Re: [squid-users] How to guess how many requests per second?

Hi Henrik,
Thanks for your response. Now I have cachemgr.cgi working fine.
You told me:
>For peak values, look at the "5 Minute Average of Counters".

I pasted it below. Based on this information, is it possible to know the
best hardware configuration for my new server?
Thank you very much, Joao

sample_start_time = 1051093738.329958 (Wed, 23 Apr 2003 10:28:58 GMT)
sample_end_time = 1051094038.400531 (Wed, 23 Apr 2003 10:33:58 GMT)
client_http.requests = 4.792206/sec
client_http.hits = 1.799577/sec
client_http.errors = 0.000000/sec
client_http.kbytes_in = 1.876225/sec
client_http.kbytes_out = 17.065985/sec
client_http.all_median_svc_time = 0.304593 seconds
client_http.miss_median_svc_time = 0.764075 seconds
client_http.nm_median_svc_time = 0.007665 seconds
client_http.nh_median_svc_time = 0.685775 seconds
client_http.hit_median_svc_time = 0.007665 seconds
server.all.requests = 3.012625/sec
server.all.errors = 0.000000/sec
server.all.kbytes_in = 14.686545/sec
server.all.kbytes_out = 1.393006/sec
server.http.requests = 3.012625/sec
server.http.errors = 0.000000/sec
server.http.kbytes_in = 14.686545/sec
server.http.kbytes_out = 1.389673/sec
server.ftp.requests = 0.000000/sec
server.ftp.errors = 0.000000/sec
server.ftp.kbytes_in = 0.000000/sec
server.ftp.kbytes_out = 0.000000/sec
server.other.requests = 0.000000/sec
server.other.errors = 0.000000/sec
server.other.kbytes_in = 0.000000/sec
server.other.kbytes_out = 0.000000/sec
icp.pkts_sent = 0.000000/sec
icp.pkts_recv = 0.000000/sec
icp.queries_sent = 0.000000/sec
icp.replies_sent = 0.000000/sec
icp.queries_recv = 0.000000/sec
icp.replies_recv = 0.000000/sec
icp.replies_queued = 0.000000/sec
icp.query_timeouts = 0.000000/sec
icp.kbytes_sent = 0.000000/sec
icp.kbytes_recv = 0.000000/sec
icp.q_kbytes_sent = 0.000000/sec
icp.r_kbytes_sent = 0.000000/sec
icp.q_kbytes_recv = 0.000000/sec
icp.r_kbytes_recv = 0.000000/sec
icp.query_median_svc_time = 0.000000 seconds
icp.reply_median_svc_time = 0.000000 seconds
dns.median_svc_time = 0.002783 seconds
unlink.requests = 1.356348/sec
page_faults = 0.000000/sec
select_loops = 45.522624/sec
select_fds = 46.482399/sec
average_select_fd_period = 0.017293/fd
median_select_fds = 0.000000
swap.outs = 1.163060/sec
swap.ins = 0.926449/sec
swap.files_cleaned = 0.000000/sec
aborted_requests = 0.336587/sec
syscalls.polls = 47.398850/sec
syscalls.disk.opens = 1.626284/sec
syscalls.disk.closes = 1.626284/sec
syscalls.disk.reads = 0.756489/sec
syscalls.disk.writes = 6.185212/sec
syscalls.disk.seeks = 0.006665/sec
syscalls.disk.unlinks = 0.000000/sec
syscalls.sock.accepts = 1.732926/sec
syscalls.sock.sockets = 1.482984/sec
syscalls.sock.connects = 1.319690/sec
syscalls.sock.binds = 0.000000/sec
syscalls.sock.closes = 2.026190/sec
syscalls.sock.reads = 27.266919/sec
syscalls.sock.writes = 22.084805/sec
syscalls.sock.recvfroms = 0.586529/sec
syscalls.sock.sendtos = 0.313260/sec
cpu_time = 7.020000 seconds
wall_time = 300.070573 seconds
cpu_usage = 2.339450%

>From: Henrik Nordstrom <hno@squid-cache.org>
>To: "Joao Coutinho" <jocoutinho@hotmail.com>, squid-users@squid-cache.org
>Subject: Re: [squid-users] How to guess how many requests per second?
>Date: Thu, 17 Apr 2003 23:41:34 +0200
>
>On Thursday 17 April 2003 22.17, Joao Coutinho wrote:
> > I want to upgrade my squid server and would like to know whats the
> > best configuration for my server. (memory, harddisk ...)
> > From the User's Guide "To decide on your machine, you need an idea
> > of the load that it will need to sustain: the peak number of
> > requests per minute" How can I know the peak number of request per
> > minute on my squid server? I have almost 200 people on my network.
> > thanks in advance.
>
>If you have a proxy running today then usage statistics will tell you
>this information.
>
>This very basic usage statistics can either be collected by running
>statistics on your access.log, or by looking into cachemgr. When
>using cachemgr make sure to read the values at peak load time, not
>after hours when the proxy is barely used..
>
>For runtime monitoring I recommend plotting requests/s and other basic
>performance metrics using MRTG or RRDTOOL. This gives very nice
>graphs showing how the traffic load varies over the day, updated in
>near real time. This type of information is easily queried by such
>tools via the SNMP interface of Squid.
>
>Regards
>Henrik
>
>--
>Donations welcome if you consider my Free Squid support helpful.
>https://www.paypal.com/xclick/business=hno%40squid-cache.org
>
>If you need commercial Squid support or cost effective Squid or
>firewall appliances please refer to MARA Systems AB, Sweden
>http://www.marasystems.com/, info@marasystems.com

_________________________________________________________________
MSN Messenger: converse com os seus amigos online.
http://messenger.msn.com.br
Received on Wed Apr 23 2003 - 07:34:47 MDT