[
Date Prev][
Date Next][
Thread Prev][
Thread Next][
Date Index][
Thread Index]
[
List Home]
Re: [jetty-dev] NIO inefficiency?
|
Hi Kristian,
On Friday, August 9, 2013 at 1:06 PM, Kristian Rosenvold wrote:
I'm reading the source of "DeflaterOutputStream" and I'm not entirely
convinced you're right about. this. A little deeper of the dump would
easily prove that I am wrong ;)
This was from a cumulative bottom-up view of the traces, so opening that sub-tree further just leads to the application code.
The compression path is different:
14.0% - java.util.zip.Deflater.deflateBytes:native
14.0% - java.util.zip.Deflater.deflate:427
14.0% - java.util.zip.Deflater.deflate:350
14.0% - java.util.zip.DeflaterOutputStream.deflate:251
9.2% - java.util.zip.DeflaterOutputStream.write:211
...
4.9% - java.util.zip.DeflaterOutputStream.finish:226
I can assure you that in a top-down view of traces, the compression and the NIO flush are on different paths – unfortunately the profiler makes it difficult to export this with formatting, so I can't simply copy-paste it for you :)
Regards,
Viktor