I've been continuing off and on to investigate TCP performance issues.
As has been noted before on this list, loss and subsequent processing
can lead to spikes in the measured RTT which confuse delay-based
congestion control algorithms.
I've done some experiments that indicate that cache size is a
> Patch 1: David Miller's red-black tree code, tweaked for 2.6.22.6,
> with some bugfixes
oops...
The original patch can cause a kernel panic if tcp_sacktag_write_queue
is called when the write queue is empty. Use this one instead.
-Tom
---
diff -ur linux-2.6.22.6/include/linux/skbuff.h
linux-
Patch 1: David Miller's red-black tree code, tweaked for 2.6.22.6,
with some bugfixes
-Tom
---
diff -ur linux-2.6.22.6/include/linux/skbuff.h
linux-2.6.22.6-rbtree-davem-fixed/include/linux/skbuff.h
--- linux-2.6.22.6/include/linux/skbuff.h 2007-08-30 23:21:01.0
-0700
+++ linux-2.
Hello,
I've been experimenting with David Miller's red-black tree patch for
SACK processing. We're sending TCP traffic between two machines with
10Gbps cards over a 1Gbps bottleneck link and were getting very high CPU
load with large windows. With a few tweaks, this patch seems to provide
a pretty
Patch 2: fixes to fack_counts and enhancement of SACK fast path
-Tom
---
diff -ur linux-2.6.22.6-rbtree-davem-fixed/include/net/tcp.h
linux-2.6.22.6-rbtree-tomq/include/net/tcp.h
--- linux-2.6.22.6-rbtree-davem-fixed/include/net/tcp.h 2007-09-19
17:36:07.0 -0700
+++ linux-2.6.22.6-rbtre
