The benchmark is supposed to measure the encoding speed and not the overhead of buffer realignments.
Signed-off-by: Janne Grunau <[email protected]> --- src/test/erasure-code/ceph_erasure_code_benchmark.cc | 1 + 1 file changed, 1 insertion(+) diff --git a/src/test/erasure-code/ceph_erasure_code_benchmark.cc b/src/test/erasure-code/ceph_erasure_code_benchmark.cc index c6a4228..3fedcd5 100644 --- a/src/test/erasure-code/ceph_erasure_code_benchmark.cc +++ b/src/test/erasure-code/ceph_erasure_code_benchmark.cc @@ -144,6 +144,7 @@ int ErasureCodeBench::encode() bufferlist in; in.append(string(in_size, 'X')); + in.rebuild_aligned(); set<int> want_to_encode; for (int i = 0; i < k + m; i++) { want_to_encode.insert(i); -- 2.1.0 -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
