On 3/5/10 8:18 AM, "Martin Sustrik" <[email protected]> wrote: > > What would be really valueable would be seeing impact of copy on _large_ > messages. We've run the tests for messages up to 1MB long and concluded > that there's no real difference. Thus it would be interesting to run the > test with/without copying for messages 1, 2, 4, 8, ..., 256MB long and > check the impact on latency. OK, will do. > This is espacially interesting as you are running on IB... is that SDP > or what? Yep, its sdp. Mike _______________________________________________ zeromq-dev mailing list [email protected] http://lists.zeromq.org/mailman/listinfo/zeromq-dev
- [zeromq-dev] Non-contiguous message thoughts Santy, Michael
- Re: [zeromq-dev] Non-contiguous message thoughts Brian Granger
- Re: [zeromq-dev] Non-contiguous message thoughts Michael Santy
- Re: [zeromq-dev] Non-contiguous message thoug... Martin Sustrik
- Re: [zeromq-dev] Non-contiguous message t... Michael Santy
- Re: [zeromq-dev] Non-contiguous message t... Michael Santy
- Re: [zeromq-dev] Non-contiguous mess... Martin Sustrik
- Re: [zeromq-dev] Non-contiguous ... Michael Santy
- Re: [zeromq-dev] Non-contigu... Carlos A. Rocha
- Re: [zeromq-dev] Non-contigu... Martin Sustrik
- Re: [zeromq-dev] Non-contiguous message t... Carlos A. Rocha
- Re: [zeromq-dev] Non-contiguous mess... Martin Sustrik
- Re: [zeromq-dev] Non-contiguous ... Carlos A. Rocha
- Re: [zeromq-dev] Non-contigu... Michael Santy
- Re: [zeromq-dev] Non-contigu... Martin Sustrik
- Re: [zeromq-dev] Non-contigu... Martin Sustrik
- Re: [zeromq-dev] Non-contigu... Santy, Michael
- Re: [zeromq-dev] Non-contigu... Steven McCoy
