Re: 2xPIIIx450 results NFS results

1999-09-20 Thread Bruce Evans
I remember this one too. I think the problem is that we fail to service the RTC intr for some reason. This patch was only a workaround, and received a verbal broadside from Bruce if I remember right. Maybe it should be added under a sysctl until a better solution is know. ---

Re: 2xPIIIx450 results NFS results

1999-09-20 Thread Poul-Henning Kamp
In message [EMAIL PROTECTED], Bruce E vans writes: I remember this one too. I think the problem is that we fail to service the RTC intr for some reason. This patch was only a workaround, and received a verbal broadside from Bruce if I remember right. Maybe it should be added under a

Re: 2xPIIIx450 results NFS results

1999-09-20 Thread Mike Smith
Use a watchdog timeout like you should for any device that may hang. Don't waste time running it every clock tick. ISTR that we thought that the bug might be caused by a bug in unwanted SMI interrupt handling. If anybody can reproduce this reliably on a *BX chipset I have code that will

Re: 2xPIIIx450 results NFS results

1999-09-20 Thread Poul-Henning Kamp
In message [EMAIL PROTECTED], Mike Smith writes: Use a watchdog timeout like you should for any device that may hang. Don't waste time running it every clock tick. ISTR that we thought that the bug might be caused by a bug in unwanted SMI interrupt handling. If anybody can reproduce this

Re: 2xPIIIx450 results NFS results

1999-09-20 Thread Michael Reifenberger
Hi, Use a watchdog timeout like you should for any device that may hang. Don't waste time running it every clock tick. ISTR that we thought that the bug might be caused by a bug in unwanted SMI interrupt handling. Upgrading the BIOS to Rev. 1010 does solve the problem for me without the

Re: 2xPIIIx450 results NFS results

1999-09-19 Thread Andrzej Bialecki
On Sun, 19 Sep 1999, Adam Strohl wrote: OK, Upgraded my Asus P2B-D machien from BIOS version 1008 to 1010, the problem disappeared. Popped back to my old 1008 BIOS, problem came back. Looks like there was some wierd issue that got resolved in 1009 or 1010. Good! Thanks for the info. Now

Re: 2xPIIIx450 results NFS results

1999-09-18 Thread Andrzej Bialecki
On Fri, 17 Sep 1999, Rodney W. Grimes wrote: : I/O, and then closing it. : :4.0-CURRENT (SMP on an ASUS P2B-DS with two CPU's installed; BIOS revision :1008.A, running `systat -vm 1' gives the normal display but without any :numbers filled in, then switches over to an empty screen

Re: 2xPIIIx450 results NFS results

1999-09-18 Thread N
Matthew Dillon wrote: 4.0-CURRENT (SMP on an ASUS P2B-DS with two CPU's installed; BIOS revision 1008.A, running `systat -vm 1' gives the normal display but without any numbers filled in, then switches over to an empty screen that says: [..] Whenever systat or top do weird things it

Re: 2xPIIIx450 results NFS results

1999-09-18 Thread Jaye Mathisen
Yes, it definitely seems ASUS related... I dropped back to uni processor ASUS boards, and it's fine. didn't need the SMP anyway, just wanted to play with it some more. On Sat, 18 Sep 1999, Andrzej Bialecki wrote: On Fri, 17 Sep 1999, Rodney W. Grimes wrote: : I/O, and then closing

Re: 2xPIIIx450 results NFS results

1999-09-18 Thread Garrett Wollman
On Sat, 18 Sep 1999 01:16:52 + (GMT), Adam Strohl [EMAIL PROTECTED] said: I've been getting this too on 4.0-C, just rebuild last night, still there. top displays: CPU states: 0.0% user, 0.0% nice, 0.0% system, 0.0% interrupt, 0.0% idle On my dual-PPro Intel BB440FX system I am not

Re: 2xPIIIx450 results NFS results

1999-09-18 Thread Andrzej Bialecki
On Sat, 18 Sep 1999, Jaye Mathisen wrote: Yes, it definitely seems ASUS related... I dropped back to uni processor ASUS boards, and it's fine. didn't need the SMP anyway, just wanted to play with it some more. Now, here's the difference - I don't play, I NEED SMP, and the machines in

Re: 2xPIIIx450 results NFS results

1999-09-18 Thread Rodney W. Grimes
On Sat, 18 Sep 1999 01:16:52 + (GMT), Adam Strohl [EMAIL PROTECTED] said: I've been getting this too on 4.0-C, just rebuild last night, still there. top displays: CPU states: 0.0% user, 0.0% nice, 0.0% system, 0.0% interrupt, 0.0% idle On my dual-PPro Intel BB440FX system

Re: 2xPIIIx450 results NFS results

1999-09-18 Thread Warner Losh
In message [EMAIL PROTECTED] Andrzej Bialecki writes: : The problem seems to occur reliably on ASUS boards - perhaps a : coincidence, but I have several machines here which behave this way. And : yes, libkvm is in perfect sync with the rest of the system (3.3-RC) We're seenig it too in the

Re: 2xPIIIx450 results NFS results

1999-09-18 Thread Poul-Henning Kamp
In message [EMAIL PROTECTED], Michael R eifenberger writes: Hi, We're seenig it too in the 19990815ish time frame. This is both with the 3.2R binaries AND the ones rebuilt and reinstalled. Saw it too on my ASUS P2B-DS (F.Rev.1008) Solved by a patch flooding around to /sys/i386/isa/clock.c

Re: 2xPIIIx450 results NFS results

1999-09-18 Thread Michael Reifenberger
Hi, We're seenig it too in the 19990815ish time frame. This is both with the 3.2R binaries AND the ones rebuilt and reinstalled. Saw it too on my ASUS P2B-DS (F.Rev.1008) Solved by a patch flooding around to /sys/i386/isa/clock.c But why? The patch is attached. Bye! Michael Reifenberger

Re: 2xPIIIx450 results NFS results

1999-09-18 Thread Peter Wemm
Mike Smith wrote: Matthew Dillon wrote: thereabouts. Patches have been posted to several ma iling lists, I was wondering whether they've been committed somewhere along the line, and whether APM was safe for inclusion into a 4.0-CURRENT SMP kernel again. APM and SMP are not

Re: 2xPIIIx450 results NFS results

1999-09-18 Thread Mike Smith
Matthew Dillon wrote: thereabouts. Patches have been posted to several mailing lists, I was wondering whether they've been committed somewhere along the line, and whether APM was safe for inclusion into a 4.0-CURRENT SMP kernel again. APM and SMP are not functional in -current; this broke

Re: 2xPIIIx450 results NFS results (was More benchmarking stuff...)

1999-09-18 Thread Greg Lehey
On Friday, 17 September 1999 at 11:17:48 -0700, Matthew Dillon wrote: : Might I then request that you help rewrite it so that it performs :a much more comprehensive testing of OS/filesystem throughput? :Myself, I'd really love to see something that lets you seriously :stress your system

Re: 2xPIIIx450 results NFS results

1999-09-18 Thread Adam Strohl
OK, Upgraded my Asus P2B-D machien from BIOS version 1008 to 1010, the problem disappeared. Popped back to my old 1008 BIOS, problem came back. Looks like there was some wierd issue that got resolved in 1009 or 1010. - ( Adam Strohl ) - -

Re: 2xPIIIx450 results NFS results

1999-09-18 Thread Rodney W. Grimes
OK, Upgraded my Asus P2B-D machien from BIOS version 1008 to 1010, the problem disappeared. Popped back to my old 1008 BIOS, problem came back. So far about alls I have confirmed is that the problem does not exists with BIOS 1009 when the apm code is not compiled into the kernel. I'll have a

Re: 2xPIIIx450 results NFS results

1999-09-18 Thread Adam Strohl
On Sat, 18 Sep 1999, Rodney W. Grimes wrote: So far about alls I have confirmed is that the problem does not exists with BIOS 1009 when the apm code is not compiled into the kernel. I'll have a full matrix of with/without apm 1008/1009/1010 some time tomarrow, as the machines are building

Re: 2xPIIIx450 results NFS results (was More benchmarking stuff...)

1999-09-17 Thread Brad Knowles
At 11:56 AM -0700 1999/9/17, Matthew Dillon wrote: In real-life... for example, with a mail or web server, the namecache tends to be somewhat more effective then 50%. The web servers at BEST generally had a 95%+ name cache hit rate. The name cache misses are what are

Re: 2xPIIIx450 results NFS results (was More benchmarking stuff...)

1999-09-17 Thread Brad Knowles
At 1:02 PM -0700 1999/9/17, Matthew Dillon wrote: Sendmail does not get into trouble with queue files it is able to retire quickly. Where sendmail gets into trouble is with queue files it ISN'T able to retire quickly. This is why you *see* 10,000+ files in mqueue at times.

Re: 2xPIIIx450 results NFS results

1999-09-17 Thread N
Matthew Dillon wrote: [..] One thing of interest to note, especially as it relates to the performance degredation with a larger number of files, is that 'systat -vm 1' reports an approximately 50% name-cache hit no matter what postmark is doing. In otherwords, postmark is

Re: 2xPIIIx450 results NFS results

1999-09-17 Thread Matthew Dillon
: I/O, and then closing it. : :4.0-CURRENT (SMP on an ASUS P2B-DS with two CPU's installed; BIOS revision :1008.A, running `systat -vm 1' gives the normal display but without any :numbers filled in, then switches over to an empty screen that says: :... Whenever systat or top do weird

Re: 2xPIIIx450 results NFS results

1999-09-17 Thread Adam Strohl
I've been getting this too on 4.0-C, just rebuild last night, still there. top displays: CPU states: 0.0% user, 0.0% nice, 0.0% system, 0.0% interrupt, 0.0% idle AND loads 2 make the machine very unresponsive, its like SMP was before that pci_support.c patch a month or two ago. - (