Re: bad trace magic

[Jens Axboe <jens.axboe@oracle.com>]

On Wed, Nov 19 2008, Martin Peschke wrote:
> 
> On Wed, 2008-11-19 at 12:49 +0100, Jens Axboe wrote:
> > On Wed, Nov 19 2008, Martin Peschke wrote:
> > > Hi,
> > > 
> > > I run across blktrace complaints about broken traces once in a while.
> > > I have pimped up the debugging output in verify_trace():
> > > ...
> > I think Alan and I debugged something like this in the early days of
> > blktrace. Is your stream consistently off when this happens? Does the
> > sequence numbers jump?
> 
> Well, consistently off? If it's off once, is there a next trace?

How are you running blktrace? If you have the blktrace output files, you
can inspect what it would have done next. blkparse may not do more after
it detects a bad trace, though.
> 
> Sequence numbers appear to jump, from 183e8 to f1b1 in this case:
> 
> --- bad trace magic ---
> magic    0x00000001
> sequence 0x0001007a
> time     0x000000000000fb40
> sector   0x000000000005925e
> bytes    0x65617407
> action   0x0000f1b1
> pid      0x00000773
> device   0xec86baa8
> cpu      0x00000000
> error    0x007f
> pdu_len  0x8430
> 
> 00000001 0001007a 00000000 0000fb40 00000000 0005925e 65617407 0000f1b1
> 00000773 ec86baa8 00000000 007f8430

So that's interesting. What byte offset did this happen at? And what is
your subbuffer size for blktrace?

> 
> bad trace in /sys/kernel/debug/block/sdae/trace0
> 
> --- previous trace ---
> magic    0x65617407
> sequence 0x000183e8
> time     0x00000815371024d2
> sector   0x000000000052cdf0
> bytes    0x00001000
> action   0x09820008
> pid      0x000019bf
> device   0x041000e0
> cpu      0x00000000
> error    0x0000
> pdu_len  0x0000
> 
> 65617407 000183e8 00000815 371024d2 00000000 0052cdf0 00001000 09820008
> 000019bf 041000e0 00000000 00000000
> 
> --
> To unsubscribe from this list: send the line "unsubscribe linux-btrace" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html

-- 
Jens Axboe