[pgpool-general: 6436] High I/O Usage on PGPool nodes

[Stephen Eilert]

Hi,

Apologies if this has been discussed before, but if so I can’t find a relevant thread.

We are experiencing some strange behavior on our PGPool nodes. In some of them, load average is well in excess of 100 – although CPU is over 70% idle (rest spent in system), so this pointed to I/O. Checking on AWS, we see that there is a lot of disk activity, including writes. This was surprising, as we did not expect the pgpool machines to have any significant disk usage, nor we can find anything in the documentation that would indicate it to be the case.

After some sysdig usage, the only file getting heavily written to appears to be /var/log/postgresql/pgpool_status

It is multiple 6 bytes writes a second, all with the same data, by pgpool. So this shouldn’t be a problem as it is not too much data. Except that it seems to be getting flushed right away (fsync?).

Is this behavior expected? The PG node status have not changed at any time, there are two nodes, always up. Why would the file get rewritten dozens (even hundreds, depending on load) of times per second?

Would this be caused by a misconfiguration?

pgpool-II version 3.7.5 (amefuriboshi)

ps -ef | grep pgpool | wc -l
507

sysdig -A -c echo_fds “fd.filename=pgpool_status"

------ Write 6B to /var/log/postgresql/pgpool_status

up
up

------ Write 6B to /var/log/postgresql/pgpool_status

up
up

------ Write 6B to /var/log/postgresql/pgpool_status

up
up

------ Write 6B to /var/log/postgresql/pgpool_status


[This is repeated and scrolls by pretty fast]

Thanks,

– Stephen
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.sraoss.jp/pipermail/pgpool-general/attachments/20190226/9be365ad/attachment.html>