1 |
Hello there, |
2 |
|
3 |
I'm sending this email about a problem with udma settings |
4 |
in a TigerMP motherboard, wich supports UDMA 100. |
5 |
The problem looks like the kernel on boot detects the disks has UDMA33 |
6 |
all the time, although one does UDMA 100 and the other one UDMA 66 |
7 |
My drive's performance are lousy, and I know they are capable of much more, |
8 |
|
9 |
here's some info from hdparm: |
10 |
--(quark)-(pts0)-(16:00/04-Oct-02)-- |
11 |
--(m3thos#:~)-- sudo hdparm -t /dev/hda |
12 |
|
13 |
/dev/hda: |
14 |
Timing buffered disk reads: 64 MB in 3.95 seconds = 16.20 MB/sec |
15 |
--(quark)-(pts0)-(18:30/04-Oct-02)-- |
16 |
--(m3thos#:~)-- sudo hdparm -i /dev/hda |
17 |
|
18 |
/dev/hda: |
19 |
|
20 |
Model=ST340016A, FwRev=3.05, SerialNo=3HS0403R |
21 |
Config={ HardSect NotMFM HdSw>15uSec Fixed DTR>10Mbs RotSpdTol>.5% } |
22 |
RawCHS=16383/16/63, TrkSize=0, SectSize=0, ECCbytes=4 |
23 |
BuffType=unknown, BuffSize=2048kB, MaxMultSect=16, MultSect=16 |
24 |
CurCHS=16383/16/63, CurSects=16514064, LBA=yes, LBAsects=78165360 |
25 |
IORDY=on/off, tPIO={min:240,w/IORDY:120}, tDMA={min:120,rec:120} |
26 |
PIO modes: pio0 pio1 pio2 pio3 pio4 |
27 |
DMA modes: mdma0 mdma1 mdma2 |
28 |
UDMA modes: udma0 udma1 *udma2 |
29 |
AdvancedPM=no WriteCache=enabled |
30 |
Drive conforms to: device does not report version: 1 2 3 4 5 |
31 |
|
32 |
NOTE: I don't understand why hdparm reports udma modes: udma0 udma1 udma2, |
33 |
if this drive acording to the manufacturer is capable of UDMA 100, udma |
34 |
modes should go up to udma5 i believe. |
35 |
My only guess is that this information is taken from the kernel since |
36 |
udma2 is udma 33 (right?) |
37 |
|
38 |
--(quark)-(pts0)-(18:30/04-Oct-02)-- |
39 |
--(m3thos#:~)-- sudo hdparm /dev/hda |
40 |
|
41 |
/dev/hda: |
42 |
multcount = 16 (on) |
43 |
IO_support = 0 (default 16-bit) |
44 |
unmaskirq = 0 (off) |
45 |
using_dma = 1 (on) |
46 |
keepsettings = 0 (off) |
47 |
readonly = 0 (off) |
48 |
readahead = 8 (on) |
49 |
geometry = 77545/16/63, sectors = 78165360, start = 0 |
50 |
|
51 |
|
52 |
dmesg gives this: |
53 |
--cut-- |
54 |
Uniform Multi-Platform E-IDE driver Revision: 6.31 |
55 |
ide: Assuming 33MHz system bus speed for PIO modes; override with idebus=xx |
56 |
AMD7411: IDE controller on PCI bus 00 dev 39 |
57 |
AMD7411: chipset revision 1 |
58 |
AMD7411: not 100% native mode: will probe irqs later |
59 |
AMD7411: disabling single-word DMA support (revision < C4) |
60 |
ide0: BM-DMA at 0xf000-0xf007, BIOS settings: hda:DMA, hdb:DMA |
61 |
ide1: BM-DMA at 0xf008-0xf00f, BIOS settings: hdc:pio, hdd:DMA |
62 |
hda: ST340016A, ATA DISK drive |
63 |
hdb: TOSHIBA CD-ROM XM-6602B, ATAPI CD/DVD-ROM drive |
64 |
hdc: PCRW804, ATAPI CD/DVD-ROM drive |
65 |
hdd: ST36421A, ATA DISK drive |
66 |
ide0 at 0x1f0-0x1f7,0x3f6 on irq 14 |
67 |
ide1 at 0x170-0x177,0x376 on irq 15 |
68 |
hda: 78165360 sectors (40021 MB) w/2048KiB Cache, CHS=77545/16/63, UDMA(33) |
69 |
hdd: 12596850 sectors (6450 MB) w/256KiB Cache, CHS=13330/15/63, UDMA(33) |
70 |
hdb: ATAPI 40X CD-ROM drive, 128kB Cache, UDMA(33) |
71 |
--cut-- |
72 |
|
73 |
hda is a Seagate Barracuda IV 7200rpm 2mb cache (40Gbs) |
74 |
URL: |
75 |
http://www.seagate.com/cda/products/discsales/marketing/detail/0,1081,384,00.html |
76 |
hdc is a Seagate "ST-36421A (U4 6421, Ultra ATA/66) |
77 |
URL: http://www.seagate.com/cgi-bin/view.cgi?/at/st36421a.txt |
78 |
|
79 |
i'm using linux-2.4.19-gentoo-r9, but I believe that the drivers are the |
80 |
same of the vanilla kernel: |
81 |
--(m3thos#:~)-- head /usr/src/linux/drivers/ide/amd74xx.c |
82 |
/* |
83 |
* linux/drivers/ide/amd74xx.c Version 0.05 June 9, 2000 |
84 |
* |
85 |
* Copyright (C) 1999-2000 Andre Hedrick <andre@×××××××××.org> |
86 |
* May be copied or modified under the terms of the GNU General Public |
87 |
License |
88 |
* |
89 |
*/ |
90 |
|
91 |
i've found a patch, tried to aply but failed, the patch was: |
92 |
http://www.uwsg.iu.edu/hypermail/linux/kernel/0109.3/att-1176/01-viper-vojtech.diff |
93 |
|
94 |
I'm not experienced enough to adapt the patch for 2.4.19 (the author |
95 |
says it was made against 2.4.10) |
96 |
|
97 |
I though that my best luck was to ask if is there any kernel patch |
98 |
against any updated kernel branch, |
99 |
or any kernel branch I should give a try to solve my problem, or some |
100 |
other possible solution |
101 |
In case of being a kernel miss configuration problem.. I send attached |
102 |
my kernel config file. |
103 |
- If any important information is missing please warn me so I can |
104 |
provide what's needed. |
105 |
|
106 |
Thanx in Advance, |
107 |
help me out! |
108 |
|
109 |
Miguel Sousa Filipe |