Slow-down every 30 secs

From: Jaroska Robert <jaroska@dont-contact.us>
Date: Tue, 24 Feb 98 12:17:53 MET

Hello squid-users,

   I'd like to ask you for help with the following issue:

We're running squid 1.1.20 on FreeBSD-2.2.5-Stable, with 256 MB RAM
and 12 GB (3 x 4 GB SCSI-UW) of disk space dedicated to the cache.

Unfortunately, we're experiencing the serious slow-down of all
connections approximately every 30 secs. - see the attached netstat -w2
output. When we try to connect to the squid in the slow-down interval,
it accepts the connection at port 3128, however it does not return
any data (we don't receive even an error message "Invalid request").
After approx. 4 seconds of slow-down, everything works OK for next 26 secs.
During the slow-down interval, the amount of memory dedicated to network
significantly increases (from approx. 40 % to 70 % - see below the output
of netstat -m)

This looks like squid operation is completely suspended every 30 sec.
for some reason - which might be e.g. kernel's syncing.

Is anyone experiencing the similar problems? Do you have any suggestion, how
to fix this? Perhaps we should we change some kernel parameters?

         Thanks in advance for your help

                        R.Jaroska & M.Durkovic
                        STU Sys. Admins

proxy:~ # netstat -w2
            input (Total) output
   packets errs bytes packets errs bytes colls
       397 0 271328 412 0 280963 51
       406 0 208766 426 0 187538 52
       412 0 157010 379 0 62279 29
       191 0 88062 176 0 39122 4
       200 0 170629 237 0 483826 7
       577 0 178377 760 0 321584 189
       472 0 145446 557 0 261108 61
       400 0 146722 470 0 233144 44
       486 0 147729 530 0 259938 54
       432 0 153428 484 0 205692 48
       780 0 155082 932 0 335349 162
       461 0 168262 525 0 194996 54
       557 0 167428 621 0 218035 66
       493 0 209874 531 0 218228 52
       499 0 181835 515 0 171754 45
       423 0 168917 468 0 170507 47
       407 0 130741 415 0 145313 42
       337 0 114678 357 0 105640 11
       260 0 118573 276 0 65651 5
       231 0 95854 215 0 16599 7
       167 0 89058 148 0 100274 13
       451 0 166235 669 0 421223 206
       531 0 182485 584 0 216583 96

top:
last pid: 5980; load averages: 0.19, 0.17, 0.16 11:52:18
24 processes: 1 running, 23 sleeping
CPU states: 3.1% user, 0.0% nice, 3.1% system, 2.7% interrupt, 91.1% idle
Mem: 168M Active, 1404K Inact, 29M Wired, 51M Cache, 8348K Buf, 848K Free
Swap: 512M Total, 8960K Used, 503M Free, 2% Inuse

  PID USERNAME PRI NICE SIZE RES STATE TIME WCPU CPU COMMAND
  166 root -6 0 164M 157M biowai 167:36 12.47% 12.47% squid
 5820 jaroska 18 0 672K 892K pause 0:00 0.00% 0.00% tcsh
  117 root 18 0 332K 356K pause 0:01 0.00% 0.00% cron

proxy:/usr/local/squid % netstat -m
1544 mbufs in use:
        473 mbufs allocated to data
        1046 mbufs allocated to packet headers
        3 mbufs allocated to protocol control blocks
        22 mbufs allocated to socket names and addresses
453/756 mbuf clusters in use
1705 Kbytes allocated to network (64% in use)
0 requests for memory denied
0 requests for memory delayed
0 calls to protocol drain routines
Received on Tue Feb 24 1998 - 03:20:21 MST

This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:38:57 MST