Nils Goroll
Nils Goroll
(edit: set `never` from vcl in an example) Based on the discussion during last bugwash, here's a proposal to clarify the questions from the last comment: For timeouts, we will...
> Do we agree that we can't set never from VCL? My proposal was that you could. Sure, this would, for all practical circumstances, be identical to `set ... =...
I am not sure if what I am asking for justifies the effort, but I am having a hard time following the first commit. If it is not too much...
Thank you, this looks good to me overall. I would still have some suggestions, but would also be OK to polish after merge, if you agree: * `struct backend_cw` should...
bugwash: proposed (re)name: global parameters: * `backend_queue_limit` * `backend_queue_timeout` VCL: ```vcl backend foo { .queue_limit = 42; .queue_timeout 1m; } sub vcl_backend_fetch { set bereq.queue_limit = 42; set bereq.queue_timeout =...
bugwash approved. please implement connection purge on health change to sick
bugwash: merge but the last commit, open new PR for the flush
Putting aside the question of whether or not NodeJS is a good choice to properly calculate benchmarks at all, I think there is a methodological issue here: ```javascript timingAverages.contentTransfer =...
The numbers from the log do not reflect your reporting at all. For Cache misses, the total processing time (second last column) is in the multiple seconds range, while for...
👍🏽 on the idea