Enforce quota and hard cap for monthly execution minutes

backend/btrixcloud/basecrawls.py

@@ -136,6 +136,9 @@ async def get_crawl(
                 crawl.config.seeds = None
 
         crawl.storageQuotaReached = await self.orgs.storage_quota_reached(crawl.oid)
+        crawl.execMinutesQuotaReached = await self.orgs.exec_mins_quota_reached(
+            crawl.oid
+        )
 
         return crawl
 

backend/btrixcloud/crawlconfigs.py

@@ -3,7 +3,7 @@
 """
 # pylint: disable=too-many-lines
 
-from typing import List, Union, Optional
+from typing import List, Union, Optional, Tuple
 
 import uuid
 import asyncio
@@ -137,7 +137,7 @@ async def add_crawl_config(
         config: CrawlConfigIn,
         org: Organization,
         user: User,
-    ) -> tuple[str, str, bool]:
+    ) -> Tuple[str, Optional[str], bool, bool]:
         """Add new crawl config"""
         data = config.dict()
         data["oid"] = org.id
@@ -174,12 +174,17 @@ async def add_crawl_config(
         )
 
         run_now = config.runNow
-        quota_reached = await self.org_ops.storage_quota_reached(org.id)
+        storage_quota_reached = await self.org_ops.storage_quota_reached(org.id)
+        exec_mins_quota_reached = await self.org_ops.exec_mins_quota_reached(org.id)
 
-        if quota_reached:
+        if storage_quota_reached:
             run_now = False
             print(f"Storage quota exceeded for org {org.id}", flush=True)
 
+        if exec_mins_quota_reached:
+            run_now = False
+            print(f"Execution minutes quota exceeded for org {org.id}", flush=True)
+
         crawl_id = await self.crawl_manager.add_crawl_config(
             crawlconfig=crawlconfig,
             storage=org.storage,
@@ -191,7 +196,12 @@ async def add_crawl_config(
         if crawl_id and run_now:
             await self.add_new_crawl(crawl_id, crawlconfig, user, manual=True)
 
-        return result.inserted_id, crawl_id, quota_reached
+        return (
+            result.inserted_id,
+            crawl_id or None,
+            storage_quota_reached,
+            exec_mins_quota_reached,
+        )
 
     async def add_new_crawl(
         self, crawl_id: str, crawlconfig: CrawlConfig, user: User, manual: bool
@@ -336,6 +346,10 @@ async def update_crawl_config(
             "updated": True,
             "settings_changed": changed,
             "metadata_changed": metadata_changed,
+            "storageQuotaReached": await self.org_ops.storage_quota_reached(org.id),
+            "execMinutesQuotaReached": await self.org_ops.exec_mins_quota_reached(
+                org.id
+            ),
         }
         if run_now:
             crawl_id = await self.run_now(cid, org, user)
@@ -757,6 +771,9 @@ async def run_now(self, cid: uuid.UUID, org: Organization, user: User):
         if await self.org_ops.storage_quota_reached(org.id):
             raise HTTPException(status_code=403, detail="storage_quota_reached")
 
+        if await self.org_ops.exec_mins_quota_reached(org.id):
+            raise HTTPException(status_code=403, detail="exec_minutes_quota_reached")
+
         try:
             crawl_id = await self.crawl_manager.create_crawl_job(
                 crawlconfig, userid=str(user.id)
@@ -991,12 +1008,18 @@ async def add_crawl_config(
         org: Organization = Depends(org_crawl_dep),
         user: User = Depends(user_dep),
     ):
-        cid, new_job_name, quota_reached = await ops.add_crawl_config(config, org, user)
+        (
+            cid,
+            new_job_name,
+            storage_quota_reached,
+            exec_mins_quota_reached,
+        ) = await ops.add_crawl_config(config, org, user)
         return {
             "added": True,
             "id": str(cid),
             "run_now_job": new_job_name,
-            "storageQuotaReached": quota_reached,
+            "storageQuotaReached": storage_quota_reached,
+            "execMinutesQuotaReached": exec_mins_quota_reached,
         }
 
     @router.patch("/{cid}", dependencies=[Depends(org_crawl_dep)])

backend/btrixcloud/crawls.py

@@ -528,11 +528,11 @@ async def update_running_crawl_stats(self, crawl_id, stats):
         query = {"_id": crawl_id, "type": "crawl", "state": "running"}
         return await self.crawls.find_one_and_update(query, {"$set": {"stats": stats}})
 
-    async def store_exec_time(self, crawl_id, exec_time):
-        """set exec time, only if not already set"""
-        query = {"_id": crawl_id, "type": "crawl", "execTime": {"$in": [0, None]}}
+    async def inc_crawl_exec_time(self, crawl_id, exec_time):
+        """increment exec time"""
         return await self.crawls.find_one_and_update(
-            query, {"$set": {"execTime": exec_time}}
+            {"_id": crawl_id, "type": "crawl"},
+            {"$inc": {"crawlExecSeconds": exec_time}},
         )
 
     async def get_crawl_state(self, crawl_id):

backend/btrixcloud/models.py

@@ -513,6 +513,7 @@ class CrawlOut(BaseMongoModel):
     cid_rev: Optional[int]
 
     storageQuotaReached: Optional[bool]
+    execMinutesQuotaReached: Optional[bool]
 
 
 # ============================================================================
@@ -722,6 +723,7 @@ class OrgQuotas(BaseModel):
     maxConcurrentCrawls: Optional[int] = 0
     maxPagesPerCrawl: Optional[int] = 0
     storageQuota: Optional[int] = 0
+    maxExecMinutesPerMonth: Optional[int] = 0
 
 
 # ============================================================================
@@ -755,6 +757,9 @@ class OrgOut(BaseMongoModel):
     webhookUrls: Optional[OrgWebhookUrls] = OrgWebhookUrls()
     quotas: Optional[OrgQuotas] = OrgQuotas()
 
+    storageQuotaReached: Optional[bool]
+    execMinutesQuotaReached: Optional[bool]
+
 
 # ============================================================================
 class Organization(BaseMongoModel):