HPT366 ide controller and very slow disks...

cav · 06-19-2004, 11:45 PM

I've been messing with this problem for a while now, basically the transfer rate of my hard drives under slackware is VERY slow. Like 2 MB/s slow. My IDE controllers are Highpoint Technologies HPT366, and I have 3 seperate drives on two different channels. Under both SuSE and FreeBSD the transfer rate is seemingly normal, around 15 MB/s. Further inspection of my slack kernel shows that hpt366 support is compiled in. Further, heres some suspicious messages from my dmesg output:

Code:

HPT366: onboard version of chipset, pin1=1 pin2=2
HPT366: IDE controller at PCI slot 00:13.0
PCI: Enabling device 00:13.0 (0005 -> 0007)
HPT366: chipset revision 1
HPT366: not 100% native mode: will probe irqs later
    ide2: BM-DMA at 0xb800-0xb807, BIOS settings: hde:DMA, hdf:DMA
    ide3: BM-DMA at 0xc400-0xc407, BIOS settings: hdg:DMA, hdh:pio
.
.
.
SCSI subsystem driver Revision: 1.00
kmod: failed to exec /sbin/modprobe -s -k scsi_hostadapter, errno = 2
kmod: failed to exec /sbin/modprobe -s -k scsi_hostadapter, errno = 2
kmod: failed to exec /sbin/modprobe -s -k scsi_hostadapter, errno = 2

I think theres supposed to be scsi emulation, but somethings not working. Does anybody else use an HPT366 controller and know whats going on here?

wpyh · 06-20-2004, 02:11 PM

I have the hpt366 controller, but I don't have your problem.

Maybe you could paste the dmesg output entirely?

cav · 06-20-2004, 04:32 PM

sure, here goes...

Code:

Linux version 2.4.26 (root@midas) (gcc version 3.3.3) #6 Sun May 30 23:07:15 PDT 2004
BIOS-provided physical RAM map:
 BIOS-e820: 0000000000000000 - 00000000000a0000 (usable)
 BIOS-e820: 00000000000f0000 - 0000000000100000 (reserved)
 BIOS-e820: 0000000000100000 - 000000000fff0000 (usable)
 BIOS-e820: 000000000fff0000 - 000000000fff3000 (ACPI NVS)
 BIOS-e820: 000000000fff3000 - 0000000010000000 (ACPI data)
 BIOS-e820: 00000000ffff0000 - 0000000100000000 (reserved)
255MB LOWMEM available.
On node 0 totalpages: 65520
zone(0): 4096 pages.
zone(1): 61424 pages.
zone(2): 0 pages.
Kernel command line: BOOT_IMAGE=linux ro root=2142 hdc=ide-scsi
ide_setup: hdc=ide-scsi
Initializing CPU#0
Detected 562.510 MHz processor.
Console: colour dummy device 80x25
Calibrating delay loop... 1120.66 BogoMIPS
Memory: 256000k/262080k available (1848k kernel code, 5696k reserved, 618k data, 120k init, 0k highmem)
Dentry cache hash table entries: 32768 (order: 6, 262144 bytes)
Inode cache hash table entries: 16384 (order: 5, 131072 bytes)
Mount cache hash table entries: 512 (order: 0, 4096 bytes)
Buffer cache hash table entries: 16384 (order: 4, 65536 bytes)
Page-cache hash table entries: 65536 (order: 6, 262144 bytes)
CPU: L1 I cache: 16K, L1 D cache: 16K
CPU: L2 cache: 128K
CPU:     After generic, caps: 0183f9ff 00000000 00000000 00000000
CPU:             Common caps: 0183f9ff 00000000 00000000 00000000
CPU: Intel Celeron (Mendocino) stepping 05
Enabling fast FPU save and restore... done.
Checking 'hlt' instruction... OK.
POSIX conformance testing by UNIFIX
mtrr: v1.40 (20010327) Richard Gooch (rgooch@atnf.csiro.au)
mtrr: detected mtrr type: Intel
PCI: PCI BIOS revision 2.10 entry at 0xfb3a0, last bus=1
PCI: Using configuration type 1
PCI: Probing PCI hardware
PCI: Probing PCI hardware (bus 00)
Limiting direct PCI/PCI transfers.
Linux NET4.0 for Linux 2.4
Based upon Swansea University Computer Society NET3.039
Initializing RT netlink socket
Starting kswapd
VFS: Disk quotas vdquot_6.5.1
Journalled Block Device driver loaded
vesafb: framebuffer at 0xe0000000, mapped to 0xd080d000, size 1536k
vesafb: mode is 1024x768x8, linelength=1024, pages=20
vesafb: protected mode interface info at c000:83ff
vesafb: scrolling: redraw
Console: switching to colour frame buffer device 128x48
fb0: VESA VGA frame buffer device
Detected PS/2 Mouse Port.
pty: 512 Unix98 ptys configured
Serial driver version 5.05c (2001-07-08) with HUB-6 MANY_PORTS MULTIPORT SHARE_IRQ SERIAL_PCI enabled
ttyS00 at 0x03f8 (irq = 4) is a 16550A
ttyS01 at 0x02f8 (irq = 3) is a 16550A
Real Time Clock Driver v1.10f
Floppy drive(s): fd0 is 1.44M
keyboard: Timeout - AT keyboard not present?(ed)
keyboard: Timeout - AT keyboard not present?(f4)
FDC 0 is a post-1991 82077
RAMDISK driver initialized: 16 RAM disks of 7777K size 1024 blocksize
loop: loaded (max 8 devices)
Uniform Multi-Platform E-IDE driver Revision: 7.00beta4-2.4
ide: Assuming 33MHz system bus speed for PIO modes; override with idebus=xx
PIIX4: IDE controller at PCI slot 00:07.1
PIIX4: chipset revision 1
PIIX4: not 100% native mode: will probe irqs later
    ide0: BM-DMA at 0xf000-0xf007, BIOS settings: hda:DMA, hdb:pio
    ide1: BM-DMA at 0xf008-0xf00f, BIOS settings: hdc:pio, hdd:pio
HPT366: onboard version of chipset, pin1=1 pin2=2
HPT366: IDE controller at PCI slot 00:13.0
PCI: Enabling device 00:13.0 (0005 -> 0007)
HPT366: chipset revision 1
HPT366: not 100% native mode: will probe irqs later
    ide2: BM-DMA at 0xb800-0xb807, BIOS settings: hde:DMA, hdf:DMA
    ide3: BM-DMA at 0xc400-0xc407, BIOS settings: hdg:DMA, hdh:pio
hda: HITACHI DVD-ROM GD-2500, ATAPI CD/DVD-ROM drive
hde: Maxtor 4D040H2, ATA DISK drive
hdf: Maxtor 4D040H2, ATA DISK drive
blk: queue c03b5c08, I/O limit 4095Mb (mask 0xffffffff)
blk: queue c03b5d44, I/O limit 4095Mb (mask 0xffffffff)
hdg: WDC WD153AA, ATA DISK drive
blk: queue c03b605c, I/O limit 4095Mb (mask 0xffffffff)
ide0 at 0x1f0-0x1f7,0x3f6 on irq 14
ide2 at 0xb000-0xb007,0xb402 on irq 11
ide3 at 0xbc00-0xbc07,0xc002 on irq 11
hde: attached ide-disk driver.
hde: host protected area => 1
hde: 80043264 sectors (40982 MB) w/2048KiB Cache, CHS=79408/16/63, UDMA(66)
hdf: attached ide-disk driver.
hdf: host protected area => 1
hdf: 80043264 sectors (40982 MB) w/2048KiB Cache, CHS=79408/16/63, UDMA(66)
hdg: attached ide-disk driver.
hdg: host protected area => 1
hdg: 30064608 sectors (15393 MB) w/2048KiB Cache, CHS=29826/16/63, UDMA(66)
hda: attached ide-cdrom driver.
hda: ATAPI 24X DVD-ROM drive, 512kB Cache, DMA
Uniform CD-ROM driver Revision: 3.12
Partition check:
 hde: [PTBL] [4982/255/63] hde1 hde2 < hde5 >
 hdf: hdf1 hdf2 hdf3
 hdg: [PTBL] [1871/255/63] hdg1
SCSI subsystem driver Revision: 1.00
kmod: failed to exec /sbin/modprobe -s -k scsi_hostadapter, errno = 2
kmod: failed to exec /sbin/modprobe -s -k scsi_hostadapter, errno = 2
kmod: failed to exec /sbin/modprobe -s -k scsi_hostadapter, errno = 2
md: linear personality registered as nr 1
md: raid0 personality registered as nr 2
md: raid1 personality registered as nr 3
md: raid5 personality registered as nr 4
raid5: measuring checksumming speed
   8regs     :   931.200 MB/sec
   32regs    :   535.600 MB/sec
   pII_mmx   :  1274.400 MB/sec
   p5_mmx    :  1326.800 MB/sec
raid5: using function: p5_mmx (1326.800 MB/sec)
md: md driver 0.90.0 MAX_MD_DEVS=256, MD_SB_DISKS=27
md: Autodetecting RAID arrays.
md: autorun ...
md: ... autorun DONE.
LVM version 1.0.8(17/11/2003)
Initializing Cryptographic API
NET4: Linux TCP/IP 1.0 for NET4.0
IP Protocols: ICMP, UDP, TCP, IGMP
IP: routing cache hash table of 2048 buckets, 16Kbytes
TCP: Hash tables configured (established 16384 bind 32768)
Linux IP multicast router 0.06 plus PIM-SM
NET4: Unix domain sockets 1.0/SMP for Linux NET4.0.
FAT: bogus logical sector size 0
UMSDOS: msdos_read_super failed, mount aborted.
FAT: bogus logical sector size 0
FAT: bogus logical sector size 0
reiserfs: found format "3.6" with standard journal
reiserfs: checking transaction log (device ide2(33,66)) ...
for (ide2(33,66))
ide2(33,66):Using r5 hash to sort names
VFS: Mounted root (reiserfs filesystem) readonly.
Freeing unused kernel memory: 120k freed
Adding Swap: 512024k swap-space (priority -1)
apm: BIOS version 1.2 Flags 0x07 (Driver version 1.16)
Linux agpgart interface v0.99 (c) Jeff Hartmann
agpgart: Maximum main memory to use for agp memory: 203M
agpgart: Detected Intel 440BX chipset
agpgart: AGP aperture is 64M @ 0xd8000000
scsi0 : SCSI host adapter emulation for IDE ATAPI devices
usb.c: registered new driver usbdevfs
usb.c: registered new driver hub
ehci_hcd 00:11.2: NEC Corporation USB 2.0
ehci_hcd 00:11.2: irq 11, pci mem d0ac0000
usb.c: new USB bus registered, assigned bus number 1
ehci_hcd 00:11.2: USB 2.0 enabled, EHCI 1.00, driver 2003-Dec-29/2.4
hub.c: USB hub found
hub.c: 5 ports detected
usb-ohci.c: USB OHCI at membase 0xd0ac8000, IRQ 12
usb-ohci.c: usb-00:11.0, NEC Corporation USB
usb.c: new USB bus registered, assigned bus number 2
hub.c: USB hub found
hub.c: 3 ports detected
usb-ohci.c: USB OHCI at membase 0xd0aca000, IRQ 10
usb-ohci.c: usb-00:11.1, NEC Corporation USB (#2)
usb.c: new USB bus registered, assigned bus number 3
hub.c: USB hub found
hub.c: 2 ports detected
Linux Tulip driver version 0.9.15-pre12 (Aug 9, 2002)
eth0: ADMtek Comet rev 17 at 0xac00, 00:20:78:1E:FB:A3, IRQ 10.
uhci.c: USB Universal Host Controller Interface driver v1.1
uhci.c: USB UHCI at I/O 0xa000, IRQ 9
usb.c: new USB bus registered, assigned bus number 4
hub.c: USB hub found
hub.c: 2 ports detected
hub.c: new USB device 00:07.2-1, assigned address 2
usb.c: USB device 2 (vend/prod 0x45e/0x39) is not claimed by any active driver.
hub.c: new USB device 00:07.2-2, assigned address 3
usb.c: USB device 3 (vend/prod 0x46d/0xc309) is not claimed by any active driver.
usb.c: registered new driver usbmouse
input0: Microsoft Microsoft 5-Button Mouse with IntelliEye(TM) on usb4:2.0
usbmouse.c: v1.6:USB HID Boot Protocol mouse driver
usb.c: registered new driver hiddev
usb.c: registered new driver hid
usb.c: registered new driver usbkbd
input: USB HID v1.10 Keyboard [Logitech Logitech USB Keyboard] on usb4:3.0
input: USB HID v1.10 Mouse [Logitech Logitech USB Keyboard] on usb4:3.1
hid-core.c: v1.8.1 Andreas Gal, Vojtech Pavlik <vojtech@suse.cz>
hid-core.c: USB HID support drivers
mice: PS/2 mouse device common for all mice
usbkbd.c: :USB HID Boot Protocol keyboard driver
[drm] Initialized tdfx 1.0.0 20010216 on minor 0
keyboard: Timeout - AT keyboard not present?(f3)
keyboard: Timeout - AT keyboard not present?(f4)
keyboard: Timeout - AT keyboard not present?(f3)
keyboard: Timeout - AT keyboard not present?(f4)

I am running slack-current (kernel 2.4.26), but I have had the same problem in slack-9.1. Wpyh, what type of motherboard do you have? Very strange that I'm having this problem and you're not.

wpyh · 06-20-2004, 10:23 PM

I have an ABIT BE6-II, ide1 (PIIXn) disabled, so the first hpt366 channel becomes ide1. It's weird... nothing seems to be wrong with your setup...

But maybe you could try measuring the speed with hdparm?

cav · 06-20-2004, 11:04 PM

Yeah, I have the same mobo...hdparm benchmarks my drives at around 34 MB/s, I just cant figure this thing out. Highpoint Technologies, which manufactured the hpt366, has a kernel patch on their website, but its way back from the 2.2 series...2.4 kernels should support this chipset natively. I dont get it.

Electro · 06-21-2004, 03:15 AM

Do not worry about the messsages. Can you create/delete partitions, format, write files, and create directories on the hard drives that is connected to the Highpoint controller. I have HPT370 on-board and it works perfectly. LINUX has detected the whole capacity (120 GB) of my hard drives that I placed on the HPT370 controller which only detected 50 GB. I do not have to load scsi emulation module to make my Highpoint controller to work.

I get:

Quote:

HPT366: not 100% native mode: will probe irqs later
ide2: BM-DMA at 0xb800-0xb807, BIOS settings: hde: DMA, hdf: DMA
ide3: BM-DMA at 0xc400-0xc407, BIOS settings: hdg: DMA, hdh: pio

Even though my Highpoint chip is model 370, I still get that similar message. It does not mean that LINUX does not recognize it. It just means it still is checking on some hardware and then eventually it will run in native mode.

To squeeze out your keyboard and mouse errors in the messages. Use PS/2 keyboard and mouse. The USB keyboard and mouse could be the problem for scsi emulation.

What does "hdparm -v" show.

I think all you need to do is to tweak your hard drives for performance. Also if you want to enable DMA during boot up. Look in the kernel documentation for some commands to enter at the boot loader.

wpyh · 06-21-2004, 03:44 AM

Or is it a filesystem problem? Because hdparm shows the transfer rate as 34 MB/s?

Well, my DeskNote has this line in lilo.conf:
append = "ide0=ata66 ide1=ata66 ide2=ata66 ide3=ata66"

And part of my menu.lst (grub):
# For booting GNU/Linux
title GNU/Linux
root (hd0,0)
kernel /bzImage root=/dev/hda1 ide0=ata66 ide1=ata66 ide2=ata66 ide3=ata66

I had to do this because Linux doesn't know that the drives can operate at ata100. But you have this line:
hde: 80043264 sectors (40982 MB) w/2048KiB Cache, CHS=79408/16/63, UDMA(66)
so actually I think it's not a problem with DMA...

cav · 06-21-2004, 04:15 PM

Yeah, I think DMA is working correctly...heres my output for hdparm -v for /dev/hde (on ide2):

Code:

/dev/hde:
 multcount    = 16 (on)
 IO_support   =  0 (default 16-bit)
 unmaskirq    =  0 (off)
 using_dma    =  1 (on)
 keepsettings =  0 (off)
 readonly     =  0 (off)
 readahead    =  8 (on)
 geometry     = 4982/255/63, sectors = 80043264, start = 0

My other drives show the same configuration. Strangely, as I was messing around with copying large files from drive to drive, I noticed that there is a burst speed at the beginning of the transfer which is at the speed it should be. Then it throttles down to a sluggish 2 MB/s.

Any tips on how I might tweak the settings using hdparm? For example, i was reading about the hdparm -X option to set ide transfer modes, but I'm pretty weary about messing with that.

Electro · 06-22-2004, 02:22 AM

Its filesystem overhead and what hard drive you are transferring it to. If you are copying from hde to hdf. It will be pretty low. If you are copying files from hde or hdf to hdg you will get around 10 MB per second to 25 MB per second. Using 80 wire (40 pin) IDE cable will give you about 10 MB boost in throughput. I suggest trying on one hard drive and see if it gives you any problem. If it does not you can replace almost all the cables. You can also try round cable to improve air flow and make the case look a little cleaner.

The file system that I use is XFS because it gives me high throughput for writing and reading. Also I can tweak the settings to optimize XFS on my system by giving a few values to the kernel. Though XFS needs some memory to do its job well. I suggest atleast 512 MB of memory to take advantage of it.

You may want to change the value for IO_support to 1. You can gradually increase the value for -X. You can start with 64 and then go up to 68.

You can upgrade 512 MB or 768 MB SDRAM.

wpyh · 06-22-2004, 09:00 AM

But the weird thing is, he doesn't have the problem with other distros...