| From | Sent On | Attachments |
|---|---|---|
| Nick Slager | Jun 20, 2000 12:27 am | |
| Don Lewis | Jun 20, 2000 12:53 am | |
| Scott Donovan | Jun 20, 2000 1:51 am | |
| Nick Slager | Jun 20, 2000 1:59 am | |
| Nick Slager | Jun 20, 2000 2:02 am | |
| Ian West | Jun 20, 2000 7:48 am | |
| Nick Slager | Jun 20, 2000 9:35 pm | |
| Don Lewis | Jun 22, 2000 12:29 am | |
| Steve Passe | Jun 22, 2000 2:27 am | |
| Don Lewis | Jun 22, 2000 2:33 am | |
| Steve Passe | Jun 22, 2000 2:40 am | |
| Nick Slager | Jun 23, 2000 12:38 am | |
| Wilko Bulte | Jun 23, 2000 10:12 am | |
| Thomas Zenker | Jun 26, 2000 2:08 am | |
| Nick Slager | Jun 26, 2000 10:45 pm | |
| Thomas Zenker | Jun 28, 2000 1:03 am | |
| Nick Slager | Jun 28, 2000 5:43 am |
| Subject: | Re: Invalidating pack messages | |
|---|---|---|
| From: | Nick Slager (nic...@albury.net.au) | |
| Date: | Jun 28, 2000 5:43:46 am | |
| List: | org.freebsd.freebsd-scsi | |
Thus spake Thomas Zenker (th...@Lennartz-electronic.de):
On Tue, Jun 27, 2000 at 03:45:36PM +1000, Nick Slager wrote:
In any case, it would appear there is something odd going on that involves write caching. I will turn write caching off again, do a 'make world', and hopefully the confidence factor will start to rise :-)
Hi, having at least the same symptoms like you, I could isolate the problem here to tagged queuing + heavy writes. It never happens for reading only, seeks etc. So I can read the whole disk (9G) to /dev/null without problems, but writing a big file with iozone or dd failes very quickly. I could eliminate the problem by switching of tagged queuing, with bad performance loss (write cache is turned off, bad this didn't help very much), but it survives buildworlds and writes of 6G files.
So far, I can't kill the thing with write caching disabled. That also has the least performance hit, so until it fails, I can live with it :-)
Regards,
Nick.
-- From a Sun Microsystems bug report (#4102680): "Workaround: don't pound on the mouse like a wild monkey."
To Unsubscribe: send mail to majo...@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message





