On Fri, May 13, 2016 at 8:34 AM, Eric Covener <cove...@gmail.com> wrote:
> On Wed, May 11, 2016 at 6:39 PM, William A Rowe Jr <wr...@rowe-clan.net> > wrote: > > In the next iteration for trunk I see a value in having both the basic > > activity flag per worker thread so we can see those states at a glance > as we > > can today, as well as a summary table per process of the number of > > recognized workers and inactive Conn/req per process by state. > > I believe we have (most of?) this data in 2.4 server-status for event. > Yup, that's certainly a great start to what we want. My open question is still, whether administrators would want to see both the per-connection and the per-thread detailed score records on the same server. Once we are in agreement on the backports of scoreboard.c to 2.4.x branch, it would be a good time to introduce a new state between reading and writing, perhaps called loading or processing, which reflects the time between the start of the request handler, and the beginning of writing to the client. This would reflect both processing time, and glomming of any input body.
