* [9fans] A shot in the dark @ 2008-05-27 22:02 ron minnich 2008-05-27 22:54 ` Pietro Gagliardi 2008-05-28 0:16 ` [9fans] A shot in the dark Bakul Shah 0 siblings, 2 replies; 13+ messages in thread From: ron minnich @ 2008-05-27 22:02 UTC (permalink / raw) To: Fans of the OS Plan 9 from Bell Labs OK, this is a long shot, but i'm running out of ideas. Long, long ago, at a Usenix, I saw a talk by some adventurous australians (are there any other kind?). It was concerning some neat hardware designed for kernel monitoring. They had done a very neat hack. Basically, they modified the C compiler so that, on function entry and exit, the code would emit a 16-bit quantity to the parallel port. They had some simple hardware to grab the data. WIth this, they were able to get some nice kernel performance numbers, all for the (low at the time) cost of an outw to the parallel port. OK, I have done some searching and can't find this. IIRC it was pre-website usenix. I am going to UCB this week and may have time to hunt it down in the paper archives, but ... just wondering ... anyone else remember this? thanks ron ^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [9fans] A shot in the dark 2008-05-27 22:02 [9fans] A shot in the dark ron minnich @ 2008-05-27 22:54 ` Pietro Gagliardi 2008-05-27 23:00 ` ron minnich 2008-05-28 0:06 ` Digby Tarvin 2008-05-28 0:16 ` [9fans] A shot in the dark Bakul Shah 1 sibling, 2 replies; 13+ messages in thread From: Pietro Gagliardi @ 2008-05-27 22:54 UTC (permalink / raw) To: Fans of the OS Plan 9 from Bell Labs No, I wasn't around that time :-) But I was looking for the Hello World X11 paper a while back, which was pre-website USENIX. But on the USENIX website it seems that you can purchase papers from before 1991(?). Perhaps they had a paper? On May 27, 2008, at 6:02 PM, ron minnich wrote: > OK, this is a long shot, but i'm running out of ideas. > > Long, long ago, at a Usenix, I saw a talk by some adventurous > australians (are there any other kind?). It was concerning some neat > hardware designed for kernel monitoring. > > They had done a very neat hack. Basically, they modified the C > compiler so that, on function entry and exit, the code would emit a > 16-bit quantity to the parallel port. They had some simple hardware to > grab the data. > > WIth this, they were able to get some nice kernel performance numbers, > all for the (low at the time) cost of an outw to the parallel port. > > OK, I have done some searching and can't find this. IIRC it was > pre-website usenix. I am going to UCB this week and may have time to > hunt it down in the paper archives, but ... just wondering ... anyone > else remember this? > > thanks > > ron > ^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [9fans] A shot in the dark 2008-05-27 22:54 ` Pietro Gagliardi @ 2008-05-27 23:00 ` ron minnich 2008-05-28 0:06 ` Digby Tarvin 1 sibling, 0 replies; 13+ messages in thread From: ron minnich @ 2008-05-27 23:00 UTC (permalink / raw) To: Fans of the OS Plan 9 from Bell Labs On Tue, May 27, 2008 at 3:54 PM, Pietro Gagliardi <pietro10@mac.com> wrote: > No, I wasn't around that time :-) But I was looking for the Hello World X11 > paper a while back, which was pre-website USENIX. But on the USENIX website > it seems that you can purchase papers from before 1991(?). Perhaps they had > a paper? They had a paper, I just don't have the proceedings any more, I was hoping someone else remembered it. ron ^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [9fans] A shot in the dark 2008-05-27 22:54 ` Pietro Gagliardi 2008-05-27 23:00 ` ron minnich @ 2008-05-28 0:06 ` Digby Tarvin 2008-05-28 2:54 ` Paul Lalonde 1 sibling, 1 reply; 13+ messages in thread From: Digby Tarvin @ 2008-05-28 0:06 UTC (permalink / raw) To: Fans of the OS Plan 9 from Bell Labs Don't know where to find that paper, but it reminds of a friend at UNSW (in Sydney) that used to instrument the OS9 kernel by setting and clearing bits in the parallel port. The monitoring hardware was indeed simple - an analogue voltmeter connected to the bit of interest to produce a simple but effective short term average. For example, a bit that is cleared when in the system idle loop produced a 'tacho' style analogue load meter. That must have been in the early 80's, but I still find the parallel interface a good method of getting real-time diagnostics, or front panel style indicators for statuses such as system/user mode. Consequently I don't welcome the current trend toward optimising them out of new hardware. USB parallel interfaces may be ok for driving printers, but they are no substitute if you want a very low overhead, low latency i/o mechanism. Regards, DigbyT On Tue, May 27, 2008 at 06:54:58PM -0400, Pietro Gagliardi wrote: > No, I wasn't around that time :-) But I was looking for the Hello > World X11 paper a while back, which was pre-website USENIX. But on the > USENIX website it seems that you can purchase papers from before > 1991(?). Perhaps they had a paper? > > On May 27, 2008, at 6:02 PM, ron minnich wrote: > > >OK, this is a long shot, but i'm running out of ideas. > > > >Long, long ago, at a Usenix, I saw a talk by some adventurous > >australians (are there any other kind?). It was concerning some neat > >hardware designed for kernel monitoring. > > > >They had done a very neat hack. Basically, they modified the C > >compiler so that, on function entry and exit, the code would emit a > >16-bit quantity to the parallel port. They had some simple hardware to > >grab the data. > > > >WIth this, they were able to get some nice kernel performance numbers, > >all for the (low at the time) cost of an outw to the parallel port. > > > >OK, I have done some searching and can't find this. IIRC it was > >pre-website usenix. I am going to UCB this week and may have time to > >hunt it down in the paper archives, but ... just wondering ... anyone > >else remember this? > > > >thanks > > > >ron > > > -- Digby R. S. Tarvin digbyt(at)digbyt.com http://www.digbyt.com ^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [9fans] A shot in the dark 2008-05-28 0:06 ` Digby Tarvin @ 2008-05-28 2:54 ` Paul Lalonde 2008-05-28 7:31 ` Bruce Ellis 0 siblings, 1 reply; 13+ messages in thread From: Paul Lalonde @ 2008-05-28 2:54 UTC (permalink / raw) To: Digby Tarvin, Fans of the OS Plan 9 from Bell Labs -----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 FWIW, we used a similar technique just last summer debugging some PS3 code. The dev system is kind enough to include 4 front panel lights and a very lightweight API for setting them. We wound up "printing" out the program counter during a deadlock by mashing too many calls to set the lights into the suspect areas. I miss hardware debuggers. Paul On May 27, 2008, at 5:06 PM, Digby Tarvin wrote: > Don't know where to find that paper, but it reminds of a friend > at UNSW (in Sydney) that used to instrument the OS9 kernel by setting > and clearing bits in the parallel port. > > The monitoring hardware was indeed simple - an analogue voltmeter > connected to the bit of interest to produce a simple but effective > short term average. > > For example, a bit that is cleared when in the system idle loop > produced a 'tacho' style analogue load meter. > > That must have been in the early 80's, but I still find the parallel > interface a good method of getting real-time diagnostics, or front > panel style indicators for statuses such as system/user mode. > Consequently I don't welcome the current trend toward optimising > them out of new hardware. USB parallel interfaces may be ok for > driving printers, but they are no substitute if you want a very low > overhead, low latency i/o mechanism. > > Regards, > DigbyT > > On Tue, May 27, 2008 at 06:54:58PM -0400, Pietro Gagliardi wrote: >> No, I wasn't around that time :-) But I was looking for the Hello >> World X11 paper a while back, which was pre-website USENIX. But on >> the >> USENIX website it seems that you can purchase papers from before >> 1991(?). Perhaps they had a paper? >> >> On May 27, 2008, at 6:02 PM, ron minnich wrote: >> >>> OK, this is a long shot, but i'm running out of ideas. >>> >>> Long, long ago, at a Usenix, I saw a talk by some adventurous >>> australians (are there any other kind?). It was concerning some neat >>> hardware designed for kernel monitoring. >>> >>> They had done a very neat hack. Basically, they modified the C >>> compiler so that, on function entry and exit, the code would emit a >>> 16-bit quantity to the parallel port. They had some simple >>> hardware to >>> grab the data. >>> >>> WIth this, they were able to get some nice kernel performance >>> numbers, >>> all for the (low at the time) cost of an outw to the parallel port. >>> >>> OK, I have done some searching and can't find this. IIRC it was >>> pre-website usenix. I am going to UCB this week and may have time to >>> hunt it down in the paper archives, but ... just wondering ... >>> anyone >>> else remember this? >>> >>> thanks >>> >>> ron >>> >> > > -- > Digby R. S. Tarvin digbyt > (at)digbyt.com > http://www.digbyt.com > -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.3 (Darwin) iD8DBQFIPMllpJeHo/Fbu1wRAtBGAJ49Ngab2WyOW+bYQ0wiUmJrqBKyeACfYhhn A9b4diGkwg2fiiLyjXVWIGY= =3r1V -----END PGP SIGNATURE----- ^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [9fans] A shot in the dark 2008-05-28 2:54 ` Paul Lalonde @ 2008-05-28 7:31 ` Bruce Ellis 2008-05-28 15:49 ` Digby Tarvin 2008-05-28 18:34 ` [9fans] OT: supporting multiple VGA cards (was "A shot in the dark") Digby Tarvin 0 siblings, 2 replies; 13+ messages in thread From: Bruce Ellis @ 2008-05-28 7:31 UTC (permalink / raw) To: Fans of the OS Plan 9 from Bell Labs When I did the port to the PS2 there wasn't even a light to blink. To get thru l.s I discovered a register I could write that resets the video. Only a hundred lines (most innocent) to binary chop. Ken has a better tale of a device that only had a speaker and debugging by tones. brucee On 5/28/08, Paul Lalonde <plalonde@telus.net> wrote: > -----BEGIN PGP SIGNED MESSAGE----- > Hash: SHA1 > > FWIW, we used a similar technique just last summer debugging some PS3 ^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [9fans] A shot in the dark 2008-05-28 7:31 ` Bruce Ellis @ 2008-05-28 15:49 ` Digby Tarvin 2008-05-28 18:34 ` [9fans] OT: supporting multiple VGA cards (was "A shot in the dark") Digby Tarvin 1 sibling, 0 replies; 13+ messages in thread From: Digby Tarvin @ 2008-05-28 15:49 UTC (permalink / raw) To: Fans of the OS Plan 9 from Bell Labs Way back in the dim distant pre-IBMPC days of Z80 PCs, my favourite debugging technique was to use the screen memory. My original Exidy Sorcerer had 1920 bytes of character oriented screen memory (this was when 8K was a respectable amount of main memory). Each byte displayed a 8x8 character defined by 8 bytes of the character generator memory, to top half of which (the non-ascii characters) was writeable memory. Not only could diagnostics be written to the display with a single assembly language instruction, but it was even possible to just run the entire program on the screen, which was entertaining as well as often quite informative. I had no assembler, so with hand assembly 1920 bytes seemed like quite a large piece of code. Running the firmware monitor memory test routines on the screen ram was also an endless source of entertainment. I have recently been tinkering with using the memory on PC text mode VGA adapters to provide a realtime visual display of what is going on inside the Linux kernel, but it seems to be one of the less well documented areas of the software and hardware, so there has been a lot of trial and error and reverse engineering involved.. If anyone knows of any good resources please let me know... Regards, DigbyT On Wed, May 28, 2008 at 05:31:27PM +1000, Bruce Ellis wrote: > When I did the port to the PS2 there wasn't even a light to blink. To > get thru l.s I discovered a register I could write that resets the > video. > > Only a hundred lines (most innocent) to binary chop. > > Ken has a better tale of a device that only had a speaker and > debugging by tones. > > brucee > > On 5/28/08, Paul Lalonde <plalonde@telus.net> wrote: > > -----BEGIN PGP SIGNED MESSAGE----- > > Hash: SHA1 > > > > FWIW, we used a similar technique just last summer debugging some PS3 -- Digby R. S. Tarvin digbyt(at)digbyt.com http://www.digbyt.com ^ permalink raw reply [flat|nested] 13+ messages in thread
* [9fans] OT: supporting multiple VGA cards (was "A shot in the dark") 2008-05-28 7:31 ` Bruce Ellis 2008-05-28 15:49 ` Digby Tarvin @ 2008-05-28 18:34 ` Digby Tarvin 2008-05-28 19:07 ` ron minnich 1 sibling, 1 reply; 13+ messages in thread From: Digby Tarvin @ 2008-05-28 18:34 UTC (permalink / raw) To: Fans of the OS Plan 9 from Bell Labs On the subject of diagnostic tools (this is not specifically a Plan9 issue, but someone on this list might know...): I am interested in connecting more than one graphics adapter so that one can be dedicated to low level diagnostics (rather than the more usual dual head user interface).. but I am not sure how the hardware deals with that given that the VGA standard seems to imply that all the cards would be using identical memory addresses and IO ports. Otherwise I would expect PCI to be able to automatically map resources to non-conflicting addresses/IO ports. In any case my BIOS has a setting which allows selection between AGP and PCI as 'primary' Video, suggesting that it is indeed possible to have at least one of each. The only thing I can think of is that perhaps the VGA/CGA/EGA etc modes are suppressed in the non-primary card, leaving only the more advanced and less standard mode available. But this would be less ideal, as text mode would be more useful for low overhead diagnostics. Does anyone know what actually happens? Regards, DigbyT On Wed, May 28, 2008 at 05:31:27PM +1000, Bruce Ellis wrote: > When I did the port to the PS2 there wasn't even a light to blink. To > get thru l.s I discovered a register I could write that resets the > video. > > Only a hundred lines (most innocent) to binary chop. > > Ken has a better tale of a device that only had a speaker and > debugging by tones. > > brucee > > On 5/28/08, Paul Lalonde <plalonde@telus.net> wrote: > > -----BEGIN PGP SIGNED MESSAGE----- > > Hash: SHA1 > > > > FWIW, we used a similar technique just last summer debugging some PS3 -- Digby R. S. Tarvin digbyt(at)digbyt.com http://www.digbyt.com ^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [9fans] OT: supporting multiple VGA cards (was "A shot in the dark") 2008-05-28 18:34 ` [9fans] OT: supporting multiple VGA cards (was "A shot in the dark") Digby Tarvin @ 2008-05-28 19:07 ` ron minnich 0 siblings, 0 replies; 13+ messages in thread From: ron minnich @ 2008-05-28 19:07 UTC (permalink / raw) To: Digby Tarvin, Fans of the OS Plan 9 from Bell Labs On Wed, May 28, 2008 at 11:34 AM, Digby Tarvin <digbyt@acm.org> wrote: > > I am interested in connecting more than one graphics adapter so that > one can be dedicated to low level diagnostics (rather than the more > usual dual head user interface).. but I am not sure how the hardware > deals with that given that the VGA standard seems to imply that all > the cards would be using identical memory addresses and IO ports. There are Rules such that only one terminal gets to own the "legacy" ports. > Otherwise I would expect PCI to be able to automatically > map resources to non-conflicting addresses/IO ports. They do. It's just the legacy stuff that gets weird. > > In any case my BIOS has a setting which allows selection between AGP and > PCI as 'primary' Video, suggesting that it is indeed possible to have at > least one of each. it is. > > The only thing I can think of is that perhaps the VGA/CGA/EGA etc modes > are suppressed in the non-primary card, leaving only the more advanced > and less standard mode available. But this would be less ideal, as text > mode would be more useful for low overhead diagnostics. if you can convince the OS to use the non-legacy addresses, you could configure BIOS to put your desired debug terminal at legacy addresses and use it for debug. ron ^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [9fans] A shot in the dark 2008-05-27 22:02 [9fans] A shot in the dark ron minnich 2008-05-27 22:54 ` Pietro Gagliardi @ 2008-05-28 0:16 ` Bakul Shah 2008-05-28 0:30 ` ron minnich 1 sibling, 1 reply; 13+ messages in thread From: Bakul Shah @ 2008-05-28 0:16 UTC (permalink / raw) To: Fans of the OS Plan 9 from Bell Labs On Tue, 27 May 2008 15:02:15 PDT "ron minnich" <rminnich@gmail.com> wrote: > OK, this is a long shot, but i'm running out of ideas. > > Long, long ago, at a Usenix, I saw a talk by some adventurous > australians (are there any other kind?). It was concerning some neat > hardware designed for kernel monitoring. > > They had done a very neat hack. Basically, they modified the C > compiler so that, on function entry and exit, the code would emit a > 16-bit quantity to the parallel port. They had some simple hardware to > grab the data. > > WIth this, they were able to get some nice kernel performance numbers, > all for the (low at the time) cost of an outw to the parallel port. > > OK, I have done some searching and can't find this. IIRC it was > pre-website usenix. I am going to UCB this week and may have time to > hunt it down in the paper archives, but ... just wondering ... anyone > else remember this? Not quite the same but perhaps you are thinking of "Hardware Profiling of Kernels" by Andrew McRae in Winter 1993 usenix. >From his paper: Three basic building blocks are used in the proling system proposed; the first is a hardware device that is used to record time and event data into a RAM block. The second is a modified C compiler that allows event triggering code to be inserted into key locations, and finally the last building block is analysis software that is used to decode the backtrace of events and relate it to the source code. http://mcrae.homeunix.net/papers/final_usenix.pdf He plugs his simple h/w in an Eprom socket and captures upto 16K events. Each event has a 16 bit tag and 24 bit us clock value (so events can be upto 16 seconds apart). Makes more sense as access to a parallel port would be much slower. For today's processors, this would be far too slow. ^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [9fans] A shot in the dark 2008-05-28 0:16 ` [9fans] A shot in the dark Bakul Shah @ 2008-05-28 0:30 ` ron minnich 2008-05-28 7:17 ` Bruce Ellis 0 siblings, 1 reply; 13+ messages in thread From: ron minnich @ 2008-05-28 0:30 UTC (permalink / raw) To: Fans of the OS Plan 9 from Bell Labs On Tue, May 27, 2008 at 5:16 PM, Bakul Shah <bakul+plan9@bitblocks.com> wrote: > Not quite the same but perhaps you are thinking of "Hardware > Profiling of Kernels" by Andrew McRae in Winter 1993 usenix. > From his paper: it's good enough, and my memory probably is bad enough that this is the right one. Thanks! ron ^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [9fans] A shot in the dark 2008-05-28 0:30 ` ron minnich @ 2008-05-28 7:17 ` Bruce Ellis 2008-05-28 15:53 ` Digby Tarvin 0 siblings, 1 reply; 13+ messages in thread From: Bruce Ellis @ 2008-05-28 7:17 UTC (permalink / raw) To: Fans of the OS Plan 9 from Bell Labs I went to that fest, it was an early AUUGM. I think it was the BFI interface team at UNSW. I'll check the c-side library (I keep everythng). brucee On 5/28/08, ron minnich <rminnich@gmail.com> wrote: > On Tue, May 27, 2008 at 5:16 PM, Bakul Shah <bakul+plan9@bitblocks.com> wrote: > > > Not quite the same but perhaps you are thinking of "Hardware > > Profiling of Kernels" by Andrew McRae in Winter 1993 usenix. > > From his paper: > > it's good enough, and my memory probably is bad enough that this is > the right one. > > Thanks! > > ron > > ^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [9fans] A shot in the dark 2008-05-28 7:17 ` Bruce Ellis @ 2008-05-28 15:53 ` Digby Tarvin 0 siblings, 0 replies; 13+ messages in thread From: Digby Tarvin @ 2008-05-28 15:53 UTC (permalink / raw) To: Fans of the OS Plan 9 from Bell Labs That brings back memories. I think it was Dave Milway who gave a talk on the BFI at UNSW, where he revealed during question time at the end that 'BFI' stood for 'Beut Fast Interface'. Regards, DigbyT On Wed, May 28, 2008 at 05:17:07PM +1000, Bruce Ellis wrote: > I went to that fest, it was an early AUUGM. > > I think it was the BFI interface team at UNSW. > > I'll check the c-side library (I keep everythng). > > brucee > > On 5/28/08, ron minnich <rminnich@gmail.com> wrote: > > On Tue, May 27, 2008 at 5:16 PM, Bakul Shah <bakul+plan9@bitblocks.com> wrote: > > > > > Not quite the same but perhaps you are thinking of "Hardware > > > Profiling of Kernels" by Andrew McRae in Winter 1993 usenix. > > > From his paper: > > > > it's good enough, and my memory probably is bad enough that this is > > the right one. > > > > Thanks! > > > > ron > > > > -- Digby R. S. Tarvin digbyt(at)digbyt.com http://www.digbyt.com ^ permalink raw reply [flat|nested] 13+ messages in thread
end of thread, other threads:[~2008-05-28 19:07 UTC | newest] Thread overview: 13+ messages (download: mbox.gz / follow: Atom feed) -- links below jump to the message on this page -- 2008-05-27 22:02 [9fans] A shot in the dark ron minnich 2008-05-27 22:54 ` Pietro Gagliardi 2008-05-27 23:00 ` ron minnich 2008-05-28 0:06 ` Digby Tarvin 2008-05-28 2:54 ` Paul Lalonde 2008-05-28 7:31 ` Bruce Ellis 2008-05-28 15:49 ` Digby Tarvin 2008-05-28 18:34 ` [9fans] OT: supporting multiple VGA cards (was "A shot in the dark") Digby Tarvin 2008-05-28 19:07 ` ron minnich 2008-05-28 0:16 ` [9fans] A shot in the dark Bakul Shah 2008-05-28 0:30 ` ron minnich 2008-05-28 7:17 ` Bruce Ellis 2008-05-28 15:53 ` Digby Tarvin
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox; as well as URLs for NNTP newsgroup(s).