9fans - fans of the OS Plan 9 from Bell Labs
 help / color / mirror / Atom feed
* Re: [9fans] venti wrarena i/o errors
@ 2007-11-29 12:12 Joshua Wood
  2007-12-04 23:02 ` Robert Raschke
  0 siblings, 1 reply; 15+ messages in thread
From: Joshua Wood @ 2007-11-29 12:12 UTC (permalink / raw)
  To: 9fans

>
> The new machine is a VIA.  I will try again without dma.

Were you manually turning dma on? If not, this is not likely to be a  
case where your problem was same as the one I mentioned. I was  
forcing dma on a chipset not listed in the distributed /sys/src/9/pc/ 
sdata.c.

> I will also
> add in the bloom partition, but I'm low on memory at the moment (256MB
> doesn't sound low to me, but I find the new venti can be a bit greedy
> if not constrained), so I'm not sure if that is actually worth doing.

It's optional, and it's not causing your problem, so I don't want to  
distract from the immediate issue, but you can kinda get the best of  
both worlds if memory is tight by starting with a bloom filter, then  
dropping it from your venti conf as the system ages toward less write- 
intensiveness.

> I will read the venti man pages more slowly to understand better.

sources/contrib/steve/doc/Venti-rescue.pdf is a mildly-dated but  
excellent supplement to the manual for the task you're attempting,  
and discusses memory allotment between venti and fossil in an  
appendix, too.

--
Josh


^ permalink raw reply	[flat|nested] 15+ messages in thread
[parent not found: <24c8b3ca4a8c192c1731e5e67d43f50a@tombob.com>]
* Re: [9fans] venti wrarena i/o errors
@ 2007-11-29 17:44 Joshua Wood
  0 siblings, 0 replies; 15+ messages in thread
From: Joshua Wood @ 2007-11-29 17:44 UTC (permalink / raw)
  To: 9fans

> ...sources/contrib/steve/doc/Venti-rescue.pdf is a mildly-dated but  
> excellent...

I was only half right. The document is not even mildly dated. It is  
however indeed excellent.

If only I could work 'ls -l' I would have seen that Steve's version  
of the Venti-rescue.pdf file on sources/contrib is as recent as 11/27.

--
Josh


^ permalink raw reply	[flat|nested] 15+ messages in thread
* Re: [9fans] venti wrarena i/o errors
@ 2007-11-29  1:11 Joshua Wood
  2007-11-29  9:30 ` Robert Raschke
  0 siblings, 1 reply; 15+ messages in thread
From: Joshua Wood @ 2007-11-29  1:11 UTC (permalink / raw)
  To: 9fans

If you suspect your hardware, you should verify it with an  
appropriate low-level tool, like a bootable utilities image from your  
drive manufacturer or similar (or memtest for memory, or etc, - using  
a low-level diagnostic on hardware can really speed up and focus  
software troubleshooting).

Given working hardware, according to the support in Plan 9 for your  
IDE or SATA controller, do you have DMA on when it shouldn't be? I  
saw i/o errors from venti when trying to force dma on a not-quite- 
supported via controller we have. If 'new' is a fresh install from a  
recent iso, you might want to ensure 'old' has been pull'd to the  
latest venti and rd/wrarena code, or invoke wrarena on 'new' itself.  
Lastly, does the venti on 'new' work for a basic operation, like vac(1)?

This month I have tested the procedure you're trying 4 or 5 times,  
and so if it is encouraging, the basic software and process works as  
expected/documented in venti-backup(8). I notice the lack of a bloom  
filter in your venti conf; I am not implying this is the direct  
source of your problem, but you should check out the latest venti(8)  
and its see also's. The bloom filter is probably most critical to  
performance, from what has been reported here and what I've seen, in  
a new initialization scenario, so you'll probably want one.

Since your



^ permalink raw reply	[flat|nested] 15+ messages in thread
* [9fans] venti wrarena i/o errors
@ 2007-11-28 22:42 Robert Raschke
  2007-11-28 23:29 ` erik quanstrom
  0 siblings, 1 reply; 15+ messages in thread
From: Robert Raschke @ 2007-11-28 22:42 UTC (permalink / raw)
  To: 9fans

Hi,

I am trying to migrate my old venti/fossil from one machine to another
(the new machine is running the new venti).  I am doing this pretty
piecemeal and by hand to find my bearings.  When I'm running
venti/wrarena on the old machine pointing at the new one, I am getting
i/o errors on the new machine.  I'm wondering if these point to disk
problems, or if they are benign?

On "new" I created the partitions and did venti/fmtarenas,
venti/fmtisect, venti/fmtindex and finally venti/venti with the
following venti.conf:
index main
isect /dev/sdC0/isect
arenas /dev/sdC0/arenas
mem 5M
bcmem 10M
icmem 15M

On "old", I saved the first arena into a file using venti/rdarena.
And then I'm running
venti/wrarena -h new arenas0
on "old" and the copying starts.

But on "new" I get these errors like these during the copy:
2007/1128 22:10:54 err 4: write /dev/sdC0/arenas offset 0x312a000 count 8192 buf 3458000 returned -1: i/o error
venti/venti: writeproc: part /dev/sdC0/arenas addr 0x312a000: write error: write /dev/sdC0/arenas offset 0x312a000 count 8192 buf 3458000 returned -1: i/o error
2007/1128 22:10:55 err 4: read /dev/sdC0/isect offset 0x7767e000 count 8192 buf 3836000 returned -1: i/o error
2007/1128 22:18:50 err 4: write /dev/sdC0/arenas offset 0x6c86000 count 8192 buf 3c0c000 returned -1: i/o error
venti/venti: writeproc: part /dev/sdC0/arenas addr 0x6c86000: write error: write /dev/sdC0/arenas offset 0x6c86000 count 8192 buf 3c0c000 returned -1: i/o error
2007/1128 22:18:50 err 4: read /dev/sdC0/isect offset 0x5d686000 count 8192 buf 348c000 returned -1: i/o error
2007/1128 22:18:50 err 4: write /dev/sdC0/arenas offset 0x6c88000 count 8192 buf 353e000 returned -1: i/o error
venti/venti: writeproc: part /dev/sdC0/arenas addr 0x6c88000: write error: write /dev/sdC0/arenas offset 0x6c88000 count 8192 buf 353e000 returned -1: i/o error
2007/1128 22:22:50 err 4: write /dev/sdC0/arenas offset 0x9e9e000 count 8192 buf 33ac000 returned -1: i/o error
venti/venti: writeproc: part /dev/sdC0/arenas addr 0x9e9e000: write error: write /dev/sdC0/arenas offset 0x9e9e000 count 8192 buf 33ac000 returned -1: i/o error
2007/1128 22:22:51 err 4: read /dev/sdC0/isect offset 0x139dc000 count 8192 buf 39b0000 returned -1: i/o error
2007/1128 22:22:51 err 4: write /dev/sdC0/arenas offset 0x9ea0000 count 8192 buf 3c00000 returned -1: i/o error
2007/1128 22:22:51 err 4: read /dev/sdC0/isect offset 0x36c6c000 count 8192 buf 3b1c000 returned -1: i/o error
venti/venti: writeproc: part /dev/sdC0/arenas addr 0x9ea0000: write error: write /dev/sdC0/arenas offset 0x9ea0000 count 8192 buf 3c00000 returned -1: i/o error
2007/1128 22:34:58 err 4: write /dev/sdC0/arenas offset 0x19a06000 count 8192 buf 3312000 returned -1: i/o error
venti/venti: writeproc: part /dev/sdC0/arenas addr 0x19a06000: write error: write /dev/sdC0/arenas offset 0x19a06000 count 8192 buf 3312000 returned -1: i/o error
2007/1128 22:34:58 err 4: read /dev/sdC0/isect offset 0x85130000 count 8192 buf 3626000 returned -1: i/o error
2007/1128 22:34:58 err 4: write /dev/sdC0/arenas offset 0x19a08000 count 8192 buf 349e000 returned -1: i/o error
venti/venti: writeproc: part /dev/sdC0/arenas addr 0x19a08000: write error: write /dev/sdC0/arenas offset 0x19a08000 count 8192 buf 349e000 returned -1: i/o error


So, I am wondering if I've got a duff disk, or if there is something
else that I can investigate.  Any pointers are gratefully received.

Robby

--
r.raschke can be found at tombob.com .



^ permalink raw reply	[flat|nested] 15+ messages in thread
end of thread, other threads:[~2007-12-14 16:05 UTC | newest]

Thread overview: 15+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2007-11-29 12:12 [9fans] venti wrarena i/o errors Joshua Wood
2007-12-04 23:02 ` Robert Raschke
2007-12-05  0:29   ` Russ Cox
     [not found] <24c8b3ca4a8c192c1731e5e67d43f50a@tombob.com>
2007-12-06  9:54 ` Robert Raschke
2007-12-11  9:41   ` Robert Raschke
2007-12-14  0:45     ` sqweek
2007-12-14  0:48       ` ron minnich
2007-12-14  8:22         ` Christian Kellermann
2007-12-14 16:05           ` ron minnich
2007-12-14 15:18     ` Richard Miller
  -- strict thread matches above, loose matches on Subject: below --
2007-11-29 17:44 Joshua Wood
2007-11-29  1:11 Joshua Wood
2007-11-29  9:30 ` Robert Raschke
2007-11-28 22:42 Robert Raschke
2007-11-28 23:29 ` erik quanstrom

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).