Re: [squid-users] RockStore "Fatal Error"

On 07/12/2014 04:04 AM, Nyamul Hassan wrote:

> Alex, as per your previous suggestion, we did all the
> "troubleshooting" steps in the link for SmpScale. Working on them
> removed the errors in our 1st Squid installation (original email).

Glad you are making progress.

> Now, we are facing problem on another machine. We did all those steps
> mentioned in SmpScale, yet this machine is giving the same problems.

You may want to show exactly what problems you are seeing on the second
machine. It is difficult to guess what "the same" means after so many
back-and-forth emails. As always, please make sure you show all errors
and warnings, not just the last FATAL message.

Where does you Squid create .ipc files? Does that directory exist? Can
Squid write there?

Thank you,

Alex.

> SHM is already installed.
>
> Amos, as for file permission, the following all have permission as
> "squid.squid":
> /var/run/squid
> /var/log/squid
>
> ls on /dev/shm shows:
> [root_at_proxy04 ~]# ll /dev/shm
> total 124912
> -rw------- 1 squid squid 7340144 Jul 12 06:57 squid-cache_mem.shm
> -rw------- 1 squid squid 68159528 Jul 12 06:57
> squid-cachestore.cache1.rock.shm
> -rw------- 1 squid squid 68159528 Jul 12 06:57
> squid-cachestore.cache4.rock.shm
> -rw------- 1 squid squid 16 Jul 12 06:57 squid-io_file__metadata.shm
> -rw------- 1 squid squid 262228 Jul 12 06:57 squid-io_file__queues.shm
> -rw------- 1 squid squid 84 Jul 12 06:57 squid-io_file__readers.shm
> -rw------- 1 squid squid 2295383692 Jul 12 06:57 squid-squid-page-pool.shm
>
> So, Squid process does seem to be able to read / write to SHM.
>
> This is the output of "df":
> [root_at_proxy04 ~]# df -H
> Filesystem Size Used Avail Use% Mounted on
> /dev/sda3 63G 9.2G 50G 16% /
> tmpfs 4.1G 128M 4.0G 4% /dev/shm
> /dev/sda1 204M 114M 80M 59% /boot
> /dev/sdb 316G 235M 299G 1% /cachestore/cache1
> /dev/sdc 316G 251M 299G 1% /cachestore/cache4
> shm 4.1G 128M 4.0G 4% /dev/shm
>
> SELINUX is disabled.
> [root_at_proxy04 ~]# sestatus
> SELinux status: disabled
>
> What else could be interfering with the SHM?
>
> Regards
> HASSAN
>
>
> On Sat, Jul 12, 2014 at 9:46 AM, Alex Rousskov
> <rousskov_at_measurement-factory.com> wrote:
>> On 07/11/2014 07:23 PM, Nyamul Hassan wrote:
>>> However, whenever we start without the "-N", we get the same error:
>>> FATAL: Rock cache_dir at /cachestore/cache1/rock/rock failed to open
>>> db file: (11) Resource temporarily unavailable
>>
>> Most likely, this is a side effect, not the cause. Ignore until all
>> other errors are gone.
>>
>>
>>> We are also seeing these lines:
>>> commBind: Cannot bind socket FD 17 to [::]: (13) Permission denied
>>
>> This is a real problem. A solution may be found in the Troubleshooting
>> section of http://wiki.squid-cache.org/Features/SmpScale
>>
>>
>> HTH,
>>
>> Alex.
>>
Received on Wed Jul 16 2014 - 23:28:47 MDT