Compare commits
16 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 317cf76bd1 | |||
| 0db1a165b9 | |||
| 3c2955376d | |||
| f09ccabc7f | |||
| 43dd5a901a | |||
| 01e1f33b66 | |||
| ed6399b914 | |||
| 14618c59c6 | |||
| 2740de9b54 | |||
| 37f2650200 | |||
| 833010e270 | |||
| 549d9d1c72 | |||
| 9b84b70581 | |||
| 92c3ee3f2a | |||
| 1be55f765d | |||
| 2f94a4b853 |
50
CLAUDE.md
50
CLAUDE.md
@@ -156,6 +156,56 @@ Complete migration from string-based metrics to structured JSON data. Eliminates
|
||||
- ✅ Backward compatibility via bridge conversion to existing UI widgets
|
||||
- ✅ All string parsing bugs eliminated
|
||||
|
||||
### Cached Collector Architecture (🚧 PLANNED)
|
||||
|
||||
**Problem:** Blocking collectors prevent timely ZMQ transmission, causing false "host offline" alerts.
|
||||
|
||||
**Previous (Sequential Blocking):**
|
||||
```
|
||||
Every 1 second:
|
||||
└─ collect_all_data() [BLOCKS for 2-10+ seconds]
|
||||
├─ CPU (fast: 10ms)
|
||||
├─ Memory (fast: 20ms)
|
||||
├─ Disk SMART (slow: 3s per drive × 4 drives = 12s)
|
||||
├─ Service disk usage (slow: 2-8s per service)
|
||||
└─ Docker (medium: 500ms)
|
||||
└─ send_via_zmq() [Only after ALL collection completes]
|
||||
|
||||
Result: If any collector takes >10s → "host offline" false alert
|
||||
```
|
||||
|
||||
**New (Cached Independent Collectors):**
|
||||
```
|
||||
Shared Cache: Arc<RwLock<AgentData>>
|
||||
|
||||
Background Collectors (independent async tasks):
|
||||
├─ Fast collectors (CPU, RAM, Network)
|
||||
│ └─ Update cache every 1 second
|
||||
├─ Medium collectors (Services, Docker)
|
||||
│ └─ Update cache every 5 seconds
|
||||
└─ Slow collectors (Disk usage, SMART data)
|
||||
└─ Update cache every 60 seconds
|
||||
|
||||
ZMQ Sender (separate async task):
|
||||
Every 1 second:
|
||||
└─ Read current cache
|
||||
└─ Send via ZMQ [Always instant, never blocked]
|
||||
```
|
||||
|
||||
**Benefits:**
|
||||
- ✅ ZMQ sends every 1 second regardless of collector speed
|
||||
- ✅ No false "host offline" alerts from slow collectors
|
||||
- ✅ Different update rates for different metrics (CPU=1s, SMART=60s)
|
||||
- ✅ System stays responsive even with slow operations
|
||||
- ✅ Slow collectors can use longer timeouts without blocking
|
||||
|
||||
**Implementation:**
|
||||
- Shared `AgentData` cache wrapped in `Arc<RwLock<>>`
|
||||
- Each collector spawned as independent tokio task
|
||||
- Collectors update their section of cache at their own rate
|
||||
- ZMQ sender reads cache every 1s and transmits
|
||||
- Stale data acceptable for slow-changing metrics (disk usage, SMART)
|
||||
|
||||
### Maintenance Mode
|
||||
|
||||
- Agent checks for `/tmp/cm-maintenance` file before sending notifications
|
||||
|
||||
57
Cargo.lock
generated
57
Cargo.lock
generated
@@ -1,6 +1,5 @@
|
||||
# This file is automatically @generated by Cargo.
|
||||
# It is not intended for manual editing.
|
||||
# This file is automatically generated by Cargo.
|
||||
version = 4
|
||||
|
||||
[[package]]
|
||||
@@ -165,9 +164,9 @@ checksum = "df8670b8c7b9dae1793364eafadf7239c40d669904660c5960d74cfd80b46a53"
|
||||
|
||||
[[package]]
|
||||
name = "cc"
|
||||
version = "1.2.46"
|
||||
version = "1.2.47"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b97463e1064cb1b1c1384ad0a0b9c8abd0988e2a91f52606c80ef14aadb63e36"
|
||||
checksum = "cd405d82c84ff7f35739f175f67d8b9fb7687a0e84ccdc78bd3568839827cf07"
|
||||
dependencies = [
|
||||
"find-msvc-tools",
|
||||
"jobserver",
|
||||
@@ -239,9 +238,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "clap"
|
||||
version = "4.5.52"
|
||||
version = "4.5.53"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "aa8120877db0e5c011242f96806ce3c94e0737ab8108532a76a3300a01db2ab8"
|
||||
checksum = "c9e340e012a1bf4935f5282ed1436d1489548e8f72308207ea5df0e23d2d03f8"
|
||||
dependencies = [
|
||||
"clap_builder",
|
||||
"clap_derive",
|
||||
@@ -249,9 +248,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "clap_builder"
|
||||
version = "4.5.52"
|
||||
version = "4.5.53"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "02576b399397b659c26064fbc92a75fede9d18ffd5f80ca1cd74ddab167016e1"
|
||||
checksum = "d76b5d13eaa18c901fd2f7fca939fefe3a0727a953561fefdf3b2922b8569d00"
|
||||
dependencies = [
|
||||
"anstream",
|
||||
"anstyle",
|
||||
@@ -279,7 +278,7 @@ checksum = "a1d728cc89cf3aee9ff92b05e62b19ee65a02b5702cff7d5a377e32c6ae29d8d"
|
||||
|
||||
[[package]]
|
||||
name = "cm-dashboard"
|
||||
version = "0.1.188"
|
||||
version = "0.1.196"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"chrono",
|
||||
@@ -301,7 +300,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "cm-dashboard-agent"
|
||||
version = "0.1.188"
|
||||
version = "0.1.196"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"async-trait",
|
||||
@@ -324,7 +323,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "cm-dashboard-shared"
|
||||
version = "0.1.188"
|
||||
version = "0.1.196"
|
||||
dependencies = [
|
||||
"chrono",
|
||||
"serde",
|
||||
@@ -664,9 +663,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "hashbrown"
|
||||
version = "0.16.0"
|
||||
version = "0.16.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "5419bdc4f6a9207fbeba6d11b604d481addf78ecd10c11ad51e76c2f6482748d"
|
||||
checksum = "841d1cc9bed7f9236f321df977030373f4a4163ae1a7dbfe1a51a2c1a51d9100"
|
||||
|
||||
[[package]]
|
||||
name = "heck"
|
||||
@@ -879,12 +878,12 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "indexmap"
|
||||
version = "2.12.0"
|
||||
version = "2.12.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "6717a8d2a5a929a1a2eb43a12812498ed141a0bcfb7e8f7844fbdbe4303bba9f"
|
||||
checksum = "0ad4bb2b565bca0645f4d68c5c9af97fba094e9791da685bf83cb5f3ce74acf2"
|
||||
dependencies = [
|
||||
"equivalent",
|
||||
"hashbrown 0.16.0",
|
||||
"hashbrown 0.16.1",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -1639,9 +1638,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "signal-hook-registry"
|
||||
version = "1.4.6"
|
||||
version = "1.4.7"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b2a4719bff48cee6b39d12c020eeb490953ad2443b7055bd0b21fca26bd8c28b"
|
||||
checksum = "7664a098b8e616bdfcc2dc0e9ac44eb231eedf41db4e9fe95d8d32ec728dedad"
|
||||
dependencies = [
|
||||
"libc",
|
||||
]
|
||||
@@ -1733,9 +1732,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "syn"
|
||||
version = "2.0.110"
|
||||
version = "2.0.111"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "a99801b5bd34ede4cf3fc688c5919368fea4e4814a4664359503e6015b280aea"
|
||||
checksum = "390cc9a294ab71bdb1aa2e99d13be9c753cd2d7bd6560c77118597410c4d2e87"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
@@ -1962,9 +1961,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "tracing-attributes"
|
||||
version = "0.1.30"
|
||||
version = "0.1.31"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "81383ab64e72a7a8b8e13130c49e3dab29def6d0c7d76a03087b3cf71c5c6903"
|
||||
checksum = "7490cfa5ec963746568740651ac6781f701c9c5ea257c58e057f3ba8cf69e8da"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
@@ -1973,9 +1972,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "tracing-core"
|
||||
version = "0.1.34"
|
||||
version = "0.1.35"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b9d12581f227e93f094d3af2ae690a574abb8a2b9b7a96e7cfe9647b2b617678"
|
||||
checksum = "7a04e24fab5c89c6a36eb8558c9656f30d81de51dfa4d3b45f26b21d61fa0a6c"
|
||||
dependencies = [
|
||||
"once_cell",
|
||||
"valuable",
|
||||
@@ -2513,9 +2512,9 @@ checksum = "d6bbff5f0aada427a1e5a6da5f1f98158182f26556f345ac9e04d36d0ebed650"
|
||||
|
||||
[[package]]
|
||||
name = "winnow"
|
||||
version = "0.7.13"
|
||||
version = "0.7.14"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "21a0236b59786fed61e2a80582dd500fe61f18b5dca67a4a067d0bc9039339cf"
|
||||
checksum = "5a5364e9d77fcdeeaa6062ced926ee3381faa2ee02d3eb83a5c27a8825540829"
|
||||
dependencies = [
|
||||
"memchr",
|
||||
]
|
||||
@@ -2567,18 +2566,18 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "zerocopy"
|
||||
version = "0.8.27"
|
||||
version = "0.8.30"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "0894878a5fa3edfd6da3f88c4805f4c8558e2b996227a3d864f47fe11e38282c"
|
||||
checksum = "4ea879c944afe8a2b25fef16bb4ba234f47c694565e97383b36f3a878219065c"
|
||||
dependencies = [
|
||||
"zerocopy-derive",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "zerocopy-derive"
|
||||
version = "0.8.27"
|
||||
version = "0.8.30"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "88d2b8d9c68ad2b9e4340d7832716a4d21a22a1154777ad56ea55c51a9cf3831"
|
||||
checksum = "cf955aa904d6040f70dc8e9384444cb1030aed272ba3cb09bbc4ab9e7c1f34f5"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "cm-dashboard-agent"
|
||||
version = "0.1.189"
|
||||
version = "0.1.196"
|
||||
edition = "2021"
|
||||
|
||||
[dependencies]
|
||||
|
||||
@@ -113,6 +113,7 @@ impl SystemdCollector {
|
||||
name: site_name.clone(),
|
||||
service_status: self.calculate_service_status(&site_name, &site_status),
|
||||
metrics,
|
||||
service_type: "nginx_site".to_string(),
|
||||
});
|
||||
}
|
||||
}
|
||||
@@ -128,12 +129,13 @@ impl SystemdCollector {
|
||||
name: container_name.clone(),
|
||||
service_status: self.calculate_service_status(&container_name, &container_status),
|
||||
metrics,
|
||||
service_type: "container".to_string(),
|
||||
});
|
||||
}
|
||||
|
||||
// Add Docker images
|
||||
let docker_images = self.get_docker_images();
|
||||
for (image_name, image_status, image_size_str, image_size_mb) in docker_images {
|
||||
for (image_name, image_status, image_size_mb) in docker_images {
|
||||
let mut metrics = Vec::new();
|
||||
metrics.push(SubServiceMetric {
|
||||
label: "size".to_string(),
|
||||
@@ -142,9 +144,10 @@ impl SystemdCollector {
|
||||
});
|
||||
|
||||
sub_services.push(SubServiceData {
|
||||
name: format!("{} ({})", image_name, image_size_str),
|
||||
name: image_name.to_string(),
|
||||
service_status: self.calculate_service_status(&image_name, &image_status),
|
||||
metrics,
|
||||
service_type: "image".to_string(),
|
||||
});
|
||||
}
|
||||
}
|
||||
@@ -824,7 +827,7 @@ impl SystemdCollector {
|
||||
}
|
||||
|
||||
/// Get docker images as sub-services
|
||||
fn get_docker_images(&self) -> Vec<(String, String, String, f32)> {
|
||||
fn get_docker_images(&self) -> Vec<(String, String, f32)> {
|
||||
let mut images = Vec::new();
|
||||
// Check if docker is available (cm-agent user is in docker group) with 3 second timeout
|
||||
let output = Command::new("timeout")
|
||||
@@ -865,9 +868,8 @@ impl SystemdCollector {
|
||||
let size_mb = self.parse_docker_size(size_str);
|
||||
|
||||
images.push((
|
||||
format!("I {}", image_name),
|
||||
image_name.to_string(),
|
||||
"inactive".to_string(), // Images are informational - use inactive for neutral display
|
||||
size_str.to_string(),
|
||||
size_mb
|
||||
));
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "cm-dashboard"
|
||||
version = "0.1.189"
|
||||
version = "0.1.196"
|
||||
edition = "2021"
|
||||
|
||||
[dependencies]
|
||||
|
||||
@@ -32,6 +32,7 @@ struct ServiceInfo {
|
||||
disk_gb: Option<f32>,
|
||||
metrics: Vec<(String, f32, Option<String>)>, // (label, value, unit)
|
||||
widget_status: Status,
|
||||
service_type: String, // "nginx_site", "container", "image", or empty for parent services
|
||||
}
|
||||
|
||||
impl ServicesWidget {
|
||||
@@ -169,7 +170,7 @@ impl ServicesWidget {
|
||||
// Convert Status enum to display text for sub-services
|
||||
match info.widget_status {
|
||||
Status::Ok => "active",
|
||||
Status::Inactive => "inactive",
|
||||
Status::Inactive => "inactive",
|
||||
Status::Critical => "failed",
|
||||
Status::Pending => "pending",
|
||||
Status::Warning => "warning",
|
||||
@@ -179,32 +180,62 @@ impl ServicesWidget {
|
||||
};
|
||||
let tree_symbol = if is_last { "└─" } else { "├─" };
|
||||
|
||||
vec![
|
||||
// Indentation and tree prefix
|
||||
ratatui::text::Span::styled(
|
||||
format!(" {} ", tree_symbol),
|
||||
Typography::tree(),
|
||||
),
|
||||
// Status icon
|
||||
ratatui::text::Span::styled(
|
||||
format!("{} ", icon),
|
||||
Style::default().fg(status_color).bg(Theme::background()),
|
||||
),
|
||||
// Service name
|
||||
ratatui::text::Span::styled(
|
||||
format!("{:<18} ", short_name),
|
||||
Style::default()
|
||||
.fg(Theme::secondary_text())
|
||||
.bg(Theme::background()),
|
||||
),
|
||||
// Status/latency text
|
||||
ratatui::text::Span::styled(
|
||||
status_str,
|
||||
Style::default()
|
||||
.fg(Theme::secondary_text())
|
||||
.bg(Theme::background()),
|
||||
),
|
||||
]
|
||||
// Docker images use docker whale icon
|
||||
if info.service_type == "image" {
|
||||
vec![
|
||||
// Indentation and tree prefix
|
||||
ratatui::text::Span::styled(
|
||||
format!(" {} ", tree_symbol),
|
||||
Typography::tree(),
|
||||
),
|
||||
// Docker icon (simple character for performance)
|
||||
ratatui::text::Span::styled(
|
||||
"D ".to_string(),
|
||||
Style::default().fg(Theme::highlight()).bg(Theme::background()),
|
||||
),
|
||||
// Service name
|
||||
ratatui::text::Span::styled(
|
||||
format!("{:<18} ", short_name),
|
||||
Style::default()
|
||||
.fg(Theme::secondary_text())
|
||||
.bg(Theme::background()),
|
||||
),
|
||||
// Status/metrics text
|
||||
ratatui::text::Span::styled(
|
||||
status_str,
|
||||
Style::default()
|
||||
.fg(Theme::secondary_text())
|
||||
.bg(Theme::background()),
|
||||
),
|
||||
]
|
||||
} else {
|
||||
vec![
|
||||
// Indentation and tree prefix
|
||||
ratatui::text::Span::styled(
|
||||
format!(" {} ", tree_symbol),
|
||||
Typography::tree(),
|
||||
),
|
||||
// Status icon
|
||||
ratatui::text::Span::styled(
|
||||
format!("{} ", icon),
|
||||
Style::default().fg(status_color).bg(Theme::background()),
|
||||
),
|
||||
// Service name
|
||||
ratatui::text::Span::styled(
|
||||
format!("{:<18} ", short_name),
|
||||
Style::default()
|
||||
.fg(Theme::secondary_text())
|
||||
.bg(Theme::background()),
|
||||
),
|
||||
// Status/latency text
|
||||
ratatui::text::Span::styled(
|
||||
status_str,
|
||||
Style::default()
|
||||
.fg(Theme::secondary_text())
|
||||
.bg(Theme::background()),
|
||||
),
|
||||
]
|
||||
}
|
||||
}
|
||||
|
||||
/// Move selection up
|
||||
@@ -282,9 +313,10 @@ impl Widget for ServicesWidget {
|
||||
disk_gb: Some(service.disk_gb),
|
||||
metrics: Vec::new(), // Parent services don't have custom metrics
|
||||
widget_status: service.service_status,
|
||||
service_type: String::new(), // Parent services have no type
|
||||
};
|
||||
self.parent_services.insert(service.name.clone(), parent_info);
|
||||
|
||||
|
||||
// Process sub-services if any
|
||||
if !service.sub_services.is_empty() {
|
||||
let mut sub_list = Vec::new();
|
||||
@@ -293,12 +325,13 @@ impl Widget for ServicesWidget {
|
||||
let metrics: Vec<(String, f32, Option<String>)> = sub_service.metrics.iter()
|
||||
.map(|m| (m.label.clone(), m.value, m.unit.clone()))
|
||||
.collect();
|
||||
|
||||
|
||||
let sub_info = ServiceInfo {
|
||||
memory_mb: None, // Not used for sub-services
|
||||
disk_gb: None, // Not used for sub-services
|
||||
metrics,
|
||||
widget_status: sub_service.service_status,
|
||||
service_type: sub_service.service_type.clone(),
|
||||
};
|
||||
sub_list.push((sub_service.name.clone(), sub_info));
|
||||
}
|
||||
@@ -342,6 +375,7 @@ impl ServicesWidget {
|
||||
disk_gb: None,
|
||||
metrics: Vec::new(),
|
||||
widget_status: Status::Unknown,
|
||||
service_type: String::new(),
|
||||
});
|
||||
|
||||
if metric.name.ends_with("_status") {
|
||||
@@ -377,6 +411,7 @@ impl ServicesWidget {
|
||||
disk_gb: None,
|
||||
metrics: Vec::new(),
|
||||
widget_status: Status::Unknown,
|
||||
service_type: String::new(), // Unknown type in legacy path
|
||||
},
|
||||
));
|
||||
&mut sub_service_list.last_mut().unwrap().1
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "cm-dashboard-shared"
|
||||
version = "0.1.189"
|
||||
version = "0.1.196"
|
||||
edition = "2021"
|
||||
|
||||
[dependencies]
|
||||
|
||||
@@ -149,6 +149,9 @@ pub struct SubServiceData {
|
||||
pub name: String,
|
||||
pub service_status: Status,
|
||||
pub metrics: Vec<SubServiceMetric>,
|
||||
/// Type of sub-service: "nginx_site", "container", "image"
|
||||
#[serde(default)]
|
||||
pub service_type: String,
|
||||
}
|
||||
|
||||
/// Individual metric for a sub-service
|
||||
|
||||
Reference in New Issue
Block a user