17300 Windows agent do not use timeout on fail for section CpuLoad an…

…d DotNetClr Previously, after a WMI error occurred during the generation of specific WMI sections, particularly the CpuLoad and DotNetClr sections, the agent would stop creating these sections for a period of one hour. This was done to reduce noise in the log file. However, this approach led to situations where a random WMI failure could prevent data collection for an hour. Since this release the delay for the CpuLoad and DotNetclr sections is eliminated thus making monitoring more smooth. Change-Id: I4fc70c6aa4d9b5a13442d4d6ea8eafc3e4248ed6
Checkmk · Jan 15, 2025 · 61793d7 · 61793d7
1 parent 574231b
commit 61793d7
Show file tree

Hide file tree

Showing 3 changed files with 38 additions and 11 deletions.
diff --git a/.werks/17300.md b/.werks/17300.md
@@ -0,0 +1,23 @@
+[//]: # (werk v2)
+# Windows agent do not use timeout on fail for section CpuLoad and DotNetClr
+
+key        | value
+---------- | ---
+date       | 2025-01-14T15:55:31+00:00
+version    | 2.4.0b1
+class      | feature
+edition    | cre
+component  | checks
+level      | 1
+compatible | yes
+
+
+Previously, after a WMI error occurred during the generation of 
+specific WMI sections, particularly the CpuLoad and DotNetClr sections, 
+the agent would stop creating these sections for a period of one 
+hour. This was done to reduce noise in the log file. However, 
+this approach led to situations where a random WMI failure could 
+prevent data collection for an hour.
+
+Since this release, the delay on fail or the CpuLoad and DotNetClr 
+sections is eliminated thus making monitoring more smooth.
diff --git a/agents/wnx/src/engine/providers/internal.cpp b/agents/wnx/src/engine/providers/internal.cpp
@@ -37,10 +37,10 @@ const std::unordered_map<std::string_view, std::chrono::seconds> &
 GetDelaysOnFail() {
     const static std::unordered_map<std::string_view, std::chrono::seconds>
         delays_on_fail = {
-            {kDotNetClrMemory, cfg::G_DefaultDelayOnFail},  //
-            {kWmiWebservices, cfg::G_DefaultDelayOnFail},   //
-            {kWmiCpuLoad, cfg::G_DefaultDelayOnFail},       //
-            {kMsExch, cfg::G_DefaultDelayOnFail},           //
+            {kDotNetClrMemory, 0s},                        //
+            {kWmiWebservices, cfg::G_DefaultDelayOnFail},  //
+            {kWmiCpuLoad, 0s},                             //
+            {kMsExch, cfg::G_DefaultDelayOnFail},          //
             {kOhm, cfg::G_DefaultDelayOnFail},
 
             // end of the real sections
@@ -145,7 +145,8 @@ void Basic::setupDelayOnFail() noexcept {
         const auto &delay_in_seconds = GetDelaysOnFail().at(uniq_name_);
         delay_on_fail_ = delay_in_seconds;
     } catch (const std::out_of_range &) {
-        // do nothing here
+        XLOG::l.crit("Unsupported section name {}", uniq_name_);
+        delay_on_fail_ = std::chrono::seconds(0);
     }
 }
 

diff --git a/agents/wnx/watest/test-section_wmi.cpp b/agents/wnx/watest/test-section_wmi.cpp
@@ -324,12 +324,11 @@ TEST(WmiProviderTest, SimulationComponent) {
     {
         Wmi dotnet_clr(kDotNetClrMemory, wmi::kSepChar);
         EXPECT_EQ(dotnet_clr.subsectionMode(), SubSection::Mode::standard);
-        EXPECT_EQ(dotnet_clr.delayOnFail(), cma::cfg::G_DefaultDelayOnFail);
+        EXPECT_EQ(dotnet_clr.delayOnFail(), 0s);
         EXPECT_EQ(dotnet_clr.object(),
                   L"Win32_PerfRawData_NETFramework_NETCLRMemory");
         EXPECT_TRUE(dotnet_clr.isAllowedByCurrentConfig());
         EXPECT_TRUE(dotnet_clr.isAllowedByTime());
-        EXPECT_EQ(dotnet_clr.delayOnFail(), 3600s);
 
         EXPECT_EQ(dotnet_clr.nameSpace(), L"Root\\Cimv2");
         std::string body;
@@ -378,7 +377,7 @@ TEST(WmiProviderTest, SimulationComponent) {
         Wmi cpu(kWmiCpuLoad, wmi::kSepChar);
         EXPECT_EQ(cpu.subsectionMode(), SubSection::Mode::standard);
         ASSERT_FALSE(cpu.headerless());
-        EXPECT_EQ(cpu.delayOnFail(), cma::cfg::G_DefaultDelayOnFail);
+        EXPECT_EQ(cpu.delayOnFail(), 0s);
 
         // this is empty section
         EXPECT_EQ(cpu.object(), L"");
@@ -398,7 +397,7 @@ TEST(WmiProviderTest, SimulationComponent) {
         // other:
         EXPECT_TRUE(cpu.isAllowedByCurrentConfig());
         EXPECT_TRUE(cpu.isAllowedByTime());
-        EXPECT_EQ(cpu.delayOnFail(), 3600s);
+        EXPECT_EQ(cpu.delayOnFail(), 0s);
     }
     {
         Wmi msexch(kMsExch, wmi::kSepChar);
@@ -513,12 +512,16 @@ TEST(WmiProviderTest, BasicWmi) {
 }
 
 TEST(WmiProviderTest, DelayOnFailDefault) {
-    for (const auto name :
-         {kOhm, kWmiCpuLoad, kWmiWebservices, kDotNetClrMemory, kMsExch}) {
+    for (const auto name : {kOhm, kWmiWebservices, kMsExch}) {
         Wmi b(name, ',');
         EXPECT_EQ(b.delayOnFail(), 3600s)
             << "bad delay for section by default " << name;
     }
+    for (const auto name : {kWmiCpuLoad, kDotNetClrMemory}) {
+        Wmi b(name, ',');
+        EXPECT_EQ(b.delayOnFail(), 0s)
+            << "bad delay for section by default " << name;
+    }
 }
 
 TEST(WmiProviderTest, DelayOnFailShift) {