Open Stack

Any ideas folks?

On Tue, Jul 8, 2014 at 4:26 PM, Shrinand Javadekar
<shrinand at maginatics.com> wrote:
> Hi,
>
> I have a question about the http connections made between the various
> swift server processes. Particularly between the swift proxy server
> and the swift object server.
>
> I see that these servers do not use a persistent http connection
> between them. So every blob get/put/delete request will create a new
> connection, use it and tear it down. In a highly concurrent
> environment with thousands of such operations happening per second,
> there could be two problems:
>
> i) Time required for creating the new connections could hamper performance.
> ii) After the requests are complete, several connections will be in
> the TIME_WAIT state and it might be possible that the proxy server and
> object server node will run out of ports or fds.
>
> If the proxy and object servers are on the same machine, the problem
> is exacerbated. I have one such instance and at one point saw ~30K
> sockets in the TIME_WAIT state. Though, this would've included
> connections with the account server and container server also.
>
> Does this analysis make sense? If yes, are there ways to do something
> about it (other than asking clients to slow down :P)?
>
> Thanks in advance.
> -Shri