Bug 6760 - very slow ahci-device detection since 2.6.17
Summary: very slow ahci-device detection since 2.6.17
Status: CLOSED PATCH_ALREADY_AVAILABLE
Alias: None
Product: IO/Storage
Classification: Unclassified
Component: Serial ATA (show other bugs)
Hardware: i386 Linux
: P2 low
Assignee: Tejun Heo
URL:
Keywords:
Depends on:
Blocks:
 
Reported: 2006-06-28 05:28 UTC by Armin Krieg
Modified: 2006-06-28 12:06 UTC (History)
1 user (show)

See Also:
Kernel Version: 2.6.17
Subsystem:
Regression: ---
Bisected commit-id:

Attachments
ahci-check-phy-status-in-srst (421 bytes, patch)
2006-06-28 12:05 UTC, Tejun Heo 		Details | Diff
Add an attachment (proposed patch, testcase, etc.)

Description Armin Krieg 2006-06-28 05:28:28 UTC 
Most recent kernel where this bug did not occur:
Distribution: Slamd64
Hardware Environment: Asus A8R-MVP
Software Environment:
Problem Description:

Since 2.6.17 the device detection of AHCI devices is very slow. More
specifically, detection of existing devices is no problem, but it takes
minutes for probing SATA-links that are down. If a link is down, there
should be no device, so why is it probing anyway (until there is a timeout)?

From dmesg:

ahci 0000:00:1f.1: AHCI 0001.0000 32 slots 4 ports 3 Gbps 0xf impl SATA mode
ahci 0000:00:1f.1: flags: ncq ilck pm led clo pmp pio slum part
ata1: SATA max UDMA/133 cmd 0xFFFFC20000004900 ctl 0x0 bmdma 0x0 irq 201
ata2: SATA max UDMA/133 cmd 0xFFFFC20000004980 ctl 0x0 bmdma 0x0 irq 201
ata3: SATA max UDMA/133 cmd 0xFFFFC20000004A00 ctl 0x0 bmdma 0x0 irq 201
ata4: SATA max UDMA/133 cmd 0xFFFFC20000004A80 ctl 0x0 bmdma 0x0 irq 201
ata1: SATA link up 1.5 Gbps (SStatus 113)
ata1: dev 0 cfg 49:2f00 82:7c6b 83:7f09 84:4673 85:7c69 86:3e21 87:4663 
88:007f
ata1: dev 0 ATA-7, max UDMA/133, 490234752 sectors: LBA48
ata1: dev 0 configured for UDMA/133
scsi0 : ahci
ata2: SATA link up 3.0 Gbps (SStatus 123)
ata2: dev 0 cfg 49:2f00 82:746b 83:7f01 84:4023 85:7469 86:3c01 87:4023 
88:40ff
ata2: dev 0 ATA-7, max UDMA7, 488397168 sectors: LBA48
ata2: dev 0 configured for UDMA/133
Losing some ticks... checking if CPU frequency changed.
scsi1 : ahci
ata3: SATA link down (SStatus 0)
ata3: qc timeout (cmd 0xec)
ata3: dev 0 failed to IDENTIFY (I/O error)
scsi2 : ahci
ata4: SATA link down (SStatus 0)
ata4: qc timeout (cmd 0xec)
ata4: dev 0 failed to IDENTIFY (I/O error)
scsi3 : ahci
  Vendor: ATA       Model: Maxtor 6L250S0    Rev: BACE
  Type:   Direct-Access                      ANSI SCSI revision: 05
  Vendor: ATA       Model: SAMSUNG SP2504C   Rev: VT10
  Type:   Direct-Access                      ANSI SCSI revision: 05

Steps to reproduce:

Just boot 2.6.17 with AHCI-drivers on Asus A8R-MVP.
This board uses an ATI RS480 chipset.
Comment 1 Tejun Heo 2006-06-28 12:05:49 UTC 
Created attachment 8441 [details]
ahci-check-phy-status-in-srst

This should fix it.  It's already fixed in devel tree but didn't get included
into 2.6.17.
Note You need to log in before you can comment on or make changes to this bug.