Hi! I have very limited access to real hardware with 4 NUMA nodes. So most of these fixes were checked with numa=fake=4 kernel cmdline.
It would be great if somebody verified it on real hardware. And: 1. What do you think about idea of assigning to each cpuset controller test a separate testcase name in runtest/controllers? Instead of using a single run_cpuset_test.sh. This will greatly simplify output results analysis. For example rename current cpuset01 testcase to cpuset12 and assign names cpuset01 cpuset11 cpuset_*.sh tests. 2. How do you think about adding a separate tst_kvercmp2 binary (using tst_kvercmp2() function). It would help in cpuset_base_ops_testset.sh because several distribution kernels have these fixes. Because on we also need to make testing based on distribution kernel version. Like this: tst_kvercmp2 X Y Z "RHEL5:234 SLES10:0.91" Thank you. ------------------------------------------------------------------------------ October Webinars: Code for Performance Free Intel webinars can help you accelerate application performance. Explore tips for MPI, OpenMP, advanced profiling, and more. Get the most from the latest Intel processors and coprocessors. See abstracts and register > http://pubads.g.doubleclick.net/gampad/clk?id=60133471&iu=/4140/ostg.clktrk _______________________________________________ Ltp-list mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/ltp-list
