this is the paper from OLS2008: http://ols.fedoraproject.org/OLS/Reprints-2008/yamato-reprint.pdf check out page 11: where the interrupts nos is shown....noticed how utrace cut down the interrupts by a whole lot. The amazing part is that utrace can reduce the interrupts (and thus the userspace to kernelspace context switch latency) by a whole, thus improving tracing performance. Does anyone have any idea of how it is achieved? -- Regards, Peter Teoh -- To unsubscribe from this list: send an email with "unsubscribe kernelnewbies" to ecartis@xxxxxxxxxxxx Please read the FAQ at http://kernelnewbies.org/FAQ
