From 5499b5ac0b2c661cc37190a23a4aee9308b3d3ee Mon Sep 17 00:00:00 2001 From: Len Brown Date: Mon, 27 Jan 2025 20:58:42 -0600 Subject: [PATCH] tools/power turbostat: Harden one-shot mode against cpu offline when turbostat interval mode can't migrate to a CPU, it complains, prints no data, re-initializes with the new CPU configuration and starts a new interval. But this strategy in the face of a CPU hotplug offline during an interval doesn't help in one-shot mode. When the missing CPU is discovered at the end of the interval, the forked program has already returned and there is nothing left for a new interval to measure. So instead of aborting get_coutners() and delta_cpu() if a missing CPU is detected, complain, but carry on and output what statistics are actually present. Use the same strategy for delta_cpu when aperf:mperf are observed to have been reset -- complain, but carry on and print data for the CPUs that are still present. Interval mode error handling is unchanged. One-shot mode can now do this: $ sudo chcpu -e 1 ; sudo ./turbostat --quiet --show PkgWatt,Busy%,CPU chcpu -d 1 CPU 1 enabled CPU 1 disabled get_counters: Could not migrate to CPU 1 ./turbostat: Counter reset detected 0.036920 sec CPU Busy% PkgWatt - 0.00 10.00 0 99.73 10.00 1 0.00 2 91.53 3 16.83 Suggested-by: Zhang Rui Signed-off-by: Len Brown --- tools/power/x86/turbostat/turbostat.c | 27 ++++++++++++--------------- 1 file changed, 12 insertions(+), 15 deletions(-) diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 1f188a0908da6..8df08819e7b41 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -2063,6 +2063,8 @@ int for_all_cpus(int (func) (struct thread_data *, struct core_data *, struct pk { int retval, pkg_no, core_no, thread_no, node_no; + retval = 0; + for (pkg_no = 0; pkg_no < topo.num_packages; ++pkg_no) { for (node_no = 0; node_no < topo.nodes_per_pkg; node_no++) { for (core_no = 0; core_no < topo.cores_per_node; ++core_no) { @@ -2078,14 +2080,12 @@ int for_all_cpus(int (func) (struct thread_data *, struct core_data *, struct pk c = GET_CORE(core_base, core_no, node_no, pkg_no); p = GET_PKG(pkg_base, pkg_no); - retval = func(t, c, p); - if (retval) - return retval; + retval |= func(t, c, p); } } } } - return 0; + return retval; } int is_cpu_first_thread_in_core(struct thread_data *t, struct core_data *c, struct pkg_data *p) @@ -3620,12 +3620,10 @@ int delta_cpu(struct thread_data *t, struct core_data *c, /* always calculate thread delta */ retval = delta_thread(t, t2, c2); /* c2 is core delta */ - if (retval) - return retval; /* calculate package delta only for 1st core in package */ if (is_cpu_first_core_in_package(t, c, p)) - retval = delta_package(p, p2); + retval |= delta_package(p, p2); return retval; } @@ -5748,6 +5746,8 @@ int for_all_cpus_2(int (func) (struct thread_data *, struct core_data *, { int retval, pkg_no, node_no, core_no, thread_no; + retval = 0; + for (pkg_no = 0; pkg_no < topo.num_packages; ++pkg_no) { for (node_no = 0; node_no < topo.nodes_per_pkg; ++node_no) { for (core_no = 0; core_no < topo.cores_per_node; ++core_no) { @@ -5769,14 +5769,12 @@ int for_all_cpus_2(int (func) (struct thread_data *, struct core_data *, p = GET_PKG(pkg_base, pkg_no); p2 = GET_PKG(pkg_base2, pkg_no); - retval = func(t, c, p, t2, c2, p2); - if (retval) - return retval; + retval |= func(t, c, p, t2, c2, p2); } } } } - return 0; + return retval; } /* @@ -9462,10 +9460,9 @@ int fork_it(char **argv) timersub(&tv_odd, &tv_even, &tv_delta); if (for_all_cpus_2(delta_cpu, ODD_COUNTERS, EVEN_COUNTERS)) fprintf(outf, "%s: Counter reset detected\n", progname); - else { - compute_average(EVEN_COUNTERS); - format_all_counters(EVEN_COUNTERS); - } + + compute_average(EVEN_COUNTERS); + format_all_counters(EVEN_COUNTERS); fprintf(outf, "%.6f sec\n", tv_delta.tv_sec + tv_delta.tv_usec / 1000000.0); -- 2.39.5