[squid-dev] Moved PID file management from Coordinator to Master

[Amos Jeffries]

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

On 14/01/2015 10:54 p.m., Tsantilas Christos wrote:
> On 01/14/2015 11:25 AM, Amos Jeffries wrote:
>> On 14/01/2015 7:37 a.m., Tsantilas Christos wrote:
>>> On 01/12/2015 07:22 PM, Amos Jeffries wrote: On 12/01/2015
>>> 6:02
> ...
>>> The Master process has no way to know if the workers are
>>> exiting early with no clients, or aborting on worker-specific 
>>> shutdown_timeout values. But the coordinator can receive a 
>>> terminated message from them over SMP sockets.
>>> 
>>>> We can use exit status.
>> 
>> Does the master process get exit status of *all* worker processes
>> and the sub-childs down N levels? It was my understanding that in
>> SMP each worker disker etc is a fork() and the child becomes new
>> coordinator.
>> 
> 
> Currently master process does not check exist status for any kid
> process and from what I know it can not get exit status down N
> levels. But it can get exit status of processes forked from master
> process, the coordinator and workers. This is should be enough. Why
> do we need to get exit status for sub-childs? If a worker process
> exited normally means that the sub-childs exited normally or
> without huge problems. Do you worry for still-running sub-childs
> after a worker process exited? Is it possible?

I suspect we will find that some diskers etc are in fact spawned by
either coordinator or a worker and one level deeper than the master
can see.

Amos
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.22 (MingW32)

iQEcBAEBAgAGBQJUtkBIAAoJELJo5wb/XPRj6hIIAIvq9pA7/CdXz7ssgvlJhyer
P42VIFRVOV+0FOaUsQCGRN5tU/lhpdAcjDZdOZrodEkds3RGWm2lu+AbWL4K0BV/
tgiEF7c4wtKeW7AbwSdwnXCozWZ13vT1nuVA0Mw2inmJvgn6U8CjarN+nF+aWYIY
O6QYxcwWcfILaVmHHJFd2k9RWEMc+qDGC1tFosZK6hCu/mRs2DQu0nsLPKoA1fQ6
WGdLXM1ePEItSAQrHBw3uv2RG6vAYBuYUl3LHkVYkqCc269cFeKxbldf52MLiS5p
VrhYRGHPREAHcNJAwmnpm4YbEAO1g2RwsWU9mHPZP/YYA1kGaYV4LTZINh6s5HY=
=uMno
-----END PGP SIGNATURE-----