[squid-users] high volume of 'missing files' in cache....TCP_SWAPFAIL

Linda W squid-user at tlinx.org
Sat Sep 12 06:50:58 UTC 2015


looking in the access log:

>  wc -l access.log
123246 access.log
>  grep TCP_SWAPFAIL access.log|wc -l
2369

 From the cache.log:
Ishtar:/var/log/squid# wc cache.log
 10263  92323 905184 cache.log
# grep "No such" /var/log/squid/cache.log|wc
   2642   27035  238727

Seems unlikely that a shutdown would cut it off:
2015/08/22 23:51:42 kid1| storeDirWriteCleanLogs: Starting...
2015/08/22 23:51:42 kid1|     65536 entries written so far.
2015/08/22 23:51:42 kid1|    131072 entries written so far.
2015/08/22 23:51:42 kid1|    196608 entries written so far.
2015/08/22 23:51:42 kid1|    262144 entries written so far.
2015/08/22 23:51:42 kid1|    327680 entries written so far.
2015/08/22 23:51:42 kid1|   Finished.  Wrote 349041 entries.
2015/08/22 23:51:42 kid1|   Took 0.08 seconds (4348607.74 entries/sec).
...
2015/09/11 17:10:41 kid1| NETDB state saved; 0 entries, 0 msec
2015/09/11 17:25:01 kid1| DiskThreadsDiskFile::openDone: (2) No such 
file or direct
ory
2015/09/11 17:25:01 kid1|   /var/cache/squid/25/30/00025C24
2015/09/11 17:25:03 kid1| DiskThreadsDiskFile::openDone: (2) No such 
file or direct
ory
2015/09/11 17:25:03 kid1|   /var/cache/squid/25/30/00025C25
2015/09/11 17:25:07 kid1| DiskThreadsDiskFile::openDone: (2) No such 
file or direct
ory
....
so like for the files mentioned above:
Notice 24 and 25 are really gone --   and they likely should have expired...

-rw-rwSr-- 1  12472 Sep 19  2014 00025C20
-rw-rwSr-- 1    348 Aug 22 14:23 00025C21
-rw-rwSr-- 1 461035 Aug  2 18:13 00025C22
-rw-rwSr-- 1   6466 Aug 22 14:23 00025C23
-rw-rwSr-- 1  37570 Aug 22 14:24 00025C26

Is there a command to run against the DB to have it check for
consistency?  I.e. maybe it will go away if the db is made consistent --
or... it will start doing this again after some period of time.






More information about the squid-users mailing list