Paul, as mentioned in my mail to Mark the original patch was stale, the correct one is here: https://github.com/CAFxX/tar/commit/8b3ccb099c6ddf9f03d12d1f7c433c7927b964d5 <https://github.com/CAFxX/tar/commit/8b3ccb099c6ddf9f03d12d1f7c433c7927b964d5> (NOREUSE was dropped because it’s a no-op in our configuration, and I have no way to validate it).
In the tests I did most of the benefit comes from POSIX_FADV_SEQUENTIAL because in linux this doubles the readhead value. To give some context, the tests were done on linux 4.4 guests running on esxi. Doubling the readhead in this configuration almost doubled the tar throughput. The change itself should be pretty safe, since we’re using the semantics of the fadvise hints quite to the letter. Carlo > On Mar 29, 2017, at 6:03 AM, Paul Eggert <egg...@cs.ucla.edu> wrote: > > On 03/27/2017 07:02 AM, Carlo Alberto Ferraris wrote: >> This is a PoC patch that improves archive creation performance at least in >> certain configurations > > What configuration performs poorly with sequential access? How much > improvement do you see with the patch, and why? >
