https://bz.apache.org/bugzilla/show_bug.cgi?id=62668
--- Comment #6 from Bernard Spil <[email protected]> --- (In reply to Yann Ylavic from comment #4) > Bernard, is this with high concurrency scenario or it can be reproduced with > a single/few requests? > > Looking at the stacktrace, the most probable looping threads are numbers 60 > to 62, thus ap_filter_output_pending(). Is the endless loop internal to this > function or MPM event's process_socket() is calling it endlessly? > > If I can't reproduce with a simple scenario, could you please debug that > loop (latest trunk) and determine why ap_filter_output_pending() either > never ends or keeps returning OK? It should stop (DECLINED) when the socket > is completely flushed... Hi Yann, I have found that I can reliably reproduce it using "ANALYZE" on https://developers.google.com/speed/pagespeed/insights I have not been able to reproduce it by merely loading a page with many resources. Tried ab too (ab -n 10000 -c 250 https://test.brnrd.eu/) but that doesn't trigger the issue either. Yesterday I had issues inspecting the running process, now trying again to see if I can find out more about the spinning thread. -- You are receiving this mail because: You are the assignee for the bug. --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
