Now I'm sending some other fixes intended for 2.6.12... they are either very
simple or potentially critical (as the PREEMPT_ACTIVE fix). Some of these
are/were still in -mm queue, but since they seem to have been dropped and
anyway haven't been merged, I'm resending them anyway.
Also, we have one big 2.6.10 regression which is still unfixed: top always
shows ksoftirqd/0 as runnable, while it gets 0% cpu time, and loadavg goes
then to 1.0, while no real load is generated...
Possible culprits could be the IRQ code rewrite, maybe; I've not found what
the hell can be arch-specific for this (except that UML does not support
PREEMPT and that SMP, and locking in general, isn't well tested yet, even if
the biggest problems are just theoretical, luckily).
I've not yet had the time to analyze it successfully (but while looking at
this I saw the PREEMPT_ACTIVE problem, which also extends to other archs, see
my other mail).
--
Paolo Giarrusso, aka Blaisorblade
Skype user "PaoloGiarrusso"
Linux registered user n. 292729
http://www.user-mode-linux.org/~blaisorblade
___________________________________
Yahoo! Mail: gratis 1GB per i messaggi e allegati da 10MB
http://mail.yahoo.it
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
[Index of Archives]
[Kernel Newbies]
[Netfilter]
[Bugtraq]
[Photo]
[Stuff]
[Gimp]
[Yosemite News]
[MIPS Linux]
[ARM Linux]
[Linux Security]
[Linux RAID]
[Video 4 Linux]
[Linux for the blind]
[Linux Resources]
