--------------- From: "Bill Stoddard" <[EMAIL PROTECTED]> I assume you are using the lastest version of 1.3. Try experimenting with the AcceptMutex config directive and see if selecting different values changes the behaviour you are seeing. ---------------
Bill, Thanks, I tried that. I used all that were available with no discernable difference. I don't think it is really the 'thundering herd' problem, just one that looks sort of like it. My gut instinct (from looking at the vmstat) is that some process was set to take the connection but fails for some reason and holds up everyone else. Perhaps the kernel gets impatient with the process not handling it and then puts it up for grabs for everyone to try. I have no knowledge of the kernel internals and only some of Apache's (well, a lot more lately...), so this interpretation is based on observation not knowledge of the software algorithms at work. Hopefully someone with better understanding of the systems at work will recognize what is going on. Help!
