diff options
author | Eric Dumazet <eric.dumazet@gmail.com> | 2010-10-15 07:44:11 +0200 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2010-10-20 12:02:23 +0200 |
commit | 27b75c95f10d249574d9c4cb9dab878107faede8 (patch) | |
tree | 466656d86aaa395951e12b50903e730203c5f86f /fs/xfs/xfs_itable.h | |
parent | net: allocate tx queues in register_netdevice (diff) | |
download | linux-27b75c95f10d249574d9c4cb9dab878107faede8.tar.xz linux-27b75c95f10d249574d9c4cb9dab878107faede8.zip |
net: avoid RCU for NOCACHE dst
There is no point using RCU for dst we allocate for a very short time
(used once).
Change dst_release() to take DST_NOCACHE into account, but also change
skb_dst_set_noref() to force a refcount increment for such dst.
This is a _huge_ gain, because we dont waste memory to store xx thousand
of dsts. Instead of queueing them to RCU, we can free them instantly.
CPU caches can stay hot, re-using same memory blocks to hold temporary
dsts.
Note : remove unneeded smp_mb__before_atomic_dec(); in dst_release(),
since atomic_dec_return() implies a full memory barrier.
Stress test, 160.000.000 udp frames sent, IP route cache disabled
(DDOS).
Before:
real 0m38.091s
user 0m13.189s
sys 7m53.018s
After:
real 0m29.946s
user 0m12.157s
sys 7m40.605s
For reference, if IP route cache was enabled :
real 0m32.030s
user 0m10.521s
sys 8m15.243s
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'fs/xfs/xfs_itable.h')
0 files changed, 0 insertions, 0 deletions