adriancole commented on issue #2579: Benchmark bytes / bytebuffer, protobuf vs 
zipkin vs wire.
URL: https://github.com/apache/incubator-zipkin/pull/2579#issuecomment-491300014
 
 
   yep.. if you revise from 10k spans per message down to 1k spans (which is a 
fairly high number anyway considering this is per host/second), there is not 
much difference between google and wire anyway. However, it does help memory 
wise to have wire decode bytes into hex strings.
   
   with wire making hex manually
   ```
   
ProtoCodecBenchmarks.bytebuffer_protobufDecoder:bytebuffer_protobufDecoder·p0.999
   sample            2716.557                us/op
   ProtoCodecBenchmarks.bytebuffer_protobufDecoder:·gc.alloc.rate.norm          
       sample     15  2271332.980 ±     49.158    B/op
   ProtoCodecBenchmarks.bytebuffer_wireDecoder:bytebuffer_wireDecoder·p0.999    
       sample            3082.207                us/op
   ProtoCodecBenchmarks.bytebuffer_wireDecoder:·gc.alloc.rate.norm              
       sample     15  2707555.118 ±     43.790    B/op
   ```
   
   with wire native hex stringing
   ```
   
ProtoCodecBenchmarks.bytebuffer_protobufDecoder:bytebuffer_protobufDecoder·p0.999
   sample            2808.340                us/op
   ProtoCodecBenchmarks.bytebuffer_protobufDecoder:·gc.alloc.rate.norm          
       sample     15  2271332.557 ±     37.638    B/op
   ProtoCodecBenchmarks.bytebuffer_wireDecoder:bytebuffer_wireDecoder·p0.999    
       sample            3045.130                us/op
   ProtoCodecBenchmarks.bytebuffer_wireDecoder:·gc.alloc.rate.norm              
       sample     15  2579549.017 ±     59.592    B/op
   ```
   

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
[email protected]


With regards,
Apache Git Services

Reply via email to