Detecting SMP in user space
Quoted 5 lines · Andreas Schwab
|> How about simply running 'top' or a 'dmesg | grep CPU'?
As I already said, I'm running a UP kernel, thus top only ever sees one CPU. The latter fails if the boot messages have already been cleared from the kernel log.
I believe the ACPI boot messages on ia64 tell you how many processors it found.
Bill
Bill Nottingham <[email protected]> writes:
|> Andreas Schwab ([email protected]) said: |> > |> How about simply running 'top' or a 'dmesg | grep CPU'? |> > |> > As I already said, I'm running a UP kernel, thus top only ever sees one |> > CPU. The latter fails if the boot messages have already been cleared from |> > the kernel log. |> |> I believe the ACPI boot messages on ia64 tell you how many processors |> it found.
How can I get at the ACPI boot messages if the kernel log is already cleared?
Andreas.
Signature · 5 lines
Andreas Schwab "And now for something SuSE Labs completely different." [email protected] SuSE GmbH, Schanzäckerstr. 10, D-90443 Nürnberg Key fingerprint = 58CA 54C7 6D53 942B 1756 01D3 44D5 214B 8276 4ED5
Andreas-
On my system the boot messages are copied into `/var/log/messages' so you can always go there even if the boot log is cleared.
Quoted 28 lines · Andreas Schwab
Bill Nottingham <[email protected]> writes:
|> Andreas Schwab ([email protected]) said: |> > |> How about simply running 'top' or a 'dmesg | grep CPU'? |> > |> > As I already said, I'm running a UP kernel, thus top only ever sees one |> > CPU. The latter fails if the boot messages have already been cleared from |> > the kernel log. |> |> I believe the ACPI boot messages on ia64 tell you how many processors |> it found.How can I get at the ACPI boot messages if the kernel log is already cleared?
Andreas.
Signature · 10 lines
Andreas Schwab "And now for something SuSE Labs completely different." [email protected] SuSE GmbH, Schanzäckerstr. 10, D-90443 Nürnberg Key fingerprint = 58CA 54C7 6D53 942B 1756 01D3 44D5 214B 8276 4ED5 _______________________________________________ Linux-IA64 mailing list [email protected] http://lists.linuxia64.org/lists/listinfo/linux-ia64
Signature · 4 lines
Don Dugger "Censeo Toto nos in Kansa esse decisse." - D. Gale [email protected] Ph: 303/938-9838
Don Dugger <[email protected]> writes:
|> Andreas- |> |> On my system the boot messages are copied into `/var/log/messages' |> so you can always go there even if the boot log is cleared.
This is not reliable. I need something that I can use without depending on the kernel messages. Is it possible to get at the ACPI tables in user space?
Andreas.
Signature · 5 lines
Andreas Schwab "And now for something SuSE Labs completely different." [email protected] SuSE GmbH, Schanzäckerstr. 10, D-90443 Nürnberg Key fingerprint = 58CA 54C7 6D53 942B 1756 01D3 44D5 214B 8276 4ED5
At least on i386, root can read the ACPI tables from /dev/mem (as done in the pmtools [acpitools] package).
~Randy________________________
-----------------------------------------------
Quoted 21 lines
-----Original Message-----
From: Andreas Schwab [mailto:[email protected]]
Sent: Thursday, April 19, 2001 7:31 AM
To: Don Dugger
Cc: [email protected]
Subject: Re: [Linux-ia64] Re: Detecting SMP in user spaceDon Dugger <[email protected]> writes:
|> Andreas- |> |> On my system the boot messages are copied into `/var/log/messages' |> so you can always go there even if the boot log is cleared.This is not reliable. I need something that I can use without depending
on the kernel messages. Is it possible to get at the ACPI tables in user space?Andreas.
"Dunlap, Randy" <[email protected]> writes:
|> At least on i386, root can read the ACPI tables from |> /dev/mem (as done in the pmtools [acpitools] package).
Where can I get this package?
Andreas.
Signature · 5 lines
Andreas Schwab "And now for something SuSE Labs completely different." [email protected] SuSE GmbH, Schanzäckerstr. 10, D-90443 Nürnberg Key fingerprint = 58CA 54C7 6D53 942B 1756 01D3 44D5 214B 8276 4ED5
At the bottom of
http://developer.intel.com/technology/IAPC/acpi/downloads.htm
~Randy________________________503-677-5408_____
-----------------------------------------------
Quoted 9 lines
-----Original Message-----
From: Andreas Schwab [mailto:[email protected]]"Dunlap, Randy" <[email protected]> writes:
|> At least on i386, root can read the ACPI tables from |>
/dev/mem(as done in the pmtools [acpitools] package).Where can I get this package?
"Dunlap, Randy" <[email protected]> writes:
|> At the bottom of
|> http://developer.intel.com/technology/IAPC/acpi/downloads.htm
Thanks, this works fine for BigSur. But on Lion I only get:
RSDP "MSLSAL" @ 0x000f57b0
0000: 52 53 44 20 50 54 52 20 00 4d 53 4c 53 41 4c 00 RSD PTR .MSLSAL.
0010: 00 00 00 00 ....
acpidmp: cannot map the RSDT
Andreas.
Signature · 5 lines
Andreas Schwab "And now for something SuSE Labs completely different." [email protected] SuSE GmbH, Schanzäckerstr. 10, D-90443 Nürnberg Key fingerprint = 58CA 54C7 6D53 942B 1756 01D3 44D5 214B 8276 4ED5
Ah, without actually looking at the code, I believe that you have proven that acpidmp doesn't understand ACPI 2.0 data structures.
Sorry about that. I don't know what the plans are for updating acpidmp (if any).
~Randy________________________503-677-5408_____
-----------------------------------------------
Quoted 18 lines
-----Original Message-----
From: Andreas Schwab [mailto:[email protected]]"Dunlap, Randy" <[email protected]> writes:
|> At the bottom of
|> http://developer.intel.com/technology/IAPC/acpi/downloads.htmThanks, this works fine for BigSur. But on Lion I only get:
RSDP "MSLSAL" @
0x000f57b0
0000: 52 53 44 20 50 54 52 20 00 4d 53 4c 53 41 4c 00 RSD
PTR .MSLSAL.
0010: 00 00 00 00 ....acpidmp: cannot map the RSDT
Andreas.
"Dunlap, Randy" <[email protected]> writes:
|> Ah, without actually looking at the code, I believe that |> you have proven that acpidmp doesn't understand ACPI 2.0 |> data structures.
I don't think this is a problem with ACPI 2.0. The Lions have the ACPI structures (both pre 2.0 and 2.0) located at adresses above 0x3f000000, but acpidump only looks at the region 0xe0000 to 0x100000. The structure located at 0x000f57b0 doesn't contain a valid ACPI 2.0 structure either (the xsdt pointer is garbage).
Andreas.
Signature · 5 lines
Andreas Schwab "And now for something SuSE Labs completely different." [email protected] SuSE GmbH, Schanzäckerstr. 10, D-90443 Nürnberg Key fingerprint = 58CA 54C7 6D53 942B 1756 01D3 44D5 214B 8276 4ED5