Bug 2670 - extremely poor performance with SATA drive on 2.6 kernel.
Summary: extremely poor performance with SATA drive on 2.6 kernel.
Status: CLOSED CODE_FIX
Alias: None
Product: IO/Storage
Classification: Unclassified
Component: Serial ATA (show other bugs)
Hardware: i386 Linux
: P2 normal
Assignee: Jeff Garzik
URL:
Keywords:
Depends on:
Blocks:
 
Reported: 2004-05-10 13:07 UTC by Gene Czarcinski
Modified: 2004-12-06 13:25 UTC (History)
0 users

See Also:
Kernel Version: 2.6.5
Subsystem:
Regression: ---
Bisected commit-id:


Attachments

Description Gene Czarcinski 2004-05-10 13:07:26 UTC
Distribution:

Fedora Core 1 with their kernel-2.4.22-1.2188

Fedora Core 2 with their kernel-2.6.5-1.356

Hardware Environment:
ASUS SK8V motherboard with Opteron 140 on an onboard VIA adapter supporting a
single SATA drive.  There are two Maxtor 120GB drives on this system a PATA
drive on /dev/hda and a SATA drive which is on /dev/hde on the 2.6 kernel and
/dev/sda on the 2.4.22 kernel.

The results of lspci are:

00:00.0 Host bridge: VIA Technologies, Inc. VT8385 [K8T800 AGP] Host Bridge (rev 01)
00:01.0 PCI bridge: VIA Technologies, Inc. VT8237 PCI bridge [K8T800 South]
00:0a.0 Ethernet controller: 3Com Corporation 3c940 10/100/1000Base-T [Marvell]
(rev 12)
00:0c.0 Multimedia audio controller: Ensoniq 5880 AudioPCI (rev 02)
00:0f.0 RAID bus controller: VIA Technologies, Inc. VIA VT6420 SATA RAID
Controller (rev 80)
00:0f.1 IDE interface: VIA Technologies, Inc.
VT82C586A/B/VT82C686/A/B/VT823x/A/C PIPC Bus Master IDE (rev 06)
00:10.0 USB Controller: VIA Technologies, Inc. VT82xxxxx UHCI USB 1.1 Controller
(rev 81)
00:10.1 USB Controller: VIA Technologies, Inc. VT82xxxxx UHCI USB 1.1 Controller
(rev 81)
00:10.2 USB Controller: VIA Technologies, Inc. VT82xxxxx UHCI USB 1.1 Controller
(rev 81)
00:10.3 USB Controller: VIA Technologies, Inc. VT82xxxxx UHCI USB 1.1 Controller
(rev 81)
00:10.4 USB Controller: VIA Technologies, Inc. USB 2.0 (rev 86)
00:11.0 ISA bridge: VIA Technologies, Inc. VT8237 ISA bridge [K8T800 South]
00:18.0 Host bridge: Advanced Micro Devices [AMD] K8 NorthBridge
00:18.1 Host bridge: Advanced Micro Devices [AMD] K8 NorthBridge
00:18.2 Host bridge: Advanced Micro Devices [AMD] K8 NorthBridge
00:18.3 Host bridge: Advanced Micro Devices [AMD] K8 NorthBridge
01:00.0 VGA compatible controller: ATI Technologies Inc Radeon R200 QM [Radeon
9100] (rev 80)
Software Environment:
Problem Description:

When I run hdparm -Tt on the FC1 system with the 2.4 kernel, I get:

/dev/hda:
 Timing buffer-cache reads:   2508 MB in  2.00 seconds = 1254.00 MB/sec
 Timing buffered disk reads:  170 MB in  3.03 seconds =  56.11 MB/sec

/dev/sda:
 Timing buffer-cache reads:   2400 MB in  2.00 seconds = 1200.00 MB/sec
 Timing buffered disk reads:  168 MB in  3.01 seconds =  55.81 MB/sec

or that the two disks operate pretty much the same.  However, when I run hdparm
-Tt on the FC2 system with the 2.6 kernel I get:

[root@hummer root]# hdparm -Tt /dev/hda
                                                                     
          
/dev/hda:
 Timing buffer-cache reads:   2364 MB in  2.00 seconds = 1181.59 MB/sec
 Timing buffered disk reads:  168 MB in  3.00 seconds =  55.93 MB/sec
[root@hummer root]# hdparm -Tt /dev/hde
                                                                     
          
/dev/hde:
 Timing buffer-cache reads:   2444 MB in  2.00 seconds = 1220.35 MB/sec
 Timing buffered disk reads:   12 MB in  3.40 seconds =   3.53 MB/sec
Comment 1 Gene Czarcinski 2004-12-06 13:25:09 UTC
I am now running Fedora Core 3 and the kernel 2.6.9-1.698_FC3.

Everything now seems to run well.  Performance on the SATA drive is now the same
as on the ATA drive.

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