On Tue, Aug 28, 2007 at 11:47:25PM -0400, Shawn O. Pearce wrote: > > core: > > real 0m3.353s > > user 0m2.108s > > sys 0m0.580s > > > > perl: > > real 0m3.138s > > user 0m2.704s > > sys 0m0.236s > > > It may also have to do with the large amount of data going over a > pipe, as well as the fact that we have to write the data into the > packfile then go back and reread all of it to compute the SHA-1 of > the entire thing. That's a lot of IO, all going through your poor > little kernel. ;-) You are reading it backwards. I fully expected the perl+fast-import version to take more sys time, but it takes half as much. We are doing fewer stat() calls, though, since we are ignoring the index. > Yea, so like the parallel pack-objects experiment that Nico had > done recently we decreased wall-clock time at the expense of using a > larger amount of the system resources. That is bad as we use more > CPU time than we saved in wallclock time. Usually a bad tradeoff, > unless you have a realtime requirement you have to meet. It depends. If we all have 64-core processors in a few years, then it might be a better tradeoff. Of course, some users might want to optimize for wall-clock time, while others want power consumption, etc. -Peff - To unsubscribe from this list: send the line "unsubscribe git" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
