply freeze for minutes at a time.
At 10:22 AM 9/22/2006, Václav Haisman wrote:
The problme was on the server, it had my address restricted in firewall.
I managed to make the tunnel. And I could ping the 192.168.23.1 address
from mine 192.168.23.4. I had to restart the serivce because I did some
changes to the OpenVPN client
At 09:25 AM 9/27/2006, Patrick M. Hausen wrote:
Hi!
On Wed, Sep 27, 2006 at 02:42:30PM +0200, Philippe Pegon wrote:
it's just a me too. On our ftp server (ftp8.fr.freebsd.org), sometimes
we see some watchdog timeout in the log with a bge card, but maybe it's
not the same problem... :
As
At 12:32 PM 9/27/2006, Scott Long wrote:
My theory here is that something in the kernel, likely VM/VFS, is
holding the Giant lock for an inordinate amount of time. During this
time, an interrupt fires on the shared em/ichsmb interrupt. The em
Hi Scott,
Do you think this issue is
At 03:15 PM 9/28/2006, O. Hartmann wrote:
/usr/src/sys/dev/usb/usb.c:282: error: for each function it appears in.)
/usr/src/sys/dev/usb/usb.c: At top level:
/usr/src/sys/dev/usb/usb.c:863: warning: 'usb_intr_task' defined but not used
*** Error code 1
Are you sure the patch applied cleanly
At 03:53 PM 10/2/2006, John Baldwin wrote:
The patch below fixes various nits (mostly adding locking) in most of the
smbus controller drivers we have in the tree. It should apply to both HEAD
and RELENG_6 with the exception that the intpm(4) driver will require the
style fixes to be applied to
At 12:27 PM 10/4/2006, Bill Moran wrote:
In response to Bill Moran [EMAIL PROTECTED]:
In my case, it's a bce driver that's doing it. I also have some em
cards in this machine that I can test if the information will be
helpful.
Note that I can _not_ reproduce the problem with an em
At 11:19 AM 10/5/2006, Karl Denninger wrote:
So what do I buy to replace this thing? Well, looking at the serial
hardware claimed supported, I seem to have a problem finding anything I can
actually purchase! I don't need real high performance - a 16550 based
multiport card is fine. I also
At 08:09 PM 10/5/2006, Karl Denninger wrote:
ugen0: American Power Conversion Smart-UPS 750 FW:651.12.D USB
FW:4.2, rev 1.10/0.06, addr 2
Does apcupsd connect to it? I tried this back on 5.x and it failed
miserably. It identified the unit, but wouldn't talk to it.
I literally have 150+
At 09:49 PM 10/5/2006, Karl Denninger wrote:
What's your config like? I hooked the USB back up and it identified, but
when I told it to use USB and specified the device
I think it says in the docs not to specify the device.
, it panics (the software,
not the machine) with a complaint about
about DIVING!
http://genesis3.blogspot.comMusings Of A Sentient Mind
On Thu, Oct 05, 2006 at 08:35:32PM -0400, Mike Tancsa wrote:
At 08:09 PM 10/5/2006, Karl Denninger wrote:
ugen0: American Power Conversion Smart-UPS 750 FW:651.12.D USB
FW:4.2, rev 1.10/0.06, addr 2
Does apcupsd connect
At 01:53 PM 10/6/2006, Karl Denninger wrote:
Now, where the problem comes in is that THIS line doesn't reference an
attached port. That sucks, but might not be hard to fix:
If there is just one USB *serial* device, it will always be
/dev/ttyU0. It doesnt matter if you have 1 or 3 other USB
At 07:10 PM 10/9/2006, JoaoBR wrote:
if you are using a pci express 1x NIC could you please so kind to confirm
which brand/model is working fine for you?
I use both the Intel (Pro1000/PT) and Broadcom (HP brand Broadcom
5751) of PCIe 1x cards.
---Mike
At 11:48 AM 10/10/2006, othermark wrote:
uart0: 16550 or compatible on puc0
uart0: [FAST]
uart1: 16550 or compatible on puc0
BTW, why use uart instead of sio ?
---Mike
___
freebsd-stable@freebsd.org mailing list
At 11:37 AM 10/12/2006, Oliver Fromme wrote:
Matthieu Michaud wrote:
I rent a small server based on a VIA C7 on which I installed a
6.2-PRERELEASE as of today (see dmesg and kernconf attached). It runs
fairly well but I wonder if it couldn't be faster.
According to padlock(4) man page,
At 05:00 PM 10/12/2006, Albert Shih wrote:
The server have all NIC in polling mode because without this flag the NIC
disapear (em0 watchdog etc...)
Today the only solution I've found is ... reboot the server :-(
I would try and disable polling and then try the patch in
At 10:34 PM 10/5/2006, Kris Kennaway wrote:
Based on successful testing on a machine with shared em interrupt, the
following patch should work around the problem *in that case*.
Note that this patch will not help you if you are not using the em
driver, or if you are seeing the problem with
At 12:31 AM 10/14/2006, Scott Long wrote:
Mike,
I have a new patch that I hope addresses the actual bug, instead of
shuffling the timing. Would you be willing to test it? I can't
guarantee that it's safe for production use yet, though. It seems
to work, but it might set your dog on fire
At 08:09 AM 10/14/2006, Balgansuren Batsukh wrote:
Hello,
I installed FreeBSD-6.1 on my home PC. After sometime frequently get
em0 UP/DOWN message.
There is a patch you can try that might help you at
http://lists.freebsd.org/pipermail/freebsd-stable/2006-October/029224.html
---Mike
At 10:32 AM 10/14/2006, Scott Long wrote:
Mike Tancsa wrote:
At 08:09 AM 10/14/2006, Balgansuren Batsukh wrote:
Hello,
I installed FreeBSD-6.1 on my home PC. After sometime frequently
get em0 UP/DOWN message.
There is a patch you can try that might help you at
http://lists.freebsd.org
At 07:52 PM 08/07/2005, Marcin wrote:
I've seen posts about this issue on current@, but without any solution.
Maybe my case will help to shed some light on this one.
2 Cpu 5.4 STABLE (from today 09.07.05) running without any problems.
The kernel is almost a GENERIC, except:
Enabled:
SMP
At 05:04 PM 11/07/2005, Robert Watson wrote:
As a further FYI, a variety of debugging features are still enabled by
default in RELENG_6, including INVARINTS, WITNESS, and user space malloc
debugging. These will remain enabled through the first snapshot from the
Apart from the kernel
At 09:23 AM 21/07/2005, Joao Barros wrote:
John started debugging this with another person with similar problems
on 5 and the debugging never got to 6 (no feedback from the other
person):
http://lists.freebsd.org/pipermail/freebsd-current/2005-July/052727.html
Yes, The other person is me :)
At 09:23 AM 21/07/2005, Joao Barros wrote:
On 7/21/05, Robert Watson [EMAIL PROTECTED] wrote:
On Thu, 21 Jul 2005, Joao Barros wrote:
I was hopping for you to mention user's feedback. I started this thread
http://lists.freebsd.org/pipermail/freebsd-current/2005-July/052288.html
There
At 03:20 PM 21/07/2005, Eli K. Breen wrote:
All,
Does anyone have a good handle on how to replicate (read: image) a freebsd
machine from one machine to an ostensibly similar machine?
So far I've used countless variations and combinations of the following:
dd (Slow, not usefull
At 03:26 PM 21/07/2005, Karl Denninger wrote:
Ok, Robert, but then here's the question
How come the ATA code which was very stable in 4.x was screwed with in a
production release, breaking it, with no path backwards to the working
code?
I understand your frustration, but others would
At 12:00 AM 24/07/2005, Karl Denninger wrote:
Finally, any pointers on a 2 port PCI SATA board that (1) is KNOWN to
work, (2) has EXTERNAL SATA connections, and (3) isn't one of those
whiz-bang all-in-one-RAID thingies that costs $500?
3ware makes an excellent 2 port SATA card (8000 series)
At 04:22 PM 21/07/2005, Karl Denninger wrote:
ATA-NG (Soren's new code) is not (from what I understand) in the 5.x
codebase.
No, but its quite different from what was in 4.x.
My understanding is that the 5.x code is a half-baked version of ATA-NG,
and IMHO it had no business going into a
!
http://genesis3.blogspot.comMusings Of A Sentient Mind
On Sun, Jul 24, 2005 at 12:06:16PM +0100, Robert Watson wrote:
On Sun, 24 Jul 2005, Mike Tancsa wrote:
At 12:00 AM 24/07/2005, Karl Denninger wrote:
Finally, any pointers on a 2 port PCI SATA board that (1) is KNOWN to
work, (2) has
At 02:13 PM 24/07/2005, Karl Denninger wrote:
On Sun, Jul 24, 2005 at 07:58:20PM +0200, Erik Trulsson wrote:
Most likely the bug you have run into is difficult or impossible to
reproduce on other hardware than the particular combination you are using.
FWIW my earlier post about it appearing
At 09:19 AM 26/07/2005, Chris Howells wrote:
Thanks, I've tried measuring that using a multimeter. The 12v rail
measures at about 12.6v, but the 5v line is only 4.9v. Is this likely to
cause problems? The PSU is a brand new 450W Antec. The same PSU in a very
similar system measures similar
At 09:35 AM 26/07/2005, Holger Kipp wrote:
Hello,
I have trouble setting sysctl-values via loader.conf
on my 5.4-STABLE from 25.06.2005.
This is my /boot/loader.conf:
--- 8 -- snip ---
# settings for xine
kern.ipc.shmmax=67108864
kern.ipc.shmall=32768
# load sound module
At 09:47 AM 26/07/2005, Chris Howells wrote:
On Tue, July 26, 2005 2:23 pm, Mike Tancsa said:
If possible, try the version of the em driver that is in RELENG_6 or
CURRENT. Not sure why the intel people didnt MFC it, but it supposedly
has
a number of bug fixes.
That driver seems to have
At 11:22 AM 28/07/2005, Karl Denninger wrote:
Got a 3Ware controller.
6.0-Beta1 is now stable with gmirror.
Just curious, why use gmirror with a 3ware ? Why not just use the native
RAID features of the card ? They work very well.
---Mike
At 04:19 PM 28/07/2005, Karl Denninger wrote:
Is there a control program for the twe driver devices, and/or an option
somewhere I'm missing? I've looked around and in the man pages, and found
nothing thus far. Or is hot plug/unplug simply not supported with this
board/driver set?
Yes, look
At 06:45 PM 28/07/2005, Karl Denninger wrote:
On Thu, Jul 28, 2005 at 05:42:50PM -0500, Karl Denninger wrote:
On Thu, Jul 28, 2005 at 04:31:40PM -0400, Mike Tancsa wrote:
At 04:19 PM 28/07/2005, Karl Denninger wrote:
Is there a control program for the twe driver devices, and/or an
option
At 08:25 PM 08/08/2005, O. Hartmann wrote:
Hello.
My box is a FreeBSD 6.0-BETA2 driven ASUS A8N-SLI Deluxe based AMD64 boxed
(see dmesg).
One of my SATA disks, the SAMSUNG SP2004C seems to show errors during
operation (and also showd under 5.4-RELEASE-p3).
Sometimes I get this error:
ad10:
At 10:46 PM 09/08/2005, Matthias Buelow wrote:
Karl Denninger wrote:
SII chipsets were ok in 4.x, but the newer ATA code broke badly with them.
I've had a PR open on this since February, and many others have reported
similar issues. The problems still exist in the 6.x-BETA releases I've
At 09:31 AM 10/08/2005, Karl Denninger wrote:
Also, I've yet to see a developer commit on the list that they WILL fix it if
such a controller board is forthcoming (and will return the board when
they're
done) - I've got two of these cards here (choose between Adaptec and Bustek)
and would be
At 12:10 PM 16/08/2005, Mark Kane wrote:
However, note that if I turn the drives speed down to UDMA100, the
errors seem to go away. Has anyone else tried this for their problems?
Yes, I have had Maxtor drives in the past where they would not work
properly at certain bus speeds-- even back in
At 12:56 PM 22/08/2005, Colin Farley wrote:
I have made this change on the switch my virtual machines are connected to.
We use HP PorCurve switches, unfortunately the switch needs to be rebooted
for the change to take effect, I will have to do this late tonight. I will
let you know the outcome.
Mike Tancsa, tel +1 519 651 3400
Sentex Communications,[EMAIL PROTECTED]
Providing Internet since 1994www.sentex.net
Cambridge, Ontario Canada
At 04:33 PM 22/08/2005, Søren Schmidt wrote:
On 22/08/2005, at 22:24, Mike Tancsa wrote:
I updated one of our boxes from RELENG_5 to 6. Couple of things I
noticed was that the smartmontools and atacontrol seems to be
broken now. I updated smartmon to the latest in the ports, but same
At 04:45 PM 22/08/2005, Kevin Oberman wrote:
The arguments for atacontrol have changed. The update to the man pages
was committed to current in the past day or two. I'm not sure it it has
made it to RELENG_6.
You can't just specify the channel number any more. The channel is now
the device
At 04:54 PM 22/08/2005, damir bikmuhametov wrote:
On Mon, Aug 22, 2005 at 04:24:12PM -0400, Mike Tancsa wrote:
I updated one of our boxes from RELENG_5 to 6. Couple of things I
noticed was that the smartmontools and atacontrol seems to be broken
now.
[...]
[verify1] /usr/ports/sysutils
At 05:05 PM 22/08/2005, Simon L. Nielsen wrote:
On 2005.08.22 16:24:12 -0400, Mike Tancsa wrote:
[verify1] /usr/ports/sysutils/smartmontools# smartctl -a ad0
smartctl version 5.33 [i386-portbld-freebsd6.0] Copyright (C) 2002-4
Bruce Allen
Home page is http://smartmontools.sourceforge.net
: / was not properly dismounted
em0: link state changed to UP
ichwd module loaded
ichwd0: Intel 82801EB/ER watchdog timer on motherboard
Mike Tancsa, tel +1 519 651 3400
Sentex Communications
+0x2c3
fork_exit(c079232c,0,cc9aad38) at fork_exit+0xa0
fork_trampoline() at fork_trampoline+0x8
--- trap 0x1, eip = 0, esp = 0xcc9aad6c, ebp = 0 ---
Mike Tancsa, tel +1 519 651 3400
Sentex
At 04:53 PM 20/09/2005, Hector Lecuanda wrote:
Perhaps i should have explained that the em(4) driver in 4.x does
include support for the Intel 82573 1000/PRO nic; while the one in 5.x
does not. =(
Is it planned to merge the work on 4.x to 5.x and HEAD?
Hi,
The driver in RELENG_4 is
At 12:58 PM 22/09/2005, Gavin Atkinson wrote:
Support seems to be in HEAD and therefore 6.x already. It looks like 5
has simply been missed. I suspect all that is needed in the 5 branch
are the following changes, though that is untested:
I think the version in 7 and 6 relies on other
At 04:54 PM 14/10/2005, Jayton Garnett wrote:
Hello,
Are there any apps/utilities to check the cpu and system temperature?
Yes, check in /usr/ports
xmbmon
lmmon
healthd
e.g.
% mbmon
Temp.= 46.0, 77.0, 40.0; Rot.= 3750, 2766,0
Vcore = 1.30, 2.62; Volt. = 1.54, 5.67, 11.73, -10.68, -4.55
At 07:59 PM 14/10/2005, Darren Pilgrim wrote:
I wouldn't trust any of these. It's been a few years since any of them have
given me complete or even correct values on current hardware. I can provide
examples on current hardware running RELENG_5 and -CURRENT, if anyone is
interested.
They
At 07:46 PM 15/10/2005, Brett Glass wrote:
The release schedule for FreeBSD 6.0, on the FreeBSD Web site, doesn't show a
projected date for the finished product. How close is it?
My guess, very soon. But for me, RELENG_6 has been small 's' stable
for some time. Got with 6.0R when it comes
At 09:56 PM 17/10/2005, Brett Glass wrote:
At 06:38 PM 10/17/2005, Mike Tancsa wrote:
Two of our scanners in the cluster are SMP boxes-- dual core AMD
running in 386 mode and an Intel D830.
Both work really well, and take quite a load against them network
/ cpu wise. Lots of threads running
At 11:56 PM 17/10/2005, Brett Glass wrote:
At 08:13 PM 10/17/2005, Mike Tancsa wrote:
One thing we're looking at doing is deploying some single-core AMD64s.
Some of the motherboards use the NVidia NForce chipsets, so we
need to know if the nve driver works
I have seen lots of problem
At 08:59 AM 20/10/2005, Thomas T. Veldhouse wrote:
I run a very small home office network and domain off of my DSL.
Currently, I have a FreeBSD 5.4p8 firewall (pf) running. I am
really not having any issues, but sometimes the machines gets a bit
stodgy for no solid reason [load shouldn't be
At 07:39 AM 03/11/2005, José M. Fandiño wrote:
Hello,
Recently I have upgraded a FBSD laptop from 5-STABLE to 6.0RC1,
all seems works except the usb-rs232 adapter which is detected
by the umct and ucom modules as:
ucom0: USB-RS232 Interface Converter USB Ver1.2 Device, rev 1.10/1.03, addr 3
At 03:10 PM 04/11/2005, Richard Bejtlich wrote:
devicecrypto
options FAST_IPSEC
options IPFIREWALL
options IPDIVERT
Can anyone shed light on why those three features are not available
in GENERIC?
It might be because FAST_IPSEC implies no IPV6 ?
At 08:04 AM 23/11/2005, kama wrote:
I have a HP DL380G3 Dual 2.4 w HT disabled.
Polling and SMP is only a recent thing, as is polling support for the
bge. I would try disabling that. In terms of seeing why its crashing,
, it just builds an additional kernel (called kernel.debug)
with debugging symbols that you can compare the crash dump
against. In other words, it wont hurt performance.
---Mike
/Bjorn
On Wed, 23 Nov 2005, Mike Tancsa wrote:
At 08:04 AM 23/11/2005, kama wrote:
I have a HP DL380G3 Dual
At 09:29 AM 29/11/2005, Lowell Gilbert wrote:
Forrest Aldrich [EMAIL PROTECTED] writes:
I have an older PC (Compaq AP200) that I'm running FreeBSD-6.0 on.
I have an Intel Gigabit interface installed in one of the PCI slots,
along with another dual 10/100 Intel in another.
The em0 device
At 12:33 PM 10/27/2006, Jack Vogel wrote:
On 10/27/06, Kurt Jaeger [EMAIL PROTECTED] wrote:
Hi!
Can someone report success with the onboard GigE ports of an
Intel S5000PAL board ?
Thanks for any report 8-}
This is one of our new systems, the onboard NICs require either
the latest driver you
on a RELENG_6 kernel
FreeBSD r6-32bit.sentex.ca 6.2-PRERELEASE FreeBSD 6.2-PRERELEASE #2:
Fri Oct 27 17:10:03 EDT 2006
---Mike
Jack
On 10/27/06, Mike Tancsa [EMAIL PROTECTED] wrote:
At 12:33 PM 10/27/2006, Jack Vogel wrote:
On 10/27/06, Kurt Jaeger [EMAIL PROTECTED] wrote:
Hi!
Can
At 05:52 PM 10/27/2006, Jack Vogel wrote:
HMMM, ok, maybe I jumped the gun, if this thing says ICH7 then its not
the NIC I was talking about, thats ICH8. I just didnt think there were any
10/100 parts that werent already in the fxp driver.
I looked at the PCI ID, and its not what I was talking
At 06:49 PM 10/27/2006, Jack Vogel wrote:
Any chance to commit the ID info to the driver ? Seems to work just
fine as an fxp.
---Mike
When the current firefight I'm in is over I'll check it out.
Super, thanks!
---Mike
___
At 05:03 AM 11/3/2006, Rink Springer wrote:
Hi people,
Recently, I installed FreeBSD on a Tyan GS14 barebone, which houses an
bge(4) and a fxp(4). However, FreeBSD does not recognize the on-board
fxp(4) NIC by default.
All that was needed was just an extra PCI ID addition; the patch can be
At 09:16 PM 11/3/2006, Jack Vogel wrote:
I, and re, would very much appreciate any test feedback you can
Thanks very much for working on this! I was not able to easily
reproduce the timeouts in the first place, but so far on the one box
I have been testing, it seems to be fine (netrate
At 04:52 PM 11/7/2006, Scott Long wrote:
I think it's more that the if_em driver watchdog was insulating the
if_xl driver. Once the if_em component was removed, the if_xl driver
was the next in line to be a victim. So yes, like you say, all of the
drivers need to be fixed.
I wonder if
At 08:19 PM 11/8/2006, Jack Vogel wrote:
BUT, I've added the FAST_INTR changes back into the code, so
if you go into your Makefile and add -DEM_FAST_INTR you will
then get the taskqueue stuff.
It certainly does make a difference performance wise. I did some
quick testing with netperf and
At 08:19 PM 11/8/2006, Jack Vogel wrote:
BUT, I've added the FAST_INTR changes back into the code, so
if you go into your Makefile and add -DEM_FAST_INTR you will
then get the taskqueue stuff.
Not sure why you would want FAST_INTR and polling in at the same
time, but I found that the two are
At 10:51 AM 11/9/2006, Scott Long wrote:
Mike Tancsa wrote:
At 08:19 PM 11/8/2006, Jack Vogel wrote:
BUT, I've added the FAST_INTR changes back into the code, so
if you go into your Makefile and add -DEM_FAST_INTR you will
then get the taskqueue stuff.
It certainly does make a difference
At 07:17 AM 11/10/2006, Vince wrote:
Hi All,
I have a bit of a wierd problem, My laptop has no serial ports, as is
the norm these days, so i have a FTDI based usb serial connector which
is very handy and works well. However, what i have found is that freebsd
still detects a serial port
At 05:00 PM 11/9/2006, Mike Tancsa wrote:
At 10:51 AM 11/9/2006, Scott Long wrote:
Mike Tancsa wrote:
At 08:19 PM 11/8/2006, Jack Vogel wrote:
BUT, I've added the FAST_INTR changes back into the code, so
if you go into your Makefile and add -DEM_FAST_INTR you will
then get the taskqueue
At 05:00 PM 11/10/2006, Jack Vogel wrote:
On 11/10/06, Mike Tancsa [EMAIL PROTECTED] wrote:
Some more tests. I tried again with what was committed to today's
RELENG_6. I am guessing its pretty well the same patch. Polling is
the only way to avoid livelock at a high pps rate. Does anyone know
At 01:42 AM 11/11/2006, Scott Long wrote:
surprised by your results. I'm still a bit unclear on the exact
topology of your setup, so if could explain it some more in private
email, I'd appreciate it.
Hi,
I made a quick diagram of the test setup that should make it
more clear
At 01:42 AM 11/11/2006, Scott Long wrote:
driver. What will help me is if you can hook up a serial console to
your machine and see if it can be made to drop to the debugger while it
is under load and otherwise unresponsive. If you can, getting a process
dump might help confirm where each CPU
At 08:45 AM 11/12/2006, Adrian Chadd wrote:
Should fiddling with the interrupt-coalescing stuff in the em driver
via sysctl be tried?
None of the recent tests in reply to your email indicate any
particular tx/rx threshold settings.
I was using whatever is the default. What would you like me
At 11:41 AM 11/12/2006, Scott Long wrote:
Mike Tancsa wrote:
At 01:42 AM 11/11/2006, Scott Long wrote:
driver. What will help me is if you can hook up a serial console to
your machine and see if it can be made to drop to the debugger while it
is under load and otherwise unresponsive. If you
At 08:47 PM 11/12/2006, Scott Long wrote:
2. Try compiling in WITNESS and running the test as before, then break
into the debugger as before. Run 'show locks'. I'm not sure how
fruitful this will be, WITNESS might make it unbearably slow.
It was in that kernel already
So you're seeing the
At 11:05 PM 11/12/2006, Scott Long wrote:
Mike Tancsa wrote:
However, if I turn on fastforwarding, its back to the old behavior
with it locking up. This was with the stock driver. I will try the
same test with
#define EM_FAST_INTR 1
as well as taking out the nfs option from the kernel
At 12:15 AM 11/13/2006, Scott Long wrote:
Is this with EM_INTR_FAST enabled also?
Yes. Havent done the stock case yet, but will do so later today.
---Mike
___
freebsd-stable@freebsd.org mailing list
At 12:15 AM 11/13/2006, Scott Long wrote:
Is this with EM_INTR_FAST enabled also?
Without it, the 2 streams are definitely lossy on the management interface
---Mike
___
freebsd-stable@freebsd.org mailing list
At 12:50 PM 11/13/2006, Ivan Voras wrote:
Mike Tancsa wrote:
At 12:15 AM 11/13/2006, Scott Long wrote:
Is this with EM_INTR_FAST enabled also?
Yes. Havent done the stock case yet, but will do so later today.
Do you have a comparison with Linux under the same circumstances?
I had a disk
At 06:36 AM 11/13/2006,
=?KOI8-R?Q?=F3=D0=C1=D2=D4=C1=CB_=F2=C1=C4=DE=C5=CE=CB=CF?= wrote:
O. Hartmann ÐÉÛÅÔ:
Sergey Matveychuk wrote:
Do you know an old sio driver is hardly usable?
There are many silo overflows, working with a terminal device is a
nightmare. There was a report about one
At 05:27 AM 11/14/2006, Spartak Radchenko wrote:
How do you switch it from sio to uart on RELENG_6 ?
Build a new kernel with device uart, change sio to uart tn the
/boot/device.hints file. Maybe rebuilding a kernel is not needed, I
never checked it.
Thanks,
For me, sio on the
At 11:13 PM 12/13/2006, Jack Vogel wrote:
On 12/13/06, Chris Buechler [EMAIL PROTECTED] wrote:
Jack Vogel wrote:
I need the PCI ID of that NIC, just to be sure that I can't reproduce
this, but
I doubt it, pciconf -l
I have another case where an EM nic can lock up the box. But I am
not
1 - 100 of 967 matches
Mail list logo