Adding upstream version 1.16.0.upstream/1.16.0

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

5 files changed, 338 insertions, 72 deletions

diff --git a/web/api/health/README.md b/web/api/health/README.md
index 2003a61e0..66a80d5f6 100644
--- a/web/api/health/README.md
+++ b/web/api/health/README.md
@@ -45,6 +45,7 @@ The following will return an SVG badge of the alarm named `NAME`, attached to th
 ## Health Management API
 
 Netdata v1.12 and beyond provides a command API to control health checks and notifications at runtime. The feature is especially useful for maintenance periods, during which you receive meaningless alarms.
+From Netdata v1.16.0 and beyond, the configuration controlled via the API commands is [persisted across netdata restarts](#persistence).
 
 Specifically, the API allows you to:
  - Disable health checks completely. Alarm conditions will not be evaluated at all and no entries will be added to the alarm log.
@@ -142,6 +143,43 @@ Example 2.2: Add one more selector, to also silence alarms for cpu1 and cpu2
 http://localhost/api/v1/manage/health?families=cpu1 cpu2
 ```
 
+### List silencers
+
+The command `LIST` was added in netdata v1.16.0 and returns a JSON with the current status of the silencers.
+
+```
+ curl "http://myserver/api/v1/manage/health?cmd=LIST" -H "X-Auth-Token: Mytoken"
+```
+
+As an example, the following response shows that we have two silencers configured, one for an alarm called `samplealarm` and one for alarms with context `random` on host `myhost`
+```
+json
+{
+        "all": false,
+        "type": "SILENCE",
+        "silencers": [
+                {
+                        "alarm": "samplealarm"
+                },
+                {
+                        "context": "random",
+                        "hosts": "myhost"
+                }
+        ]
+}
+```
+
+The response below shows that we have disabled all health checks.
+
+```
+json
+{
+        "all": true,
+        "type": "DISABLE",
+        "silencers": []
+}
+
+
 ### Responses
 
 - "Auth Error" : Token authentication failed
@@ -155,6 +193,17 @@ http://localhost/api/v1/manage/health?families=cpu1 cpu2
 - "WARNING: Added alarm selector to silence/disable alarms without a SILENCE or DISABLE command." : Added to the response if a selector is added without a selector-specific command.
 - "WARNING: SILENCE or DISABLE command is ineffective without defining any alarm selectors." : Added to the response if a selector-specific command is issued without a selector.
 
+### Persistence
+
+From netdata v1.16.0 and beyond, the silencers configuration is persisted to disk and loaded when netdata starts.
+The JSON string returned by the [LIST command](#list-silencers) is automatically saved to the `silencers file`, every time a command alters the silencers configuration.
+The file's location is configurable in `netdata.conf`. The default is shown below:
+
+```
+[health]
+        # silencers file = /var/lib/netdata/health.silencers.json
+```
+
 ### Further reading
 
 The test script under [tests/health_mgmtapi](../../../tests/health_mgmtapi) contains a series of tests that you can either run or read through to understand the various calls and responses better.
diff --git a/web/api/health/health_cmdapi.c b/web/api/health/health_cmdapi.c
index ec177751b..468054c67 100644
--- a/web/api/health/health_cmdapi.c
+++ b/web/api/health/health_cmdapi.c
@@ -1,17 +1,16 @@
 //
-// Created by christopher on 11/12/18.
+// Created by Christopher on 11/12/18.
 //
 
 #include "health_cmdapi.h"
 
-
-static SILENCER *create_silencer(void) {
-    SILENCER *t = callocz(1, sizeof(SILENCER));
-    debug(D_HEALTH, "HEALTH command API: Created empty silencer");
-
-    return t;
-}
-
+/**
+ * Free Silencers
+ *
+ * Clean the silencer structure
+ *
+ * @param t is the structure that will be cleaned.
+ */
 void free_silencers(SILENCER *t) {
     if (!t) return;
     if (t->next) free_silencers(t->next);
@@ -31,38 +30,104 @@ void free_silencers(SILENCER *t) {
     return;
 }
 
+/**
+ * Silencers to JSON Entry
+ *
+ * Fill the buffer with the other values given.
+ *
+ * @param wb a pointer to the output buffer
+ * @param var the json variable
+ * @param val the json value
+ * @param hasprev has it a previous value?
+ *
+ * @return
+ */
+int health_silencers2json_entry(BUFFER *wb, char* var, char* val, int hasprev) {
+    if (val) {
+        buffer_sprintf(wb, "%s\n\t\t\t\"%s\": \"%s\"", (hasprev)?",":"", var, val);
+        return 1;
+    } else {
+        return hasprev;
+    }
+}
 
+/**
+ * Silencer to JSON
+ *
+ * Write the silencer values using JSON format inside a buffer.
+ *
+ * @param wb is the buffer to write the silencers.
+ */
+void health_silencers2json(BUFFER *wb) {
+    buffer_sprintf(wb, "{\n\t\"all\": %s,"
+                       "\n\t\"type\": \"%s\","
+                       "\n\t\"silencers\": [",
+                   (silencers->all_alarms)?"true":"false",
+                   (silencers->stype == STYPE_NONE)?"None":((silencers->stype == STYPE_DISABLE_ALARMS)?"DISABLE":"SILENCE"));
+
+    SILENCER *silencer;
+    int i = 0, j = 0;
+    for(silencer = silencers->silencers; silencer ; silencer = silencer->next) {
+        if(likely(i)) buffer_strcat(wb, ",");
+        buffer_strcat(wb, "\n\t\t{");
+        j=health_silencers2json_entry(wb, HEALTH_ALARM_KEY, silencer->alarms, j);
+        j=health_silencers2json_entry(wb, HEALTH_CHART_KEY, silencer->charts, j);
+        j=health_silencers2json_entry(wb, HEALTH_CONTEXT_KEY, silencer->contexts, j);
+        j=health_silencers2json_entry(wb, HEALTH_HOST_KEY, silencer->hosts, j);
+        health_silencers2json_entry(wb, HEALTH_FAMILIES_KEY, silencer->families, j);
+        j=0;
+        buffer_strcat(wb, "\n\t\t}");
+        i++;
+    }
+    if(likely(i)) buffer_strcat(wb, "\n\t");
+    buffer_strcat(wb, "]\n}\n");
+}
 
+/**
+ * Silencer to FILE
+ *
+ * Write the sliencer buffer to a file.
+ * @param wb
+ */
+void health_silencers2file(BUFFER *wb) {
+    if (wb->len == 0) return;
+
+    FILE *fd = fopen(silencers_filename, "wb");
+    if(fd) {
+        size_t written = (size_t)fprintf(fd, "%s", wb->buffer) ;
+        if (written == wb->len ) {
+            info("Silencer changes written to %s", silencers_filename);
+        }
+        fclose(fd);
+        return;
+    }
+    error("Silencer changes could not be written to %s. Error %s", silencers_filename, strerror(errno));
+}
+
+/**
+ * Request V1 MGMT Health
+ *
+ * Function called by api to management the health.
+ *
+ * @param host main structure with client information!
+ * @param w is the structure with all information of the client request.
+ * @param url is the url that netdata is working
+ *
+ * @return It returns 200 on success and another code otherwise.
+ */
 int web_client_api_request_v1_mgmt_health(RRDHOST *host, struct web_client *w, char *url) {
     int ret = 400;
     (void) host;
 
-
-
     BUFFER *wb = w->response.data;
     buffer_flush(wb);
     wb->contenttype = CT_TEXT_PLAIN;
 
     buffer_flush(w->response.data);
 
-    static uint32_t
-            hash_alarm = 0,
-            hash_template = 0,
-            hash_chart = 0,
-            hash_context = 0,
-            hash_host = 0,
-            hash_families = 0;
-
-    if (unlikely(!hash_alarm)) {
-        hash_alarm = simple_uhash(HEALTH_ALARM_KEY);
-        hash_template = simple_uhash(HEALTH_TEMPLATE_KEY);
-        hash_chart = simple_uhash(HEALTH_CHART_KEY);
-        hash_context = simple_uhash(HEALTH_CONTEXT_KEY);
-        hash_host = simple_uhash(HEALTH_HOST_KEY);
-        hash_families = simple_uhash(HEALTH_FAMILIES_KEY);
-    }
-
+    //Local instance of the silencer
     SILENCER *silencer = NULL;
+    int config_changed = 1;
 
     if (!w->auth_bearer_token) {
         buffer_strcat(wb, HEALTH_CMDAPI_MSG_AUTHERROR);
@@ -105,50 +170,17 @@ int web_client_api_request_v1_mgmt_health(RRDHOST *host, struct web_client *w, c
                         free_silencers(silencers->silencers);
                         silencers->silencers = NULL;
                         buffer_strcat(wb, HEALTH_CMDAPI_MSG_RESET);
+                    } else if (!strcmp(value, HEALTH_CMDAPI_CMD_LIST)) {
+                        w->response.data->contenttype = CT_APPLICATION_JSON;
+                        health_silencers2json(wb);
+                        config_changed=0;
                     }
                 } else {
-                    uint32_t hash = simple_uhash(key);
-                    if (unlikely(silencer == NULL)) {
-                        if (
-                                (hash == hash_alarm && !strcasecmp(key, HEALTH_ALARM_KEY)) ||
-                                (hash == hash_template && !strcasecmp(key, HEALTH_TEMPLATE_KEY)) ||
-                                (hash == hash_chart && !strcasecmp(key, HEALTH_CHART_KEY)) ||
-                                (hash == hash_context && !strcasecmp(key, HEALTH_CONTEXT_KEY)) ||
-                                (hash == hash_host && !strcasecmp(key, HEALTH_HOST_KEY)) ||
-                                (hash == hash_families && !strcasecmp(key, HEALTH_FAMILIES_KEY))
-                                ) {
-                            silencer = create_silencer();
-                        }
-                    }
-
-                    if (hash == hash_alarm && !strcasecmp(key, HEALTH_ALARM_KEY)) {
-                        silencer->alarms = strdupz(value);
-                        silencer->alarms_pattern = simple_pattern_create(silencer->alarms, NULL, SIMPLE_PATTERN_EXACT);
-                    } else if (hash == hash_chart && !strcasecmp(key, HEALTH_CHART_KEY)) {
-                        silencer->charts = strdupz(value);
-                        silencer->charts_pattern = simple_pattern_create(silencer->charts, NULL, SIMPLE_PATTERN_EXACT);
-                    } else if (hash == hash_context && !strcasecmp(key, HEALTH_CONTEXT_KEY)) {
-                        silencer->contexts = strdupz(value);
-                        silencer->contexts_pattern = simple_pattern_create(silencer->contexts, NULL, SIMPLE_PATTERN_EXACT);
-                    } else if (hash == hash_host && !strcasecmp(key, HEALTH_HOST_KEY)) {
-                        silencer->hosts = strdupz(value);
-                        silencer->hosts_pattern = simple_pattern_create(silencer->hosts, NULL, SIMPLE_PATTERN_EXACT);
-                    } else if (hash == hash_families && !strcasecmp(key, HEALTH_FAMILIES_KEY)) {
-                        silencer->families = strdupz(value);
-                        silencer->families_pattern = simple_pattern_create(silencer->families, NULL, SIMPLE_PATTERN_EXACT);
-                    } else {
-                        buffer_strcat(wb, HEALTH_CMDAPI_MSG_INVALID_KEY);
-                    }
+                    silencer = health_silencers_addparam(silencer, key, value);
                 }
-
             }
             if (likely(silencer)) {
-                // Add the created instance to the linked list in silencers
-                silencer->next = silencers->silencers;
-                silencers->silencers = silencer;
-                debug(D_HEALTH, "HEALTH command API: Added silencer %s:%s:%s:%s:%s", silencer->alarms,
-                      silencer->charts, silencer->contexts, silencer->hosts, silencer->families
-                );
+                health_silencers_add(silencer);
                 buffer_strcat(wb, HEALTH_CMDAPI_MSG_ADDED);
                 if (silencers->stype == STYPE_NONE) {
                     buffer_strcat(wb, HEALTH_CMDAPI_MSG_STYPEWARNING);
@@ -162,5 +194,11 @@ int web_client_api_request_v1_mgmt_health(RRDHOST *host, struct web_client *w, c
     }
     w->response.data = wb;
     buffer_no_cacheable(w->response.data);
+    if (ret == 200 && config_changed) {
+        BUFFER *jsonb = buffer_create(200);
+        health_silencers2json(jsonb);
+        health_silencers2file(jsonb);
+    }
+
     return ret;
 }
diff --git a/web/api/health/health_cmdapi.h b/web/api/health/health_cmdapi.h
index d0f30401c..d8ec6aaa0 100644
--- a/web/api/health/health_cmdapi.h
+++ b/web/api/health/health_cmdapi.h
@@ -12,6 +12,7 @@
 #define HEALTH_CMDAPI_CMD_SILENCE "SILENCE"
 #define HEALTH_CMDAPI_CMD_DISABLE "DISABLE"
 #define HEALTH_CMDAPI_CMD_RESET "RESET"
+#define HEALTH_CMDAPI_CMD_LIST "LIST"
 
 #define HEALTH_CMDAPI_MSG_AUTHERROR "Auth Error\n"
 #define HEALTH_CMDAPI_MSG_SILENCEALL "All alarm notifications are silenced\n"
@@ -20,7 +21,6 @@
 #define HEALTH_CMDAPI_MSG_DISABLE "Health checks disabled for alarms matching the selectors\n"
 #define HEALTH_CMDAPI_MSG_SILENCE "Alarm notifications silenced for alarms matching the selectors\n"
 #define HEALTH_CMDAPI_MSG_ADDED "Alarm selector added\n"
-#define HEALTH_CMDAPI_MSG_INVALID_KEY "Invalid key. Ignoring it.\n"
 #define HEALTH_CMDAPI_MSG_STYPEWARNING "WARNING: Added alarm selector to silence/disable alarms without a SILENCE or DISABLE command.\n"
 #define HEALTH_CMDAPI_MSG_NOSELECTORWARNING "WARNING: SILENCE or DISABLE command is ineffective without defining any alarm selectors.\n"
 
diff --git a/web/api/netdata-swagger.json b/web/api/netdata-swagger.json
index 2fa55c4fa..63bc5638d 100644
--- a/web/api/netdata-swagger.json
+++ b/web/api/netdata-swagger.json
@@ -77,6 +77,39 @@
         }
       }
     },
+    "/alarm_variables": {
+      "get": {
+        "summary": "List variables available to configure alarms for a chart",
+        "description": "Returns the basic information of a chart and all the variables that can be used in alarm and template health configurations for the particular chart or family",
+        "parameters": [
+          {
+            "name": "chart",
+            "in": "query",
+            "description": "The id of the chart as returned by the /charts call.",
+            "required": true,
+            "type": "string",
+            "format": "as returned by /charts"
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "A javascript object with information about the chart and the available variables",
+            "schema": {
+              "$ref": "#/definitions/alarm_variables"
+            }
+          },
+          "400": {
+            "description": "Bad request - the body will include a message stating what is wrong."
+          },
+          "404": {
+            "description": "No chart with the given id is found."
+          },
+          "500": {
+            "description": "Internal server error. This usually means the server is out of memory."
+          }
+        }
+      }
+    },
     "/data": {
       "get": {
         "summary": "Get collected data for a specific chart",
@@ -631,7 +664,7 @@
           {
             "name": "cmd",
             "in": "query",
-            "description": "DISABLE ALL: No alarm criteria are evaluated, nothing is written in the alarm log. SILENCE ALL: No notifications are sent. RESET: Return to the default state. DISABLE/SILENCE: Set the mode to be used for the alarms matching the criteria of the alarm selectors.",
+            "description": "DISABLE ALL: No alarm criteria are evaluated, nothing is written in the alarm log. SILENCE ALL: No notifications are sent. RESET: Return to the default state. DISABLE/SILENCE: Set the mode to be used for the alarms matching the criteria of the alarm selectors. LIST: Show active configuration.",
             "required": false,
             "type": "string",
             "enum": [
@@ -639,7 +672,8 @@
               "SILENCE ALL",
               "DISABLE",
               "SILENCE",
-              "RESET"
+              "RESET",
+              "LIST"
             ]
           },
           {
@@ -951,6 +985,70 @@
         }
       }
     },
+    "alarm_variables": {
+      "type": "object",
+      "properties": {
+        "chart": {
+          "type": "string",
+          "description": "The unique id of the chart"
+        },
+        "chart_name": {
+          "type": "string",
+          "description": "The name of the chart"
+        },
+        "cnart_context": {
+          "type": "string",
+          "description": "The context of the chart. It is shared across multiple monitored software or hardware instances and used in alarm templates"
+        },
+        "family": {
+          "type": "string",
+          "description": "The family of the chart."
+        },
+        "host": {
+          "type": "string",
+          "description": "The host containing the chart."
+        },
+        "chart_variables": {
+          "type": "object",
+          "properties": {
+            "varname1": {
+              "type": "number",
+              "format": "float"
+            },
+            "varname2": {
+              "type": "number",
+              "format": "float"
+            }
+          }
+        },
+        "family_variables": {
+          "type": "object",
+          "properties": {
+            "varname1": {
+              "type": "number",
+              "format": "float"
+            },
+            "varname2": {
+              "type": "number",
+              "format": "float"
+            }
+          }
+        },
+        "host_variables": {
+          "type": "object",
+          "properties": {
+            "varname1": {
+              "type": "number",
+              "format": "float"
+            },
+            "varname2": {
+              "type": "number",
+              "format": "float"
+            }
+          }
+        }
+      }
+    },
     "dimension": {
       "type": "object",
       "properties": {
@@ -1208,6 +1306,14 @@
                 "crit_parsed": {
                   "type": "string"
                 },
+                "warn_repeat_every": {
+                  "type": "integer",
+                  "format": "int32"
+                },
+                "crit_repeat_every": {
+                  "type": "integer",
+                  "format": "int32"
+                },
                 "green": {
                   "type": "string",
                   "format": "nullable"
diff --git a/web/api/netdata-swagger.yaml b/web/api/netdata-swagger.yaml
index c021efefa..3386e01a7 100644
--- a/web/api/netdata-swagger.yaml
+++ b/web/api/netdata-swagger.yaml
@@ -63,6 +63,28 @@ paths:
             $ref: '#/definitions/chart'
         '404':
           description: 'No chart with the given id is found.'
+  /alarm_variables:
+    get:
+      summary: 'List variables available to configure alarms for a chart'
+      description: 'Returns the basic information of a chart and all the variables that can be used in alarm and template health configurations for the particular chart or family'
+      parameters:
+        - name: chart
+          in: query
+          description: 'The id of the chart as returned by the /charts call.'
+          required: true
+          type: string
+          format: 'as returned by /charts'
+      responses:
+        '200':
+            description: 'A javascript object with information about the chart and the available variables'
+            schema:
+              $ref: '#/definitions/alarm_variables'
+        '400':
+          description: 'Bad request - the body will include a message stating what is wrong.'
+        '404':
+          description: 'No chart with the given id is found.'
+        '500':
+          description: 'Internal server error. This usually means the server is out of memory.'
   /data:
     get:
       summary: 'Get collected data for a specific chart'
@@ -415,10 +437,10 @@ paths:
       parameters:
         - name: cmd
           in: query
-          description: 'DISABLE ALL: No alarm criteria are evaluated, nothing is written in the alarm log. SILENCE ALL: No notifications are sent. RESET: Return to the default state. DISABLE/SILENCE: Set the mode to be used for the alarms matching the criteria of the alarm selectors.'
+          description: 'DISABLE ALL: No alarm criteria are evaluated, nothing is written in the alarm log. SILENCE ALL: No notifications are sent. RESET: Return to the default state. DISABLE/SILENCE: Set the mode to be used for the alarms matching the criteria of the alarm selectors. LIST: Show active configuration.'
           required: false
           type: string
-          enum: ['DISABLE ALL', 'SILENCE ALL', 'DISABLE', 'SILENCE', 'RESET']
+          enum: ['DISABLE ALL', 'SILENCE ALL', 'DISABLE', 'SILENCE', 'RESET', 'LIST']
         - name: alarm
           in: query
           description: 'The expression provided will match both `alarm` and `template` names.'
@@ -638,6 +660,51 @@ definitions:
       red:
         type: number
         description: 'Chart health red trheshold'
+  alarm_variables:
+    type: object
+    properties:
+      chart:
+        type: string
+        description: 'The unique id of the chart'
+      chart_name:
+        type: string
+        description: 'The name of the chart'
+      cnart_context:
+        type: string
+        description: 'The context of the chart. It is shared across multiple monitored software or hardware instances and used in alarm templates'
+      family:
+        type: string
+        description: 'The family of the chart.'
+      host:
+        type: string
+        description: 'The host containing the chart.'
+      chart_variables:
+        type: object
+        properties:
+          varname1:
+            type: number
+            format: float
+          varname2:
+            type: number
+            format: float
+      family_variables:
+        type: object
+        properties:
+          varname1:
+            type: number
+            format: float
+          varname2:
+            type: number
+            format: float
+      host_variables:
+        type: object
+        properties:
+          varname1:
+            type: number
+            format: float
+          varname2:
+            type: number
+            format: float
   dimension:
     type: object
     properties:
@@ -825,6 +892,12 @@ definitions:
                 type: string
               crit_parsed: 
                 type: string
+              warn_repeat_every:
+                type: integer
+                format: int32
+              crit_repeat_every:
+                type: integer
+                format: int32
               green: 
                 type: string
                 format: nullable