-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 Chuck,
On 10/17/2011 3:42 PM, Caldarale, Charles R wrote: >> From: André Warnier [mailto:a...@ice-sa.com] Subject: Re: Is >> incoming connection request queue totally ordered? > >> As ar as I know, this is something controlled by the TCP/IP >> stack of your host. > > And by network topology. I think Andre was not considering network topology since the queue is entirely on the server. Once the request has been received (or, really, the first properly routable packet), it goes into *a* queue which no longer depends on such factors. >> But yes, intuitively, it should always be a FIFO. > > I don't think that assumption is warranted. Given that different > packets between a pair of IP nodes may take wildly different > routes over the network, there's no guarantee on the order of > arrival of TCP connection requests from a client to a server. Assuming that the requests arrive at a server in a particular order (in time), both Andre and Stevo are speculating that the OS/JVM/connector queue(s) are all FIFOs, which is a reasonable assumption unless the OS is doing some kind of QOS priority-queuing based upon ... I dunno, maybe remote IP address or something like that. Fairness isn't guaranteed at any level, really, but is probably a reasonable assumption. - -chris -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.10 (MingW32) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/ iEYEARECAAYFAk6cjBgACgkQ9CaO5/Lv0PDaugCffTrWNT7Jqg4xifscpAqm12cT aw4An0wxqvHQ9sGae78tt2WhitcLt+tO =iMvX -----END PGP SIGNATURE----- --------------------------------------------------------------------- To unsubscribe, e-mail: users-unsubscr...@tomcat.apache.org For additional commands, e-mail: users-h...@tomcat.apache.org
