LITTLE ENDIAN: Performance

["이희승 (Trustin Lee)"]

I think you can attach source code to a JIRA issue. Please let me know 
if it does not work.

Netty's buffer is simply a byte[]. There is no reason why little endian 
access should be that slow.

Thanks

Replicator wrote:
 > @Trustin,
 >
 > I could, but I can't attach any code to it ( unfortunately ) => will it
 > still make sense to do so?
 >
 > I guess what I want to understand: is that expected? Because Netty does
 > translation for each frame?
 >
 > Thank you!
 >
 > On Thu, Oct 27, 2011 at 2:25 PM, Trustin Lee [via Netty Forums and 
Mailing
 > Lists]<ml-node+s685743n6937496h75 at n2.nabble.com> wrote:
 >
 >> It sounds awfully slow. Could you file a JIRA issue?
 >>
 >> Thanks,
 >> Trustin
 >>
 >>
 >> Replicator wrote:
 >>> bootstrap.setOption( "bufferFactory", new HeapChannelBufferFactory(
 >>> ByteOrder.LITTLE_ENDIAN ) )
 >>>
 >>> on my client
 >>>
 >>> and
 >>>
 >>> bootstrap.setOption( "child.bufferFactory", new
 >>> HeapChannelBufferFactory( ByteOrder.LITTLE_ENDIAN ) )
 >>>
 >>> on my test server
 >>>
 >>> On Thu, Oct 27, 2011 at 6:43 AM, Norman Maurer-2 [via Netty Forums and
 >>> Mailing Lists]<[hidden 
email]<http://user/SendEmail.jtp?type=node&node=6937496&i=0>>
 >> wrote:
 >>>> How do you do set it to LITTLE ENDIAN ? Setting a ChannelBufferFactory
 >>>> via SocketConfig ?
 >>>>
 >>>> Bye,
 >>>> Norman
 >>>>
 >>>>
 >>>> 2011/10/27 zx spectrum<[hidden email]<
 >> http://user/SendEmail.jtp?type=node&node=6935794&i=0>>:
 >>
 >>>>
 >>>>> Seems like a simple test with a FrameDecoder runs about 9(!) times
 >> slower
 >>>> if
 >>>>> everything is set to LITTLE ENDIAN, than the same test with a 
default (
 >>>> BIG
 >>>>> ENDIAN ).
 >>>>> Is that expected? ( because Netty needs to do the conversion for 
every
 >>>>> frame? )
 >>>>> Is there a way to improve it to be as good as BIG ENDIAN?
 >>>>> Thank you!
 >>>>> _______________________________________________
 >>>>> netty-users mailing list
 >>>>> [hidden email]<http://user/SendEmail.jtp?type=node&node=6935794&i=1>
 >>>>> https://lists.jboss.org/mailman/listinfo/netty-users
 >>>>>
 >>>> _______________________________________________
 >>>> netty-users mailing list
 >>>> [hidden email]<http://user/SendEmail.jtp?type=node&node=6935794&i=2>
 >>>> https://lists.jboss.org/mailman/listinfo/netty-users
 >>>>
 >>>>
 >>>> ------------------------------
 >>>> If you reply to this email, your message will be added to the
 >> discussion
 >>>> below:
 >>>>
 >>>>
 >> 
http://netty-forums-and-mailing-lists.685743.n2.nabble.com/LITTLE-ENDIAN-Performance-tp6935190p6935794.html
 >>>> To unsubscribe from LITTLE ENDIAN: Performance, click here< >>
 >>>>
 >>>
 >>> --
 >>> View this message in context:
 >> 
http://netty-forums-and-mailing-lists.685743.n2.nabble.com/LITTLE-ENDIAN-Performance-tp6935190p6936360.html
 >>> Sent from the Netty User Group mailing list archive at Nabble.com.
 >>> _______________________________________________
 >>> netty-users mailing list
 >>> [hidden email]<http://user/SendEmail.jtp?type=node&node=6937496&i=1>
 >>> https://lists.jboss.org/mailman/listinfo/netty-users
 >> _______________________________________________
 >> netty-users mailing list
 >> [hidden email]<http://user/SendEmail.jtp?type=node&node=6937496&i=2>
 >> https://lists.jboss.org/mailman/listinfo/netty-users
 >> what we call human nature in actuality is human habit
 >> http://gleamynode.net/
 >>
 >>
 >> ------------------------------
 >> If you reply to this email, your message will be added to the discussion
 >> below:
 >>
 >> 
http://netty-forums-and-mailing-lists.685743.n2.nabble.com/LITTLE-ENDIAN-Performance-tp6935190p6937496.html
 >> To unsubscribe from LITTLE ENDIAN: Performance, click 
here<http://netty-forums-and-mailing-lists.685743.n2.nabble.com/template/NamlServlet.jtp?macro=unsubscribe_by_code&node=6935190&code=d2ViYWthdW50QGdtYWlsLmNvbXw2OTM1MTkwfC0xODA0ODQ0MTcz>.
 >>
 >>
 >
 >
 > --
 > View this message in context: 
http://netty-forums-and-mailing-lists.685743.n2.nabble.com/LITTLE-ENDIAN-Performance-tp6935190p6937516.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
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lists.jboss.org/pipermail/netty-users/attachments/20111027/3c6efbe8/attachment.html