lkml.org 
[lkml]   [1996]   [Nov]   [6]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
SubjectRe: Since so many people have asked me this
Date
From
Hiho

>
> Whats in 2.0.23ac#2 thats not in 2.0.24
>
> 1. SMP irq forwarding, this gives BIG performance/latency improvements
> with Linux/SMP, but its not exactly a bug fix.
>
> 2. Linus version of the socket change uses int not __u32. I'll submit
> that as a patch again to use __u32 for the benefit of the folks trying to
> get the Linux stack running on a certain 16bit OS
>
> 3. Several bugs that Linus and others fixed between 2.0.23/2.0.24
>
> Thats it.. so unless you want to play with some of the fun SMP stuff, use
> 2.0.24. My next patch will be 2.0.24ac#1 and will just be whatever patches

I havn't seen 2.0.24ac#1 yet (on shadow.cabi.net).

> I send to Linus for 2.0.25, and the SMP improvements for those who need
> good SMP interrupt latency etc.

This patch (2.0.23ac#2 changed for 2.0.24) results in an unstable machine for
me. When I do a kernelcompile with make -j5 (5 is basically too much to get a
good performance with 24MB RAM but it triggers the SMP bug much easier)
my machine is just dead (without any messages in the logfiles or on the
console with sys/klogd not used). Is this still the error with physical CPU #1
not present?

My setup is:
- patched linux 2.0.24
- gigabyte 586DX dual pentium motherboard (HX chipset) with 2xP100, 24 mb RAM
and adaptec 2940UW on board.

/proc/cpuinfo says:

processor : 0
cpu : 586
model : Pentium 75+
vendor_id : GenuineIntel
stepping : 6
fdiv_bug : no
hlt_bug : no
fpu : yes
fpu_exception : yes
cpuid : yes
wp : yes
flags : fpu vme de pse tsc msr mce cx8 apic
bogomips : 40.04

processor : 1
cpu : 586
model : Pentium 75+
vendor_id : GenuineIntel
stepping : 5
fdiv_bug : no
hlt_bug : no
fpu : yes
fpu_exception : yes
cpuid : yes
wp : yes
flags : fpu vme de pse tsc msr mce cx8 apic
bogomips : 40.04


And the (relevant) bootmessages of my system:
Nov 3 17:11:19 gandalf kernel: Scan SMP from 00000000 for 1024 bytes.
Nov 3 17:11:19 gandalf kernel: Scan SMP from 0009fc00 for 1024 bytes.
Nov 3 17:11:19 gandalf kernel: Scan SMP from 000f0000 for 65536 bytes.
Nov 3 17:11:19 gandalf kernel: Intel MultiProcessor Specification v1.1
Nov 3 17:11:19 gandalf kernel: Virtual Wire compatibility mode.
Nov 3 17:11:19 gandalf kernel: OEM ID: OEM00000 Product ID: PROD00000000 APIC at: 0xFEE00000
Nov 3 17:11:19 gandalf kernel: Processor #0 Pentium(tm) APIC version 17
Nov 3 17:11:19 gandalf kernel: Floating point unit present.
Nov 3 17:11:19 gandalf kernel: Machine Exception supported.
Nov 3 17:11:19 gandalf kernel: 64 bit compare & exchange supported.
Nov 3 17:11:19 gandalf kernel: Internal APIC present.
Nov 3 17:11:19 gandalf kernel: Bootup CPU
Nov 3 17:11:19 gandalf kernel: Processor #1 Pentium(tm) APIC version 17
Nov 3 17:11:19 gandalf kernel: Floating point unit present.
Nov 3 17:11:19 gandalf kernel: Machine Exception supported.
Nov 3 17:11:19 gandalf kernel: 64 bit compare & exchange supported.
Nov 3 17:11:19 gandalf kernel: Internal APIC present.
Nov 3 17:11:19 gandalf kernel: Bus #0 is ISA
Nov 3 17:11:19 gandalf kernel: Bus #1 is PCI
Nov 3 17:11:19 gandalf kernel: I/O APIC #2 Version 17 at 0xFEC00000.
Nov 3 17:11:19 gandalf kernel: Processors: 2
......
Nov 3 17:11:19 gandalf kernel: Getting VERSION: 30010
Nov 3 17:11:19 gandalf kernel: Getting VERSION: 30010
Nov 3 17:11:19 gandalf kernel: Getting LVT0: 700
Nov 3 17:11:19 gandalf kernel: Getting LVT1: 400
Nov 3 17:11:19 gandalf kernel: CPU map: 3
Nov 3 17:11:19 gandalf kernel: Booting processor 1 stack 00002000: Setting warm reset code and vector.
Nov 3 17:11:19 gandalf kernel: Asserting INIT.
Nov 3 17:11:19 gandalf kernel: Deasserting INIT.
Nov 3 17:11:19 gandalf kernel: Sending STARTUP #1.
Nov 3 17:11:19 gandalf kernel: CALLIN 1
Nov 3 17:11:19 gandalf kernel: Calibrating delay loop.. Sending STARTUP #2.
Nov 3 17:11:19 gandalf kernel: ok - 40.04 BogoMIPS
Nov 3 17:11:19 gandalf kernel: Total of 2 processors activated (80.08 BogoMIPS).


Matthias

O .---------------. .___________. O
/\/ . `. m_sattle@ ,' / \ +FAX . \/\
__..--- ' /\/ | `._________,' | (___)/ * * \(___) \/ \ ` ---..__
""---__ \/`. | informatik. | / | \ +49 (0)6333 ,'\/ __---""
`.. / | .uni-kl.de | | `...' | -65079 \ ...'
`---------------' `._____.'

--> Don't take life too seriously -- you'll never get out of it alive. <--

\
 
 \ /
  Last update: 2005-03-22 13:38    [W:0.232 / U:0.204 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site