Bug 11635 - strange message in dmesg for IDE HDD: cannot use LBA48 DMA - PIO mode will be used for accessing sectors > 268435456
Summary: strange message in dmesg for IDE HDD: cannot use LBA48 DMA - PIO mode will be...
Status: REJECTED WILL_NOT_FIX
Alias: None
Product: IO/Storage
Classification: Unclassified
Component: IDE (show other bugs)
Hardware: All Linux
: P1 normal
Assignee: io_ide@kernel-bugs.osdl.org
URL:
Keywords:
Depends on:
Blocks:
 
Reported: 2008-09-24 02:20 UTC by Enrique
Modified: 2008-09-24 07:44 UTC (History)
0 users

See Also:
Kernel Version: 2.6.26.1
Subsystem:
Regression: ---
Bisected commit-id:


Attachments

Description Enrique 2008-09-24 02:20:25 UTC
Latest working kernel version: unknown
Earliest failing kernel version: detected on kernel-2.6.25
Distribution: gentoo
Hardware Environment: Asus A7A266 motherboard with BIOS upgraded to latest release (no beta version of upgrade) lspci output:
00:00.0 Host bridge: ALi Corporation M1647 Northbridge [MAGiK 1 / MobileMAGiK 1] (rev 04)
00:01.0 PCI bridge: ALi Corporation PCI to AGP Controller
00:02.0 USB Controller: ALi Corporation USB 1.1 Controller (rev 03)
00:04.0 IDE interface: ALi Corporation M5229 IDE (rev c4)
00:05.0 Multimedia audio controller: C-Media Electronics Inc CM8738 (rev 10)
00:06.0 USB Controller: ALi Corporation USB 1.1 Controller (rev 03)
00:07.0 ISA bridge: ALi Corporation M1533/M1535 PCI to ISA Bridge [Aladdin IV/V/V+]
00:0a.0 Ethernet controller: Realtek Semiconductor Co., Ltd. RTL-8139/8139C/8139C+ (rev 10)
00:0c.0 Serial controller: Rockwell International HCF 56k Data/Fax Modem (rev 01)
00:11.0 Bridge: ALi Corporation M7101 Power Management Controller [PMU]
01:00.0 VGA compatible controller: nVidia Corporation NV4 [RIVA TNT] (rev 04)

Software Environment: Gentoo Linux.
Problem Description: Hdd is slow and dmesg show a strange message

Steps to reproduce:compile kernel and boot

Output of script/ver_linux
If some fields are empty or look unusual you may have an old version.
Compare to the current minimal requirements in Documentation/Changes.
 
Linux AServer 2.6.26.1 #1 Wed Sep 24 00:18:06 CEST 2008 i686 AMD Athlon(TM) XP1600+ AuthenticAMD GNU/Linux
 
Gnu C                  4.1.2
Gnu make               3.81
binutils               2.18
util-linux             2.13.1.1
mount                  2.13.1.1
module-init-tools      3.4
e2fsprogs              1.40.9
reiserfsprogs          3.6.19
Linux C Library        2.6.1
Dynamic linker (ldd)   2.6.1
Procps                 3.2.7
Net-tools              1.60
Kbd                    1.13
Sh-utils               6.9
udev                   124
Modules Loaded         ipt_REJECT ipt_LOG ipt_addrtype xt_pkttype xt_multiport xt_MARK xt_mac xt_iprange xt_tcpudp xt_state nf_conntrack_ipv4 nf_conntrack iptable_mangle nfnetlink iptable_filter ip_tables x_tables ohci_hcd usbcore i2c_ali1535

dmesg output:
ide0 at 0x1f0-0x1f7,0x3f6 on irq 14
ide1 at 0x170-0x177,0x376 on irq 15
hda: max request size: 128KiB
hda: cannot use LBA48 DMA - PIO mode will be used for accessing sectors >
268435456
hda: 488397168 sectors (250059 MB) w/8192KiB Cache, CHS=30401/255/63
hda: cache flushes supported
 hda: hda1 hda2 hda3 hda4
hdc: max request size: 128KiB
hdc: cannot use LBA48 DMA - PIO mode will be used for accessing sectors >
268435456
hdc: 488397168 sectors (250059 MB) w/8192KiB Cache, CHS=30401/255/63

hdparm output:
hdparm -Tt /dev/hdc output:
/dev/hdc:
 Timing cached reads:   388 MB in  2.01 seconds = 193.07 MB/sec
 Timing buffered disk reads:  142 MB in  3.03 seconds =  46.89 MB/sec
(I want to get something above 500MB/sec)

May it help (googled)
i found that related info:
https://bugs.launchpad.net/ubuntu/+source/linux-source-2.6.20/+bug/119730
http://osdir.com/ml/ide/2005-03/msg00064.html
Comment 1 Sergei Shtylyov 2008-09-24 03:18:07 UTC
(In reply to comment #0)
> hdc: cannot use LBA48 DMA - PIO mode will be used for accessing sectors >
> 268435456

The IDE core honestly warns you that the controller doesn't support DMA for accesses abobe 137 GB. Where's the problem?

> hdc: 488397168 sectors (250059 MB) w/8192KiB Cache, CHS=30401/255/63

> hdparm output:
> hdparm -Tt /dev/hdc output:
> /dev/hdc:
>  Timing cached reads:   388 MB in  2.01 seconds = 193.07 MB/sec
>  Timing buffered disk reads:  142 MB in  3.03 seconds =  46.89 MB/sec
> (I want to get something above 500MB/sec)

500 MB/s on disk reads?! That's totally wrong expectaion. What I am seeing seems quite adequate speed for UltraDMA. And cached reads don't measure disk transfer speed but rather your CPU bus/memory bandwidth.

> May it help (googled)
> i found that related info:
> https://bugs.launchpad.net/ubuntu/+source/linux-source-2.6.20/+bug/119730
> http://osdir.com/ml/ide/2005-03/msg00064.html

The latter reports DMA timeouts -- now that's an error indeed. But the report is against 2.6.11. :-)

I suggest this to be resolved INVALID.
Comment 2 Alan 2008-09-24 03:27:03 UTC
This is a hardware limit.
Comment 3 Enrique 2008-09-24 07:11:24 UTC
> 500 MB/s on disk reads?! That's totally wrong expectaion

For my personal computer (Pentium IV)

hdparm -Tt /dev/hda

/dev/hda:
 Timing cached reads:   1500 MB in  2.00 seconds = 749.31 MB/sec
 Timing buffered disk reads:  184 MB in  3.01 seconds =  61.14 MB/sec

Server I'm using its athlon 1800MHz and I got same performance as previous server I got (k6-II @ 450MHz) I found server slow in transfers and high CPU usage (and k6-II never warnning me for hardware limits :S) This is the reason I'm in doubt.
Upgrading server didn't increase transfers between my PC and my server, in my local network :(
Thanks for replies.
Comment 4 Alan 2008-09-24 07:44:41 UTC
> Timing buffered disk reads:  184 MB in  3.01 seconds =  61.14 MB/sec

is the disk speed

Note You need to log in before you can comment on or make changes to this bug.