Implement the rdc_lib API to support the job stats

Add the function to start and stop the job recording.
Add the function to get the job stats for each GPU and summary of multiple GPUs
Add the function to remove the jobs.

Add a class RdcLogger which can control the log level using the environment variable RDC_LOG.
This is similar to GRPC_VERBOSITY gRPC. When the customer has the issues, he can enable the verbose
log to help us to troubleshoot the issues.

Add the -u support in the rdci group, fieldgroup and dmon for connecting to rdcd without authentication.

Change-Id: I22c591823c1ee6485db106b911bed8271d1b2769
This commit is contained in:
Bill(Shuzhou) Liu
2020-04-08 08:47:29 -04:00
committed by Chris Freehill
parent 16bce67835
commit a547dc7efd
26 changed files with 805 additions and 102 deletions
+10 -2
View File
@@ -58,6 +58,7 @@ void RdciDmonSubSystem::parse_cmd_opts(int argc, char ** argv) {
const struct option long_options[] = {
{"host", required_argument, nullptr, HOST_OPTIONS },
{"help", optional_argument, nullptr, 'h' },
{"unauth", optional_argument, nullptr, 'u' },
{"list", optional_argument, nullptr, 'l' },
{"field-group-id", required_argument, nullptr, 'f' },
{"field-id", required_argument, nullptr, 'e' },
@@ -73,7 +74,7 @@ void RdciDmonSubSystem::parse_cmd_opts(int argc, char ** argv) {
std::string gpu_indexes;
std::string field_ids;
while ((opt = getopt_long(argc, argv, "hlf:g:c:d:e:i:",
while ((opt = getopt_long(argc, argv, "hluf:g:c:d:e:i:",
long_options, &option_index)) != -1) {
switch (opt) {
case HOST_OPTIONS:
@@ -82,9 +83,12 @@ void RdciDmonSubSystem::parse_cmd_opts(int argc, char ** argv) {
case 'h':
dmon_ops_ = DMON_HELP;
return;
case 'u':
use_auth_ = false;
break;
case 'l':
dmon_ops_ = DMON_LIST_FIELDS;
return;
break;
case 'f':
if (!IsNumber(optarg)) {
show_help();
@@ -130,6 +134,10 @@ void RdciDmonSubSystem::parse_cmd_opts(int argc, char ** argv) {
}
}
if (dmon_ops_ == DMON_LIST_FIELDS) {
return;
}
if (options_.find(OPTIONS_FIELD_GROUP_ID) == options_.end()) {
if (field_ids == "") {
show_help();