From 14618c59c61b2f8d731697f01b8388ace825a809 Mon Sep 17 00:00:00 2001
From: Christoffer Martinsson <cm@cmtec.se>
Date: Thu, 27 Nov 2025 22:45:44 +0100
Subject: [PATCH] Fix data duplication in cached collector architecture

Critical bug fix: Collectors were appending to Vecs instead of replacing them,
causing duplicate entries with each collection cycle.

Fixed by adding .clear() calls before populating:
- Memory collector: tmpfs Vec (was showing 11+ duplicates)
- Disk collector: drives and pools Vecs
- Systemd collector: services Vec
- Network collector: Already correct (assigns new Vec)

This prevents the exponential growth of duplicate entries in the dashboard UI.
---
 agent/src/collectors/disk.rs    | 6 ++++++
 agent/src/collectors/memory.rs  | 5 ++++-
 agent/src/collectors/systemd.rs | 3 +++
 3 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/agent/src/collectors/disk.rs b/agent/src/collectors/disk.rs
index 588bec8..dfbd5fa 100644
--- a/agent/src/collectors/disk.rs
+++ b/agent/src/collectors/disk.rs
@@ -530,6 +530,9 @@ impl DiskCollector {
 
     /// Populate drives data into AgentData
     fn populate_drives_data(&self, physical_drives: &[PhysicalDrive], smart_data: &HashMap<String, SmartData>, agent_data: &mut AgentData) -> Result<(), CollectorError> {
+        // Clear existing drives data to prevent duplicates in cached architecture
+        agent_data.system.storage.drives.clear();
+
         for drive in physical_drives {
             let smart = smart_data.get(&drive.name);
             
@@ -567,6 +570,9 @@ impl DiskCollector {
 
     /// Populate pools data into AgentData
     fn populate_pools_data(&self, mergerfs_pools: &[MergerfsPool], smart_data: &HashMap<String, SmartData>, agent_data: &mut AgentData) -> Result<(), CollectorError> {
+        // Clear existing pools data to prevent duplicates in cached architecture
+        agent_data.system.storage.pools.clear();
+
         for pool in mergerfs_pools {
             // Calculate pool health and statuses based on member drive health
             let (pool_health, health_status, usage_status, data_drive_data, parity_drive_data) = self.calculate_pool_health(pool, smart_data);
diff --git a/agent/src/collectors/memory.rs b/agent/src/collectors/memory.rs
index e186704..9151ee2 100644
--- a/agent/src/collectors/memory.rs
+++ b/agent/src/collectors/memory.rs
@@ -97,9 +97,12 @@ impl MemoryCollector {
 
     /// Populate tmpfs data into AgentData
     async fn populate_tmpfs_data(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
+        // Clear existing tmpfs data to prevent duplicates in cached architecture
+        agent_data.system.memory.tmpfs.clear();
+
         // Discover all tmpfs mount points
         let tmpfs_mounts = self.discover_tmpfs_mounts()?;
-        
+
         if tmpfs_mounts.is_empty() {
             debug!("No tmpfs mounts found to monitor");
             return Ok(());
diff --git a/agent/src/collectors/systemd.rs b/agent/src/collectors/systemd.rs
index 9ba8663..4e17cf4 100644
--- a/agent/src/collectors/systemd.rs
+++ b/agent/src/collectors/systemd.rs
@@ -915,6 +915,9 @@ impl SystemdCollector {
 #[async_trait]
 impl Collector for SystemdCollector {
     async fn collect_structured(&self, agent_data: &mut AgentData) -> Result<(), CollectorError> {
+        // Clear existing services data to prevent duplicates in cached architecture
+        agent_data.services.clear();
+
         // Use cached complete data if available and fresh
         if let Some(cached_complete_services) = self.get_cached_complete_services() {
             for service_data in cached_complete_services {