make -j as a stress test (was: Re: Quality of FreeBSD) [WARNING - 6.0-BETA1 still hosed!]

Fri Jul 22 19:40:12 GMT 2005

It is definitely NOT fixed in 6.0-BETA1

Within SECONDS of starting a buildworld after the provider rebuild
completed, I got this...

GEOM_MIRROR: Device boot: provider ad4s1 detected.
GEOM_MIRROR: Device boot: rebuilding provider ad4s1.
GEOM_MIRROR: Device boot: provider ad6s1 detected.
GEOM_MIRROR: Device boot: rebuilding provider ad6s1.
GEOM_MIRROR: Device boot: rebuilding provider ad4s1 finished.
GEOM_MIRROR: Device boot: provider ad4s1 activated.
GEOM_MIRROR: Device boot: rebuilding provider ad6s1 finished.
GEOM_MIRROR: Device boot: provider ad6s1 activated.
subdisk4: detached
ad4: detached
unknown: FAILURE - SETFEATURES SET TRANSFER MODE timed out
unknown: timeout waiting to issue command
unknown: error issueing SETFEATURES SET TRANSFER MODE command
GEOM_MIRROR: Device boot: provider ad4s1 disconnected.
GEOM_MIRROR: Request failed (error=6). ad4s1[READ(offset=35096543232,
length=10240)]
GEOM_MIRROR: Request failed (error=6). ad4s1[WRITE(offset=35463411712,
length=2048)]
GEOM_MIRROR: Request failed (error=6). ad4s1[WRITE(offset=35467393024,
length=2048)]
GEOM_MIRROR: Request failed (error=6). ad4s1[WRITE(offset=35501357056,
length=2048)]
GEOM_MIRROR: Request failed (error=6). ad4s1[WRITE(offset=35501551616,
length=2048)]
GEOM_MIRROR: Request failed (error=6). ad4s1[WRITE(offset=35501553664,
length=2048)]
GEOM_MIRROR: Request failed (error=6). ad4s1[WRITE(offset=35502305280,
length=2048)]
GEOM_MIRROR: Request failed (error=6). ad4s1[WRITE(offset=35502583808,
length=2048)]
GEOM_MIRROR: Request failed (error=6). ad4s1[WRITE(offset=35502764032,
length=2048)]
GEOM_MIRROR: Request failed (error=6). ad4s1[WRITE(offset=35648684032,
length=16384)]
GEOM_MIRROR: Request failed (error=6). ad4s1[WRITE(offset=35705600000,
length=2048)]
GEOM_MIRROR: Request failed (error=6). ad4s1[WRITE(offset=35840983040,
length=16384)]
GEOM_MIRROR: Request failed (error=6). ad4s1[WRITE(offset=35840999424,
length=16384)]
GEOM_MIRROR: Request failed (error=6). ad4s1[WRITE(offset=35848910848,
length=2048)]
GEOM_MIRROR: Request failed (error=6). ad4s1[WRITE(offset=35854632960,
length=2048)]
GEOM_MIRROR: Request failed (error=6). ad4s1[WRITE(offset=35866456064,
length=2048)]
GEOM_MIRROR: Request failed (error=6). ad4s1[WRITE(offset=36226842624,
length=16384)]
GEOM_MIRROR: Request failed (error=6). ad4s1[WRITE(offset=36226859008,
length=16384)]
GEOM_MIRROR: Request failed (error=6). ad4s1[WRITE(offset=36233115648,
length=2048)]
GEOM_MIRROR: Request failed (error=6). ad4s1[WRITE(offset=36234352640,
length=2048)]
GEOM_MIRROR: Request failed (error=6). ad4s1[WRITE(offset=36234868736,
length=2048)]
GEOM_MIRROR: Request failed (error=6). ad4s1[WRITE(offset=36274173952,
length=2048)]
unknown: req=0xc1e2e320 SETFEATURES SET TRANSFER MODE semaphore timeout !!
DANGER Will Robinson !!
unknown: req=0xc1e2e320 SETFEATURES SET TRANSFER MODE semaphore timeout !!
DANGER Will Robinson !!
unknown: req=0xc1e2e320 SETFEATURES SET TRANSFER MODE semaphore timeout !!
DANGER Will Robinson !!
unknown: req=0xc1e2e320 SETFEATURES SET TRANSFER MODE semaphore timeout !!
DANGER Will Robinson !!
unknown: req=0xc1e2e320 SETFEATURES SET TRANSFER MODE semaphore timeout !!
DANGER Will Robinson !!
unknown: req=0xc1e2e320 SETFEATURES SET TRANSFER MODE semaphore timeout !!
DANGER Will Robinson !!
unknown: req=0xc1e2e320 SETFEATURES SET TRANSFER MODE semaphore timeout !!
DANGER Will Robinson !!
unknown: req=0xc1e2e320 SETFEATURES SET TRANSFER MODE semaphore timeout !!
DANGER Will Robinson !!
unknown: req=0xc1e2e320 SETFEATURES SET TRANSFER MODE semaphore timeout !!
DANGER Will Robinson !!
unknown: req=0xc1e2e320 SETFEATURES SET TRANSFER MODE semaphore timeout !!
DANGER Will Robinson !!
unknown: req=0xc1e2e320 SETFEATURES SET TRANSFER MODE semaphore timeout !!
DANGER Will Robinson !!
unknown: req=0xc1e2e320 SETFEATURES SET TRANSFER MODE semaphore timeout !!
DANGER Will Robinson !!
unknown: req=0xc1e2e320 SETFEATURES SET TRANSFER MODE semaphore timeout !!
DANGER Will Robinson !!
unknown: req=0xc1e2e320 SETFEATURES SET TRANSFER MODE semaphore timeout !!
DANGER Will Robinson !!
unknown: req=0xc1e2e320 SETFEATURES SET TRANSFER MODE semaphore timeout !!
DANGER Will Robinson !!
unknown: req=0xc1e2e320 SETFEATURES SET TRANSFER MODE semaphore timeout !!
DANGER Will Robinson !!
unknown: req=0xc1e2e320 SETFEATURES SET TRANSFER MODE semaphore timeout !!
DANGER Will Robinson !!
unknown: req=0xc1e2e320 SETFEATURES SET TRANSFER MODE semaphore timeout !!
DANGER Will Robinson !!
unknown: req=0xc1e2e320 SETFEATURES SET TRANSFER MODE semaphore timeout !!
DANGER Will Robinson !!
unknown: req=0xc1e2e320 SETFEATURES SET TRANSFER MODE semaphore timeout !!
DANGER Will Robinson !!
unknown: req=0xc1e2e320 SETFEATURES SET TRANSFER MODE semaphore timeout !!
DANGER Will Robinson !!

This is significantly WORSE than 5.3-RELEASE in that it appears not only
to detach the disk, but then to go on to whine mightily about other things
(I have no idea whether I've taken a data corruption hit at this point or
not.)

That didn't take long to verify....

--
-- 
Karl Denninger (karl at denninger.net) Internet Consultant & Kids Rights Activist
http://www.denninger.net	My home on the net - links to everything I do!
http://scubaforum.org		Your UNCENSORED place to talk about DIVING!
http://homecuda.com		Emerald Coast: Buy / sell homes, cars, boats!
http://genesis3.blogspot.com	Musings Of A Sentient Mind

On Fri, Jul 22, 2005 at 03:48:46PM +0200, Angelo Turetta wrote:
> Karl Denninger wrote:
> >As I pointed out in my PR, "make -j4 buildworld" is more than sufficient
> >to demonstrate the problem.
>     ( ... )
> >I'll pull over 6.0-BETA1, rebuild the array (that is the time-consuming
> >part of this test - takes 6-8 hours for the rebuild to run) and see if it
> >fails during a buildworld.
> 
> Maybe I'm wrong, but in my tests I had the impression that RELENG_6 
> includes the phk's update to make which corrects the -j behaviour.
> 
> In 4.x and 5.x, every submake will spawn up to n tasks (n being the 
> number provided with -j), and a buildworld -j4 in UP hardware easily 
> produces a 2 digits system load.
> 
> That's not more the case with 6.x (if I'm not wrong), in my test 
> buildworld -j4 puts the load right near 4.
> 
> So I hope you have other ways to test the new ATA, as make buildworld 
> might not more be the monster it used to be.
> 
> Angelo Turetta
> _______________________________________________
> freebsd-stable at freebsd.org mailing list
> http://lists.freebsd.org/mailman/listinfo/freebsd-stable
> To unsubscribe, send any mail to "freebsd-stable-unsubscribe at freebsd.org"
> 
> 
> %SPAMBLOCK-SYS: Matched [@freebsd.org+], message ok