| View previous topic :: View next topic |
| Author |
Message |
netster
n00b
Joined: 08 Sep 2002
Posts: 41
Location: germany
|
 Posted: Thu Feb 05, 2004 11:57 am Post subject: hda with slow preformence :-/ |
 |
|
hey everyone ....
i got problems with my preformance on hba .... i tried alot stuff to speedup, but nothing helped this far .... perhaphs someone can say i'm a blind fool ?
atm working with ' hdparm -m16 -c1 -d1 -u1 -k1 -X68 /dev/hda '
my stats are following ...
| Code: | | 2.4.20-gentoo-r8 #1 SMP Wed Nov 26 18:11:08 CET 2003 i686 VIA Samuel 2 CentaurHauls GNU/Linux / 256megs ram / hda is a quantum fireball 20gb 7.200rpm / 2nd nic in pci |
i cannot try to connect the disc to 2nd ide, cause its a 533 epia with a single ide-connector 
thx for any help !!!! 
cheers, john
| Code: |
root@mailserver log # hdparm -Tt /dev/hda
/dev/hda:
Timing buffer-cache reads: 116 MB in 2.04 seconds = 56.86 MB/sec
Timing buffered disk reads: 12 MB in 3.05 seconds = 3.93 MB/sec
|
my kernel log about my ide-sub:
| Code: |
Feb 5 06:09:26 mailserver kernel: Uniform Multi-Platform E-IDE driver Revision: 6.31
Feb 5 06:09:26 mailserver kernel: ide: Assuming 33MHz system bus speed for PIO modes; override with idebus=xx
Feb 5 06:09:26 mailserver kernel: VP_IDE: IDE controller on PCI bus 00 dev 89
Feb 5 06:09:26 mailserver kernel: VP_IDE: chipset revision 6
Feb 5 06:09:26 mailserver kernel: VP_IDE: not 100%% native mode: will probe irqs later
Feb 5 06:09:26 mailserver kernel: ide: Assuming 33MHz system bus speed for PIO modes; override with idebus=xx
Feb 5 06:09:26 mailserver kernel: VP_IDE: VIA vt8231 (rev 10) IDE UDMA100 controller on pci00:11.1
Feb 5 06:09:26 mailserver kernel: ide0: BM-DMA at 0xd000-0xd007, BIOS settings: hda:DMA, hdb:pio
Feb 5 06:09:26 mailserver kernel: hda: QUANTUM FIREBALLP LM20.5, ATA DISK drive
Feb 5 06:09:26 mailserver kernel: ide0 at 0x1f0-0x1f7,0x3f6 on irq 14
Feb 5 06:09:26 mailserver kernel: blk: queue c01b5944, I/O limit 4095Mb (mask 0xffffffff)
Feb 5 06:09:26 mailserver kernel: hda: 40132503 sectors (20548 MB) w/1900KiB Cache, CHS=2498/255/63, UDMA(66)
Feb 5 06:09:26 mailserver kernel: Partition check:
Feb 5 06:09:26 mailserver kernel: /dev/ide/host0/bus0/target0/lun0: p1 p2 p3
Feb 5 06:09:26 mailserver kernel: RAMDISK driver initialized: 16 RAM disks of 8192K size 1024 blocksize
|
my hdparm infos :
| Code: |
root@mailserver log # hdparm -i /dev/hda
/dev/hda:
Model=QUANTUM FIREBALLP LM20.5, FwRev=A35.0700, SerialNo=884028164904
Config={ HardSect NotMFM HdSw>15uSec Fixed DTR>10Mbs }
RawCHS=16383/16/63, TrkSize=32256, SectSize=21298, ECCbytes=4
BuffType=DualPortCache, BuffSize=1900kB, MaxMultSect=16, MultSect=16
CurCHS=16383/16/63, CurSects=16514064, LBA=yes, LBAsects=40132503
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
AdvancedPM=no WriteCache=enabled
Drive conforms to: ATA/ATAPI-5 T13 1321D revision 1:
* signifies the current active mode
root@mailserver log # hdparm /dev/hda
/dev/hda:
multcount = 16 (on)
IO_support = 3 (32-bit w/sync)
unmaskirq = 1 (on)
using_dma = 1 (on)
keepsettings = 0 (off)
readonly = 0 (off)
readahead = 8 (on)
geometry = 2498/255/63, sectors = 40132503, start = 0
|
my proc-info :
| Code: |
root@mailserver johnr # cat /proc/ide/via
----------VIA BusMastering IDE Configuration----------------
Driver Version: 3.35
South Bridge: VIA vt8231
Revision: ISA 0x10 IDE 0x6
Highest DMA rate: UDMA100
BM-DMA base: 0xd000
PCI clock: 33.3MHz
Master Read Cycle IRDY: 0ws
Master Write Cycle IRDY: 0ws
BM IDE Status Register Read Retry: yes
Max DRDY Pulse Width: No limit
-----------------------Primary IDE-------Secondary IDE------
Read DMA FIFO flush: yes yes
End Sector FIFO flush: no no
Prefetch Buffer: yes yes
Post Write Buffer: yes yes
Enabled: yes no
Simplex only: no no
Cable Type: 80w 40w
-------------------drive0----drive1----drive2----drive3-----
Transfer Mode: UDMA PIO PIO PIO
Address Setup: 30ns 120ns 120ns 120ns
Cmd Active: 90ns 90ns 480ns 480ns
Cmd Recovery: 30ns 30ns 480ns 480ns
Data Active: 90ns 330ns 330ns 330ns
Data Recovery: 30ns 270ns 270ns 270ns
Cycle Time: 30ns 600ns 600ns 600ns
Transfer Rate: 66.6MB/s 3.3MB/s 3.3MB/s 3.3MB/s
|
|
|
| Back to top |
|
 |
drakos7
Apprentice
Joined: 21 Feb 2003
Posts: 294
Location: Rockville, MD, USA, Earth, Sol
|
| Posted: Thu Feb 05, 2004 5:36 pm Post subject: |
|
|
have you tried adding: idebus=66 to your lilo/grub kernel line?
You will notice that your kernel log says: | Code: | | ide: Assuming 33MHz system bus speed for PIO modes; override with idebus=xx |
Drakos7
_________________
"People demand freedom of speech as a compensation for the freedom of thought which they seldom use." Soren Kierkegaard (1813 - 1855) |
|
| Back to top |
|
|
netster
n00b
Joined: 08 Sep 2002
Posts: 41
Location: germany
|
| Posted: Fri Feb 06, 2004 11:12 am Post subject: |
|
|
| Code: |
Feb 6 11:57:43 mailserver kernel: ide: Assuming 66MHz system bus speed for PIO modes
|
did the update, preformance of the drive now ~4.08megs/s ...
any further hints?  |
|
| Back to top |
|
|
mlsfit138
Guru
Joined: 20 Sep 2003
Posts: 406
Location: Washington
|
| Posted: Fri Feb 06, 2004 8:48 pm Post subject: |
|
|
ok, looks like I posted a dupe! I'm going to try setting ide=bus66 in my lilo.conf. Does this increase the speed of things other than drive performance? How do I know if my machine is capable of a higher settting? (I don't have access to original documentation for my box)
_________________
"Everytime you justify
another good in you dies"
-Converge, The Saddest Day, Petitioning the Empty Sky |
|
| Back to top |
|
|
drakos7
Apprentice
Joined: 21 Feb 2003
Posts: 294
Location: Rockville, MD, USA, Earth, Sol
|
| Posted: Mon Feb 09, 2004 3:37 pm Post subject: |
|
|
Last I checked (about 2 months ago) 66 was the highest the kernel would support. That may have changed.
chances are, anything built in the past 3 years is 66 or better. |
|
| Back to top |
|
|
mlsfit138
Guru
Joined: 20 Sep 2003
Posts: 406
Location: Washington
|
| Posted: Mon Feb 09, 2004 4:12 pm Post subject: |
|
|
| drakos7 wrote: | Last I checked (about 2 months ago) 66 was the highest the kernel would support. That may have changed.
chances are, anything built in the past 3 years is 66 or better. |
I did some googling around, and seemed to find that you don't want to override that setting.
| Quote: | > > I have an AMD 1.1ghz Athalon running a 133 bus. I just booted my box and
> > it said the bus was at 33, use idebus= to override. Before I go and
> > risk nuking my box by screwing up a setting, is it just a lilo append
> > line that says something like append="idebus=133"?
Your FSB, not your PCI, is running at 133 MHz
> This should do. I don't know about your board but I have my P5AB
> set up like:
>
> image = /vmlinuz
> label = new
> root = /dev/hda1
> vga = normal
> read-only
> append = "debug=2 noapic nosmp hdc=ide-scsi hdb=ide-scsi hdd=ide-scsi idebus=66"
You almost certainly *don't* want to do that. idebus is the speed of your
PCI bus, which is probably 33 MHz. That's kinda a confusingly named option
-- lots of people seem to think it has something to do with ATA/33 vs ATA/66
vs ATA/100, but it doesn't. See drivers/ide/ide.c....
later,
chris |
http://www.ale.org/archive/ale/ale-2001-04/msg00188.html and dozens of other threads seem to say the same. of course that info IS three years old, but so is my system. 
Doing all this searching on this topic has really made me realize that I need a new hard drive, or maybe a whole new box! I've seen people concerned about getting 3X my hard drive stats! Oh the speed of technology.
_________________
"Everytime you justify
another good in you dies"
-Converge, The Saddest Day, Petitioning the Empty Sky |
|
| Back to top |
|
|
mlsfit138
Guru
Joined: 20 Sep 2003
Posts: 406
Location: Washington
|
| Posted: Mon Feb 09, 2004 4:31 pm Post subject: |
|
|
better yet, I looked at the code to ide.c:
| Code: | * "idebus=xx" : inform IDE driver of VESA/PCI bus speed in MHz,
* where "xx" is between 20 and 66 inclusive,
* used when tuning chipset PIO modes.
* For PCI bus, 25 is correct for a P75 system,
* 30 is correct for P90,P120,P180 systems,
* and 33 is used for P100,P133,P166 systems.
* If in doubt, use idebus=33 for PCI.
* As for VLB, it is safest to not specify it. |
so it definitely looks to me like I should not specify! 
_________________
"Everytime you justify
another good in you dies"
-Converge, The Saddest Day, Petitioning the Empty Sky |
|
| Back to top |
|
|
borchi
n00b
Joined: 05 Dec 2002
Posts: 44
|
| Posted: Wed Nov 10, 2004 9:50 am Post subject: |
|
|
i have exactly the same problem with my Via EPIA 800, but what i found out is that if i remove the 2nd nic (from PCI slot) my hd transfer rates go WAY up. from 3.8Mb/s to 30Mb/s.
i disabled ACPI in kernel, Plug 'n Play in BIOS and everything i could think of, but couldn't get a decent hd performace with nic in the PCI slot.
but i need the second nic! can anyone help? |
|
| Back to top |
|
|
|
|
You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot vote in polls in this forum
|
|
Kernel & Hardware
