adriancole edited a comment 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 traced 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
