[pgpool-general: 3397] Re: v3.4.0.(3)? - memory issue and connection hangs

[Tatsuo Ishii]

>>> :: Hang on in-rush :::
>>>
>>> We've been using PGBench to stress test the environment.  One test in
>>> particular is how our environment handles a sudden burst of
>>> connections.
>>
>> Ok, I will try to reproduce the problem using your test case.

I think I have identified the problem. pgpool-II 3.4.x seems to forget
to close connections to clients if connection_cache is on. This causes
CLOSE_WAIT flood. Included is a patch trying to fix the problem. Could
you please try it out?

Best regards,
--
Tatsuo Ishii
SRA OSS, Inc. Japan
English: http://www.sraoss.co.jp/index_en.php
Japanese:http://www.sraoss.co.jp

> ... and again:  thank you.
> 
>> In the mean time I would suggest increasing
>> listen_backlog_multiplier might help.
> 
> Yes, we have increased this parameter to 107:
> 
>    listen_backlog_multiplier = 107
> 
> and I've set the respective kernel parameter to 10,240:
> 
>    # Default:  128
>    net.core.somaxconn = 10240
> 
> Cheers,
> --
> Pablo Sanchez - Blueoak Database Engineering, Inc
> Ph:    819.459.1926         Blog:  http://pablo-blog.blueoakdb.com
> iNum:  883.5100.0990.1054
> 
-------------- next part --------------
A non-text attachment was scrubbed...
Name: child.c.patch
Type: text/x-patch
Size: 1538 bytes
Desc: not available
URL: <http://www.sraoss.jp/pipermail/pgpool-general/attachments/20150103/8488ed50/attachment.bin>