David S. Miller a228dfd5dc [SPARC64]: Fix bad performance side effect of strbuf timeout changes. ... The recent change to add a timeout to strbuf flushing had a negative performance impact. The udelay()'s are too long, and they were done in the wrong order wrt. the register read checks. Fix both, and things are happy again. There are more possible improvements in this area. In fact, PCI streaming buffer flushing seems to be part of the bottleneck in network receive performance on my SunBlade1000 box. Signed-off-by: David S. Miller <davem@davemloft.net>		2005-05-20 11:40:32 -07:00
..
alpha	[PATCH] alpha/osf_sys: use helper functions to convert between tv and jiffies	2005-05-17 07:59:21 -07:00
arm
arm26
cris
frv
h8300
i386	[PATCH] fix memory scribble in arch/i386/pci/fixup.c	2005-05-17 09:27:05 -07:00
ia64	[PATCH] kill <asm/ioctl32.h>	2005-05-17 07:59:21 -07:00
m32r
m68k
m68knommu
mips	[PATCH] mips: add resource management to pmu	2005-05-17 07:59:20 -07:00
parisc
ppc	[PATCH] ppx32: Fix uninitialized variable in set_preferred_console	2005-05-20 07:54:11 -07:00
ppc64
s390
sh
sh64
sparc
sparc64	[SPARC64]: Fix bad performance side effect of strbuf timeout changes.	2005-05-20 11:40:32 -07:00
um
v850
x86_64	[PATCH] x86_64: Update defconfig	2005-05-17 07:59:17 -07:00