On Thu, May 12, 2011 at 7:34 AM, Mark Phippard <markp...@gmail.com> wrote: > On Thu, May 12, 2011 at 10:31 AM, Justin Erenkrantz > <jus...@erenkrantz.com> wrote: >> On Thu, May 12, 2011 at 7:23 AM, Mark Phippard <markp...@gmail.com> wrote: >>> I re-ran the results with your latest changes and posted the new numbers. >> >> Is that with the commit as well as the patch I posted (but did not commit)? > > Just the commit.
There was a patch I posted to ra_serf: http://mail-archives.apache.org/mod_mbox/subversion-dev/201105.mbox/%3CBANLkTinWWyXKw=w4jnbfufpyytaxugw...@mail.gmail.com%3E That patch should halve the amount of data transferred between client and server for the basic benchmark test. However, I didn't commit it as I think it might be papering over a larger issue with us not svndiff'ing when we could (should) be doing so. Yet, as I said in my followup, ra_neon does the exact same thing as this patch - so it's not far-fetched that we should apply this to ra_serf as well. > Wasn't the patch for mod_deflate? And just to fix the memory leak > when a client that does not support gzip connects? I did that as well. =) -- justin
