I've enabled the higher performance features for my ATA drive by getting
2.2.17, applying Andre Hendrick's IDE patch, adding:
append="idebus=66 ide0=ata66"
to lilo.conf. I was told that Alan's patches from here:
ftp.kernel.org/pub/linux/kernel/people/alan
should be used. Is this true if I used Andre's patch? Is the warning
message in my bootlog anything to worry about? The board is an ABIT KT7A
w/ KT133A chipset.
Also, the machine locked up once (hard, couldn't connect via network). I
am using the Matrox G450 beta driver with XF 4.0.2 though. Maybe that
was the cause?
Thanks,
Mike
syslogd 1.3-3: restart.
syslog: syslogd startup succeeded
kernel: klogd 1.3-3, log source = /proc/kmsg started.
syslog: klogd startup succeeded
kernel: Inspecting /boot/System.map
kernel: Loaded 6567 symbols from /boot/System.map.
kernel: Symbols match kernel version 2.2.17.
kernel: No module symbols loaded.
kernel: Linux version 2.2.17 (root@nano) (gcc version egcs-2.91.66 19990314/Linux (egcs-1.1.2 release)) #2 Wed Feb 21 02:33:48 EST 2001
kernel: Detected 900061 kHz processor.
kernel: ide_setup: idebus=66
kernel: ide_setup: ide0=ata66
kernel: Console: colour VGA+ 80x25
I thought the BogoMIPS sort of went along with the CPU MHz?
kernel: Calibrating delay loop... 1795.69 BogoMIPS
kernel: Memory: 257852k/262080k available (976k kernel code, 412k reserved, 2796k data, 44k init)
kernel: Dentry hash table entries: 32768 (order 6, 256k)
kernel: Buffer cache hash table entries: 262144 (order 8, 1024k)
kernel: Page cache hash table entries: 65536 (order 6, 256k)
kernel: CPU: L1 I Cache: 64K L1 D Cache: 64K
kernel: CPU: L2 Cache: 256K
kernel: CPU: AMD Athlon(tm) Processor stepping 02
kernel: Checking 386/387 coupling... OK, FPU using exception 16 error reporting.
kernel: Checking 'hlt' instruction... OK.
kernel: POSIX conformance testing by UNIFIX
kernel: PCI: PCI BIOS revision 2.10 entry at 0xfb430
kernel: PCI: Using configuration type 1
kernel: PCI: Probing PCI hardware
kernel: Linux NET4.0 for Linux 2.2
kernel: Based upon Swansea University Computer Society NET3.039
kernel: NET4: Unix domain sockets 1.0 for Linux NET4.0.
kernel: NET4: Linux TCP/IP 1.0 for NET4.0
kernel: IP Protocols: ICMP, UDP, TCP
kernel: TCP: Hash tables configured (ehash 262144 bhash 65536)
kernel: Starting kswapd v 1.5
kernel: Detected PS/2 Mouse Port.
kernel: Serial driver version 4.27 with no serial options enabled
kernel: ttyS00 at 0x03f8 (irq = 4) is a 16550A
kernel: ttyS01 at 0x02f8 (irq = 3) is a 16550A
kernel: pty: 256 Unix98 ptys configured
kernel: Uniform Multi-Platform E-IDE driver Revision: 6.30
kernel: ide: Assuming 66MHz system bus speed for PIO modes
kernel: VP_IDE: IDE controller on PCI bus 00 dev 39
kernel: VP_IDE: chipset revision 6
kernel: VP_IDE: not 100% native mode: will probe irqs later
This is what I'm worried about right here:
kernel: VP_IDE: ATA-66/100 forced bit set (WARNING)!!
kernel: ide0: BM-DMA at 0xe000-0xe007, BIOS settings: hda:DMA, hdb:pio
kernel: ide1: BM-DMA at 0xe008-0xe00f, BIOS settings: hdc:pio, hdd:pio
kernel: hda: IBM-DTLA-307030, ATA DISK drive
kernel: hdc: PLEXTOR CD-R PX-W1210A, ATAPI CDROM drive
kernel: ide0 at 0x1f0-0x1f7,0x3f6 on irq 14
kernel: ide1 at 0x170-0x177,0x376 on irq 15
kernel: hda: IBM-DTLA-307030, 29314MB w/1916kB Cache, CHS=3737/255/63, UDMA(100)
kernel: Floppy drive(s): fd0 is 1.44M
kernel: FDC 0 is a post-1991 82077
And why do I have 8 cdroms?
kernel: scsi0 : SCSI host adapter emulation for IDE ATAPI devices
kernel: scsi : 1 host.
kernel: Vendor: PLEXTOR Model: CD-R PX-W1210A Rev: 1.07
kernel: Type: CD-ROM ANSI SCSI revision: 02
kernel: Detected scsi CD-ROM sr0 at scsi0, channel 0, id 0, lun 0
kernel: Vendor: PLEXTOR Model: CD-R PX-W1210A Rev: 1.07
kernel: Type: CD-ROM ANSI SCSI revision: 02
kernel: Detected scsi CD-ROM sr1 at scsi0, channel 0, id 0, lun 1
kernel: Vendor: PLEXTOR Model: CD-R PX-W1210A Rev: 1.07
kernel: Type: CD-ROM ANSI SCSI revision: 02
kernel: Detected scsi CD-ROM sr2 at scsi0, channel 0, id 0, lun 2
kernel: Vendor: PLEXTOR Model: CD-R PX-W1210A Rev: 1.07
kernel: Type: CD-ROM ANSI SCSI revision: 02
kernel: Detected scsi CD-ROM sr3 at scsi0, channel 0, id 0, lun 3
kernel: Vendor: PLEXTOR Model: CD-R PX-W1210A Rev: 1.07
kernel: Type: CD-ROM ANSI SCSI revision: 02
kernel: Detected scsi CD-ROM sr4 at scsi0, channel 0, id 0, lun 4
kernel: Vendor: PLEXTOR Model: CD-R PX-W1210A Rev: 1.07
kernel: Type: CD-ROM ANSI SCSI revision: 02
kernel: Detected scsi CD-ROM sr5 at scsi0, channel 0, id 0, lun 5
kernel: Vendor: PLEXTOR Model: CD-R PX-W1210A Rev: 1.07
kernel: Type: CD-ROM ANSI SCSI revision: 02
kernel: Detected scsi CD-ROM sr6 at scsi0, channel 0, id 0, lun 6
kernel: Vendor: PLEXTOR Model: CD-R PX-W1210A Rev: 1.07
kernel: Type: CD-ROM ANSI SCSI revision: 02
kernel: Detected scsi CD-ROM sr7 at scsi0, channel 0, id 0, lun 7
kernel: scsi : detected 8 SCSI generics 8 SCSI cdroms total.
kernel: sr0: scsi3-mmc drive: 32x/32x writer cd/rw xa/form2 cdda tray
kernel: Uniform CD-ROM driver Revision: 3.11
kernel: sr1: scsi3-mmc drive: 32x/32x writer cd/rw xa/form2 cdda tray
kernel: sr2: scsi3-mmc drive: 32x/32x writer cd/rw xa/form2 cdda tray
kernel: sr3: scsi3-mmc drive: 32x/32x writer cd/rw xa/form2 cdda tray
kernel: sr4: scsi3-mmc drive: 32x/32x writer cd/rw xa/form2 cdda tray
kernel: sr5: scsi3-mmc drive: 32x/32x writer cd/rw xa/form2 cdda tray
kernel: sr6: scsi3-mmc drive: 32x/32x writer cd/rw xa/form2 cdda tray
kernel: sr7: scsi3-mmc drive: 32x/32x writer cd/rw xa/form2 cdda tray
kernel: 3c59x.c 16Aug00 Donald Becker and others http://www.scyld.com/network/vortex.html
kernel: eth0: 3Com 3c905C Tornado at 0xec00, 00:01:02:cf:5f:18, IRQ 11
kernel: 8K byte-wide RAM 5:3 Rx:Tx split, autoselect/Autonegotiate interface.
kernel: MII transceiver found at address 24, status 782d.
kernel: Enabling bus-master transmits and whole-frame receives.
kernel: Partition check:
kernel: hda: hda1 hda2
kernel: VFS: Mounted root (ext2 filesystem) readonly.
kernel: Freeing unused kernel memory: 44k freed
kernel: Adding Swap: 136544k swap-space (priority -1)
identd: identd startup succeeded
atd: atd startup succeeded
crond: crond startup succeeded
inet: inetd startup succeeded
lpd: lpd startup succeeded
lpd[457]: restarted
rc.sysinit: Mounting proc filesystem succeeded
sysctl: net.ipv4.ip_forward = 0
sysctl: net.ipv4.conf.all.rp_filter = 1
sysctl: net.ipv4.ip_always_defrag = 0
Here's another little error?
sysctl: error: 'kernel.sysrq' is an unknown key
rc.sysinit: Configuring kernel parameters succeeded
date: Wed Feb 21 17:38:31 EST 2001
rc.sysinit: Setting clock : Wed Feb 21 17:38:31 EST 2001 succeeded
rc.sysinit: Loading default keymap succeeded
rc.sysinit: Activating swap partitions succeeded
succeeded
fsck: /dev/hda1: clean, 62090/788704 files, 279756/1574362 blocks
rc.sysinit: Checking root filesystem succeeded
rc.sysinit: Remounting root filesystem in read-write mode succeeded
rc.sysinit: Finding module dependencies succeeded
rc.sysinit: Checking filesystems succeeded
rc.sysinit: Mounting local filesystems succeeded
rc.sysinit: Turning on user and group quotas for local filesystems succeeded
rc.sysinit: Enabling swap space succeeded
init: Entering runlevel: 5
sysctl: net.ipv4.ip_forward = 0
sysctl: net.ipv4.conf.all.rp_filter = 1
sysctl: net.ipv4.ip_always_defrag = 0
Mmm, here's that sysctl stuff again?
sysctl: error: 'kernel.sysrq' is an unknown key
network: Setting network parameters succeeded
Err, I have lot's of errors!
ifup: SIOCADDRT: Network is unreachable
network: Bringing up interface lo succeeded
network: Bringing up interface eth0 succeeded
portmap: portmap startup succeeded
nfslock: rpc.lockd startup succeeded
nfslock: rpc.statd startup succeeded
random: Initializing random number generator succeeded
netfs: Mounting other filesystems succeeded
keytable: Loading keymap:
keytable: Loading /usr/lib/kbd/keymaps/i386/qwerty/us.kmap.gz
keytable: Loading system font:
rc: Starting keytable succeeded
sendmail: sendmail startup succeeded
PAM_pwdb[533]: (gdm) session opened for user miallen by (uid=0)
gdm[533]: gdm_slave_session_start: miallen on :0
PAM_pwdb[615]: (su) session opened for user root by miallen(uid=500)
--
signature pending
On Wed, 21 Feb 2001, Michael B. Allen wrote:
> And why do I have 8 cdroms?
> kernel: scsi0 : SCSI host adapter emulation for IDE ATAPI devices
> kernel: scsi : 1 host.
> kernel: Vendor: PLEXTOR Model: CD-R PX-W1210A Rev: 1.07
> kernel: Type: CD-ROM ANSI SCSI revision: 02
It's an old old bug with the ide-scsi lun probing code. Dont know if 2.4.x
fixed it yet. Solution -- disable lun probing in scsi config.
-Dan
On Wed, Feb 21, 2001 at 03:48:06PM -0800, Wayne Whitney wrote:
> > append="idebus=66 ide0=ata66"
>
> The idebus=66 part is incorrect. This option refers to the clock of
> the PCI bus the IDE controller is on and should rarely be changed from
> the default of 33MHz (i.e., only if you are overclocking the PCI bus).
Ah, well I just added that based on the end of this boot message:
ide: Assuming 33MHz system bus speed for PIO modes; override with idebus=xx
> >kernel: VP_IDE: ATA-66/100 forced bit set (WARNING)!!
>
> I'm sure this is just telling you that you passed the ide0=ata66
> parameter. Usually it is best not to do this--the driver should run
> your chipset/drive as fast as possible without 'forcing' the
> configuration. Of course, testing with hdparm -t is considered the
> definitive way to check how fast the interface is running.
If I don't add it hdparm -t /dev/hda reports:
Timing buffered disk reads: 64 MB in 16.46 seconds = 3.89 MB/sec
Then if I do hdparm -d1 -X66 /dev/hda I get:
/dev/hda:
setting using_dma to 1 (on)
setting xfermode to 66 (UltraDMA mode2)
using_dma = 1 (on)
[root@nano /root]# hdparm -t /dev/hda
/dev/hda:
Timing buffered disk reads: 64 MB in 4.04 seconds = 15.84 MB/sec
Now if I add it via append, reboot and do hdparm -t I get:
Timing buffered disk reads: 64 MB in 3.70 seconds = 17.30 MB/sec
This last difference is consistently better. Weird.
All your other bets were right too.
Thanks Wayne,
Mike
--
signature pending
> I've enabled the higher performance features for my ATA drive by getting
> 2.2.17, applying Andre Hendrick's IDE patch, adding:
> append="idebus=66 ide0=ata66"
> to lilo.conf. I was told that Alan's patches from here:
> should be used. Is this true if I used Andre's patch? Is the warning
> message in my bootlog anything to worry about? The board is an ABIT KT7A
> w/ KT133A chipset.
Alan = kernel, Andre = IDE. 2.2.18 (kernel) + ide.2.2.18.1221 (IDE
patch) + 2.2.19pre8 (kernel patch). See samples below.
> Also, the machine locked up once (hard, couldn't connect via network). I
> am using the Matrox G450 beta driver with XF 4.0.2 though. Maybe that
> was the cause?
Ensoniq AudioPCI (ES1370) was problematic if I tried to assign IRQ5 on
the KA7 (hard trailess lockups, all IRQ's migrated to 10 or 11
regardless of config, digital audio ScreamOfAgony), whereas IRQ 3 worked
fine. Similar experiements with Intel chipset boards P3B-F & BP6 suffer
no such issues so I assume it's VT82C686/ES1370 specific.
Abit KA7, 2.2.19pre8 + ide.2.2.18.1221
--------------------------------------
Linux version 2.2.19pre8+IDE (root@abit) (gcc version egcs-2.91.66
19990314/Linux (egcs-1.1.2 release)) #6 Tue Feb 20
01:14:30 PST 2001
USER-provided physical RAM map:
USER: 0009f000 @ 00000000 (usable)
USER: 1ff00000 @ 00100000 (usable)
Detected 800063 kHz processor.
ide_setup: idebus=33
ide_setup: ide0=ata66
ide_setup: ide1=ata66
Console: colour VGA+ 80x25
Calibrating delay loop... 1595.80 BogoMIPS
Memory: 517204k/524288k available (1116k kernel code, 412k reserved,
5508k data, 48k init)
Dentry hash table entries: 65536 (order 7, 512k)
Buffer cache hash table entries: 524288 (order 9, 2048k)
Page cache hash table entries: 131072 (order 7, 512k)
CPU: L1 I Cache: 64K L1 D Cache: 64K
CPU: L2 Cache: 512K
CPU: AMD Athlon(tm) Processor stepping 02
Checking 386/387 coupling... OK, FPU using exception 16 error reporting.
Checking 'hlt' instruction... OK.
POSIX conformance testing by UNIFIX
mtrr: v1.35a (19990819) Richard Gooch ([email protected])
PCI: PCI BIOS revision 2.10 entry at 0xfb4d0
PCI: Probing PCI hardware
...
Uniform Multi-Platform E-IDE driver Revision: 6.30
ide: Assuming 33MHz system bus speed for PIO modes
VP_IDE: IDE controller on PCI bus 00 dev 39
VP_IDE: chipset revision 16
VP_IDE: not 100% native mode: will probe irqs later
VT 8371
Chipset Core ATA-66
VP_IDE: ATA-66/100 forced bit set (WARNING)!!
Split FIFO Configuration: 8 Primary buffers, threshold = 1/2
8 Second. buffers, threshold = 1/2
ide0: BM-DMA at 0xd000-0xd007, BIOS settings: hda:DMA, hdb:DMA
ide0: VIA Bus-Master (U)DMA Timing Config Success
VP_IDE: ATA-66/100 forced bit set (WARNING)!!
ide1: BM-DMA at 0xd008-0xd00f, BIOS settings: hdc:DMA, hdd:DMA
ide1: VIA Bus-Master (U)DMA Timing Config Success
hda: IBM-DTLA-307020, ATA DISK drive
hdb: YAMAHA CRW4416E, ATAPI CDROM drive
hdc: IBM-DTLA-307020, ATA DISK drive
hdd: HP COLORADO 20GB, ATAPI TAPE drive
ide0 at 0x1f0-0x1f7,0x3f6 on irq 14
ide1 at 0x170-0x177,0x376 on irq 15
hda: IBM-DTLA-307020, 19623MB w/1916kB Cache, CHS=2501/255/63, UDMA(66)
hdc: IBM-DTLA-307020, 19623MB w/1916kB Cache, CHS=39870/16/63, UDMA(66)
...
# lspci -v
00:00.0 Host bridge: VIA Technologies, Inc.: Unknown device 0391 (rev
02)
Flags: bus master, medium devsel, latency 0
Memory at d0000000 (32-bit, prefetchable)
Capabilities: [a0] AGP version 2.0
00:01.0 PCI bridge: VIA Technologies, Inc.: Unknown device 8391 (prog-if
00 [Normal decode])
Flags: bus master, 66Mhz, medium devsel, latency 0
Bus: primary=00, secondary=01, subordinate=01, sec-latency=0
Memory behind bridge: d2000000-d3ffffff
Prefetchable memory behind bridge: d4000000-d5ffffff
Capabilities: [80] Power Management version 2
00:07.0 ISA bridge: VIA Technologies, Inc. VT82C686 [Apollo Super] (rev
22)
Subsystem: VIA Technologies, Inc.: Unknown device 0000
Flags: bus master, stepping, medium devsel, latency 0
00:07.1 IDE interface: VIA Technologies, Inc. VT82C586 IDE [Apollo] (rev
10) (prog-if 8a [Master SecP PriP])
Flags: bus master, medium devsel, latency 32
I/O ports at d000
Capabilities: [c0] Power Management version 2
00:07.4 Host bridge: VIA Technologies, Inc. VT82C686 [Apollo Super ACPI]
(rev 30)
Flags: medium devsel
Capabilities: [68] Power Management version 2
Generic Socket7, 2.2.19pre8 + ide.2.2.18.1221
---------------------------------------------
Linux version 2.2.19pre8+IDE ([email protected]) (gcc version
egcs-2.91.66 19990314/Linux (egcs-1.1.2 release)) #3 Mon Feb 19 21:07:58
PST 2001
BIOS-provided physical RAM map:
BIOS-e820: 0009f000 @ 00000000 (usable)
BIOS-e820: 03f00000 @ 00100000 (usable)
Detected 166405 kHz processor.
Console: colour VGA+ 80x25
Calibrating delay loop... 331.77 BogoMIPS
Memory: 63060k/65536k available (1044k kernel code, 412k reserved, 972k
data, 48k init)
Dentry hash table entries: 8192 (order 4, 64k)
Buffer cache hash table entries: 65536 (order 6, 256k)
Page cache hash table entries: 16384 (order 4, 64k)
CPU: Intel Pentium 75 - 200 stepping 0c
Checking 386/387 coupling... OK, FPU using exception 16 error reporting.
Checking 'hlt' instruction... OK.
Intel Pentium with F0 0F bug - workaround enabled.
POSIX conformance testing by UNIFIX
PCI: PCI BIOS revision 2.10 entry at 0xfb470
PCI: Using configuration type 1
PCI: Probing PCI hardware
PCI: 00:38 [1106/0586]: Work around ISA DMA hangs (00)
Activating ISA DMA hang workarounds.
...
Uniform Multi-Platform E-IDE driver Revision: 6.30
ide: Assuming 33MHz system bus speed for PIO modes; override with
idebus=xx
VP_IDE: IDE controller on PCI bus 00 dev 39
VP_IDE: chipset revision 2
VP_IDE: not 100% native mode: will probe irqs later
ide: Assuming 33MHz system bus speed for PIO modes; override with
idebus=xx
VT 82C585 Apollo VP1/VPX
Chipset Core ATA-33
Split FIFO Configuration: 16 Primary buffers, threshold = 3/4
0 Second. buffers, threshold = 1/2
ide0: BM-DMA at 0x6000-0x6007, BIOS settings: hda:DMA, hdb:DMA
ide0: VIA Bus-Master (U)DMA Timing Config Success
hda: IBM-DJNA-370910, ATA DISK drive
hdb: BCD-F520D CD-ROM, ATAPI CDROM drive
ide0 at 0x1f0-0x1f7,0x3f6 on irq 14
hda: IBM-DJNA-370910, 8693MB w/1966kB Cache, CHS=1108/255/63, (U)DMA
...
# lspci -v
00:00.0 Host bridge: VIA Technologies, Inc. VT82C585VP [Apollo VP1/VPX]
(rev 10)
Flags: bus master, 66Mhz, medium devsel, latency 32
00:07.0 ISA bridge: VIA Technologies, Inc. VT82C586/A/B PCI-to-ISA
[Apollo VP] (rev 02)
Flags: bus master, medium devsel, latency 0
00:07.1 IDE interface: VIA Technologies, Inc. VT82C586 IDE [Apollo] (rev
02) (prog-if 8a [Master SecP PriP])
Flags: bus master, medium devsel, latency 32
I/O ports at 6000
Memory at e1020000 (32-bit, non-prefetchable)
--
timothymoore
bigfoot
com