On 12/10/2015 11:25 AM, Francesco Chemolli wrote: > > Well, slow in starting up, not in operating, hopefully.
Yes, I expect runtime performance to negligibly(?) improve during warmup (on correctly configured deployments) due to pre-allocation of all shared memory used during runtime. > And it is actually pretty detectable: let’s choose an arbitrary size > of the shared segment and output a warning message to cache.log. This > won’t help with the speed, but it might help with the confusion.. Excellent idea! And we can improve it by warning if the combined mlock(2) _delay_ exceeds some hard-coded value. I wonder what that warning should say to avoid a [usually wrong] implication that memory locking should be turned off. How about something like this: """ 2015/12/09 11:24:51| Total mlock() delay exceeded 5.3 seconds. See shared_memory_locking in squid.conf.documented. """ We can set level-1 reporting threshold at 5 or even 10 seconds. We do not need to add a shared_memory_locking parameter to disable this reporting (while still locking), do we? Thank you, Alex. _______________________________________________ squid-dev mailing list squid-dev@lists.squid-cache.org http://lists.squid-cache.org/listinfo/squid-dev