linux/net/decnet
Eric Dumazet fc66f95c68 net dst: use a percpu_counter to track entries
struct dst_ops tracks number of allocated dst in an atomic_t field,
subject to high cache line contention in stress workload.

Switch to a percpu_counter, to reduce number of time we need to dirty a
central location. Place it on a separate cache line to avoid dirtying
read only fields.

Stress test :

(Sending 160.000.000 UDP frames,
IP route cache disabled, dual E5540 @2.53GHz,
32bit kernel, FIB_TRIE, SLUB/NUMA)

Before:

real    0m51.179s
user    0m15.329s
sys     10m15.942s

After:

real	0m45.570s
user	0m15.525s
sys	9m56.669s

With a small reordering of struct neighbour fields, subject of a
following patch, (to separate refcnt from other read mostly fields)

real	0m41.841s
user	0m15.261s
sys	8m45.949s

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-11 13:06:53 -07:00
..
netfilter
af_decnet.c
dn_dev.c
dn_fib.c
dn_neigh.c net neigh: RCU conversion of neigh hash table 2010-10-05 14:54:36 -07:00
dn_nsp_in.c
dn_nsp_out.c
dn_route.c net dst: use a percpu_counter to track entries 2010-10-11 13:06:53 -07:00
dn_rules.c
dn_table.c
dn_timer.c
Kconfig
Makefile
README
sysctl_net_decnet.c
TODO

                       Linux DECnet Project
                      ======================

The documentation for this kernel subsystem is available in the
Documentation/networking subdirectory of this distribution and also
on line at http://www.chygwyn.com/DECnet/

Steve Whitehouse <SteveW@ACM.org>