Updated a few metrics names and descriptions to be more intuitive.

Signed-off-by: TG, Hari <hari.tg@intel.com>

diff --git a/src/collectd.conf.pod b/src/collectd.conf.pod
index 32cecb7746350b9735a2b5396e748464247013d1..1d7063893786a6e2c625e197d42d2a839a7cd57e 100644 (file)
--- a/src/collectd.conf.pod
+++ b/src/collectd.conf.pod
@@ -2564,16 +2564,18 @@ This will override the I<global Interval> for I<dcpmm> plugin. None of the other
 Collects health information. I<CollectHealth and CollectPerfMetrics cannot be true at the same time>. Defaults to C<false>.
 
 The health information metrics are the following:
-  health_status        Overall health summary (0: normal | 1: non-critical | 2: critical | 3: fatal).
-  percentage_remaining The module’s remaining life as a percentage value of factory expected life span.
-  percentage_used      The module’s used life as a percentage value of factory expected life span.
-  power_on_time        The lifetime the DIMM has been powered on in seconds.
-  uptime               The current uptime of the DIMM for the current power cycle in seconds.
-  last_shutdown_time   The time the system was last shutdown. The time is represented in epoch (seconds).
-  media_temp           The media’s current temperature in degrees Celsius.
-  controller_temp      The controller’s current temperature in degrees Celsius.
-  max_media_temp       The media’s the highest temperature reported in degrees Celsius.
-  max_controller_temp  The controller’s highest temperature reported in degrees Celsius.
+  health_status              Overall health summary (0: normal | 1: non-critical | 2: critical | 3: fatal).
+  lifespan_remaining         The module’s remaining life as a percentage value of factory expected life span.
+  lifespan_used              The module’s used life as a percentage value of factory expected life span.
+  power_on_time              The lifetime the DIMM has been powered on in seconds.
+  uptime                     The current uptime of the DIMM for the current power cycle in seconds.
+  last_shutdown_time         The time the system was last shutdown. The time is represented in epoch (seconds).
+  media_temperature          The media’s current temperature in degree Celsius.
+  controller_temperature     The controller’s current temperature in degree Celsius.
+  max_media_temperature      The media’s the highest temperature reported in degree Celsius.
+  max_controller_temperature The controller’s highest temperature reported in degree Celsius.
+  tsc_cycles                 The number of tsc cycles during each interval.
+  epoch                      The timestamp in seconds at which the metrics are collected from DCPMM DIMMs.
 
 =item B<CollectPerfMetrics> I<true>|I<false>
 
@@ -2588,8 +2590,10 @@ The memory performance metrics are the following:
   media_write_ops     Number of write operations performed to the physical media.
   host_reads          Number of read operations received from the CPU (memory controller).
   host_writes         Number of write operations received from the CPU (memory controller).
-  read_hit_ratio      Measures the efficiency of the buffer in the read path. Range of 0.0 - 0.75.
+  read_hit_ratio      Measures the efficiency of the buffer in the read path. Range of 0.0 - 1.0.
   write_hit_ratio     Measures the efficiency of the buffer in the write path. Range of 0.0 - 1.0.
+  tsc_cycles          The number of tsc cycles during each interval.
+  epoch               The timestamp in seconds at which the metrics are collected from DCPMM DIMMs.
 
 =item B<EnableDispatchAll> I<false>
 

diff --git a/src/dcpmm.c b/src/dcpmm.c
index 7d58f5e2be9a658b1840846447e3b659f8697e44..cf8292f7f45390baf2143cdba5b02c8d5b287588 100644 (file)
--- a/src/dcpmm.c
+++ b/src/dcpmm.c
@@ -69,8 +69,10 @@ static void add_metric(const char *plugin_inst, const char *type,
 
   if (strncmp(type_inst, "read_hit_ratio", strlen("read_hit_ratio")) == 0 ||
       strncmp(type_inst, "write_hit_ratio", strlen("write_hit_ratio")) == 0 ||
-      strncmp(type_inst, "media_temp", strlen("media_temp")) == 0 ||
-      strncmp(type_inst, "controller_temp", strlen("controller_temp")) == 0) {
+      strncmp(type_inst, "media_temperature", strlen("media_temperature")) ==
+          0 ||
+      strncmp(type_inst, "controller_temperature",
+              strlen("controller_temperature")) == 0) {
     snprintf(n.message, sizeof(n.message), "Value: %0.2f", value);
   } else {
     snprintf(n.message, sizeof(n.message), "Value: %0.0f", value);
@@ -106,7 +108,7 @@ static int dcpmm_read(__attribute__((unused)) user_data_t *ud) {
     if (pmwatch_config.collect_perf_metrics) {
       add_metric(dimm_num, "timestamp", "epoch",
                  PMWATCH_OP_BUF_EPOCH(&pmw_output_buf[i]));
-      add_metric(dimm_num, "timestamp", "timestamp",
+      add_metric(dimm_num, "timestamp", "tsc_cycles",
                  PMWATCH_OP_BUF_TIMESTAMP(&pmw_output_buf[i]));
       add_metric(dimm_num, "media", "total_bytes_read",
                  PMWATCH_OP_BUF_TOTAL_BYTES_READ(&pmw_output_buf[i]));
@@ -136,13 +138,13 @@ static int dcpmm_read(__attribute__((unused)) user_data_t *ud) {
       }
       add_metric(dimm_num, "timestamp", "epoch",
                  PMWATCH_OP_BUF_EPOCH(&pmw_output_buf[i]));
-      add_metric(dimm_num, "timestamp", "timestamp",
+      add_metric(dimm_num, "timestamp", "tsc_cycles",
                  PMWATCH_OP_BUF_TIMESTAMP(&pmw_output_buf[i]));
       add_metric(dimm_num, "health", "health_status",
                  PMWATCH_OP_BUF_HEALTH_STATUS(&pmw_output_buf[i]));
-      add_metric(dimm_num, "health", "percentage_remaining",
+      add_metric(dimm_num, "health", "lifespan_remaining",
                  PMWATCH_OP_BUF_PERCENTAGE_REMAINING(&pmw_output_buf[i]));
-      add_metric(dimm_num, "health", "percentage_used",
+      add_metric(dimm_num, "health", "lifespan_used",
                  PMWATCH_OP_BUF_PERCENTAGE_USED(&pmw_output_buf[i]));
       add_metric(dimm_num, "health", "power_on_time",
                  PMWATCH_OP_POWER_ON_TIME(&pmw_output_buf[i]));
@@ -150,13 +152,13 @@ static int dcpmm_read(__attribute__((unused)) user_data_t *ud) {
                  PMWATCH_OP_BUF_UPTIME(&pmw_output_buf[i]));
       add_metric(dimm_num, "health", "last_shutdown_time",
                  PMWATCH_OP_BUF_LAST_SHUTDOWN_TIME(&pmw_output_buf[i]));
-      add_metric(dimm_num, "health", "media_temp",
+      add_metric(dimm_num, "health", "media_temperature",
                  PMWATCH_OP_BUF_MEDIA_TEMP(&pmw_output_buf[i]));
-      add_metric(dimm_num, "health", "controller_temp",
+      add_metric(dimm_num, "health", "controller_temperature",
                  PMWATCH_OP_BUF_CONTROLLER_TEMP(&pmw_output_buf[i]));
-      add_metric(dimm_num, "health", "max_media_temp",
+      add_metric(dimm_num, "health", "max_media_temperature",
                  PMWATCH_OP_BUF_MAX_MEDIA_TEMP(&pmw_output_buf[i]));
-      add_metric(dimm_num, "health", "max_controller_temp",
+      add_metric(dimm_num, "health", "max_controller_temperature",
                  PMWATCH_OP_BUF_MAX_CONTROLLER_TEMP(&pmw_output_buf[i]));
     }
   }