Netty speed bottleneck

이희승 (Trustin Lee) trustin at gmail.com
Wed Jan 26 11:55:58 EST 2011


-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA256

It seems like you are using only a single connection.  OIO outperforms NIO for small number of connections and that is why you are seeing the difference.  To improve the throughput, 1) open multiple connections to utilize all cores and 2) merge multiple small messages into larger one.

"frankdurden" <frank.durden at gmail.com> wrote:

>
>Thanks Christian for your reply!
>
>I based my test on the LocalTime example, but I just changed it to use
>the
>OioXXXSocketChannelFactory classes instead of the Nio-ones. Now I'm
>getting
>speeds of ~90MBytes/sec. Far better then. Is this the best I should
>expect?
>
>Does anybody have experience with Java Fast Sockets? Supposed to be
>open
>source, don't know about the licence. Code available upon request...
>
>http://jfs.des.udc.es/
>http://jfs.des.udc.es/files/publications/COMCOM-JFS.pdf
>
>Best Regards,
>Frank
>--
>View this message in context:
>http://netty-forums-and-mailing-lists.685743.n2.nabble.com/Netty-speed-bottleneck-tp5962953p5963255.html
>Sent from the Netty User Group mailing list archive at Nabble.com.
>_______________________________________________
>netty-users mailing list
>netty-users at lists.jboss.org
>https://lists.jboss.org/mailman/listinfo/netty-users

- --
Trustin Lee, http://gleamynode.net/
Sent from a mobile device. Please excuse my brevity.
-----BEGIN PGP SIGNATURE-----
Version: APG v1.0.8

iIkEAREIADEFAk1AUh4qHFRydXN0aW4gSGV1aXNldW5nIExlZSA8dHJ1c3RpbkBn
bWFpbC5jb20+AAoJEJb7nbIZ8zONzV4A+wVi3cNzhVX3JUPqBYzcDMO7KvME6mLJ
iJYfG4Nc2lzoAP45h6+H+RYuTAjDdbcBZ5QTrN+kohDt5Y3tP42AWgnYUw==
=zPMd
-----END PGP SIGNATURE-----




More information about the netty-users mailing list