diff options
author | David Herrmann <dh.herrmann@gmail.com> | 2017-01-21 17:26:13 +0100 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2017-01-23 22:10:38 +0100 |
commit | b8a943e2942296aad37a8e7adc43db493413e54b (patch) | |
tree | 60d9d1e583a232e729f965670b2e21dd14a6bc84 /samples/mic | |
parent | bpf: Add tests for the lpm trie map (diff) | |
download | linux-b8a943e2942296aad37a8e7adc43db493413e54b.tar.xz linux-b8a943e2942296aad37a8e7adc43db493413e54b.zip |
samples/bpf: add lpm-trie benchmark
Extend the map_perf_test_{user,kern}.c infrastructure to stress test
lpm-trie lookups. We hook into the kprobe on sys_gettid() and measure
the latency depending on trie size and lookup count.
On my Intel Haswell i7-6400U, a single gettid() syscall with an empty
bpf program takes roughly 6.5us on my system. Lookups in empty tries
take ~1.8us on first try, ~0.9us on retries. Lookups in tries with 8192
entries take ~7.1us (on the first _and_ any subsequent try).
Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Reviewed-by: Daniel Mack <daniel@zonque.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'samples/mic')
0 files changed, 0 insertions, 0 deletions