New crash that as found is: #0 0x000002375f1bd2c4 in pick_numa_nodes (pid=<optimized out>, cpus=<optimized out>, mbs=<optimized out>, assume_enough_cpus=<optimized out>) at numad.c:1796 1791: numad_log(LOG_DEBUG, "Interleaved MBs: %ld\n", ix, p->process_MBs[ix]); 1792: } else { 1793: numad_log(LOG_DEBUG, "PROCESS_MBs[%d]: %ld\n", ix, p->process_MBs[ix]); 1794: } 1795: } 1796: if (ID_IS_IN_LIST(ix, p->node_list_p)) { 1797: proc_avg_node_CPUs_free += node[ix].CPUs_free; 1798: } 1799: } 1800: proc_avg_node_CPUs_free /= NUM_IDS_IN_LIST(p->node_list_p); 1801: if ((process_has_interleaved_memory) && (keep_interleaved_memory)) { #1 0x0000000000000000 in ?? ()
That already smells like a different symptom due to the same root cause (sparse node IDs) Most likely the node[ix] access.
New crash that as found is: enough_ cpus=<optimized out>) at numad.c:1796 LOG_DEBUG, "Interleaved MBs: %ld\n", ix, p->process_ MBs[ix] ); LOG_DEBUG, "PROCESS_MBs[%d]: %ld\n", ix, p->process_ MBs[ix] ); node_CPUs_ free += node[ix].CPUs_free; node_CPUs_ free /= NUM_IDS_ IN_LIST( p->node_ list_p) ; has_interleaved _memory) && (keep_interleav ed_memory) ) {
#0 0x000002375f1bd2c4 in pick_numa_nodes (pid=<optimized out>, cpus=<optimized out>, mbs=<optimized out>, assume_
1791: numad_log(
1792: } else {
1793: numad_log(
1794: }
1795: }
1796: if (ID_IS_IN_LIST(ix, p->node_list_p)) {
1797: proc_avg_
1798: }
1799: }
1800: proc_avg_
1801: if ((process_
#1 0x0000000000000000 in ?? ()
That already smells like a different symptom due to the same root cause (sparse node IDs)
Most likely the node[ix] access.