linux-ide.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Tejun Heo <htejun@gmail.com>
To: jonas@local.se
Cc: linux-ide@vger.kernel.org, torvalds@osdl.org
Subject: Re: Scary Intel SATA problem: "frozen"
Date: Wed, 29 Nov 2006 16:29:03 +0900	[thread overview]
Message-ID: <456D36BF.1060809@gmail.com> (raw)
In-Reply-To: <456D3370.5050003@local.se>

Jonas Lundgren wrote:
>> Also, does 'mount -o remount,barrier=0 /' change anything?
> 
> I will post this info as soon as I can "reproduce" the error.

If it doesn't occur as soon as you boot, it's probably irrelevant.

> Atm I run the ICH8 SATA ports in AHCI mode with "IDE bus master"(To be
> honest I don't really know what this option does, no info about it in
> the BIOS nor the mobo manual) turned off in BIOS. The drives are
> connected to port 1, 3, 6 and 8 (raptor+raptor on 1+3, and WD 250G + WD
> 250G (also a raid0) on ports 6+8)

I guess that's just your mobo's way of telling that ahci mode is active.

[--snip--]
>> Please full dmesg after your computer got really slow.  I suspect libata
>> decided to switch to PIO mode.
> 
> If that's so, how come I still get good read speeds? o.O

Yeah, if you're still getting good read speed, PIO mode hasn't kicked in.

>>> I don't know what causes it, but most of the times when I've gotten it
>>> my system has been under heavy load (compiling, downloading torrents in
>>> 11mb/sec etc). Please let me know if you want any additional info, want
>>> me to try something out, or whatever. My recent hardware upgrade for
>>> around $1200 (to a core2duo system, i965 mobo) is just going to waste
>>> because of this problem. :/
>> Heh, nice machine you got there.  When you look at the dmesg, do the
>> error messages occur only on one of the two drives?  Or are both
>> affected?  If only one is affected,
> 
> IIRC only sda is affected, and later today I'm gonna switch back to
> non-AHCI mode and try to reproduce this error (This might be my
> imagination, but it feels like I get the error more frequently if I
> don't run the ports in AHCI mode..) so I can try out the things you've
> listed here.. Would suck if there's a hardware problem with one of my
> disks, but I guess it's possible.

Cabling/power issue is more likely than faulty hard drive, I think. 
Interestingly, you're more likely to encounter insufficient power 
problem if you have multi-lane power supply (most high-powered ones are 
multi-lane these days) because they have less power per lane.

e.g. Single-lane 350w power supply won't have problem powering 5 drives 
no matter how you connect them but if you somehow hook up five drives to 
a single lane in 450w multi-lane power, you're screwed.  Furthermore, 
it's not always clear which cable belongs to which power lane.

>> 1. swap the two.  you'll probably have to dance a little bit with boot
>> loader but md should handle that fine once the kernel is loaded.  does
>> the errors persist?  on which device do they occur?  do they follow the
>> drive or stay on the mobo port?
> 
> (I'm running my /boot on a raid1, so switching drives should require no
> reconfiguration at all :)
> 
>> 2. try different cable / port.  if you change port, again, you need to
>> dance w/ boot loader.  who's carrying the error messages with it?
>>
>> 3. try different power plug from different power lane.
>>
>>> I just got so glad when I saw the post of this on linux-ide, I've been
>>> searching like crazy to find another person having the same problem (and
>>> possibly a solution) for the past 2-3 weeks or so.
>> My first guess is frequent transmission errors.  Please report the test
>> results.  Thanks.
>>
> 
> I've pushing my system really hard for half an hour or so to reproduce
> this problem, and I got something else (no write speed slowdown, but
> some page allocation errors, no idea if this has something to do with
> anything, but I'll post it anyways)

You pushed your box really hard and the kernel can't get the memory it 
wants.  Not really relevant to SATA problem.

-- 
tejun

  reply	other threads:[~2006-11-29  7:29 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-11-28 22:24 Scary Intel SATA problem: "frozen" Jonas Lundgren
2006-11-28 22:59 ` Linus Torvalds
2006-11-28 23:22   ` Jeff Garzik
2006-11-28 23:43     ` Linus Torvalds
2006-11-29  0:38       ` Jeff Garzik
2006-11-29  0:51         ` Linus Torvalds
2006-11-29  2:51       ` Mark Lord
2006-11-29  0:57 ` Tejun Heo
2006-11-29  7:14   ` Jonas Lundgren
2006-11-29  7:29     ` Tejun Heo [this message]
2006-11-29 14:11       ` Mark Lord
2006-11-29 16:19       ` Linus Torvalds
2006-12-06 17:58   ` Jonas Lundgren
2006-12-06 18:45     ` Andrew Lyon
2006-12-07  1:25     ` Tejun Heo
  -- strict thread matches above, loose matches on Subject: below --
2006-11-14 15:04 [git patches] libata fixes Jeff Garzik
2006-11-28 17:31 ` Scary Intel SATA problem: "frozen" Linus Torvalds
2006-11-28 17:37   ` Mark Lord
2006-11-28 17:55     ` Sergei Shtylyov
2006-11-28 20:12       ` Eric D. Mudama
2006-11-28 20:36         ` Sergei Shtylyov
2006-11-29  1:12     ` Tejun Heo
2006-11-28 18:05   ` Alan
2006-11-28 18:33     ` Linus Torvalds
2006-11-28 21:03   ` Jeff Garzik
2006-11-28 21:45     ` Linus Torvalds
2006-11-28 22:18   ` Jeff Garzik

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=456D36BF.1060809@gmail.com \
    --to=htejun@gmail.com \
    --cc=jonas@local.se \
    --cc=linux-ide@vger.kernel.org \
    --cc=torvalds@osdl.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).