Re: hw.setperf strangeness
On Sat, 2005-11-26 at 01:51 -0800, Ted Unangst wrote: > since the dmesg you posted previously contains the line: > ichpcib0 at pci0 dev 31 function 0 "Intel 82801DBM LPC" rev 0x03: SpeedStep > > i think you're confused about something. Indeed, I must be very confused. I did the dmesg check on the wrong box. DUH! It does have SpeedStep in it. -- Lars
Re: hw.setperf strangeness
On 11/26/05, Lars Hansson <[EMAIL PROTECTED]> wrote: > On Sat, 2005-11-26 at 01:33 -0800, Ted Unangst wrote: > > On 11/25/05, Lars Hansson <[EMAIL PROTECTED]> wrote: > > > Is there any way to determine from the dmesg if speedstep is > > > detected? > > > > dmesg | grep SpeedStep works pretty well. > > Well, that comes up empty so I guess the speedstep in this > box isnt being detected. I'll try to fiddle with the BIOS > SpeedStep options to see if that has any effect. since the dmesg you posted previously contains the line: ichpcib0 at pci0 dev 31 function 0 "Intel 82801DBM LPC" rev 0x03: SpeedStep i think you're confused about something.
Re: hw.setperf strangeness
On Sat, 2005-11-26 at 01:33 -0800, Ted Unangst wrote: > On 11/25/05, Lars Hansson <[EMAIL PROTECTED]> wrote: > > Is there any way to determine from the dmesg if speedstep is > > detected? > > dmesg | grep SpeedStep works pretty well. Well, that comes up empty so I guess the speedstep in this box isnt being detected. I'll try to fiddle with the BIOS SpeedStep options to see if that has any effect. --- Lars Hansson
Re: hw.setperf strangeness
On 11/25/05, Lars Hansson <[EMAIL PROTECTED]> wrote: > Is there any way to determine from the dmesg if speedstep is > detected? dmesg | grep SpeedStep works pretty well.
Re: hw.setperf strangeness
On Friday 25 November 2005 20:03, Ted Unangst wrote: > maybe, speedstep can only be set to fast and slow, and the driver > won't move things if it thinks nothing is changing. maybe there's a > bug, maybe you need to fiddle it up and down some to make it actually > work, but 0 and 100 are the only settings that really mean anything. It would seem nothing is happening: $ sysctl hw | tail -2 hw.cpuspeed=1296 hw.setperf=100 $ md5 -t MD5 time trial. Processing 1 1-byte blocks... Digest = 52e5f9c9e6f656f3e1800dfa5579d089 Time = 0.691865 seconds Speed = 144536867.741539 bytes/second $ sudo sysctl -w hw.setperf=0 hw.setperf: 100 -> 0 $ sysctl hw | tail -2 hw.cpuspeed=1296 hw.setperf=0 $ md5 -t MD5 time trial. Processing 1 1-byte blocks... Digest = 52e5f9c9e6f656f3e1800dfa5579d089 Time = 0.693320 seconds Speed = 144233542.952749 bytes/second $ sudo sysctl -w hw.setperf=80 hw.setperf: 0 -> 80 $ sysctl hw | tail -2 hw.cpuspeed=750 hw.setperf=80 $ md5 -t MD5 time trial. Processing 1 1-byte blocks... Digest = 52e5f9c9e6f656f3e1800dfa5579d089 Time = 0.695775 seconds Speed = 143724623.621142 bytes/second Is there any way to determine from the dmesg if speedstep is detected? --- Lars Hansson
Re: hw.setperf strangeness
On 11/23/05, Lars Hansson <[EMAIL PROTECTED]> wrote: > This seems a bit strange to ne: > $ sysctl hw | tail -2 > hw.cpuspeed=1296 > hw.setperf=100 > > $ sudo sysctl -w hw.setperf=0 > hw.setperf: 100 -> 0 > $ sysctl hw | tail -2 > hw.cpuspeed=1296 > hw.setperf=0 > > Hmm..shouldnt cpuspeed have changed? maybe, speedstep can only be set to fast and slow, and the driver won't move things if it thinks nothing is changing. maybe there's a bug, maybe you need to fiddle it up and down some to make it actually work, but 0 and 100 are the only settings that really mean anything.
Re: hw.setperf strangeness
On Thu, 24 Nov 2005 18:48:44 -0700 Theo de Raadt <[EMAIL PROTECTED]> wrote: > Oh come on. > > You think we have all day to find various mails from various people and > piece them together? Indeed, that would be silly. I should have attached it. My mistake. --- Lars Hansson
Re: hw.setperf strangeness
On Thu, 24 Nov 2005 10:03:44 +0800 Lars Hansson <[EMAIL PROTECTED]> wrote: > It would appear that changing hw-setperf doesn't actually do anything at all > on this box. The dmesg says it has Speedstep though. Err, it has speedstep but that's not in the dmesg. --- Lars Hansson
Re: hw.setperf strangeness
> > *classic* bug report. You completely fail to mention the machine > > type, or show a dmesg. > Actually, I sent the dmesg in my immediatelly previous message to the list > and therefore I didnt attach again. Oh come on. You think we have all day to find various mails from various people and piece them together? Maybe there is a bug. Maybe it should be fixed. But this particular bug right here, with your attitude -- wow -- you just lost my attention.
Re: hw.setperf strangeness
On Thu, 24 Nov 2005 09:23:32 -0700 Theo de Raadt <[EMAIL PROTECTED]> wrote: > *classic* bug report. You completely fail to mention the machine > type, or show a dmesg. Actually, I sent the dmesg in my immediatelly previous message to the list and therefore I didnt attach again. As for the machine type, it's a completely generic laptop called X-Mobile C24i. I really did forget to attach the md5 -t output so here it is: $ sysctl hw | tail -2 hw.cpuspeed=1296 hw.setperf=100 $ md5 -t MD5 time trial. Processing 1 1-byte blocks... Digest = 52e5f9c9e6f656f3e1800dfa5579d089 Time = 0.691865 seconds Speed = 144536867.741539 bytes/second $ sudo sysctl -w hw.setperf=0 hw.setperf: 100 -> 0 $ sysctl hw | tail -2 hw.cpuspeed=1296 hw.setperf=0 $ md5 -t MD5 time trial. Processing 1 1-byte blocks... Digest = 52e5f9c9e6f656f3e1800dfa5579d089 Time = 0.693320 seconds Speed = 144233542.952749 bytes/second $ sudo sysctl -w hw.setperf=80 hw.setperf: 0 -> 80 $ sysctl hw | tail -2 hw.cpuspeed=750 hw.setperf=80 MD5 time trial. Processing 1 1-byte blocks... Digest = 52e5f9c9e6f656f3e1800dfa5579d089 Time = 0.695775 seconds Speed = 143724623.621142 bytes/second It would appear that changing hw-setperf doesn't actually do anything at all on this box. The dmesg says it has Speedstep though. (dmesg attached again) --- Lars Hansson OpenBSD 3.8-current (GENERIC) #265: Wed Nov 23 15:06:35 MST 2005 [EMAIL PROTECTED]:/usr/src/sys/arch/i386/compile/GENERIC cpu0: Intel(R) Celeron(R) M processor 1.30GHz ("GenuineIntel" 686-class) 1.30 GHz cpu0: FPU,V86,DE,PSE,TSC,MSR,PAE,MCE,CX8,SEP,MTRR,PGE,MCA,CMOV,PAT,CFLUSH,ACPI,MMX,FXSR,SSE,SSE2,SS,TM,SBF real mem = 234397696 (228904K) avail mem = 206987264 (202136K) using 2886 buffers containing 11821056 bytes (11544K) of memory mainbus0 (root) bios0 at mainbus0: AT/286+(17) BIOS, date 05/21/01, BIOS32 rev. 0 @ 0xe9b90 apm0 at bios0: Power Management spec V1.2 apm0: AC on, battery charge unknown apm0: flags 30102 dobusy 0 doidle 1 pcibios0 at bios0: rev 2.1 @ 0xe7000/0x661 pcibios0: PCI IRQ Routing Table rev 1.0 @ 0xfe840/144 (7 entries) pcibios0: PCI Interrupt Router at 000:31:0 ("Intel 82801AA LPC" rev 0x00) pcibios0: PCI bus #2 is the last bus bios0: ROM list: 0xc/0xc800! 0xe/0x1800 0xe6000/0x1000! cpu0 at mainbus0 esm at mainbus0 not configured pci0 at mainbus0 bus 0: configuration mode 1 (no bios) pchb0 at pci0 dev 0 function 0 "Intel 82852GM Hub-PCI" rev 0x02 "Intel 82852GM Memory" rev 0x02 at pci0 dev 0 function 1 not configured "Intel 82852GM Configuration" rev 0x02 at pci0 dev 0 function 3 not configured vga1 at pci0 dev 2 function 0 "Intel 82852GM AGP" rev 0x02: aperture at 0xb000, size 0x800 wsdisplay0 at vga1 mux 1: console (80x25, vt100 emulation) wsdisplay0: screen 1-5 added (80x25, vt100 emulation) "Intel 82852GM AGP" rev 0x02 at pci0 dev 2 function 1 not configured uhci0 at pci0 dev 29 function 0 "Intel 82801DB USB" rev 0x03: irq 10 usb0 at uhci0: USB revision 1.0 uhub0 at usb0 uhub0: Intel UHCI root hub, rev 1.00/1.00, addr 1 uhub0: 2 ports with 2 removable, self powered uhci1 at pci0 dev 29 function 1 "Intel 82801DB USB" rev 0x03: irq 11 usb1 at uhci1: USB revision 1.0 uhub1 at usb1 uhub1: Intel UHCI root hub, rev 1.00/1.00, addr 1 uhub1: 2 ports with 2 removable, self powered uhci2 at pci0 dev 29 function 2 "Intel 82801DB USB" rev 0x03: irq 11 usb2 at uhci2: USB revision 1.0 uhub2 at usb2 uhub2: Intel UHCI root hub, rev 1.00/1.00, addr 1 uhub2: 2 ports with 2 removable, self powered ehci0 at pci0 dev 29 function 7 "Intel 82801DB USB" rev 0x03: irq 7 usb3 at ehci0: USB revision 2.0 uhub3 at usb3 uhub3: Intel EHCI root hub, rev 2.00/1.00, addr 1 uhub3: 6 ports with 6 removable, self powered ppb0 at pci0 dev 30 function 0 "Intel 82801BAM Hub-to-PCI" rev 0x83 pci1 at ppb0 bus 1 cbb0 at pci1 dev 0 function 0 "Texas Instruments PCI1410 CardBus" rev 0x02: irq 5 rl0 at pci1 dev 2 function 0 "Realtek 8139" rev 0x10: irq 11, address 00:e0:4c:44:00:4e rlphy0 at rl0 phy 0: RTL internal phy cardslot0 at cbb0 slot 0 flags 0 cardbus0 at cardslot0: bus 2 device 0 cacheline 0x0, lattimer 0x40 pcmcia0 at cardslot0 ichpcib0 at pci0 dev 31 function 0 "Intel 82801DBM LPC" rev 0x03: SpeedStep pciide0 at pci0 dev 31 function 1 "Intel 82801DBM IDE" rev 0x03: DMA, channel 0 configured to compatibility, channel 1 configured to compatibility wd0 at pciide0 channel 0 drive 0: wd0: 16-sector PIO, LBA, 38154MB, 78140160 sectors wd0(pciide0:0:0): using PIO mode 4, Ultra-DMA mode 5 atapiscsi0 at pciide0 channel 1 drive 0 scsibus0 at atapiscsi0: 2 targets cd0 at scsibus0 targ 0 lun 0: SCSI0 5/cdrom removable cd0(pciide0:1:0): using PIO mode 4, Ultra-DMA mode 2 "Intel 82801DB SMBus" rev 0x03 at pci0 dev 31 function 3 not configured auich0 at pci0 dev 31 function 5 "Intel 82801DB AC97" rev 0x03: irq 5, ICH4 AC97 ac97: codec id 0x414c4760 (Avance Logic ALC655) audio0 at auich0 "Intel 82801DB Modem" rev 0x03 a
Re: hw.setperf strangeness
*classic* bug report. You completely fail to mention the machine type, or show a dmesg. I just don't get it. How is it that people keep forgetting that? Are they just totally unaware that there are machine differences, and they might matter? > This seems a bit strange to ne: > $ sysctl hw | tail -2 > hw.cpuspeed=1296 > hw.setperf=100 > > $ sudo sysctl -w hw.setperf=0 > hw.setperf: 100 -> 0 > $ sysctl hw | tail -2 > hw.cpuspeed=1296 > hw.setperf=0 > > Hmm..shouldnt cpuspeed have changed? > > $ sudo sysctl -w hw.setperf=10 > hw.setperf: 0 -> 10 > $ sysctl hw | tail -2 > hw.cpuspeed=1296 > hw.setperf=10 > > Still no change. > > $ sudo sysctl -w hw.setperf=80 > hw.setperf: 10 -> 80 > $ sysctl hw | tail -2 > hw.cpuspeed=750 > hw.setperf=80 > > Say what? 80% is 750? Ok, at least something happened now. > > $ sudo sysctl -w hw.setperf=60 > hw.setperf: 80 -> 60 > $ sysctl hw | tail -2 > hw.cpuspeed=750 > hw.setperf=60 > > Ok, I guess I cant go lower than 750. > > $ sudo sysctl -w hw.setperf=90 > hw.setperf: 60 -> 90 > $ sysctl hw | tail -2 > hw.cpuspeed=750 > hw.setperf=90 > > Hmmm..Shouldnt this have set cpuspeed higher than 750? > > $ sudo sysctl -w hw.setperf=100 > hw.setperf: 90 -> 100 > $ sysctl hw | tail -2 > hw.cpuspeed=750 > hw.setperf=100 > > Shouldnt cpuspeed be back to full now? > (dmesg in previous email) > > --- > Lars Hansson
hw.setperf strangeness
This seems a bit strange to ne: $ sysctl hw | tail -2 hw.cpuspeed=1296 hw.setperf=100 $ sudo sysctl -w hw.setperf=0 hw.setperf: 100 -> 0 $ sysctl hw | tail -2 hw.cpuspeed=1296 hw.setperf=0 Hmm..shouldnt cpuspeed have changed? $ sudo sysctl -w hw.setperf=10 hw.setperf: 0 -> 10 $ sysctl hw | tail -2 hw.cpuspeed=1296 hw.setperf=10 Still no change. $ sudo sysctl -w hw.setperf=80 hw.setperf: 10 -> 80 $ sysctl hw | tail -2 hw.cpuspeed=750 hw.setperf=80 Say what? 80% is 750? Ok, at least something happened now. $ sudo sysctl -w hw.setperf=60 hw.setperf: 80 -> 60 $ sysctl hw | tail -2 hw.cpuspeed=750 hw.setperf=60 Ok, I guess I cant go lower than 750. $ sudo sysctl -w hw.setperf=90 hw.setperf: 60 -> 90 $ sysctl hw | tail -2 hw.cpuspeed=750 hw.setperf=90 Hmmm..Shouldnt this have set cpuspeed higher than 750? $ sudo sysctl -w hw.setperf=100 hw.setperf: 90 -> 100 $ sysctl hw | tail -2 hw.cpuspeed=750 hw.setperf=100 Shouldnt cpuspeed be back to full now? (dmesg in previous email) --- Lars Hansson