Nick De Decker wrote:
>Sorry for the delay, but i've strace'd both apache 1.3 and 2.0 (prefork) as
>you asked :
>I traced all 5 childs, because i didnt know which one he was going to use :
>Here is the output for apache 1.3.24
>
[...]
Thanks. I see two odd things in the 2.0 trace:
>read(10, "GET /test.txt HTTP/1.0\r\nUser-Age"..., 8000) = 92
>gettimeofday({1018386426, 197988}, NULL) = 0
>gettimeofday({1018386426, 198146}, NULL) = 0
>stat("/iVision/users/i-vision/main/htdocs/test.txt", {st_mode=S_IFREG|0644,
>st_size=13924, ...}) = 0
>open("/iVision/users/i-vision/main/htdocs/test.txt", O_RDONLY) = 11
>open("/etc/localtime", O_RDONLY) = 12
>read(12, "TZif\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\n\0\0\0\n\0"..., 44) =
>44
>read(12, "\230DI\200\233\f%p\233\325\332\360\234\331\256\220\235"..., 925) =
>925
>fstat(12, {st_mode=S_IFREG|0644, st_size=1067, ...}) = 0
>old_mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0)
>= 0x40043000
>read(12, "\0\0\0\0\0\0\0\0\16\20\0\4\0\0\34 \1\10\0\0\16\20\0\4\0"..., 4096)
>= 98
>close(12) = 0
>munmap(0x40043000, 4096) = 0
>brk(0x81b7000) = 0x81b700
>
What's it doing opening /etc/localtime? Especially in
between reading the request and sending the response?
Can anyone tell what module this is from?
Then, later in the request,
>write(6, "192.168.1.253 - - [09/Apr/2002:2"..., 107) = 107
>times({tms_utime=1, tms_stime=0, tms_cutime=0, tms_cstime=0}) = 2769909
>
From the times() call, I'd guess that you have ExtendedStatus
enabled for 2.0, but not 1.3?
However, I'm not convinced that either of these things is the
root cause of the problems you're seeing. We definitely seem
to have at least one problem with the worker MPM: the blocking
of newly accepted requests when the queue is full but other
child procs have idle threads. This isn't a problem under
normal load conditions, but it's something that I want to
fix. I'll spend some time investigating it this evening.
--Brian
