httpd-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Brian Pane <brian.p...@cnet.com>
Subject Re: What is the source of this 'Thundering herd' redux?
Date Thu, 02 Jan 2003 22:31:26 GMT
Steven Roussey wrote:

>---------------
>From: "Bill Stoddard" <bill@wstoddard.com>
>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.
>

Can you grab a stack trace from each of the httpd processes (e.g.,
with pstack, or by scripting gdb) to see what they're doing when
the load drops to zero?

Also, does netstat show connections piling up in 'established' state
on the port on which your httpd is listening?

Brian



Mime
View raw message