Hello !

It is obviously, that cpdn scientific application has problems to correctly handle the stop and (re)start when running boinc as a service. Although windows service control manager reports no problems stopping and starting the boinc service, I can reproduce an error resp. model crash stopping the service during cpdn model is in initialisation process after (re)start.

Perhaps the developers can take a look at this to avoid model crashes (and wasted time), I will try my best to work around this error.

Regards, Frank

From reading posts of a few months back, it seems that this problem is already known.
It is the BOINC part that is a problem, not CPDN, and BOINC is American. (B stands for Berkley).
The usual recommendation is to PAUSE BOINC, and then EXIT. If you allow Windows to do the stopping / exiting,
then you can be in for a rough time.

Les

Thanx Les !

I try to remember the problem everytime shutting down and restarting my computers, but I cannot promise much ;-)

I thought it was an cpdn problem because there is always a cpdn WU affected, never seen this behaviour an seti or lhc WUs.

Nevertheless, I had walked a bit through the BOINC code and I finally think, it's a timing problem how long boinc client resp. windows service control manager waits that the application completes the stop-request until it kills the process.

BTW: the problem never arises when running boinc as normal application and not as a service. So it seems a problem handling windows service control manager request.

I will try to work out some fix, because I myself have developed a lot of windows services.

Regards, Frank

>
> BTW: the problem never arises when running boinc as normal application and not
> as a service. So it seems a problem handling windows service control manager
> request.

Prior to 4.13, it <b>was</b> a big problem with the GUI application. The new 4.5x version now being tested may have addressed it, as it was envisaged as a unified client.

---

I have seen this problem (or a similar problem) with GUI and with 4.5x versions of the client. I think it is a CPDN problem but it may just be more noticeable due to the size of the workunits. I think it has to do with the multiple applications that CPDN uses. It seems like if the model is paused or stopped before it is completely started there is a fairly high chance of it crashing.

My theory is that the main program has to pass start up info to the secondary program leaving them both in an unstable state temporarly. If the shutdown/pause comes during this time it can/will cause the model to crash.

I have no real data to back this up and only basic knowledge of how the programs interact so I may be way off.

---

BOINC WIKI

BOINCing since 2002/12/8