Re: [SM-USERS] Giving up on SM because of CPU and load issues

[Lesli St. Clair]

I thought of that, but I tried a fresh install of apache 2.x and the 
beta of the next release of SM, and saw the same thing, at least insofar 
as apache using more than its share of the cpu. Really, this whole thing 
is bizarre! I have an identical model machine running as a spamtrap/AV 
machine, processing up to 180,000 messages a day (and spam scanning is 
pretty cpu intensive). The machine might as well be napping for all the 
work it's doing. That's why I was just blown away by the CPU problem here.

Just as an example: I'm simulating 500 users on this 4-CPU sparc. Here's 
the top output:
166 processes: 159 sleeping, 3 running, 4 on cpu
CPU states: 12.7% idle, 82.7% user,  4.7% kernel,  0.0% iowait,  0.0% swap
Memory: 16G real, 13G free, 1320M swap in use, 28G swap free

   PID USERNAME LWP PRI NICE  SIZE   RES STATE    TIME    CPU COMMAND
  6815 httpd      1  15    0   15M   13M run      0:13  3.15% httpd
  6700 httpd      1  55    0   15M   13M sleep    0:14  2.32% httpd
  6733 httpd      1  51    0   14M   13M sleep    0:19  2.06% httpd
  7102 httpd      1  59    0   14M   13M sleep    0:02  1.99% httpd
  7043 httpd      1  29    0   15M   13M run      0:03  1.97% httpd
  7045 httpd      1  53    0   14M   13M sleep    0:05  1.89% httpd
  7126 httpd      1  42    0   15M   13M sleep    0:03  1.81% httpd
  7075 httpd      1  52    0   15M   13M sleep    0:04  1.68% httpd
  6758 httpd      1  55    0   15M   14M sleep    0:06  1.59% httpd
  6797 httpd      1  55    0   14M   13M sleep    0:09  1.57% httpd
  6844 httpd      1  55    0   15M   14M sleep    0:10  1.56% httpd
  6818 httpd      1  59    0   14M   13M sleep    0:10  1.37% httpd
  6845 httpd      1  53    0   16M   14M sleep    0:10  1.34% httpd
  6621 httpd      1  59    0   15M   13M sleep    0:14  1.33% httpd
  6839 httpd      1  52    0   19M   17M sleep    0:15  1.31% httpd
Ralf Hildebrandt wrote:
* Lesli St. Clair <[EMAIL PROTECTED]>:

Fresh install of apache 1.3x, SM, and mysql, but the same revs etc.

Maybe a bug in the software? I've seen that on RH systems -- apache
starts hogging the cpu.
begin:vcard
fn:Lesli St. Clair
n:St. Clair;Lesli
email;internet:[EMAIL PROTECTED]
version:2.1
end:vcard