| View previous topic :: View next topic |
| Author |
Message |
mugurelu
n00b
Joined: 10 Sep 2003
Posts: 39
Location: Bucharest, Romania
|
 Posted: Wed Feb 04, 2004 11:33 pm Post subject: kernel 2.6 and my harddisk ... |
 |
|
I've noticed something strange after an upgrade to 2.6:
| Code: | enkidu root # hdparm -i /dev/hda
/dev/hda:
Model=Maxtor 6Y120P0, FwRev=YAR41BW0, SerialNo=Y41E78JE
Config={ Fixed }
RawCHS=16383/16/63, TrkSize=0, SectSize=0, ECCbytes=57
BuffType=DualPortCache, BuffSize=7936kB, MaxMultSect=16, MultSect=16
CurCHS=4047/16/255, CurSects=16511760, LBA=yes, LBAsects=240121728
IORDY=on/off, tPIO={min:120,w/IORDY:120}, tDMA={min:120,rec:120}
PIO modes: pio0 pio1 pio2 pio3 pio4
DMA modes: mdma0 mdma1 mdma2
UDMA modes: udma0 udma1 udma2
AdvancedPM=yes: disabled (255) WriteCache=enabled
Drive conforms to: (null):
* signifies the current active mode |
As you can see, hdparm say that there is no pio or dma active for my hard drive (there is no * sign in front on any of those options).
Performance seems to be OK:
| Code: | enkidu root # hdparm -tT /dev/hda
/dev/hda:
Timing buffer-cache reads: 764 MB in 2.01 seconds = 380.35 MB/sec
Timing buffered disk reads: 150 MB in 3.01 seconds = 49.82 MB/sec
|
Any ideas about what is wrong ? For example, for my second hard disk (a quantum fireball), udma4 is highlighted ...
_________________
In God we Trust. All others must have valid md5 checksums. |
|
| Back to top |
|
 |
dsd
Developer
Joined: 30 Mar 2003
Posts: 2162
Location: nr London
|
| Posted: Wed Feb 04, 2004 11:36 pm Post subject: |
|
|
when you run "hdparm /dev/hda" does it say that using_dma is 'yes'?
did you compile support into your kernel for your IDE controller?
_________________
http://dev.gentoo.org/~dsd |
|
| Back to top |
|
|
Vivid5500
n00b
Joined: 28 Jan 2004
Posts: 20
|
| Posted: Thu Feb 05, 2004 12:40 am Post subject: |
|
|
The WIERD thing is I have the complete opposite as you mugurelu.
Look at this:
| Code: |
bash-2.05b# hdparm -i /dev/hda
/dev/hda:
Model=Maxtor 6Y160P0, FwRev=YAR41BW0, SerialNo=Y41G4DZE
Config={ Fixed }
RawCHS=16383/16/63, TrkSize=0, SectSize=0, ECCbytes=57
BuffType=DualPortCache, BuffSize=7936kB, MaxMultSect=16, MultSect=16
CurCHS=16383/16/63, CurSects=16514064, LBA=yes, LBAsects=268435455
IORDY=on/off, tPIO={min:120,w/IORDY:120}, tDMA={min:120,rec:120}
PIO modes: pio0 pio1 pio2 pio3 pio4
DMA modes: mdma0 mdma1 mdma2
UDMA modes: udma0 udma1 udma2 udma3 udma4 udma5 *udma6
AdvancedPM=yes: disabled (255) WriteCache=enabled
Drive conforms to: (null):
* signifies the current active mode
|
Which indicates that its set to UDMA6 (as it should be) since my drive is said to be UDMA 133. Now the wierd part is the performance, look at this:
| Code: |
bash-2.05b# hdparm -tT /dev/hda
/dev/hda:
Timing buffer-cache reads: 996 MB in 2.00 seconds = 497.58 MB/sec
Timing buffered disk reads: 4 MB in 3.19 seconds = 1.25 MB/sec
|
Now how wierd is that? I posted a similar thread earlier today but nobody has replied yet. I have an A7N8X Deluxe and I built in AMD and nVidia support. There is a wierd part though, in dmesg:
| Code: |
ide: Assuming 33MHz system bus speed for PIO modes; override with idebus=xx
NFORCE2: IDE controller at PCI slot 0000:00:09.0
NFORCE2: chipset revision 162
NFORCE2: not 100% native mode: will probe irqs later
NFORCE2: BIOS didn't set cable bits correctly. Enabling workaround.
|
Which leads me to believe its the BIOS thats causing the problem. Any body have any similar problems? |
|
| Back to top |
|
|
dsd
Developer
Joined: 30 Mar 2003
Posts: 2162
Location: nr London
|
| Posted: Thu Feb 05, 2004 7:33 am Post subject: |
|
|
i dont think those messages are causing any problems, at least, they arent for me on my Abit nf7-S.
| Code: | -> dmesg | grep NFORCE2
NFORCE2: IDE controller at PCI slot 0000:00:09.0
NFORCE2: chipset revision 162
NFORCE2: not 100% native mode: will probe irqs later
NFORCE2: BIOS didn't set cable bits correctly. Enabling workaround.
NFORCE2: 0000:00:09.0 (rev a2) UDMA133 controller
-> hdparm -t /dev/hda
/dev/hda:
Timing buffered disk reads: 164 MB in 3.01 seconds = 54.48 MB/sec
|
_________________
http://dev.gentoo.org/~dsd |
|
| Back to top |
|
|
Vivid5500
n00b
Joined: 28 Jan 2004
Posts: 20
|
| Posted: Thu Feb 05, 2004 7:47 am Post subject: |
|
|
| Thats so wierd.. I have no clue as to why my performance is so bad compared to everybody else's.. |
|
| Back to top |
|
|
mugurelu
n00b
Joined: 10 Sep 2003
Posts: 39
Location: Bucharest, Romania
|
| Posted: Thu Feb 05, 2004 8:03 am Post subject: |
|
|
| Code: | enkidu root # hdparm /dev/hda
/dev/hda:
multcount = 16 (on)
IO_support = 1 (32-bit)
unmaskirq = 1 (on)
using_dma = 1 (on)
keepsettings = 0 (off)
readonly = 0 (off)
readahead = 256 (on)
geometry = 65535/16/63, sectors = 240121728, start = 0 |
Ies, I selected the required IDE controller in the kernel (VIA).
_________________
In God we Trust. All others must have valid md5 checksums. |
|
| Back to top |
|
|
mugurelu
n00b
Joined: 10 Sep 2003
Posts: 39
Location: Bucharest, Romania
|
| Posted: Thu Feb 05, 2004 11:13 am Post subject: |
|
|
The problem may reside somewhere else, not in kernel 2.6, as I believed initially. I just booted with the 2.4.20 gentoo-sources kernel, and the problem is manifesting there too.
I can't complain the performance (50MB/s is nice, i think  ), but why the hell that stinkin' * does not appear where it should be ?
_________________
In God we Trust. All others must have valid md5 checksums. |
|
| Back to top |
|
|
Insanity5902
Veteran
Joined: 23 Jan 2004
Posts: 1228
Location: Fort Worth, Texas
|
| Posted: Mon Feb 16, 2004 9:10 pm Post subject: |
|
|
I just foudn this in another post ... basically instead of generic ide, goto pci ide and then generic pci-bus master and then you should see your chipset 
https://forums.gentoo.org/viewtopic.php?p=798408#798408
I will let you know how it works |
|
| Back to top |
|
|
Insanity5902
Veteran
Joined: 23 Jan 2004
Posts: 1228
Location: Fort Worth, Texas
|
| Posted: Mon Feb 16, 2004 9:14 pm Post subject: |
|
|
yeah that worked, but now for some reason mine is stuck at 33mhz. I might have a bad cable in there 
[edit]
okay or not, I just read the specs for my drive and it read time maxes out at 35 mb/s and I am getting 33.72 in my buffered disk reads. hmm oh well
[/edit] |
|
| Back to top |
|
|
dsd
Developer
Joined: 30 Mar 2003
Posts: 2162
Location: nr London
|
| Posted: Mon Feb 16, 2004 11:53 pm Post subject: |
|
|
33mhz is good.
lower is better, for once.
_________________
http://dev.gentoo.org/~dsd |
|
| Back to top |
|
|
Insanity5902
Veteran
Joined: 23 Jan 2004
Posts: 1228
Location: Fort Worth, Texas
|
| Posted: Tue Feb 17, 2004 1:37 am Post subject: |
|
|
| not when it is supposed to run at 133 mhz ? |
|
| Back to top |
|
|
geoffs
n00b
Joined: 15 Feb 2003
Posts: 35
Location: Canada
|
| Posted: Wed Mar 10, 2004 9:58 pm Post subject: |
|
|
i have been having issues with correct speeds. Mobo is an Abit NF7 (nforce2), everything else works fine.
hdparm /dev/hda
| Code: |
/dev/hda:
multcount = 16 (on)
IO_support = 1 (32-bit)
unmaskirq = 1 (on)
using_dma = 1 (on)
keepsettings = 0 (off)
readonly = 0 (off)
readahead = 256 (on)
geometry = 16383/255/63, sectors = 234441648, start = 0
|
hdparm -tT /dev/hda
| Code: |
/dev/hda:
Timing buffer-cache reads: 2040 MB in 2.00 seconds = 1019.65 MB/sec
Timing buffered disk reads: 78 MB in 3.02 seconds = 25.87 MB/sec
|
dmesg snippet
| Code: |
ide: Assuming 33MHz system bus speed for PIO modes; override with idebus=xx
NFORCE2: IDE controller at PCI slot 0000:00:09.0
NFORCE2: chipset revision 162
NFORCE2: not 100% native mode: will probe irqs later
NFORCE2: 0000:00:09.0 (rev a2) UDMA133 controller
ide0: BM-DMA at 0xf000-0xf007, BIOS settings: hda:DMA, hdb:DMA
ide1: BM-DMA at 0xf008-0xf00f, BIOS settings: hdc:DMA, hdd:DMA
hda: WDC WD1200JB-00DUA3, ATA DISK drive
Using cfq io scheduler
ide0 at 0x1f0-0x1f7,0x3f6 on irq 14
hdc: LITE-ON LTR-52246S, ATAPI CD/DVD-ROM drive
hdd: SONY DVD-ROM DDU1211, ATAPI CD/DVD-ROM drive
ide1 at 0x170-0x177,0x376 on irq 15
hda: max request size: 1024KiB
hda: 234441648 sectors (120034 MB) w/8192KiB Cache, CHS=16383/255/63, UDMA(33)
/dev/ide/host0/bus0/target0/lun0: p1 p2 p3 p4
hdc: ATAPI 52X CD-ROM CD-R/RW CD-MRW drive, 2048kB Cache, UDMA(33)
Uniform CD-ROM driver Revision: 3.20
hdd: ATAPI 40X DVD-ROM drive, 512kB Cache, UDMA(33)
|
uname -a
| Code: |
Linux opbot 2.6.4-rc2-love1 #1 Wed Mar 10 15:22:17 Local time zone must be set--see zic manu i686 AMD Athlon(tm) XP 3200+ AuthenticAMD GNU/Linux
|
I have a 120GB WD JB (8mb cache) it should be detected / running at udma(100) not udma(33). And based on hdparm on other gentoo machines with the same drive my disk reads should be double.
Any ideas?
_________________
CAT |
|
| Back to top |
|
|
dsd
Developer
Joined: 30 Mar 2003
Posts: 2162
Location: nr London
|
| Posted: Wed Mar 10, 2004 10:12 pm Post subject: |
|
|
| Quote: | | not when it is supposed to run at 133 mhz ? |
its not. the bus speed is a different thing entirely. lower is better, 33mhz is right for nforce2, i believe most other boards have 66mhz.
| geoffs wrote: | | I have a 120GB WD JB (8mb cache) it should be detected / running at udma(100) not udma(33). And based on hdparm on other gentoo machines with the same drive my disk reads should be double. |
are you using 80 conductor cables? is there anything else on the same IDE cable alongside the HDD?
_________________
http://dev.gentoo.org/~dsd |
|
| Back to top |
|
|
geoffs
n00b
Joined: 15 Feb 2003
Posts: 35
Location: Canada
|
| Posted: Wed Mar 10, 2004 10:29 pm Post subject: |
|
|
dsd: I am using 80pin cable and there isn't anything else on that channel. I will switch out the cable to make sure it isn't the culprit.
_________________
CAT |
|
| Back to top |
|
|
dsd
Developer
Joined: 30 Mar 2003
Posts: 2162
Location: nr London
|
| Posted: Wed Mar 10, 2004 10:42 pm Post subject: |
|
|
also check bios settings. either set it to auto or run the IDE HDD AUTO DETECTION.
_________________
http://dev.gentoo.org/~dsd |
|
| Back to top |
|
|
geoffs
n00b
Joined: 15 Feb 2003
Posts: 35
Location: Canada
|
| Posted: Thu Mar 11, 2004 12:26 am Post subject: |
|
|
well dsd, that was it, for some reason UDMA was disabled in the BIOS. If other NF7 owners are having troubles I suggest starting in there. I didn't disable this setting, so I assume it was like this from the factory.
thanks for the help! Made all those kernel recompiles pretty pointless...but still fun. 
_________________
CAT |
|
| Back to top |
|
|
Insanity5902
Veteran
Joined: 23 Jan 2004
Posts: 1228
Location: Fort Worth, Texas
|
| Posted: Thu Mar 11, 2004 2:52 pm Post subject: |
|
|
| dsd wrote: | | Quote: | | not when it is supposed to run at 133 mhz ? |
its not. the bus speed is a different thing entirely. lower is better, 33mhz is right for nforce2, i believe most other boards have 66mhz. |
I am sorry for my ignorance, but I work in the IT world and only work on linux when it is on my personal PC. I have not heard of this beofre, do you mind elaborating on this speed and what it is for, etc. Or do you have link where I could read up on this. I like to pride myself of knowing just about everything with comptuers and i have never heard of this speed before. I feel like such a n00b again
_________________
Join the adopt an unanswered post initiative today |
|
| Back to top |
|
|
neenee
Veteran
Joined: 20 Jul 2003
Posts: 1786
|
| Posted: Thu Mar 11, 2004 3:10 pm Post subject: |
|
|
if you have a normal pci motherboard, your bus speed should always
be 33 mhz (ide runs over pci bus). this is something else than the
numbers ata 66/100/133. that is is the speed in mbit/s that the bus
supports as in protocol. a pci bus of 33 mhz and 32 bit can theoretically
support a data throughput of 33 * 10^6 * 4 bytes / sec = 133 mbyte/s,
which is enough for all ata modes available today (one byte is 8 bits).
normal ata 133 is therefore at the limit of what a *normal* pci bus can
support. ofcourse there is also 64 bit pci and/or 66mhz pci bus, but you
normally won't have those. serial ata is the next generation and i don't
know how that is done.
conclusion: the ide bus (or pci) speed at 33 mhz is just fine.
look for transfer mode instead: hdparm -X?? |
|
| Back to top |
|
|
Insanity5902
Veteran
Joined: 23 Jan 2004
Posts: 1228
Location: Fort Worth, Texas
|
| Posted: Thu Mar 11, 2004 3:20 pm Post subject: |
|
|
Okay that makes sense. I just wasn't understanding where the 33 was coming from. I didn't know the ide speed came from the pci bus. It is true, you learn something knew everyday.
So I am guessing that sata ... i guess works off of its own bus. I am suing it on my linux box with raid 0, quite ncie with two WD Raptors
_________________
Join the adopt an unanswered post initiative today |
|
| Back to top |
|
|
|
Kernel & Hardware
