linux-kernel - Re: 2.6.24.X: SATA/AHCI related boot delay.

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <200805291654.03617.volker.armin.hemmann@tu-clausthal.de>
Date:	Thu, 29 May 2008 16:54:03 +0200
From:	"Hemmann, Volker Armin" <volker.armin.hemmann@...clausthal.de>
To:	Tejun Heo <htejun@...il.com>
Cc:	Peer Chen <pchen@...dia.com>, Jeff Garzik <jeff@...zik.org>,
	linux-kernel@...r.kernel.org, linux-ide@...r.kernel.org,
	Kuan Luo <kluo@...dia.com>
Subject: Re: 2.6.24.X: SATA/AHCI related boot delay. - not with 2.6.24.3

Hi,

Since 2.6.26-rc4 is out, I updated the bios and replaced one harddisk I 
think its time for a status report ;)

Bios is now version 2.10 from 05/12/2008
 (http://www.asrock.com/mb/download.asp?Model=ALiveNF5-eSATA2%2b&s=AM2)

-AHCI+nomsi: boots fine. Works fine. But: I still can not enable ncq
-AHCI+msi: the usual. No harddisks found, waiting for the timeouts, then 
kernel panic because of missing root.

-NON-RAID/IDE+msi: works fine. No delays. No NCQ (not surprising since mobos 
handbook says that AHCI mode is required).
-NON-RAID/IDE+nomsi: see above.

Attached are kernel config used, lspci outputs and dmesgs. lspci was done 
straight after boot without the nvidia-module loaded. Kernel is patched with 
reiser4. 

One thing that confuses me is this:
echo 31 > /sys/block/sda/device/queue_depth
echo: write error: invalid argument

but:
[14315325.624510] ahci 0000:00:0a.0: AHCI 0001.0100 32 slots 4 ports 3 Gbps 
0xf impl SATA mode
[14315325.624559] ahci 0000:00:0a.0: flags: 64bit sntf led clo pmp pio
[14315325.624599] PCI: Setting latency timer of device 0000:00:0a.0 to 64
[14315325.626674] scsi0 : ahci
[14315325.626674] scsi1 : ahci
[14315325.626674] scsi2 : ahci
[14315325.626674] scsi3 : ahci
[14315325.626674] ata1: SATA max UDMA/133 abar m8192@...9dfc000 port 
0xf9dfc100 irq 23
[14315325.626674] ata2: SATA max UDMA/133 abar m8192@...9dfc000 port 
0xf9dfc180 irq 23
[14315325.626674] ata3: SATA max UDMA/133 abar m8192@...9dfc000 port 
0xf9dfc200 irq 23
[14315325.626674] ata4: SATA max UDMA/133 abar m8192@...9dfc000 port 
0xf9dfc280 irq 23
[14315325.943951] ata1: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
[14315325.950222] ata1.00: ATA-7: SAMSUNG HD502IJ, 1AA01109, max UDMA7
[14315325.950222] ata1.00: 976773168 sectors, multi 16: LBA48 NCQ (depth 0/32)
[14315325.953942] ata1.00: configured for UDMA/133
[14315326.273949] ata2: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
[14315326.286509] ata2.00: ATA-8: SAMSUNG HD501LJ, CR100-12, max UDMA7
[14315326.286509] ata2.00: 976773168 sectors, multi 16: LBA48 NCQ (depth 0/32)
[14315326.286509] ata2.00: configured for UDMA/133

shouldn't controller and harddisks support turning on NCQ? The handbooks says 
that NCQ is supported in AHCI mode and the harddisks doesn't seem to be 
blacklisted.

Glück Auf,
Volker

View attachment "dmesg_2.6.26_rc4_reiser_non_raid_coldboot" of type "text/plain" (31482 bytes)

Download attachment "dmesg_2.6.26_rc4_reiser_ahci_nomsi" of type "application/octet-stream" (31530 bytes)

View attachment "lspci_ahci_nomsi_2.6.26-rc4_vxxx" of type "text/plain" (26366 bytes)

View attachment "lspci_non_raid_msi_2.6.24-rc4_vxxx" of type "text/plain" (26404 bytes)

View attachment "lspci_non_raid_nomsi_2.6.24-rc4_vxxx" of type "text/plain" (26402 bytes)

View attachment ".config" of type "text/plain" (40542 bytes)