> > So: I changed line 186 in sys/dev/ata/ata-disk.c from > > > > adp->num_tags = atadev->param->queuelen; > > > > to > > > > adp->num_tags = 0x10; > > > > which is roughly the half of the reported queuelenght (which is 0x1F). > > > > And, Terry, I can't avoid to disappoint you... there's absolutely *no* > > change in the behaviour of the new kernel :-( > > Uh... the "16" you changed to "10" was decimal, so changining it > to 0x10 changes it to ... 16. > > Rather than point out the hex/decimal confusion earlier, that's > why I said "/2".
Ahm, Terry, perhaps I misunderstand you, but: The reported queue-length is 31(dec), which is 0x1F(hex), as stated above. The half of it would be 15.5(dec) what I rounded up to 16(dec), which is approx. 0x10(hex). Where's your point? > Soren's commit is for a -current specific merge. The problems > you are seeing supposedly are in RELENG_4, and will probably not > be effected... though the commit will provide much better > diagnostics than I've suggested. 8-). All I posted here is done, even if my signature states something different, under -current. This last test was done under a -current of Apr 18,2002, 18:00 UTC. I run my allday system, from which I'm posting and writing my e-mail, under -STABLE... I hope that clears things a bit. Ciao/BSD - Matthias To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-current" in the body of the message