summaryrefslogtreecommitdiffhomepage
path: root/test/syscalls/linux/msync.cc
diff options
context:
space:
mode:
authorAndrei Vagin <avagin@google.com>2019-10-18 15:00:07 -0700
committergVisor bot <gvisor-bot@google.com>2019-10-18 15:01:40 -0700
commit8ae70f864d7ab9ca6aa2b47d144d1a2671857603 (patch)
tree1d70c2f2a59b0abe09c04b9f53619cb57ed81789 /test/syscalls/linux/msync.cc
parent4e6f3a0c71e4107efb5c9446508876f942b30ec7 (diff)
test/perf: optimize the getdents test
* Use mknod instead of open&close to create an empty file. * Limit a number of files to (1<<16) instead of 100K. In this case, a test set is (1, 8, 64, 512, 4K, 32K, 64K) instead of (1, 8, 64, 512, 4K, 32K, 98K). I think it is easier to compare results for 32K and 64K than 32K and 98K. And results for 98K doesn't give us more information than for 54K. PiperOrigin-RevId: 275552507
Diffstat (limited to 'test/syscalls/linux/msync.cc')
0 files changed, 0 insertions, 0 deletions