[src/trunk]: src/doc Write about bpf's statistic counters

[ozaki-r <ozaki-r%NetBSD.org@localhost>]

details:   https://anonhg.NetBSD.org/src/rev/b8f68a157bbe
branches:  trunk
changeset: 352390:b8f68a157bbe
user:      ozaki-r <ozaki-r%NetBSD.org@localhost>
date:      Thu Mar 30 06:50:53 2017 +0000

description:
Write about bpf's statistic counters

diffstat:

 doc/TODO.smpnet |  8 ++++++--
 1 files changed, 6 insertions(+), 2 deletions(-)

diffs (19 lines):

diff -r f3051bd83a07 -r b8f68a157bbe doc/TODO.smpnet
--- a/doc/TODO.smpnet   Thu Mar 30 06:42:05 2017 +0000
+++ b/doc/TODO.smpnet   Thu Mar 30 06:50:53 2017 +0000
@@ -1,4 +1,4 @@
-$NetBSD: TODO.smpnet,v 1.10 2017/03/30 04:37:58 ozaki-r Exp $
+$NetBSD: TODO.smpnet,v 1.11 2017/03/30 06:50:53 ozaki-r Exp $
 
 MP-safe components
 ==================
@@ -140,4 +140,8 @@
 obtained via kvm(3). bpf_d#_bd_next, bpf_d#_bd_filter and bpf_d#_bd_list
 member variables are obsolete but remain. ifnet#if_xname is also accessed
 via struct bpf_if and obsolete ifnet#if_list is required to remain to not change
-the offset of ifnet#if_xname.
+the offset of ifnet#if_xname. The statistic counters (bpf#bd_rcount,
+bpf#bd_dcount and bpf#bd_ccount) are also victims of this restriction; for
+scalability the statistic counters should be per-CPU and we should stop using
+atomic operations for them however we have to remain the counters and atomic
+operations.