Re: Reducing HDD writing affect on whole system.
On Mon, 17 Oct 2011 18:00:26 +0700, Sthu Deus wrote:
> Thank You for Your time and answer, Camaleón:
>
>>> For system that I'm speaking now is a Dell's laptop w/ AMD Tutorion64
>>> 2.4 GHz, 2G RAM, w/ Hitachi SATA 750G in it.
>>
>>If memory serves me right, Turion64 sounds like an "old" CPU, right?
>>
>>("old" for today CPU's rhythms of life means a mactufacturing date of
>>2005/2006)
>
> Yes, it is old - that is relating to its date of manufacturing, and not
> its value. :)
Of course!
It's pretty usual to see older machines last more than the new ones ;-)
>>Yes, there are many reports on that error:
>>
>>http://www.google.com/webhp?complete=0&hl=en#q=debian+MP-BIOS+bug:+8254
+timer+not+connected+to+IO-
APIC&hl=en&tbo=1&complete=0&prmd=imvns&tbas=0&source=lnt&sa=X&ei=2RKbTrePHMfAswbhocmUBA&ved=0CAkQpwUoAA&bav=on.2,or.r_gc.r_pw.,cf.osb&fp=bd638b897581bb57&biw=1280&bih=888
>
> Uhh. Why chromium does not open the link? :/
It can't? :-?
Copy/paste the full URL then.
Does this work better?
<http://www.google.com/webhp?complete=0&hl=en#q=debian+MP-BIOS+bug:+8254+timer+not+connected+to+IO-APIC&hl=en&tbo=1&complete=0&prmd=imvns&tbas=0&source=lnt&sa=X&ei=2RKbTrePHMfAswbhocmUBA&ved=0CAkQpwUoAA&bav=on.2,or.r_gc.r_pw.,cf.osb&fp=bd638b897581bb57&biw=1280&bih=888>
(I have enclosed the URI between "<...>" to avoid it breaks)
>>But the relation between this message and the hard disk slowdown is
>>unclear :-?
>
> I do not say that, just saw that - as we are talking on performance, I
> thought may that timer bug has any affect on HDD too. :\
Okay. Anyway, being related or not, true is that there are lots of ACPI errors :-(
>>> If interested I can upload some where whole dmesg output. Or some
>>> grep-ed info related to HDD performance problem.
>>
>>Yes please, the more accurate information you provide, the more changes
>>for a kernel hacker who reads your message can help you :-)
>
> OK. Here it is.
>
> http://pastebin.com/QYHxZmHd
Thanks!
Let me point the entries I would investigate further:
[ 0.007507] ACPI: Core revision 20110413
[ 0.012429] ..TIMER: vector=0x30 apic1=0 pin1=0 apic2=-1 pin2=-1
[ 0.016000] ..MP-BIOS bug: 8254 timer not connected to IO-APIC
[ 0.016000] ...trying to set up timer (IRQ0) through the 8259A ...
[ 0.016000] ..... (found apic 0 pin 0) ...
[ 0.058537] ....... works.
[ 0.157099] ACPI: EC: Look up EC in DSDT
[ 0.157099] [Firmware Bug]: ACPI: BIOS _OSI(Linux) query ignored
[ 0.164082] ACPI: Interpreter enabled
[ 0.164087] ACPI: (supports S0 S3 S4 S5)
[ 0.164121] ACPI: Using IOAPIC for interrupt routing
[ 0.175454] [Firmware Bug]: ACPI: No _BQC method, cannot determine initial brightness
[ 0.180367] ACPI: EC: GPE = 0x14, I/O: command/status = 0x66, data = 0x62
[ 0.180588] ACPI: No dock devices found.
[ 0.180592] HEST: Table not found.
[ 0.180596] PCI: Ignoring host bridge windows from ACPI; if necessary, use "pci=use_crs" and report a bug
[ 0.180852] ACPI Error: Needed type [Reference], found [Device] ffff880077bddda8 (20110413/exresop-104)
[ 0.180861] ACPI Exception: AE_AML_OPERAND_TYPE, While resolving operands for [OpcodeName unavailable] (20110413/dswexec-460)
[ 0.180869] ACPI Error: Method parse/execution failed [\_SB_.PCI0._OSC] (Node ffff880077bfdb00), AE_AML_OPERAND_TYPE (20110413/psparse-536)
[ 0.180887] ACPI: PCI Root Bridge [PCI0] (domain 0000 [bus 00-ff])
[ 0.186100] ACPI Error: Needed type [Reference], found [Device] ffff880077bddda8 (20110413/exresop-104)
[ 0.186108] ACPI Exception: AE_AML_OPERAND_TYPE, While resolving operands for [OpcodeName unavailable] (20110413/dswexec-460)
[ 0.186116] ACPI Error: Method parse/execution failed [\_SB_.PCI0._OSC] (Node ffff880077bfdb00), AE_AML_OPERAND_TYPE (20110413/psparse-536)
[ 0.186132] pci0000:00: Requesting ACPI _OSC control (0x1d)
[ 0.186196] ACPI Error: Needed type [Reference], found [Device] ffff880077bddda8 (20110413/exresop-104)
[ 0.186203] ACPI Exception: AE_AML_OPERAND_TYPE, While resolving operands for [OpcodeName unavailable] (20110413/dswexec-460)
[ 0.186211] ACPI Error: Method parse/execution failed [\_SB_.PCI0._OSC] (Node ffff880077bfdb00), AE_AML_OPERAND_TYPE (20110413/psparse-536)
[ 0.186227] pci0000:00: ACPI _OSC request failed (AE_AML_OPERAND_TYPE), returned control mask: 0x1d
[ 0.186230] ACPI _OSC control for PCIe not granted, disabling ASPM
[ 6.936172] [Firmware Bug]: ACPI: No _BQC method, cannot determine initial brightness
Don't ask me how to fix those messages (you can start trying by passing
to the kernel "pci=use_crs" as suggested) but they need to be
investigated. While they all seem to be harmless and related to ACPI
brightness and other ACPI functions (suspension state, device docking) a
quick Google search finds several references so this can be a know
problem and with a bit of luck, with a known by-pass.
Lastly, there is a log for an ext4 error:
[ 304.096062] EXT4-fs (sda2): error count: 15
[ 304.096073] EXT4-fs (sda2): initial error at 1313766195: ext4_mb_generate_buddy:736
[ 304.096083] EXT4-fs (sda2): last error at 1315801717: ext4_reserve_inode_write:5619
If those errors are logged frequently it may indicate a problem with the filesystem.
Greetings,
--
Camaleón
Reply to: