tbf: improved accuracy at high rates
authorJiri Pirko <jiri@resnulli.us>
Tue, 12 Feb 2013 00:12:05 +0000 (00:12 +0000)
committerDavid S. Miller <davem@davemloft.net>
Tue, 12 Feb 2013 23:59:45 +0000 (18:59 -0500)
commitb757c9336d63f94c6b57532bb4e8651d8b28786f
treec269cb8abddd6d563e466436c8abf6684a3da5e7
parent34c5d292ce05d2bf52e692c44292b0ababba2853
tbf: improved accuracy at high rates

Current TBF uses rate table computed by the "tc" userspace program,
which has the following issue:

The rate table has 256 entries to map packet lengths to
token (time units).  With TSO sized packets, the 256 entry granularity
leads to loss/gain of rate, making the token bucket inaccurate.

Thus, instead of relying on rate table, this patch explicitly computes
the time and accounts for packet transmission times with nanosecond
granularity.

This is a followup to 56b765b79e9a78dc7d3f8850ba5e5567205a3ecd
("htb: improved accuracy at high rates").

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
net/sched/sch_tbf.c