[squid-users] Missing cache files

Odhiambo Washington odhiambo at gmail.com
Sat Dec 17 13:39:37 UTC 2016


On 17 December 2016 at 15:17, Garri Djavadyan <garryd at comnet.uz> wrote:

> 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/sh
> ow_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 Using an outdated swap.state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
>

Hi Garri,

So, checking, I don't see swap.state being written to disk and there is no
core dump either.
There is no directive in my squid.conf to suppress the two.


-- 
Best regards,
Odhiambo WASHINGTON,
Nairobi,KE
+254 7 3200 0004/+254 7 2274 3223
"Oh, the cruft."
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.squid-cache.org/pipermail/squid-users/attachments/20161217/86e4ea5b/attachment-0001.html>


More information about the squid-users mailing list