RE: [squid-users] calling Henrick , Joe ,Adrian ...SOS pls help out

From: Mitesh P Choksi <mitesh.choksi@dont-contact.us>
Date: Mon, 20 Aug 2001 11:22:56 +0300

send in the following information as well.

vmstat: vmstat 5 10
iostat: iostat 5 10
cpu: /proc/cpuinfo
hard-disks: df ()
kernel version: /proc/version
reiserfs version: (if need be)
strace output: strace -c -p <pid> (press CTRL+BREAK after 1 minute)
ipchains/iptables version:

The point is to eliminate where exactly is the problem. CPU?, MEMORY?,
DISK?, NETWORK?, KERNEL?, etc

Describe the problem as follows to get quicker answer:
   kreiserfsd taking up 10% cpu at times
   squid taking up 80% most of time

The above is from my experience of analysing similary problem I had with my
squid server hitting the roof in CPU utilisation. Until I did this I could
not even understand where is my problem.

-----Original Message-----
From: khiz code [mailto:khizcode@yahoo.com]
Sent: 20 August 2001 10:44
To: joe@swelltech.com; squid-users@squid-cache.org;
wojtek@wojtek.3miasto.net; adrian@squid-cache.org; hno@hem.passagen.se
Subject: Re: [squid-users] calling Henrick , Joe ,Adrian ...SOS pls help
out

Hi all
i ve been chaecking my mails almost nonstop for any
sort of advice from all u squid Gurus
but :-(
to repeat i will say that i get
2001/08/15 12:44:18| clientReadRequest: FD 16: no data
to process ((11) Resource
 temporarily unavailable)
message almost after every http request
i ve done almost everything correctly
well i ve been using redhat linux 6.2
i upgraded the kernel to 2.2.19
my glibc version is 2.1.3-22
i m sure i ve not missed anything
i hv the foll in my startup scripts
i hv the foll in my startup scripts
echo 1 >/proc/sys/net/ipv4/ip_forward
 ulimit -HSn 16384
 echo 10000 > /proc/sys/fs/file-max
 echo 32768 >/proc/sys/fs/inode-max
echo 1024 65000 /proc/sys/net/ipv4/ip_local_port_range
 echo 1024 > /proc/sys/net/ipv4/tcp_max_syn_backlog
 echo 100 > /proc/sys/net/ipv4/tcp_fin_timeout
 echo 300 > /proc/sys/net/ipv4/tcp_keepalive_time
 echo 0 > /proc/sys/net/ipv4/tcp_sack
 echo 0 > /proc/sys/net/ipv4/tcp_timestamp

under load of less than 10 req /sec it takes me abt 2
mins to telnet to the squid port even from the same
machine as squid

i dunno why this is happening
PLS pls help me out
in dire need of help
khizcode

P.S : i m not a spammer ,, but this flurry of mails is
a sign of desperation
Received on Mon Aug 20 2001 - 02:26:49 MDT

This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 17:01:44 MST