ensure running crawl configmap is updated when exclusions are added/removed (#2409)

exclusions are already updated dynamically if crawler pod is running,
but when crawler pod is restarted, this ensures new exclusions are also
picked up:
- mount configmap in separate path, avoiding subPath, to allow dynamic
updates of mounted volume
- adds a lastConfigUpdate timestamp to CrawlJob - if lastConfigUpdate in
spec is different from current, the configmap is recreated by operator
- operator: also update image from channel avoid any issues with
updating crawler in channel
- only updates for exclusion add/remove so far, can later be expanded to
other crawler settings (see: #2355 for broader running crawl config
updates)
- fixes #2408

backend/btrixcloud/crawlmanager.py

@@ -220,6 +220,12 @@ class CrawlManager(K8sAPI):
             proxy_id=crawlconfig.proxyId or DEFAULT_PROXY_ID,
         )
 
+    async def reload_running_crawl_config(self, crawl_id: str):
+        """force reload of configmap for crawl"""
+        return await self._patch_job(
+            crawl_id, {"lastConfigUpdate": date_to_str(dt_now())}
+        )
+
     async def create_qa_crawl_job(
         self,
         crawlconfig: CrawlConfig,

backend/btrixcloud/crawls.py

@@ -544,6 +544,8 @@ class CrawlOps(BaseCrawlOps):
             regex, cid, org, user, add
         )
 
+        await self.crawl_manager.reload_running_crawl_config(crawl.id)
+
         await self.crawls.find_one_and_update(
             {"_id": crawl_id, "type": "crawl", "oid": org.id},
             {"$set": {"config": new_config.dict()}},

backend/btrixcloud/operator/crawls.py

@@ -274,12 +274,9 @@ class CrawlOperator(BaseOperator):
         params["storage_path"] = storage_path
         params["storage_secret"] = storage_secret
 
-        # only resolve if not already set
-        # not automatically updating image for existing crawls
-        if not status.crawlerImage:
-            status.crawlerImage = self.crawl_config_ops.get_channel_crawler_image(
-                crawl.crawler_channel
-            )
+        status.crawlerImage = self.crawl_config_ops.get_channel_crawler_image(
+            crawl.crawler_channel
+        )
 
         params["crawler_image"] = status.crawlerImage
 
@@ -306,7 +303,16 @@ class CrawlOperator(BaseOperator):
         else:
             params["force_restart"] = False
 
-        children.extend(await self._load_crawl_configmap(crawl, data.children, params))
+        config_update_needed = (
+            spec.get("lastConfigUpdate", "") != status.lastConfigUpdate
+        )
+        status.lastConfigUpdate = spec.get("lastConfigUpdate", "")
+
+        children.extend(
+            await self._load_crawl_configmap(
+                crawl, data.children, params, config_update_needed
+            )
+        )
 
         if crawl.qa_source_crawl_id:
             params["qa_source_crawl_id"] = crawl.qa_source_crawl_id
@@ -364,11 +370,13 @@ class CrawlOperator(BaseOperator):
 
         return behaviors
 
-    async def _load_crawl_configmap(self, crawl: CrawlSpec, children, params):
+    async def _load_crawl_configmap(
+        self, crawl: CrawlSpec, children, params, config_update_needed: bool
+    ):
         name = f"crawl-config-{crawl.id}"
 
         configmap = children[CMAP].get(name)
-        if configmap:
+        if configmap and not config_update_needed:
             metadata = configmap["metadata"]
             configmap["metadata"] = {
                 "name": metadata["name"],
@@ -390,6 +398,9 @@ class CrawlOperator(BaseOperator):
 
         params["config"] = json.dumps(raw_config)
 
+        if config_update_needed:
+            print(f"Updating config for {crawl.id}")
+
         return self.load_from_yaml("crawl_configmap.yaml", params)
 
     async def _load_qa_configmap(self, params, children):

backend/btrixcloud/operator/models.py

@@ -209,6 +209,7 @@ class CrawlStatus(BaseModel):
     stopReason: Optional[StopReason] = None
     initRedis: bool = False
     crawlerImage: Optional[str] = None
+    lastConfigUpdate: str = ""
 
     lastActiveTime: str = ""
     podStatus: DefaultDict[str, Annotated[PodInfo, Field(default_factory=PodInfo)]] = (

chart/app-templates/crawler.yaml

@@ -127,7 +127,7 @@ spec:
       command:
         - {{ "crawl" if not qa_source_crawl_id else "qa" }}
         - --config
-        - /tmp/crawl-config.json
+        - /tmp/config/crawl-config.json
         - --workers
         - "{{ workers }}"
         - --redisStoreUrl
@@ -153,8 +153,7 @@ spec:
       {% endif %}
       volumeMounts:
         - name: crawl-config
-          mountPath: /tmp/crawl-config.json
-          subPath: crawl-config.json
+          mountPath: /tmp/config/
           readOnly: True
 
       {% if qa_source_crawl_id %}