增加了判断是否存在D状态进程，以不同方式执行nvidia-bug-report.sh来避免卡死；另外增加了搜集nvrm信息

log_collect.sh

@@ -66,13 +66,19 @@ GPULogCollect() {
     if [ -f /usr/bin/nvidia-bug-report.sh ] && [ $gpuInstanceState -gt 0 ]; then
         mkdir -p ${LOG_FILE_PATH}/GPULogCollect
         echo "Start to collect gpu log for instance $(hostname) by nvidia-bug-report.sh"
-        nvidia-bug-report.sh --safe-mode --output-file ${LOG_FILE_PATH}/GPULogCollect/nvidia-bug-report.log.gz.gz
+        d_processes=$(ps aux | awk '$8=="D" {print}')
+        if [ -n "$d_processes" ]; then
+            nvidia-bug-report.sh --safe-mode --extra-system-data --output-file ${LOG_FILE_PATH}/GPULogCollect/nvidia-bug-report.log.gz
+        else
+            nvidia-bug-report.sh --safe-mode --output-file ${LOG_FILE_PATH}/GPULogCollect/nvidia-bug-report.log.gz
+        fi
         timeout 30 nvidia-smi >${LOG_FILE_PATH}/GPULogCollect/nvidia-smi.log
         nvidia-smi topo -m >>${LOG_FILE_PATH}/GPULogCollect/nvidia-smi.log
         lspci -d 10de: | egrep "VGA|3D" >${LOG_FILE_PATH}/GPULogCollect/lspci-nvidia.log
         lspci -vvv -t >>${LOG_FILE_PATH}/GPULogCollect/lspci-nvidia.log
         lspci -vvv >>${LOG_FILE_PATH}/GPULogCollect/lspci-nvidia.log
         dmesg -T >${LOG_FILE_PATH}/GPULogCollect/dmesg-gpu.log
+        journalctl  | grep -i nvrm > journalctl_nvrm.txt
         # get slot info
         touch ${LOG_FILE_PATH}/GPULogCollect/slot-info.txt
         nvidia-smi --query-gpu=index,gpu_name,gpu_bus_id,uuid --format=csv  > ${LOG_FILE_PATH}/GPULogCollect/slot-info.txt