Linux Low-Latency Tracing for Multicore Hard Real-Time Systems

<table class="table-group" id="tab4"><tr><td><table class="table"><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr class="thead"><td align="left">  Kernel </td><td align="center"> All tracepoints </td><td align="center"> Syscalls only </td></tr><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr><td align="left">Standard </td><td align="center"> 2.0 </td><td align="center"> 2.4 </td></tr><tr><td align="left"><span class="monospace">P</span><span class="monospace">REEMPT_RT </span></td><td align="center"> 2.2 </td><td align="center"> 2.9 </td></tr><tr class="table-tr"><td colspan="3"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

Millions of tracepoints per second we are able to generate without any drops, in our system, with userspace and kernel tracing active, using 32 subbuffers of 1 MB for UST and 32 subbuffers of 4 MB for the kernel.

Advances in Computer Engineering

tab4

Table 4

Table 4: Linux Low-Latency Tracing for Multicore Hard Real-Time Systems 