From: Eric Dumazet [EMAIL PROTECTED]
Date: Tue, 11 Sep 2007 14:56:13 +0200
When the periodic IP route cache flush is done (every 600 seconds on
default configuration), some hosts suffer a lot and eventually trigger
the soft lockup message.
dst_run_gc() is doing a scan of a possibly huge
This looks nice in general, getting things out of softirq context is
always good.
On Tue, Sep 11, 2007 at 02:56:13PM +0200, Eric Dumazet wrote:
#if RT_CACHE_DEBUG = 2
static atomic_t dst_total = ATOMIC_INIT(0);
#endif
-static unsigned long dst_gc_timer_expires;
On Wed, 12 Sep 2007 02:05:25 -0700 (PDT)
David Miller [EMAIL PROTECTED] wrote:
From: Eric Dumazet [EMAIL PROTECTED]
Date: Tue, 11 Sep 2007 14:56:13 +0200
When the periodic IP route cache flush is done (every 600 seconds on
default configuration), some hosts suffer a lot and eventually
On Wed, 12 Sep 2007 11:00:54 +0100
Christoph Hellwig [EMAIL PROTECTED] wrote:
This looks nice in general, getting things out of softirq context is
always good.
I am preparing a patch to net/ipv4/route.c to migrate rt_check_expire()
as well.
On Tue, Sep 11, 2007 at 02:56:13PM +0200, Eric
On Wed, 12 Sep 2007 04:12:00 -0700 (PDT)
David Miller [EMAIL PROTECTED] wrote:
From: Eric Dumazet [EMAIL PROTECTED]
Date: Wed, 12 Sep 2007 12:08:45 +0200
Unfortunatly, there is no equivalent for this one.
This gives on my Opterons a nice prefetchnta
prefetch(addr) is more like
From: Eric Dumazet [EMAIL PROTECTED]
Date: Wed, 12 Sep 2007 14:16:56 +0200
OK, let's try a normal prefetch(), I'll change it later when/if a
new generic macro is added. I added the missing 'static' and a comment
about the struct {} dst_garbage. I also corrected spelling error on
patch title