RE: async-io for 2.4

> I'm not going to argue that it shouldn't go in because this
> is much more
> stable than the current 2.3 async code (which is probably
> unusable), but
> I think there are some stability issues still needing to be
> addressed.
> Now that the cache is filled, and I've tried running the rest of the
> benchmarks, the box seems to regularly crash pretty hard.
> I'm going to
> try it on a ext2 partition next to see if the problem is with ReiserFS
> (the box is freezing due to a ReiserFS deadlock
> condition...but I think
> it is triggered by a Squid issue, since I don't see this problem with
> 2.2STABLE5+hno--I don't think...I've never run this set of
> benchmarks on
> that Squid before).

I've seen the same problem to my production box (dual-P3, Linux-2.2.17,
ReiserFS-3.5.26, caches on 5 JBOD reiserfs UW2 SCSI disks).
Every 3 days or so I'd get a "stuck on TLB IPI wait" system (essentially
hard-locked).
Asked Alan Cox, he said he'd seen reports of similar lockups
on SMP+ReiserFS situations. Backformatted to Ext2, now it's been
running for 6 days without a problem (except for an insane amout
of used RAM, 35 gigs of disk cache, 1.5M StoreEntries can do that).

-- 
	/kinkie