[squid-dev] [RFC] Fix shared memory initialization, cleanup. Ensure its usability.

[Alex Rousskov]

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.