[squid-users] Missing cache files

[Garri Djavadyan]

On 2016-12-17 15:41, Odhiambo Washington wrote:
> Hi,
> 
> I keep seeing something that I think is odd. Squid has been exiting on
> signal 6, and I keep seeing this:
> 
> root at gw:/usr/local/openssl # tail -f /opt/squid-3.5/var/logs/cache.log
> 2016/12/17 13:38:32| DiskThreadsDiskFile::openDone: (2) No such file
> or directory
> 2016/12/17 13:38:32|    /opt/squid-3.5/var/cache/00/26/0000264D
> 2016/12/17 13:40:24| DiskThreadsDiskFile::openDone: (2) No such file
> or directory
> 2016/12/17 13:40:24|    /opt/squid-3.5/var/cache/00/3B/00003B56
> 2016/12/17 13:42:34| DiskThreadsDiskFile::openDone: (2) No such file
> or directory
> 2016/12/17 13:42:34|    /opt/squid-3.5/var/cache/00/6B/00006B0D
> 2016/12/17 13:43:36| DiskThreadsDiskFile::openDone: (2) No such file
> or directory
> 2016/12/17 13:43:36|    /opt/squid-3.5/var/cache/00/00/00000050
> 2016/12/17 13:44:25| DiskThreadsDiskFile::openDone: (2) No such file
> or directory
> 2016/12/17 13:44:25|    /opt/squid-3.5/var/cache/00/AF/0000AFF1
> 
> So, what could be making the files disappear?


Hi,

(Reply from Amos Jeffries from 
http://bugs.squid-cache.org/show_bug.cgi?id=4367#c2)
> This is Squid *detecting* complete absence of disk files. Not causing
> corruption.
> 
> Please check if you have multiple Squid instances running and accessing 
> the
> same cache_dir. That includes multiple workers using the same 
> ufs/aufs/diskd
> cache_dir configuration line.
> 
> Also whether swap.state for that cache_dir is being correctly and 
> completely
> written out to disk on shutdown or restart. Using an outdated 
> swap.state
> file can also lead to these warnings.

The last paragraph explains your issue. The signal 6 (abort) forces 
Squid worker to terminate immediately (to avoid all required shutdown 
procedures) and leave core dump. You can find a reason for abort in 
cache.log.


Garri