LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
* [PATCH 0/2] enable irqs when waiting for rwlocks
@ 2008-10-22  8:33 Petr Tesarik
  2008-10-22  8:34 ` [PATCH 1/2] Allow rwlocks to re-enable interrupts Petr Tesarik
  2008-10-22 17:31 ` [PATCH 0/2] enable irqs when waiting for rwlocks Rick Jones
  0 siblings, 2 replies; 9+ messages in thread
From: Petr Tesarik @ 2008-10-22  8:33 UTC (permalink / raw)
  To: linux-kernel, linux-ia64; +Cc: tee

Hello,

SGI has observed that on large systems, interrupts are not serviced for
a long period of time when waiting for a rwlock. The following patch
series re-enables irqs while waiting for the lock, resembling the code
which is already there for spinlocks.

I only made the ia64 version, because the patch adds some overhead to
the fast path. In particular, I wasn't able to make a reasonably
lightweight implementation for x86, so I assume there are not such large
systems based on x86(_64). Of course, the possibility to implement
raw_{read|write}_lock_flags for any architecture is still there.

Petr Tesarik



^ permalink raw reply	[flat|nested] 9+ messages in thread

end of thread, other threads:[~2008-10-23 14:12 UTC | newest]

Thread overview: 9+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2008-10-22  8:33 [PATCH 0/2] enable irqs when waiting for rwlocks Petr Tesarik
2008-10-22  8:34 ` [PATCH 1/2] Allow rwlocks to re-enable interrupts Petr Tesarik
2008-10-22  8:45   ` Peter Zijlstra
2008-10-22  8:58     ` Petr Tesarik
2008-10-22 17:24       ` Peter Zijlstra
2008-10-22 19:05         ` Matthew Wilcox
2008-10-22 19:19           ` Peter Zijlstra
2008-10-22 17:31 ` [PATCH 0/2] enable irqs when waiting for rwlocks Rick Jones
2008-10-23 14:12   ` Robin Holt

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).