Skip site navigation (1)Skip section navigation (2)
Date:      Tue, 24 Jun 2014 18:07:57 +0200
From:      Eduardo Morras <emorrasg@yahoo.es>
To:        freebsd-questions@freebsd.org
Subject:   Re: kern.ipc.nmbclusters limit reached makes a server go down, please help
Message-ID:  <20140624180757.0f9f0310af1a201a6cf403c0@yahoo.es>
In-Reply-To: <1403617939.95369.YahooMailNeo@web162504.mail.bf1.yahoo.com>
References:  <1403617939.95369.YahooMailNeo@web162504.mail.bf1.yahoo.com>

next in thread | previous in thread | raw e-mail | index | archive | help
On Tue, 24 Jun 2014 06:52:19 -0700
Stefan Stere <icetor.is@bitmessage.ro> wrote:

> Hi,
> 
> I have a vmware virtual server running FreeBSD 10.0 STABLE
> The virtual server has 100mbps port.
> 
> It is running a Tor router, consuming an average of 6-7 TB of monthly
> traffic. Its the only purpose of the server.
> 
> Last night it went down, and vmware console log was saying:
> [zone: Mbuf_cluster] kern.ipc.nmbclusters limit reached
> 

nmbclusters shows/sets the number of network buffers the system has. Each connection needs one buffer, if you get a connection peak, it can be exhasuted.

> 
> I don't know what this means - the traffic of the server is unlimited
> and nothing is capped in any way. What can I do to fix this? I have
> read on freebsd wiki that I might need to add some lines to sysctl ?
> can you please confirm? Thank you in advance.

Show us the values of:

#sysctl kern.ipc.nmbclusters
kern.ipc.nmbclusters: 25600

#sysctl kern.ipc.somaxconn
kern.ipc.somaxconn: 128

I put mine as example, but those values are for desktop use. Yours should be bigger (131072, 512, f.ex.), don't set an arbitrarly high value because increasing both values increase the memory needed by the kernel.

HTH


---   ---
Eduardo Morras <emorrasg@yahoo.es>



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20140624180757.0f9f0310af1a201a6cf403c0>