Compare commits
59 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 7a3ee3d5ba | |||
| 0e8b149718 | |||
| 2c27d0e1db | |||
| 9f18488752 | |||
| fab6404cca | |||
| c3626cc362 | |||
| d68ecfbc64 | |||
| d1272a6c13 | |||
| 33b3beb342 | |||
| f9384d9df6 | |||
| 156d707377 | |||
| dc1a2e3a0f | |||
| 5d6b8e6253 | |||
| 0cba083305 | |||
| a6be7a4788 | |||
| 2384f7f9b9 | |||
| cd5ef65d3d | |||
| 7bf9ca6201 | |||
| f587b42797 | |||
| 7ae464e172 | |||
| 980c9a20a2 | |||
| 448a38dede | |||
| f12e20b0f3 | |||
| 564d1f37e7 | |||
| 65bfb9f617 | |||
| 4f4ef6259b | |||
| 505263cec6 | |||
| 61dd686fb9 | |||
| c0f7a97a6f | |||
| 9575077045 | |||
| 34a1f7b9dc | |||
| d11aa11f99 | |||
| 0ca06d2507 | |||
| 6693f3a05f | |||
| de252d27b9 | |||
| db0e41a7d3 | |||
| ec460496d8 | |||
| 33e700529e | |||
| d644b7d40a | |||
| f635ba9c75 | |||
| 76b6e3373e | |||
| 0a13cab897 | |||
| d33ec5d225 | |||
| d31c2384df | |||
| c8db463204 | |||
| e8e50ef9bb | |||
| 0faed9309e | |||
| c980346d05 | |||
| 3e3d3f0c2b | |||
| 9eb7444d56 | |||
| 278d1763aa | |||
| f874264e13 | |||
| 5f6e47ece5 | |||
| 0e7cf24dbb | |||
| 2d080a2f51 | |||
| 6179bd51a7 | |||
| 57de4c366a | |||
| e18778e962 | |||
| e4469a0ebf |
@@ -113,13 +113,13 @@ jobs:
|
||||
NIX_HASH="sha256-$(python3 -c "import base64, binascii; print(base64.b64encode(binascii.unhexlify('$NEW_HASH')).decode())")"
|
||||
|
||||
# Update the NixOS configuration
|
||||
sed -i "s|version = \"v[^\"]*\"|version = \"$VERSION\"|" hosts/common/cm-dashboard.nix
|
||||
sed -i "s|sha256 = \"sha256-[^\"]*\"|sha256 = \"$NIX_HASH\"|" hosts/common/cm-dashboard.nix
|
||||
sed -i "s|version = \"v[^\"]*\"|version = \"$VERSION\"|" hosts/services/cm-dashboard.nix
|
||||
sed -i "s|sha256 = \"sha256-[^\"]*\"|sha256 = \"$NIX_HASH\"|" hosts/services/cm-dashboard.nix
|
||||
|
||||
# Commit and push changes
|
||||
git config user.name "Gitea Actions"
|
||||
git config user.email "actions@gitea.cmtec.se"
|
||||
git add hosts/common/cm-dashboard.nix
|
||||
git add hosts/services/cm-dashboard.nix
|
||||
git commit -m "Auto-update cm-dashboard to $VERSION
|
||||
|
||||
- Update version to $VERSION with automated release
|
||||
|
||||
120
CLAUDE.md
120
CLAUDE.md
@@ -49,8 +49,12 @@ hostname2 = [
|
||||
### Navigation
|
||||
- **Tab**: Switch between hosts
|
||||
- **↑↓ or j/k**: Select services
|
||||
- **s**: Start selected service (UserStart)
|
||||
- **S**: Stop selected service (UserStop)
|
||||
- **J**: Show service logs (journalctl)
|
||||
- **L**: Show custom log files
|
||||
- **R**: Rebuild current host
|
||||
- **B**: Run backup on current host
|
||||
- **q**: Quit dashboard
|
||||
|
||||
## Core Architecture Principles
|
||||
@@ -115,7 +119,7 @@ This automatically:
|
||||
- Uploads binaries via Gitea API
|
||||
|
||||
### NixOS Configuration Updates
|
||||
Edit `~/projects/nixosbox/hosts/common/cm-dashboard.nix`:
|
||||
Edit `~/projects/nixosbox/hosts/services/cm-dashboard.nix`:
|
||||
|
||||
```nix
|
||||
version = "v0.1.X";
|
||||
@@ -140,6 +144,120 @@ nix-build --no-out-link -E 'with import <nixpkgs> {}; fetchurl {
|
||||
- **Workspace builds**: `nix-shell -p openssl pkg-config --run "cargo build --workspace"`
|
||||
- **Clean compilation**: Remove `target/` between major changes
|
||||
|
||||
## Enhanced Storage Pool Visualization
|
||||
|
||||
### Auto-Discovery Architecture
|
||||
|
||||
The dashboard uses automatic storage discovery to eliminate manual configuration complexity while providing intelligent storage pool grouping.
|
||||
|
||||
### Discovery Process
|
||||
|
||||
**At Agent Startup:**
|
||||
1. Parse `/proc/mounts` to identify all mounted filesystems
|
||||
2. Detect MergerFS pools by analyzing `fuse.mergerfs` mount sources
|
||||
3. Identify member disks and potential parity relationships via heuristics
|
||||
4. Store discovered storage topology for continuous monitoring
|
||||
5. Generate pool-aware metrics with hierarchical relationships
|
||||
|
||||
**Continuous Monitoring:**
|
||||
- Use stored discovery data for efficient metric collection
|
||||
- Monitor individual drives for SMART data, temperature, wear
|
||||
- Calculate pool-level health based on member drive status
|
||||
- Generate enhanced metrics for dashboard visualization
|
||||
|
||||
### Supported Storage Types
|
||||
|
||||
**Single Disks:**
|
||||
- ext4, xfs, btrfs mounted directly
|
||||
- Individual drive monitoring with SMART data
|
||||
- Traditional single-disk display for root, boot, etc.
|
||||
|
||||
**MergerFS Pools:**
|
||||
- Auto-detect from `/proc/mounts` fuse.mergerfs entries
|
||||
- Parse source paths to identify member disks (e.g., "/mnt/disk1:/mnt/disk2")
|
||||
- Heuristic parity disk detection (sequential device names, "parity" in path)
|
||||
- Pool health calculation (healthy/degraded/critical)
|
||||
- Hierarchical tree display with data/parity disk grouping
|
||||
|
||||
**Future Extensions Ready:**
|
||||
- RAID arrays via `/proc/mdstat` parsing
|
||||
- ZFS pools via `zpool status` integration
|
||||
- LVM logical volumes via `lvs` discovery
|
||||
|
||||
### Configuration
|
||||
|
||||
```toml
|
||||
[collectors.disk]
|
||||
enabled = true
|
||||
auto_discover = true # Default: true
|
||||
# Optional exclusions for special filesystems
|
||||
exclude_mount_points = ["/tmp", "/proc", "/sys", "/dev"]
|
||||
exclude_fs_types = ["tmpfs", "devtmpfs", "sysfs", "proc"]
|
||||
```
|
||||
|
||||
### Display Format
|
||||
|
||||
```
|
||||
Storage:
|
||||
● /srv/media (mergerfs (2+1)):
|
||||
├─ Pool Status: ● Healthy (3 drives)
|
||||
├─ Total: ● 63% 2355.2GB/3686.4GB
|
||||
├─ Data Disks:
|
||||
│ ├─ ● sdb T: 24°C
|
||||
│ └─ ● sdd T: 27°C
|
||||
└─ Parity: ● sdc T: 24°C
|
||||
● /:
|
||||
├─ ● nvme0n1 W: 13%
|
||||
└─ ● 7% 14.5GB/218.5GB
|
||||
```
|
||||
|
||||
### Implementation Benefits
|
||||
|
||||
- **Zero Configuration**: No manual pool definitions required
|
||||
- **Always Accurate**: Reflects actual system state automatically
|
||||
- **Scales Automatically**: Handles any number of pools without config changes
|
||||
- **Backwards Compatible**: Single disks continue working unchanged
|
||||
- **Future Ready**: Easy extension for additional storage technologies
|
||||
|
||||
### Current Status (v0.1.100)
|
||||
|
||||
**✅ Completed:**
|
||||
- Auto-discovery system implemented and deployed
|
||||
- `/proc/mounts` parsing with smart heuristics for parity detection
|
||||
- Storage topology stored at agent startup for efficient monitoring
|
||||
- Universal zero-configuration for all hosts (cmbox, steambox, simonbox, srv01, srv02, srv03)
|
||||
- Enhanced pool health calculation (healthy/degraded/critical)
|
||||
- Hierarchical tree visualization with data/parity disk separation
|
||||
|
||||
**🔄 In Progress - Unified Pool Visualization:**
|
||||
|
||||
Current auto-discovery works but displays filesystems separately instead of grouped by physical drives. Need to implement unified pool concept where single drives are treated as pools.
|
||||
|
||||
**Current Display (needs improvement):**
|
||||
```
|
||||
● /boot: (separate entry)
|
||||
● /nix_store: (separate entry)
|
||||
● /: (separate entry)
|
||||
```
|
||||
|
||||
**Target Display (unified pools):**
|
||||
```
|
||||
● nvme0n1:
|
||||
├─ Drive: T: 35°C W: 1%
|
||||
├─ /boot: 11% 0.1GB/1.0GB
|
||||
├─ /nix_store: 23% 214.9GB/928.2GB
|
||||
└─ /: 23% 214.9GB/928.2GB
|
||||
```
|
||||
|
||||
**Required Changes:**
|
||||
1. **Enhanced Auto-Discovery**: Group filesystems by backing physical drive during discovery
|
||||
2. **UI Pool Logic**: Treat single drives as "pools" with drive name as header
|
||||
3. **Drive Info Display**: Show temperature, wear, health at pool level for single drives
|
||||
4. **Filesystem Children**: Display mount points as children under their physical drives
|
||||
5. **Hybrid Rendering**: Physical grouping for single drives, logical grouping for mergerfs pools
|
||||
|
||||
**Expected Result**: Consistent hierarchical storage visualization where everything follows pool->children pattern, regardless of underlying storage technology.
|
||||
|
||||
## Important Communication Guidelines
|
||||
|
||||
Keep responses concise and focused. Avoid extensive implementation summaries unless requested.
|
||||
|
||||
237
Cargo.lock
generated
237
Cargo.lock
generated
@@ -17,9 +17,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "aho-corasick"
|
||||
version = "1.1.3"
|
||||
version = "1.1.4"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "8e60d3430d3a69478ad0993f19238d2df97c507009a52b3c10addcd7f6bcb916"
|
||||
checksum = "ddd31a130427c27518df266943a5308ed92d4b226cc639f5a8f1002816174301"
|
||||
dependencies = [
|
||||
"memchr",
|
||||
]
|
||||
@@ -71,22 +71,22 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "anstyle-query"
|
||||
version = "1.1.4"
|
||||
version = "1.1.5"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "9e231f6134f61b71076a3eab506c379d4f36122f2af15a9ff04415ea4c3339e2"
|
||||
checksum = "40c48f72fd53cd289104fc64099abca73db4166ad86ea0b4341abe65af83dadc"
|
||||
dependencies = [
|
||||
"windows-sys 0.60.2",
|
||||
"windows-sys 0.61.2",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "anstyle-wincon"
|
||||
version = "3.0.10"
|
||||
version = "3.0.11"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "3e0633414522a32ffaac8ac6cc8f748e090c5717661fddeea04219e2344f5f2a"
|
||||
checksum = "291e6a250ff86cd4a820112fb8898808a366d8f9f58ce16d1f538353ad55747d"
|
||||
dependencies = [
|
||||
"anstyle",
|
||||
"once_cell_polyfill",
|
||||
"windows-sys 0.60.2",
|
||||
"windows-sys 0.61.2",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -95,6 +95,15 @@ version = "1.0.100"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "a23eb6b1614318a8071c9b2521f36b424b2c83db5eb3a0fead4a6c0809af6e61"
|
||||
|
||||
[[package]]
|
||||
name = "ar_archive_writer"
|
||||
version = "0.2.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "f0c269894b6fe5e9d7ada0cf69b5bf847ff35bc25fc271f08e1d080fce80339a"
|
||||
dependencies = [
|
||||
"object",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "async-trait"
|
||||
version = "0.1.89"
|
||||
@@ -144,9 +153,9 @@ checksum = "46c5e41b57b8bba42a04676d81cb89e9ee8e859a1a66f80a5a72e1cb76b34d43"
|
||||
|
||||
[[package]]
|
||||
name = "bytes"
|
||||
version = "1.10.1"
|
||||
version = "1.11.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "d71b6127be86fdcfddb610f7182ac57211d4b18a3e9c82eb2d17662f2227ad6a"
|
||||
checksum = "b35204fbdc0b3f4446b89fc1ac2cf84a8a68971995d0bf2e925ec7cd960f9cb3"
|
||||
|
||||
[[package]]
|
||||
name = "cassowary"
|
||||
@@ -156,9 +165,9 @@ checksum = "df8670b8c7b9dae1793364eafadf7239c40d669904660c5960d74cfd80b46a53"
|
||||
|
||||
[[package]]
|
||||
name = "cc"
|
||||
version = "1.2.41"
|
||||
version = "1.2.46"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "ac9fe6cdbb24b6ade63616c0a0688e45bb56732262c158df3c0c4bea4ca47cb7"
|
||||
checksum = "b97463e1064cb1b1c1384ad0a0b9c8abd0988e2a91f52606c80ef14aadb63e36"
|
||||
dependencies = [
|
||||
"find-msvc-tools",
|
||||
"jobserver",
|
||||
@@ -230,9 +239,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "clap"
|
||||
version = "4.5.49"
|
||||
version = "4.5.52"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "f4512b90fa68d3a9932cea5184017c5d200f5921df706d45e853537dea51508f"
|
||||
checksum = "aa8120877db0e5c011242f96806ce3c94e0737ab8108532a76a3300a01db2ab8"
|
||||
dependencies = [
|
||||
"clap_builder",
|
||||
"clap_derive",
|
||||
@@ -240,9 +249,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "clap_builder"
|
||||
version = "4.5.49"
|
||||
version = "4.5.52"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "0025e98baa12e766c67ba13ff4695a887a1eba19569aad00a472546795bd6730"
|
||||
checksum = "02576b399397b659c26064fbc92a75fede9d18ffd5f80ca1cd74ddab167016e1"
|
||||
dependencies = [
|
||||
"anstream",
|
||||
"anstyle",
|
||||
@@ -270,7 +279,7 @@ checksum = "a1d728cc89cf3aee9ff92b05e62b19ee65a02b5702cff7d5a377e32c6ae29d8d"
|
||||
|
||||
[[package]]
|
||||
name = "cm-dashboard"
|
||||
version = "0.1.50"
|
||||
version = "0.1.108"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"chrono",
|
||||
@@ -286,12 +295,13 @@ dependencies = [
|
||||
"toml",
|
||||
"tracing",
|
||||
"tracing-subscriber",
|
||||
"wake-on-lan",
|
||||
"zmq",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "cm-dashboard-agent"
|
||||
version = "0.1.50"
|
||||
version = "0.1.108"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"async-trait",
|
||||
@@ -314,7 +324,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "cm-dashboard-shared"
|
||||
version = "0.1.50"
|
||||
version = "0.1.108"
|
||||
dependencies = [
|
||||
"chrono",
|
||||
"serde",
|
||||
@@ -502,9 +512,9 @@ checksum = "37909eebbb50d72f9059c3b6d82c0463f2ff062c9e95845c43a6c9c0355411be"
|
||||
|
||||
[[package]]
|
||||
name = "find-msvc-tools"
|
||||
version = "0.1.4"
|
||||
version = "0.1.5"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "52051878f80a721bb68ebfbc930e07b65ba72f2da88968ea5c06fd6ca3d3a127"
|
||||
checksum = "3a3076410a55c90011c298b04d0cfa770b00fa04e1e3c97d3f6c9de105a03844"
|
||||
|
||||
[[package]]
|
||||
name = "fnv"
|
||||
@@ -767,9 +777,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "icu_collections"
|
||||
version = "2.0.0"
|
||||
version = "2.1.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "200072f5d0e3614556f94a9930d5dc3e0662a652823904c3a75dc3b0af7fee47"
|
||||
checksum = "4c6b649701667bbe825c3b7e6388cb521c23d88644678e83c0c4d0a621a34b43"
|
||||
dependencies = [
|
||||
"displaydoc",
|
||||
"potential_utf",
|
||||
@@ -780,9 +790,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "icu_locale_core"
|
||||
version = "2.0.0"
|
||||
version = "2.1.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "0cde2700ccaed3872079a65fb1a78f6c0a36c91570f28755dda67bc8f7d9f00a"
|
||||
checksum = "edba7861004dd3714265b4db54a3c390e880ab658fec5f7db895fae2046b5bb6"
|
||||
dependencies = [
|
||||
"displaydoc",
|
||||
"litemap",
|
||||
@@ -793,11 +803,10 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "icu_normalizer"
|
||||
version = "2.0.0"
|
||||
version = "2.1.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "436880e8e18df4d7bbc06d58432329d6458cc84531f7ac5f024e93deadb37979"
|
||||
checksum = "5f6c8828b67bf8908d82127b2054ea1b4427ff0230ee9141c54251934ab1b599"
|
||||
dependencies = [
|
||||
"displaydoc",
|
||||
"icu_collections",
|
||||
"icu_normalizer_data",
|
||||
"icu_properties",
|
||||
@@ -808,42 +817,38 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "icu_normalizer_data"
|
||||
version = "2.0.0"
|
||||
version = "2.1.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "00210d6893afc98edb752b664b8890f0ef174c8adbb8d0be9710fa66fbbf72d3"
|
||||
checksum = "7aedcccd01fc5fe81e6b489c15b247b8b0690feb23304303a9e560f37efc560a"
|
||||
|
||||
[[package]]
|
||||
name = "icu_properties"
|
||||
version = "2.0.1"
|
||||
version = "2.1.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "016c619c1eeb94efb86809b015c58f479963de65bdb6253345c1a1276f22e32b"
|
||||
checksum = "e93fcd3157766c0c8da2f8cff6ce651a31f0810eaa1c51ec363ef790bbb5fb99"
|
||||
dependencies = [
|
||||
"displaydoc",
|
||||
"icu_collections",
|
||||
"icu_locale_core",
|
||||
"icu_properties_data",
|
||||
"icu_provider",
|
||||
"potential_utf",
|
||||
"zerotrie",
|
||||
"zerovec",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "icu_properties_data"
|
||||
version = "2.0.1"
|
||||
version = "2.1.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "298459143998310acd25ffe6810ed544932242d3f07083eee1084d83a71bd632"
|
||||
checksum = "02845b3647bb045f1100ecd6480ff52f34c35f82d9880e029d329c21d1054899"
|
||||
|
||||
[[package]]
|
||||
name = "icu_provider"
|
||||
version = "2.0.0"
|
||||
version = "2.1.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "03c80da27b5f4187909049ee2d72f276f0d9f99a42c306bd0131ecfe04d8e5af"
|
||||
checksum = "85962cf0ce02e1e0a629cc34e7ca3e373ce20dda4c4d7294bbd0bf1fdb59e614"
|
||||
dependencies = [
|
||||
"displaydoc",
|
||||
"icu_locale_core",
|
||||
"stable_deref_trait",
|
||||
"tinystr",
|
||||
"writeable",
|
||||
"yoke",
|
||||
"zerofrom",
|
||||
@@ -884,9 +889,12 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "indoc"
|
||||
version = "2.0.6"
|
||||
version = "2.0.7"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "f4c7245a08504955605670dbf141fceab975f15ca21570696aebe9d2e71576bd"
|
||||
checksum = "79cf5c93f93228cf8efb3ba362535fb11199ac548a09ce117c9b1adc3030d706"
|
||||
dependencies = [
|
||||
"rustversion",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "ipnet"
|
||||
@@ -896,9 +904,9 @@ checksum = "469fb0b9cefa57e3ef31275ee7cacb78f2fdca44e4765491884a2b119d4eb130"
|
||||
|
||||
[[package]]
|
||||
name = "is_terminal_polyfill"
|
||||
version = "1.70.1"
|
||||
version = "1.70.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "7943c866cc5cd64cbc25b2e01621d07fa8eb2a1a23160ee81ce38704e97b8ecf"
|
||||
checksum = "a6cb138bb79a146c1bd460005623e142ef0181e3d0219cb493e02f7d08a35695"
|
||||
|
||||
[[package]]
|
||||
name = "itertools"
|
||||
@@ -927,9 +935,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "js-sys"
|
||||
version = "0.3.81"
|
||||
version = "0.3.82"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "ec48937a97411dcb524a265206ccd4c90bb711fca92b2792c407f268825b9305"
|
||||
checksum = "b011eec8cc36da2aab2d5cff675ec18454fad408585853910a202391cf9f8e65"
|
||||
dependencies = [
|
||||
"once_cell",
|
||||
"wasm-bindgen",
|
||||
@@ -987,9 +995,9 @@ checksum = "df1d3c3b53da64cf5760482273a98e575c651a67eec7f77df96b5b642de8f039"
|
||||
|
||||
[[package]]
|
||||
name = "litemap"
|
||||
version = "0.8.0"
|
||||
version = "0.8.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "241eaef5fd12c88705a01fc1066c48c4b36e0dd4377dcdc7ec3942cea7a69956"
|
||||
checksum = "6373607a59f0be73a39b6fe456b8192fcc3585f602af20751600e974dd455e77"
|
||||
|
||||
[[package]]
|
||||
name = "lock_api"
|
||||
@@ -1103,6 +1111,15 @@ dependencies = [
|
||||
"autocfg",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "object"
|
||||
version = "0.32.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "a6a622008b6e321afc04970976f62ee297fdbaa6f95318ca343e3eebb9648441"
|
||||
dependencies = [
|
||||
"memchr",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "once_cell"
|
||||
version = "1.21.3"
|
||||
@@ -1111,15 +1128,15 @@ checksum = "42f5e15c9953c5e4ccceeb2e7382a716482c34515315f7b03532b8b4e8393d2d"
|
||||
|
||||
[[package]]
|
||||
name = "once_cell_polyfill"
|
||||
version = "1.70.1"
|
||||
version = "1.70.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "a4895175b425cb1f87721b59f0f286c2092bd4af812243672510e1ac53e2e0ad"
|
||||
checksum = "384b8ab6d37215f3c5301a95a4accb5d64aa607f1fcb26a11b5303878451b4fe"
|
||||
|
||||
[[package]]
|
||||
name = "openssl"
|
||||
version = "0.10.74"
|
||||
version = "0.10.75"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "24ad14dd45412269e1a30f52ad8f0664f0f4f4a89ee8fe28c3b3527021ebb654"
|
||||
checksum = "08838db121398ad17ab8531ce9de97b244589089e290a384c900cb9ff7434328"
|
||||
dependencies = [
|
||||
"bitflags 2.10.0",
|
||||
"cfg-if",
|
||||
@@ -1149,9 +1166,9 @@ checksum = "d05e27ee213611ffe7d6348b942e8f942b37114c00cc03cec254295a4a17852e"
|
||||
|
||||
[[package]]
|
||||
name = "openssl-sys"
|
||||
version = "0.9.110"
|
||||
version = "0.9.111"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "0a9f0075ba3c21b09f8e8b2026584b1d18d49388648f2fbbf3c97ea8deced8e2"
|
||||
checksum = "82cab2d520aa75e3c58898289429321eb788c3106963d0dc886ec7a5f4adc321"
|
||||
dependencies = [
|
||||
"cc",
|
||||
"libc",
|
||||
@@ -1261,36 +1278,37 @@ checksum = "7edddbd0b52d732b21ad9a5fab5c704c14cd949e5e9a1ec5929a24fded1b904c"
|
||||
|
||||
[[package]]
|
||||
name = "potential_utf"
|
||||
version = "0.1.3"
|
||||
version = "0.1.4"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "84df19adbe5b5a0782edcab45899906947ab039ccf4573713735ee7de1e6b08a"
|
||||
checksum = "b73949432f5e2a09657003c25bca5e19a0e9c84f8058ca374f49e0ebe605af77"
|
||||
dependencies = [
|
||||
"zerovec",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "proc-macro2"
|
||||
version = "1.0.101"
|
||||
version = "1.0.103"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "89ae43fd86e4158d6db51ad8e2b80f313af9cc74f5c0e03ccb87de09998732de"
|
||||
checksum = "5ee95bc4ef87b8d5ba32e8b7714ccc834865276eab0aed5c9958d00ec45f49e8"
|
||||
dependencies = [
|
||||
"unicode-ident",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "psm"
|
||||
version = "0.1.27"
|
||||
version = "0.1.28"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "e66fcd288453b748497d8fb18bccc83a16b0518e3906d4b8df0a8d42d93dbb1c"
|
||||
checksum = "d11f2fedc3b7dafdc2851bc52f277377c5473d378859be234bc7ebb593144d01"
|
||||
dependencies = [
|
||||
"ar_archive_writer",
|
||||
"cc",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "quote"
|
||||
version = "1.0.41"
|
||||
version = "1.0.42"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "ce25767e7b499d1b604768e7cde645d14cc8584231ea6b295e9c9eb22c02e1d1"
|
||||
checksum = "a338cc41d27e6cc6dce6cefc13a0729dfbb81c262b1f519331575dd80ef3067f"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
]
|
||||
@@ -1610,9 +1628,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "signal-hook-mio"
|
||||
version = "0.2.4"
|
||||
version = "0.2.5"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "34db1a06d485c9142248b7a054f034b349b212551f3dfd19c94d45a754a217cd"
|
||||
checksum = "b75a19a7a740b25bc7944bdee6172368f988763b744e3d4dfe753f6b4ece40cc"
|
||||
dependencies = [
|
||||
"libc",
|
||||
"mio 0.8.11",
|
||||
@@ -1715,9 +1733,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "syn"
|
||||
version = "2.0.107"
|
||||
version = "2.0.110"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "2a26dbd934e5451d21ef060c018dae56fc073894c5a7896f882928a76e6d081b"
|
||||
checksum = "a99801b5bd34ede4cf3fc688c5919368fea4e4814a4664359503e6015b280aea"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
@@ -1825,9 +1843,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "tinystr"
|
||||
version = "0.8.1"
|
||||
version = "0.8.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "5d4f6d1145dcb577acf783d4e601bc1d76a13337bb54e6233add580b07344c8b"
|
||||
checksum = "42d3e9c45c09de15d06dd8acf5f4e0e399e85927b7f00711024eb7ae10fa4869"
|
||||
dependencies = [
|
||||
"displaydoc",
|
||||
"zerovec",
|
||||
@@ -1873,9 +1891,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "tokio-util"
|
||||
version = "0.7.16"
|
||||
version = "0.7.17"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "14307c986784f72ef81c89db7d9e28d6ac26d16213b109ea501696195e6e3ce5"
|
||||
checksum = "2efa149fe76073d6e8fd97ef4f4eca7b67f599660115591483572e406e165594"
|
||||
dependencies = [
|
||||
"bytes",
|
||||
"futures-core",
|
||||
@@ -2000,9 +2018,9 @@ checksum = "e421abadd41a4225275504ea4d6566923418b7f05506fbc9c0fe86ba7396114b"
|
||||
|
||||
[[package]]
|
||||
name = "unicode-ident"
|
||||
version = "1.0.19"
|
||||
version = "1.0.22"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "f63a545481291138910575129486daeaf8ac54aee4387fe7906919f7830c7d9d"
|
||||
checksum = "9312f7c4f6ff9069b165498234ce8be658059c6728633667c526e27dc2cf1df5"
|
||||
|
||||
[[package]]
|
||||
name = "unicode-segmentation"
|
||||
@@ -2054,9 +2072,9 @@ checksum = "accd4ea62f7bb7a82fe23066fb0957d48ef677f6eeb8215f372f52e48bb32426"
|
||||
|
||||
[[package]]
|
||||
name = "version-compare"
|
||||
version = "0.2.0"
|
||||
version = "0.2.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "852e951cb7832cb45cb1169900d19760cfa39b82bc0ea9c0e5a14ae88411c98b"
|
||||
checksum = "03c2856837ef78f57382f06b2b8563a2f512f7185d732608fd9176cb3b8edf0e"
|
||||
|
||||
[[package]]
|
||||
name = "version_check"
|
||||
@@ -2064,6 +2082,12 @@ version = "0.9.5"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "0b928f33d975fc6ad9f86c8f283853ad26bdd5b10b7f1542aa2fa15e2289105a"
|
||||
|
||||
[[package]]
|
||||
name = "wake-on-lan"
|
||||
version = "0.2.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "1ccf60b60ad7e5b1b37372c5134cbcab4db0706c231d212e0c643a077462bc8f"
|
||||
|
||||
[[package]]
|
||||
name = "walkdir"
|
||||
version = "2.5.0"
|
||||
@@ -2100,9 +2124,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "wasm-bindgen"
|
||||
version = "0.2.104"
|
||||
version = "0.2.105"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "c1da10c01ae9f1ae40cbfac0bac3b1e724b320abfcf52229f80b547c0d250e2d"
|
||||
checksum = "da95793dfc411fbbd93f5be7715b0578ec61fe87cb1a42b12eb625caa5c5ea60"
|
||||
dependencies = [
|
||||
"cfg-if",
|
||||
"once_cell",
|
||||
@@ -2111,25 +2135,11 @@ dependencies = [
|
||||
"wasm-bindgen-shared",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "wasm-bindgen-backend"
|
||||
version = "0.2.104"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "671c9a5a66f49d8a47345ab942e2cb93c7d1d0339065d4f8139c486121b43b19"
|
||||
dependencies = [
|
||||
"bumpalo",
|
||||
"log",
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
"syn",
|
||||
"wasm-bindgen-shared",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "wasm-bindgen-futures"
|
||||
version = "0.4.54"
|
||||
version = "0.4.55"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "7e038d41e478cc73bae0ff9b36c60cff1c98b8f38f8d7e8061e79ee63608ac5c"
|
||||
checksum = "551f88106c6d5e7ccc7cd9a16f312dd3b5d36ea8b4954304657d5dfba115d4a0"
|
||||
dependencies = [
|
||||
"cfg-if",
|
||||
"js-sys",
|
||||
@@ -2140,9 +2150,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "wasm-bindgen-macro"
|
||||
version = "0.2.104"
|
||||
version = "0.2.105"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "7ca60477e4c59f5f2986c50191cd972e3a50d8a95603bc9434501cf156a9a119"
|
||||
checksum = "04264334509e04a7bf8690f2384ef5265f05143a4bff3889ab7a3269adab59c2"
|
||||
dependencies = [
|
||||
"quote",
|
||||
"wasm-bindgen-macro-support",
|
||||
@@ -2150,31 +2160,31 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "wasm-bindgen-macro-support"
|
||||
version = "0.2.104"
|
||||
version = "0.2.105"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "9f07d2f20d4da7b26400c9f4a0511e6e0345b040694e8a75bd41d578fa4421d7"
|
||||
checksum = "420bc339d9f322e562942d52e115d57e950d12d88983a14c79b86859ee6c7ebc"
|
||||
dependencies = [
|
||||
"bumpalo",
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
"syn",
|
||||
"wasm-bindgen-backend",
|
||||
"wasm-bindgen-shared",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "wasm-bindgen-shared"
|
||||
version = "0.2.104"
|
||||
version = "0.2.105"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "bad67dc8b2a1a6e5448428adec4c3e84c43e561d8c9ee8a9e5aabeb193ec41d1"
|
||||
checksum = "76f218a38c84bcb33c25ec7059b07847d465ce0e0a76b995e134a45adcb6af76"
|
||||
dependencies = [
|
||||
"unicode-ident",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "web-sys"
|
||||
version = "0.3.81"
|
||||
version = "0.3.82"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "9367c417a924a74cae129e6a2ae3b47fabb1f8995595ab474029da749a8be120"
|
||||
checksum = "3a1f95c0d03a47f4ae1f7a64643a6bb97465d9b740f0fa8f90ea33915c99a9a1"
|
||||
dependencies = [
|
||||
"js-sys",
|
||||
"wasm-bindgen",
|
||||
@@ -2528,17 +2538,16 @@ checksum = "f17a85883d4e6d00e8a97c586de764dabcc06133f7f1d55dce5cdc070ad7fe59"
|
||||
|
||||
[[package]]
|
||||
name = "writeable"
|
||||
version = "0.6.1"
|
||||
version = "0.6.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "ea2f10b9bb0928dfb1b42b65e1f9e36f7f54dbdf08457afefb38afcdec4fa2bb"
|
||||
checksum = "9edde0db4769d2dc68579893f2306b26c6ecfbe0ef499b013d731b7b9247e0b9"
|
||||
|
||||
[[package]]
|
||||
name = "yoke"
|
||||
version = "0.8.0"
|
||||
version = "0.8.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "5f41bb01b8226ef4bfd589436a297c53d118f65921786300e427be8d487695cc"
|
||||
checksum = "72d6e5c6afb84d73944e5cedb052c4680d5657337201555f9f2a16b7406d4954"
|
||||
dependencies = [
|
||||
"serde",
|
||||
"stable_deref_trait",
|
||||
"yoke-derive",
|
||||
"zerofrom",
|
||||
@@ -2546,9 +2555,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "yoke-derive"
|
||||
version = "0.8.0"
|
||||
version = "0.8.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "38da3c9736e16c5d3c8c597a9aaa5d1fa565d0532ae05e27c24aa62fb32c0ab6"
|
||||
checksum = "b659052874eb698efe5b9e8cf382204678a0086ebf46982b79d6ca3182927e5d"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
@@ -2609,9 +2618,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "zerotrie"
|
||||
version = "0.2.2"
|
||||
version = "0.2.3"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "36f0bbd478583f79edad978b407914f61b2972f5af6fa089686016be8f9af595"
|
||||
checksum = "2a59c17a5562d507e4b54960e8569ebee33bee890c70aa3fe7b97e85a9fd7851"
|
||||
dependencies = [
|
||||
"displaydoc",
|
||||
"yoke",
|
||||
@@ -2620,9 +2629,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "zerovec"
|
||||
version = "0.11.4"
|
||||
version = "0.11.5"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "e7aa2bd55086f1ab526693ecbe444205da57e25f4489879da80635a46d90e73b"
|
||||
checksum = "6c28719294829477f525be0186d13efa9a3c602f7ec202ca9e353d310fb9a002"
|
||||
dependencies = [
|
||||
"yoke",
|
||||
"zerofrom",
|
||||
@@ -2631,9 +2640,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "zerovec-derive"
|
||||
version = "0.11.1"
|
||||
version = "0.11.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "5b96237efa0c878c64bd89c436f661be4e46b2f3eff1ebb976f7ef2321d2f58f"
|
||||
checksum = "eadce39539ca5cb3985590102671f2567e659fca9666581ad3411d59207951f3"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
|
||||
@@ -88,7 +88,9 @@ cm-dashboard • ● cmbox ● srv01 ● srv02 ● steambox
|
||||
- **s**: Start selected service (UserStart)
|
||||
- **S**: Stop selected service (UserStop)
|
||||
- **J**: Show service logs (journalctl in tmux popup)
|
||||
- **L**: Show custom log files (tail -f custom paths in tmux popup)
|
||||
- **R**: Rebuild current host
|
||||
- **B**: Run backup on current host
|
||||
- **q**: Quit
|
||||
|
||||
### Status Indicators
|
||||
@@ -173,9 +175,10 @@ subscriber_ports = [6130]
|
||||
[hosts]
|
||||
predefined_hosts = ["cmbox", "srv01", "srv02"]
|
||||
|
||||
[ui]
|
||||
ssh_user = "cm"
|
||||
[ssh]
|
||||
rebuild_user = "cm"
|
||||
rebuild_alias = "nixos-rebuild-cmtec"
|
||||
backup_alias = "cm-backup-run"
|
||||
```
|
||||
|
||||
## Technical Implementation
|
||||
@@ -329,7 +332,7 @@ This triggers automated:
|
||||
- Tarball upload to Gitea
|
||||
|
||||
### NixOS Integration
|
||||
Update `~/projects/nixosbox/hosts/common/cm-dashboard.nix`:
|
||||
Update `~/projects/nixosbox/hosts/services/cm-dashboard.nix`:
|
||||
|
||||
```nix
|
||||
version = "v0.1.43";
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "cm-dashboard-agent"
|
||||
version = "0.1.51"
|
||||
version = "0.1.109"
|
||||
edition = "2021"
|
||||
|
||||
[dependencies]
|
||||
|
||||
@@ -4,7 +4,7 @@ use std::time::Duration;
|
||||
use tokio::time::interval;
|
||||
use tracing::{debug, error, info};
|
||||
|
||||
use crate::communication::{AgentCommand, ServiceAction, ZmqHandler};
|
||||
use crate::communication::{AgentCommand, ZmqHandler};
|
||||
use crate::config::AgentConfig;
|
||||
use crate::metrics::MetricCollectionManager;
|
||||
use crate::notifications::NotificationManager;
|
||||
@@ -78,10 +78,11 @@ impl Agent {
|
||||
info!("Initial metric collection completed - all data cached and ready");
|
||||
}
|
||||
|
||||
// Separate intervals for collection, transmission, and email notifications
|
||||
// Separate intervals for collection, transmission, heartbeat, and email notifications
|
||||
let mut collection_interval =
|
||||
interval(Duration::from_secs(self.config.collection_interval_seconds));
|
||||
let mut transmission_interval = interval(Duration::from_secs(self.config.zmq.transmission_interval_seconds));
|
||||
let mut heartbeat_interval = interval(Duration::from_secs(self.config.zmq.heartbeat_interval_seconds));
|
||||
let mut notification_interval = interval(Duration::from_secs(self.config.notifications.aggregation_interval_seconds));
|
||||
|
||||
loop {
|
||||
@@ -98,6 +99,12 @@ impl Agent {
|
||||
error!("Failed to broadcast metrics: {}", e);
|
||||
}
|
||||
}
|
||||
_ = heartbeat_interval.tick() => {
|
||||
// Send standalone heartbeat for host connectivity detection
|
||||
if let Err(e) = self.send_heartbeat().await {
|
||||
error!("Failed to send heartbeat: {}", e);
|
||||
}
|
||||
}
|
||||
_ = notification_interval.tick() => {
|
||||
// Process batched email notifications (separate from dashboard updates)
|
||||
if let Err(e) = self.host_status_manager.process_pending_notifications(&mut self.notification_manager).await {
|
||||
@@ -180,6 +187,10 @@ impl Agent {
|
||||
let version_metric = self.get_agent_version_metric();
|
||||
metrics.push(version_metric);
|
||||
|
||||
// Add heartbeat metric for host connectivity detection
|
||||
let heartbeat_metric = self.get_heartbeat_metric();
|
||||
metrics.push(heartbeat_metric);
|
||||
|
||||
// Check for user-stopped services that are now active and clear their flags
|
||||
self.clear_user_stopped_flags_for_active_services(&metrics);
|
||||
|
||||
@@ -201,6 +212,12 @@ impl Agent {
|
||||
async fn process_metrics(&mut self, metrics: &[Metric]) -> bool {
|
||||
let mut status_changed = false;
|
||||
for metric in metrics {
|
||||
// Filter excluded metrics from email notification processing only
|
||||
if self.config.notifications.exclude_email_metrics.contains(&metric.name) {
|
||||
debug!("Excluding metric '{}' from email notification processing", metric.name);
|
||||
continue;
|
||||
}
|
||||
|
||||
if self.host_status_manager.process_metric(metric, &mut self.notification_manager).await {
|
||||
status_changed = true;
|
||||
}
|
||||
@@ -226,6 +243,35 @@ impl Agent {
|
||||
format!("v{}", env!("CARGO_PKG_VERSION"))
|
||||
}
|
||||
|
||||
/// Create heartbeat metric for host connectivity detection
|
||||
fn get_heartbeat_metric(&self) -> Metric {
|
||||
use std::time::{SystemTime, UNIX_EPOCH};
|
||||
|
||||
let timestamp = SystemTime::now()
|
||||
.duration_since(UNIX_EPOCH)
|
||||
.unwrap()
|
||||
.as_secs();
|
||||
|
||||
Metric::new(
|
||||
"agent_heartbeat".to_string(),
|
||||
MetricValue::Integer(timestamp as i64),
|
||||
Status::Ok,
|
||||
)
|
||||
}
|
||||
|
||||
/// Send standalone heartbeat for connectivity detection
|
||||
async fn send_heartbeat(&mut self) -> Result<()> {
|
||||
let heartbeat_metric = self.get_heartbeat_metric();
|
||||
let message = MetricMessage::new(
|
||||
self.hostname.clone(),
|
||||
vec![heartbeat_metric],
|
||||
);
|
||||
|
||||
self.zmq_handler.publish_metrics(&message).await?;
|
||||
debug!("Sent standalone heartbeat for connectivity detection");
|
||||
Ok(())
|
||||
}
|
||||
|
||||
async fn handle_commands(&mut self) -> Result<()> {
|
||||
// Try to receive commands (non-blocking)
|
||||
match self.zmq_handler.try_receive_command() {
|
||||
@@ -269,75 +315,10 @@ impl Agent {
|
||||
info!("Processing Ping command - agent is alive");
|
||||
// Could send a response back via ZMQ if needed
|
||||
}
|
||||
AgentCommand::ServiceControl { service_name, action } => {
|
||||
info!("Processing ServiceControl command: {} {:?}", service_name, action);
|
||||
if let Err(e) = self.handle_service_control(&service_name, &action).await {
|
||||
error!("Failed to execute service control: {}", e);
|
||||
}
|
||||
}
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Handle systemd service control commands
|
||||
async fn handle_service_control(&mut self, service_name: &str, action: &ServiceAction) -> Result<()> {
|
||||
let (action_str, is_user_action) = match action {
|
||||
ServiceAction::Start => ("start", false),
|
||||
ServiceAction::Stop => ("stop", false),
|
||||
ServiceAction::Status => ("status", false),
|
||||
ServiceAction::UserStart => ("start", true),
|
||||
ServiceAction::UserStop => ("stop", true),
|
||||
};
|
||||
|
||||
info!("Executing systemctl {} {} (user action: {})", action_str, service_name, is_user_action);
|
||||
|
||||
// Handle user-stopped service tracking before systemctl execution (stop only)
|
||||
match action {
|
||||
ServiceAction::UserStop => {
|
||||
info!("Marking service '{}' as user-stopped", service_name);
|
||||
if let Err(e) = self.service_tracker.mark_user_stopped(service_name) {
|
||||
error!("Failed to mark service as user-stopped: {}", e);
|
||||
} else {
|
||||
// Sync to global tracker
|
||||
UserStoppedServiceTracker::update_global(&self.service_tracker);
|
||||
}
|
||||
}
|
||||
_ => {}
|
||||
}
|
||||
|
||||
let output = tokio::process::Command::new("sudo")
|
||||
.arg("systemctl")
|
||||
.arg(action_str)
|
||||
.arg(format!("{}.service", service_name))
|
||||
.output()
|
||||
.await?;
|
||||
|
||||
if output.status.success() {
|
||||
info!("Service {} {} completed successfully", service_name, action_str);
|
||||
if !output.stdout.is_empty() {
|
||||
debug!("stdout: {}", String::from_utf8_lossy(&output.stdout));
|
||||
}
|
||||
|
||||
// Note: User-stopped flag will be cleared by systemd collector
|
||||
// when service actually reaches 'active' state, not here
|
||||
} else {
|
||||
let stderr = String::from_utf8_lossy(&output.stderr);
|
||||
error!("Service {} {} failed: {}", service_name, action_str, stderr);
|
||||
return Err(anyhow::anyhow!("systemctl {} {} failed: {}", action_str, service_name, stderr));
|
||||
}
|
||||
|
||||
// Force refresh metrics after service control to update service status
|
||||
if matches!(action, ServiceAction::Start | ServiceAction::Stop | ServiceAction::UserStart | ServiceAction::UserStop) {
|
||||
info!("Triggering immediate metric refresh after service control");
|
||||
if let Err(e) = self.collect_metrics_only().await {
|
||||
error!("Failed to refresh metrics after service control: {}", e);
|
||||
} else {
|
||||
info!("Service status refreshed immediately after {} {}", action_str, service_name);
|
||||
}
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Check metrics for user-stopped services that are now active and clear their flags
|
||||
fn clear_user_stopped_flags_for_active_services(&mut self, metrics: &[Metric]) {
|
||||
|
||||
@@ -25,6 +25,25 @@ impl BackupCollector {
|
||||
}
|
||||
|
||||
async fn read_backup_status(&self) -> Result<Option<BackupStatusToml>, CollectorError> {
|
||||
// Check if we're in maintenance mode
|
||||
if std::fs::metadata("/tmp/cm-maintenance").is_ok() {
|
||||
// Return special maintenance mode status
|
||||
let maintenance_status = BackupStatusToml {
|
||||
backup_name: "maintenance".to_string(),
|
||||
start_time: chrono::Utc::now().format("%Y-%m-%d %H:%M:%S UTC").to_string(),
|
||||
current_time: chrono::Utc::now().format("%Y-%m-%d %H:%M:%S UTC").to_string(),
|
||||
duration_seconds: 0,
|
||||
status: "pending".to_string(),
|
||||
last_updated: chrono::Utc::now().format("%Y-%m-%d %H:%M:%S UTC").to_string(),
|
||||
disk_space: None,
|
||||
disk_product_name: None,
|
||||
disk_serial_number: None,
|
||||
disk_wear_percent: None,
|
||||
services: HashMap::new(),
|
||||
};
|
||||
return Ok(Some(maintenance_status));
|
||||
}
|
||||
|
||||
// Check if backup status file exists
|
||||
if !std::path::Path::new(&self.backup_status_file).exists() {
|
||||
return Ok(None); // File doesn't exist, but this is not an error
|
||||
@@ -79,7 +98,9 @@ impl BackupCollector {
|
||||
}
|
||||
}
|
||||
"failed" => Status::Critical,
|
||||
"warning" => Status::Warning, // Backup completed with warnings
|
||||
"running" => Status::Ok, // Currently running is OK
|
||||
"pending" => Status::Pending, // Maintenance mode or backup starting
|
||||
_ => Status::Unknown,
|
||||
}
|
||||
}
|
||||
@@ -136,10 +157,12 @@ impl Collector for BackupCollector {
|
||||
name: "backup_overall_status".to_string(),
|
||||
value: MetricValue::String(match overall_status {
|
||||
Status::Ok => "ok".to_string(),
|
||||
Status::Inactive => "inactive".to_string(),
|
||||
Status::Pending => "pending".to_string(),
|
||||
Status::Warning => "warning".to_string(),
|
||||
Status::Critical => "critical".to_string(),
|
||||
Status::Unknown => "unknown".to_string(),
|
||||
Status::Offline => "offline".to_string(),
|
||||
}),
|
||||
status: overall_status,
|
||||
timestamp,
|
||||
@@ -198,10 +221,12 @@ impl Collector for BackupCollector {
|
||||
name: format!("backup_service_{}_status", service_name),
|
||||
value: MetricValue::String(match service_status {
|
||||
Status::Ok => "ok".to_string(),
|
||||
Status::Inactive => "inactive".to_string(),
|
||||
Status::Pending => "pending".to_string(),
|
||||
Status::Warning => "warning".to_string(),
|
||||
Status::Critical => "critical".to_string(),
|
||||
Status::Unknown => "unknown".to_string(),
|
||||
Status::Offline => "offline".to_string(),
|
||||
}),
|
||||
status: service_status,
|
||||
timestamp,
|
||||
@@ -375,6 +400,25 @@ impl Collector for BackupCollector {
|
||||
});
|
||||
}
|
||||
|
||||
if let Some(wear_percent) = backup_status.disk_wear_percent {
|
||||
let wear_status = if wear_percent >= 90.0 {
|
||||
Status::Critical
|
||||
} else if wear_percent >= 75.0 {
|
||||
Status::Warning
|
||||
} else {
|
||||
Status::Ok
|
||||
};
|
||||
|
||||
metrics.push(Metric {
|
||||
name: "backup_disk_wear_percent".to_string(),
|
||||
value: MetricValue::Float(wear_percent),
|
||||
status: wear_status,
|
||||
timestamp,
|
||||
description: Some("Backup disk wear percentage from SMART data".to_string()),
|
||||
unit: Some("percent".to_string()),
|
||||
});
|
||||
}
|
||||
|
||||
// Count services by status
|
||||
let mut status_counts = HashMap::new();
|
||||
for service in backup_status.services.values() {
|
||||
@@ -408,6 +452,7 @@ pub struct BackupStatusToml {
|
||||
pub disk_space: Option<DiskSpace>,
|
||||
pub disk_product_name: Option<String>,
|
||||
pub disk_serial_number: Option<String>,
|
||||
pub disk_wear_percent: Option<f32>,
|
||||
pub services: HashMap<String, ServiceStatus>,
|
||||
}
|
||||
|
||||
|
||||
@@ -5,22 +5,82 @@ use cm_dashboard_shared::{Metric, MetricValue, Status, StatusTracker, Hysteresis
|
||||
use crate::config::DiskConfig;
|
||||
use std::process::Command;
|
||||
use std::time::Instant;
|
||||
use std::fs;
|
||||
use tracing::debug;
|
||||
|
||||
use super::{Collector, CollectorError};
|
||||
|
||||
/// Mount point information from /proc/mounts
|
||||
#[derive(Debug, Clone)]
|
||||
struct MountInfo {
|
||||
device: String, // e.g., "/dev/sda1" or "/mnt/disk1:/mnt/disk2"
|
||||
mount_point: String, // e.g., "/", "/srv/media"
|
||||
fs_type: String, // e.g., "ext4", "xfs", "fuse.mergerfs"
|
||||
}
|
||||
|
||||
/// Auto-discovered storage topology
|
||||
#[derive(Debug, Clone)]
|
||||
struct StorageTopology {
|
||||
single_disks: Vec<MountInfo>,
|
||||
mergerfs_pools: Vec<MergerfsPoolInfo>,
|
||||
}
|
||||
|
||||
/// MergerFS pool information
|
||||
#[derive(Debug, Clone)]
|
||||
struct MergerfsPoolInfo {
|
||||
mount_point: String, // e.g., "/srv/media"
|
||||
data_members: Vec<String>, // e.g., ["/mnt/disk1", "/mnt/disk2"]
|
||||
parity_disks: Vec<String>, // e.g., ["/mnt/parity"]
|
||||
}
|
||||
|
||||
/// Information about a storage pool (mount point with underlying drives)
|
||||
#[derive(Debug, Clone)]
|
||||
struct StoragePool {
|
||||
name: String, // e.g., "steampool", "root"
|
||||
mount_point: String, // e.g., "/mnt/steampool", "/"
|
||||
filesystem: String, // e.g., "mergerfs", "ext4", "zfs", "btrfs"
|
||||
storage_type: String, // e.g., "mergerfs", "single", "raid", "zfs"
|
||||
pool_type: StoragePoolType, // Enhanced pool type with configuration
|
||||
size: String, // e.g., "2.5TB"
|
||||
used: String, // e.g., "2.1TB"
|
||||
available: String, // e.g., "400GB"
|
||||
usage_percent: f32, // e.g., 85.0
|
||||
underlying_drives: Vec<DriveInfo>, // Individual physical drives
|
||||
pool_health: PoolHealth, // Overall pool health status
|
||||
}
|
||||
|
||||
/// Enhanced storage pool types with specific configurations
|
||||
#[derive(Debug, Clone)]
|
||||
enum StoragePoolType {
|
||||
Single, // Traditional single disk (legacy)
|
||||
PhysicalDrive { // Physical drive with multiple filesystems
|
||||
filesystems: Vec<String>, // Mount points on this drive
|
||||
},
|
||||
MergerfsPool { // MergerFS with optional parity
|
||||
data_disks: Vec<String>, // Member disk names (sdb, sdd)
|
||||
parity_disks: Vec<String>, // Parity disk names (sdc)
|
||||
},
|
||||
#[allow(dead_code)]
|
||||
RaidArray { // Hardware RAID (future)
|
||||
level: String, // "RAID1", "RAID5", etc.
|
||||
member_disks: Vec<String>,
|
||||
spare_disks: Vec<String>,
|
||||
},
|
||||
#[allow(dead_code)]
|
||||
ZfsPool { // ZFS pool (future)
|
||||
pool_name: String,
|
||||
vdevs: Vec<String>,
|
||||
}
|
||||
}
|
||||
|
||||
/// Pool health status for redundant storage
|
||||
#[derive(Debug, Clone, Copy, PartialEq)]
|
||||
enum PoolHealth {
|
||||
Healthy, // All drives OK, parity current
|
||||
Degraded, // One drive failed or parity outdated, still functional
|
||||
Critical, // Multiple failures, data at risk
|
||||
#[allow(dead_code)]
|
||||
Rebuilding, // Actively rebuilding/scrubbing (future: SnapRAID status integration)
|
||||
Unknown, // Cannot determine status
|
||||
}
|
||||
|
||||
/// Information about an individual physical drive
|
||||
@@ -37,6 +97,7 @@ pub struct DiskCollector {
|
||||
config: DiskConfig,
|
||||
temperature_thresholds: HysteresisThresholds,
|
||||
detected_devices: std::collections::HashMap<String, Vec<String>>, // mount_point -> devices
|
||||
storage_topology: Option<StorageTopology>, // Auto-discovered storage layout
|
||||
}
|
||||
|
||||
impl DiskCollector {
|
||||
@@ -49,12 +110,57 @@ impl DiskCollector {
|
||||
5.0, // 5°C gap for recovery
|
||||
);
|
||||
|
||||
// Detect devices for all configured filesystems at startup
|
||||
// Perform auto-discovery of storage topology
|
||||
let storage_topology = match Self::auto_discover_storage() {
|
||||
Ok(topology) => {
|
||||
debug!("Auto-discovered storage topology: {} single disks, {} mergerfs pools",
|
||||
topology.single_disks.len(), topology.mergerfs_pools.len());
|
||||
Some(topology)
|
||||
}
|
||||
Err(e) => {
|
||||
debug!("Failed to auto-discover storage topology: {}", e);
|
||||
None
|
||||
}
|
||||
};
|
||||
|
||||
// Detect devices for discovered storage
|
||||
let mut detected_devices = std::collections::HashMap::new();
|
||||
for fs_config in &config.filesystems {
|
||||
if fs_config.monitor {
|
||||
if let Ok(devices) = Self::detect_device_for_mount_point_static(&fs_config.mount_point) {
|
||||
detected_devices.insert(fs_config.mount_point.clone(), devices);
|
||||
if let Some(ref topology) = storage_topology {
|
||||
// Add single disks
|
||||
for disk in &topology.single_disks {
|
||||
if let Ok(devices) = Self::detect_device_for_mount_point_static(&disk.mount_point) {
|
||||
detected_devices.insert(disk.mount_point.clone(), devices);
|
||||
}
|
||||
}
|
||||
|
||||
// Add mergerfs pools and their members
|
||||
for pool in &topology.mergerfs_pools {
|
||||
// Detect devices for the pool itself
|
||||
if let Ok(devices) = Self::detect_device_for_mount_point_static(&pool.mount_point) {
|
||||
detected_devices.insert(pool.mount_point.clone(), devices);
|
||||
}
|
||||
|
||||
// Detect devices for member disks
|
||||
for member in &pool.data_members {
|
||||
if let Ok(devices) = Self::detect_device_for_mount_point_static(member) {
|
||||
detected_devices.insert(member.clone(), devices);
|
||||
}
|
||||
}
|
||||
|
||||
// Detect devices for parity disks
|
||||
for parity in &pool.parity_disks {
|
||||
if let Ok(devices) = Self::detect_device_for_mount_point_static(parity) {
|
||||
detected_devices.insert(parity.clone(), devices);
|
||||
}
|
||||
}
|
||||
}
|
||||
} else {
|
||||
// Fallback: use legacy filesystem config detection
|
||||
for fs_config in &config.filesystems {
|
||||
if fs_config.monitor {
|
||||
if let Ok(devices) = Self::detect_device_for_mount_point_static(&fs_config.mount_point) {
|
||||
detected_devices.insert(fs_config.mount_point.clone(), devices);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -63,58 +169,431 @@ impl DiskCollector {
|
||||
config,
|
||||
temperature_thresholds,
|
||||
detected_devices,
|
||||
storage_topology,
|
||||
}
|
||||
}
|
||||
|
||||
/// Auto-discover storage topology by parsing system information
|
||||
fn auto_discover_storage() -> Result<StorageTopology> {
|
||||
let mounts = Self::parse_proc_mounts()?;
|
||||
let mut single_disks = Vec::new();
|
||||
let mut mergerfs_pools = Vec::new();
|
||||
|
||||
// Filter out unwanted filesystem types and mount points
|
||||
let exclude_fs_types = ["tmpfs", "devtmpfs", "sysfs", "proc", "cgroup", "cgroup2", "devpts"];
|
||||
let exclude_mount_prefixes = ["/proc", "/sys", "/dev", "/tmp", "/run"];
|
||||
|
||||
for mount in mounts {
|
||||
// Skip excluded filesystem types
|
||||
if exclude_fs_types.contains(&mount.fs_type.as_str()) {
|
||||
continue;
|
||||
}
|
||||
|
||||
// Skip excluded mount point prefixes
|
||||
if exclude_mount_prefixes.iter().any(|prefix| mount.mount_point.starts_with(prefix)) {
|
||||
continue;
|
||||
}
|
||||
|
||||
match mount.fs_type.as_str() {
|
||||
"fuse.mergerfs" => {
|
||||
// Parse mergerfs pool
|
||||
let data_members = Self::parse_mergerfs_sources(&mount.device);
|
||||
let parity_disks = Self::detect_parity_disks(&data_members);
|
||||
|
||||
mergerfs_pools.push(MergerfsPoolInfo {
|
||||
mount_point: mount.mount_point.clone(),
|
||||
data_members,
|
||||
parity_disks,
|
||||
});
|
||||
|
||||
debug!("Discovered mergerfs pool at {}", mount.mount_point);
|
||||
}
|
||||
"ext4" | "xfs" | "btrfs" | "ntfs" | "vfat" => {
|
||||
// Check if this mount is part of a mergerfs pool
|
||||
let is_mergerfs_member = mergerfs_pools.iter()
|
||||
.any(|pool| pool.data_members.contains(&mount.mount_point) ||
|
||||
pool.parity_disks.contains(&mount.mount_point));
|
||||
|
||||
if !is_mergerfs_member {
|
||||
debug!("Discovered single disk at {}", mount.mount_point);
|
||||
single_disks.push(mount);
|
||||
}
|
||||
}
|
||||
_ => {
|
||||
debug!("Skipping unsupported filesystem type: {}", mount.fs_type);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Ok(StorageTopology {
|
||||
single_disks,
|
||||
mergerfs_pools,
|
||||
})
|
||||
}
|
||||
|
||||
/// Parse /proc/mounts to get all mount information
|
||||
fn parse_proc_mounts() -> Result<Vec<MountInfo>> {
|
||||
let mounts_content = fs::read_to_string("/proc/mounts")?;
|
||||
let mut mounts = Vec::new();
|
||||
|
||||
for line in mounts_content.lines() {
|
||||
let parts: Vec<&str> = line.split_whitespace().collect();
|
||||
if parts.len() >= 3 {
|
||||
mounts.push(MountInfo {
|
||||
device: parts[0].to_string(),
|
||||
mount_point: parts[1].to_string(),
|
||||
fs_type: parts[2].to_string(),
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
Ok(mounts)
|
||||
}
|
||||
|
||||
/// Parse mergerfs source string to extract member paths
|
||||
fn parse_mergerfs_sources(source: &str) -> Vec<String> {
|
||||
// MergerFS source format: "/mnt/disk1:/mnt/disk2:/mnt/disk3"
|
||||
source.split(':')
|
||||
.map(|s| s.trim().to_string())
|
||||
.filter(|s| !s.is_empty())
|
||||
.collect()
|
||||
}
|
||||
|
||||
/// Detect potential parity disks based on data member heuristics
|
||||
fn detect_parity_disks(data_members: &[String]) -> Vec<String> {
|
||||
let mut parity_disks = Vec::new();
|
||||
|
||||
// Heuristic 1: Look for mount points with "parity" in the name
|
||||
if let Ok(mounts) = Self::parse_proc_mounts() {
|
||||
for mount in mounts {
|
||||
if mount.mount_point.to_lowercase().contains("parity") &&
|
||||
(mount.fs_type == "xfs" || mount.fs_type == "ext4") {
|
||||
debug!("Detected parity disk by name: {}", mount.mount_point);
|
||||
parity_disks.push(mount.mount_point);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Heuristic 2: Look for sequential device pattern
|
||||
// If data members are /mnt/disk1, /mnt/disk2, look for /mnt/disk* that's not in data
|
||||
if parity_disks.is_empty() {
|
||||
if let Some(pattern) = Self::extract_mount_pattern(data_members) {
|
||||
if let Ok(mounts) = Self::parse_proc_mounts() {
|
||||
for mount in mounts {
|
||||
if mount.mount_point.starts_with(&pattern) &&
|
||||
!data_members.contains(&mount.mount_point) &&
|
||||
(mount.fs_type == "xfs" || mount.fs_type == "ext4") {
|
||||
debug!("Detected parity disk by pattern: {}", mount.mount_point);
|
||||
parity_disks.push(mount.mount_point);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
parity_disks
|
||||
}
|
||||
|
||||
/// Extract common mount point pattern from data members
|
||||
fn extract_mount_pattern(data_members: &[String]) -> Option<String> {
|
||||
if data_members.is_empty() {
|
||||
return None;
|
||||
}
|
||||
|
||||
// Find common prefix (e.g., "/mnt/disk" from "/mnt/disk1", "/mnt/disk2")
|
||||
let first = &data_members[0];
|
||||
if let Some(last_slash) = first.rfind('/') {
|
||||
let base = &first[..last_slash + 1]; // Include the slash
|
||||
|
||||
// Check if all members share this base
|
||||
if data_members.iter().all(|member| member.starts_with(base)) {
|
||||
return Some(base.to_string());
|
||||
}
|
||||
}
|
||||
|
||||
None
|
||||
}
|
||||
|
||||
/// Calculate disk temperature status using hysteresis thresholds
|
||||
fn calculate_temperature_status(&self, metric_name: &str, temperature: f32, status_tracker: &mut StatusTracker) -> Status {
|
||||
status_tracker.calculate_with_hysteresis(metric_name, temperature, &self.temperature_thresholds)
|
||||
}
|
||||
|
||||
|
||||
/// Get configured storage pools with individual drive information
|
||||
/// Get storage pools using auto-discovered topology or fallback to configuration
|
||||
fn get_configured_storage_pools(&self) -> Result<Vec<StoragePool>> {
|
||||
if let Some(ref topology) = self.storage_topology {
|
||||
self.get_auto_discovered_storage_pools(topology)
|
||||
} else {
|
||||
self.get_legacy_configured_storage_pools()
|
||||
}
|
||||
}
|
||||
|
||||
/// Get storage pools from auto-discovered topology
|
||||
fn get_auto_discovered_storage_pools(&self, topology: &StorageTopology) -> Result<Vec<StoragePool>> {
|
||||
let mut storage_pools = Vec::new();
|
||||
|
||||
// Group single disks by physical drive for unified pool display
|
||||
let grouped_disks = self.group_filesystems_by_physical_drive(&topology.single_disks)?;
|
||||
|
||||
// Process grouped single disks (each physical drive becomes a pool)
|
||||
for (drive_name, filesystems) in grouped_disks {
|
||||
// Create a unified pool for this physical drive
|
||||
let pool = self.create_physical_drive_pool(&drive_name, &filesystems)?;
|
||||
storage_pools.push(pool);
|
||||
}
|
||||
|
||||
// IMPORTANT: Do not create individual filesystem pools when using auto-discovery
|
||||
// All single disk filesystems should be grouped into physical drive pools above
|
||||
|
||||
// Process mergerfs pools (these remain as logical pools)
|
||||
for pool_info in &topology.mergerfs_pools {
|
||||
if let Ok((total_bytes, used_bytes)) = self.get_filesystem_info(&pool_info.mount_point) {
|
||||
let available_bytes = total_bytes - used_bytes;
|
||||
let usage_percent = if total_bytes > 0 {
|
||||
(used_bytes as f64 / total_bytes as f64) * 100.0
|
||||
} else { 0.0 };
|
||||
|
||||
let size = self.bytes_to_human_readable(total_bytes);
|
||||
let used = self.bytes_to_human_readable(used_bytes);
|
||||
let available = self.bytes_to_human_readable(available_bytes);
|
||||
|
||||
// Collect all member and parity drives
|
||||
let mut all_drives = Vec::new();
|
||||
|
||||
// Add data member drives
|
||||
for member in &pool_info.data_members {
|
||||
if let Some(devices) = self.detected_devices.get(member) {
|
||||
all_drives.extend(devices.clone());
|
||||
}
|
||||
}
|
||||
|
||||
// Add parity drives
|
||||
for parity in &pool_info.parity_disks {
|
||||
if let Some(devices) = self.detected_devices.get(parity) {
|
||||
all_drives.extend(devices.clone());
|
||||
}
|
||||
}
|
||||
|
||||
let underlying_drives = self.get_drive_info_for_devices(&all_drives)?;
|
||||
|
||||
// Calculate pool health
|
||||
let pool_health = self.calculate_mergerfs_pool_health(&pool_info.data_members, &pool_info.parity_disks, &underlying_drives);
|
||||
|
||||
// Generate pool name from mount point
|
||||
let name = pool_info.mount_point.trim_start_matches('/').replace('/', "_");
|
||||
|
||||
storage_pools.push(StoragePool {
|
||||
name,
|
||||
mount_point: pool_info.mount_point.clone(),
|
||||
filesystem: "fuse.mergerfs".to_string(),
|
||||
pool_type: StoragePoolType::MergerfsPool {
|
||||
data_disks: pool_info.data_members.iter()
|
||||
.filter_map(|member| self.detected_devices.get(member).and_then(|devices| devices.first().cloned()))
|
||||
.collect(),
|
||||
parity_disks: pool_info.parity_disks.iter()
|
||||
.filter_map(|parity| self.detected_devices.get(parity).and_then(|devices| devices.first().cloned()))
|
||||
.collect(),
|
||||
},
|
||||
size,
|
||||
used,
|
||||
available,
|
||||
usage_percent: usage_percent as f32,
|
||||
underlying_drives,
|
||||
pool_health,
|
||||
});
|
||||
|
||||
debug!("Auto-discovered mergerfs pool: {} with {} data + {} parity disks",
|
||||
pool_info.mount_point, pool_info.data_members.len(), pool_info.parity_disks.len());
|
||||
}
|
||||
}
|
||||
|
||||
Ok(storage_pools)
|
||||
}
|
||||
|
||||
/// Group filesystems by their backing physical drive
|
||||
fn group_filesystems_by_physical_drive(&self, filesystems: &[MountInfo]) -> Result<std::collections::HashMap<String, Vec<MountInfo>>> {
|
||||
let mut grouped = std::collections::HashMap::new();
|
||||
|
||||
for fs in filesystems {
|
||||
// Get the physical drive name for this mount point
|
||||
if let Some(devices) = self.detected_devices.get(&fs.mount_point) {
|
||||
if let Some(device_name) = devices.first() {
|
||||
// Extract base drive name from detected device
|
||||
let drive_name = Self::extract_base_device(device_name)
|
||||
.unwrap_or_else(|| device_name.clone());
|
||||
|
||||
debug!("Grouping filesystem {} (device: {}) under drive: {}",
|
||||
fs.mount_point, device_name, drive_name);
|
||||
|
||||
grouped.entry(drive_name).or_insert_with(Vec::new).push(fs.clone());
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
debug!("Filesystem grouping result: {} drives with filesystems: {:?}",
|
||||
grouped.len(),
|
||||
grouped.keys().collect::<Vec<_>>());
|
||||
|
||||
Ok(grouped)
|
||||
}
|
||||
|
||||
/// Create a physical drive pool containing multiple filesystems
|
||||
fn create_physical_drive_pool(&self, drive_name: &str, filesystems: &[MountInfo]) -> Result<StoragePool> {
|
||||
if filesystems.is_empty() {
|
||||
return Err(anyhow::anyhow!("No filesystems for drive {}", drive_name));
|
||||
}
|
||||
|
||||
// Calculate total usage across all filesystems on this drive
|
||||
let mut total_capacity = 0u64;
|
||||
let mut total_used = 0u64;
|
||||
|
||||
for fs in filesystems {
|
||||
if let Ok((capacity, used)) = self.get_filesystem_info(&fs.mount_point) {
|
||||
total_capacity += capacity;
|
||||
total_used += used;
|
||||
}
|
||||
}
|
||||
|
||||
let total_available = total_capacity.saturating_sub(total_used);
|
||||
let usage_percent = if total_capacity > 0 {
|
||||
(total_used as f64 / total_capacity as f64) * 100.0
|
||||
} else { 0.0 };
|
||||
|
||||
// Get drive information for SMART data
|
||||
let device_names = vec![drive_name.to_string()];
|
||||
let underlying_drives = self.get_drive_info_for_devices(&device_names)?;
|
||||
|
||||
// Collect filesystem mount points for this drive
|
||||
let filesystem_mount_points: Vec<String> = filesystems.iter()
|
||||
.map(|fs| fs.mount_point.clone())
|
||||
.collect();
|
||||
|
||||
Ok(StoragePool {
|
||||
name: drive_name.to_string(),
|
||||
mount_point: format!("(physical drive)"), // Special marker for physical drives
|
||||
filesystem: "physical".to_string(),
|
||||
pool_type: StoragePoolType::PhysicalDrive {
|
||||
filesystems: filesystem_mount_points,
|
||||
},
|
||||
size: self.bytes_to_human_readable(total_capacity),
|
||||
used: self.bytes_to_human_readable(total_used),
|
||||
available: self.bytes_to_human_readable(total_available),
|
||||
usage_percent: usage_percent as f32,
|
||||
pool_health: if underlying_drives.iter().all(|d| d.health_status == "PASSED") {
|
||||
PoolHealth::Healthy
|
||||
} else {
|
||||
PoolHealth::Critical
|
||||
},
|
||||
underlying_drives,
|
||||
})
|
||||
}
|
||||
|
||||
/// Calculate pool health specifically for mergerfs pools
|
||||
fn calculate_mergerfs_pool_health(&self, data_members: &[String], parity_disks: &[String], drives: &[DriveInfo]) -> PoolHealth {
|
||||
// Get device names for data and parity drives
|
||||
let mut data_device_names = Vec::new();
|
||||
let mut parity_device_names = Vec::new();
|
||||
|
||||
for member in data_members {
|
||||
if let Some(devices) = self.detected_devices.get(member) {
|
||||
data_device_names.extend(devices.clone());
|
||||
}
|
||||
}
|
||||
|
||||
for parity in parity_disks {
|
||||
if let Some(devices) = self.detected_devices.get(parity) {
|
||||
parity_device_names.extend(devices.clone());
|
||||
}
|
||||
}
|
||||
|
||||
let failed_data = drives.iter()
|
||||
.filter(|d| data_device_names.contains(&d.device) && d.health_status != "PASSED")
|
||||
.count();
|
||||
let failed_parity = drives.iter()
|
||||
.filter(|d| parity_device_names.contains(&d.device) && d.health_status != "PASSED")
|
||||
.count();
|
||||
|
||||
match (failed_data, failed_parity) {
|
||||
(0, 0) => PoolHealth::Healthy,
|
||||
(1, 0) => PoolHealth::Degraded, // Can recover with parity
|
||||
(0, 1) => PoolHealth::Degraded, // Lost parity protection
|
||||
_ => PoolHealth::Critical, // Multiple failures
|
||||
}
|
||||
}
|
||||
|
||||
/// Fallback to legacy configuration-based storage pools
|
||||
fn get_legacy_configured_storage_pools(&self) -> Result<Vec<StoragePool>> {
|
||||
let mut storage_pools = Vec::new();
|
||||
let mut processed_pools = std::collections::HashSet::new();
|
||||
|
||||
// Legacy implementation: use filesystem configuration
|
||||
for fs_config in &self.config.filesystems {
|
||||
if !fs_config.monitor {
|
||||
continue;
|
||||
}
|
||||
|
||||
let (pool_type, skip_in_single_mode) = self.determine_pool_type(&fs_config.storage_type);
|
||||
|
||||
// Skip member disks if they're part of a pool
|
||||
if skip_in_single_mode {
|
||||
continue;
|
||||
}
|
||||
|
||||
// Check if this pool was already processed (in case of multiple member disks)
|
||||
let pool_key = match &pool_type {
|
||||
StoragePoolType::MergerfsPool { .. } => {
|
||||
// For mergerfs pools, use the main mount point
|
||||
if fs_config.fs_type == "fuse.mergerfs" {
|
||||
fs_config.mount_point.clone()
|
||||
} else {
|
||||
continue; // Skip member disks
|
||||
}
|
||||
}
|
||||
_ => fs_config.mount_point.clone()
|
||||
};
|
||||
|
||||
if processed_pools.contains(&pool_key) {
|
||||
continue;
|
||||
}
|
||||
processed_pools.insert(pool_key.clone());
|
||||
|
||||
// Get filesystem stats for the mount point
|
||||
match self.get_filesystem_info(&fs_config.mount_point) {
|
||||
Ok((total_bytes, used_bytes)) => {
|
||||
let available_bytes = total_bytes - used_bytes;
|
||||
let usage_percent = if total_bytes > 0 {
|
||||
(used_bytes as f64 / total_bytes as f64) * 100.0
|
||||
} else {
|
||||
0.0
|
||||
};
|
||||
} else { 0.0 };
|
||||
|
||||
// Convert bytes to human-readable format
|
||||
let size = self.bytes_to_human_readable(total_bytes);
|
||||
let used = self.bytes_to_human_readable(used_bytes);
|
||||
let available = self.bytes_to_human_readable(available_bytes);
|
||||
|
||||
// Get individual drive information using pre-detected devices
|
||||
let device_names = self.detected_devices.get(&fs_config.mount_point).cloned().unwrap_or_default();
|
||||
let underlying_drives = self.get_drive_info_for_devices(&device_names)?;
|
||||
// Get underlying drives based on pool type
|
||||
let underlying_drives = self.get_pool_drives(&pool_type, &fs_config.mount_point)?;
|
||||
|
||||
// Calculate pool health
|
||||
let pool_health = self.calculate_pool_health(&pool_type, &underlying_drives);
|
||||
let drive_count = underlying_drives.len();
|
||||
|
||||
storage_pools.push(StoragePool {
|
||||
name: fs_config.name.clone(),
|
||||
mount_point: fs_config.mount_point.clone(),
|
||||
filesystem: fs_config.fs_type.clone(),
|
||||
storage_type: fs_config.storage_type.clone(),
|
||||
pool_type: pool_type.clone(),
|
||||
size,
|
||||
used,
|
||||
available,
|
||||
usage_percent: usage_percent as f32,
|
||||
underlying_drives,
|
||||
pool_health,
|
||||
});
|
||||
|
||||
debug!(
|
||||
"Storage pool '{}' ({}) at {} with {} detected drives",
|
||||
fs_config.name, fs_config.storage_type, fs_config.mount_point, device_names.len()
|
||||
"Legacy configured storage pool '{}' ({:?}) at {} with {} drives, health: {:?}",
|
||||
fs_config.name, pool_type, fs_config.mount_point, drive_count, pool_health
|
||||
);
|
||||
}
|
||||
Err(e) => {
|
||||
@@ -129,6 +608,138 @@ impl DiskCollector {
|
||||
Ok(storage_pools)
|
||||
}
|
||||
|
||||
/// Determine the storage pool type from configuration
|
||||
fn determine_pool_type(&self, storage_type: &str) -> (StoragePoolType, bool) {
|
||||
match storage_type {
|
||||
"single" => (StoragePoolType::Single, false),
|
||||
"mergerfs_pool" | "mergerfs" => {
|
||||
// Find associated member disks
|
||||
let data_disks = self.find_pool_member_disks("mergerfs_member");
|
||||
let parity_disks = self.find_pool_member_disks("parity");
|
||||
(StoragePoolType::MergerfsPool { data_disks, parity_disks }, false)
|
||||
}
|
||||
"mergerfs_member" => (StoragePoolType::Single, true), // Skip, part of pool
|
||||
"parity" => (StoragePoolType::Single, true), // Skip, part of pool
|
||||
"raid1" | "raid5" | "raid6" => {
|
||||
let member_disks = self.find_pool_member_disks(&format!("{}_member", storage_type));
|
||||
(StoragePoolType::RaidArray {
|
||||
level: storage_type.to_uppercase(),
|
||||
member_disks,
|
||||
spare_disks: Vec::new()
|
||||
}, false)
|
||||
}
|
||||
_ => (StoragePoolType::Single, false) // Default to single
|
||||
}
|
||||
}
|
||||
|
||||
/// Find member disks for a specific storage type
|
||||
fn find_pool_member_disks(&self, member_type: &str) -> Vec<String> {
|
||||
let mut member_disks = Vec::new();
|
||||
|
||||
for fs_config in &self.config.filesystems {
|
||||
if fs_config.storage_type == member_type && fs_config.monitor {
|
||||
// Get device names for this mount point
|
||||
if let Some(devices) = self.detected_devices.get(&fs_config.mount_point) {
|
||||
member_disks.extend(devices.clone());
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
member_disks
|
||||
}
|
||||
|
||||
/// Get drive information for a specific pool type
|
||||
fn get_pool_drives(&self, pool_type: &StoragePoolType, mount_point: &str) -> Result<Vec<DriveInfo>> {
|
||||
match pool_type {
|
||||
StoragePoolType::Single => {
|
||||
// Single disk - use detected devices for this mount point
|
||||
let device_names = self.detected_devices.get(mount_point).cloned().unwrap_or_default();
|
||||
self.get_drive_info_for_devices(&device_names)
|
||||
}
|
||||
StoragePoolType::PhysicalDrive { .. } => {
|
||||
// Physical drive - get drive info for the drive directly (mount_point not used)
|
||||
let device_names = vec![mount_point.to_string()];
|
||||
self.get_drive_info_for_devices(&device_names)
|
||||
}
|
||||
StoragePoolType::MergerfsPool { data_disks, parity_disks } => {
|
||||
// Mergerfs pool - collect all member drives
|
||||
let mut all_disks = data_disks.clone();
|
||||
all_disks.extend(parity_disks.clone());
|
||||
self.get_drive_info_for_devices(&all_disks)
|
||||
}
|
||||
StoragePoolType::RaidArray { member_disks, spare_disks, .. } => {
|
||||
// RAID array - collect member and spare drives
|
||||
let mut all_disks = member_disks.clone();
|
||||
all_disks.extend(spare_disks.clone());
|
||||
self.get_drive_info_for_devices(&all_disks)
|
||||
}
|
||||
StoragePoolType::ZfsPool { .. } => {
|
||||
// ZFS pool - use detected devices (future implementation)
|
||||
let device_names = self.detected_devices.get(mount_point).cloned().unwrap_or_default();
|
||||
self.get_drive_info_for_devices(&device_names)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Calculate pool health based on drive status and pool type
|
||||
fn calculate_pool_health(&self, pool_type: &StoragePoolType, drives: &[DriveInfo]) -> PoolHealth {
|
||||
match pool_type {
|
||||
StoragePoolType::Single => {
|
||||
// Single disk - health is just the drive health
|
||||
if drives.is_empty() {
|
||||
PoolHealth::Unknown
|
||||
} else if drives.iter().all(|d| d.health_status == "PASSED") {
|
||||
PoolHealth::Healthy
|
||||
} else {
|
||||
PoolHealth::Critical
|
||||
}
|
||||
}
|
||||
StoragePoolType::PhysicalDrive { .. } => {
|
||||
// Physical drive - health is just the drive health (similar to Single)
|
||||
if drives.is_empty() {
|
||||
PoolHealth::Unknown
|
||||
} else if drives.iter().all(|d| d.health_status == "PASSED") {
|
||||
PoolHealth::Healthy
|
||||
} else {
|
||||
PoolHealth::Critical
|
||||
}
|
||||
}
|
||||
StoragePoolType::MergerfsPool { data_disks, parity_disks } => {
|
||||
let failed_data = drives.iter()
|
||||
.filter(|d| data_disks.contains(&d.device) && d.health_status != "PASSED")
|
||||
.count();
|
||||
let failed_parity = drives.iter()
|
||||
.filter(|d| parity_disks.contains(&d.device) && d.health_status != "PASSED")
|
||||
.count();
|
||||
|
||||
match (failed_data, failed_parity) {
|
||||
(0, 0) => PoolHealth::Healthy,
|
||||
(1, 0) => PoolHealth::Degraded, // Can recover with parity
|
||||
(0, 1) => PoolHealth::Degraded, // Lost parity protection
|
||||
_ => PoolHealth::Critical, // Multiple failures
|
||||
}
|
||||
}
|
||||
StoragePoolType::RaidArray { level, .. } => {
|
||||
let failed_drives = drives.iter().filter(|d| d.health_status != "PASSED").count();
|
||||
|
||||
// Basic RAID health logic (can be enhanced per RAID level)
|
||||
match failed_drives {
|
||||
0 => PoolHealth::Healthy,
|
||||
1 if level.contains('1') || level.contains('5') || level.contains('6') => PoolHealth::Degraded,
|
||||
_ => PoolHealth::Critical,
|
||||
}
|
||||
}
|
||||
StoragePoolType::ZfsPool { .. } => {
|
||||
// ZFS health would require zpool status parsing (future)
|
||||
if drives.iter().all(|d| d.health_status == "PASSED") {
|
||||
PoolHealth::Healthy
|
||||
} else {
|
||||
PoolHealth::Degraded
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Get drive information for a list of device names
|
||||
fn get_drive_info_for_devices(&self, device_names: &[String]) -> Result<Vec<DriveInfo>> {
|
||||
let mut drives = Vec::new();
|
||||
@@ -288,6 +899,11 @@ impl DiskCollector {
|
||||
}
|
||||
}
|
||||
|
||||
/// Convert bytes to gigabytes
|
||||
fn bytes_to_gb(&self, bytes: u64) -> f32 {
|
||||
bytes as f32 / (1024.0 * 1024.0 * 1024.0)
|
||||
}
|
||||
|
||||
/// Detect device backing a mount point using lsblk (static version for startup)
|
||||
fn detect_device_for_mount_point_static(mount_point: &str) -> Result<Vec<String>> {
|
||||
let output = Command::new("lsblk")
|
||||
@@ -448,8 +1064,8 @@ impl Collector for DiskCollector {
|
||||
let used_gb = self.parse_size_to_gb(&storage_pool.used);
|
||||
let avail_gb = self.parse_size_to_gb(&storage_pool.available);
|
||||
|
||||
// Calculate status based on configured thresholds
|
||||
let pool_status = if storage_pool.usage_percent >= self.config.usage_critical_percent {
|
||||
// Calculate status based on configured thresholds and pool health
|
||||
let usage_status = if storage_pool.usage_percent >= self.config.usage_critical_percent {
|
||||
Status::Critical
|
||||
} else if storage_pool.usage_percent >= self.config.usage_warning_percent {
|
||||
Status::Warning
|
||||
@@ -457,6 +1073,14 @@ impl Collector for DiskCollector {
|
||||
Status::Ok
|
||||
};
|
||||
|
||||
let pool_status = match storage_pool.pool_health {
|
||||
PoolHealth::Critical => Status::Critical,
|
||||
PoolHealth::Degraded => Status::Warning,
|
||||
PoolHealth::Rebuilding => Status::Warning,
|
||||
PoolHealth::Healthy => usage_status,
|
||||
PoolHealth::Unknown => Status::Unknown,
|
||||
};
|
||||
|
||||
// Storage pool info metrics
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_mount_point", pool_name),
|
||||
@@ -476,15 +1100,50 @@ impl Collector for DiskCollector {
|
||||
timestamp,
|
||||
});
|
||||
|
||||
// Enhanced pool type information
|
||||
let pool_type_str = match &storage_pool.pool_type {
|
||||
StoragePoolType::Single => "single".to_string(),
|
||||
StoragePoolType::PhysicalDrive { filesystems } => {
|
||||
format!("drive ({})", filesystems.len())
|
||||
}
|
||||
StoragePoolType::MergerfsPool { data_disks, parity_disks } => {
|
||||
format!("mergerfs ({}+{})", data_disks.len(), parity_disks.len())
|
||||
}
|
||||
StoragePoolType::RaidArray { level, member_disks, spare_disks } => {
|
||||
format!("{} ({}+{})", level, member_disks.len(), spare_disks.len())
|
||||
}
|
||||
StoragePoolType::ZfsPool { pool_name, .. } => {
|
||||
format!("zfs ({})", pool_name)
|
||||
}
|
||||
};
|
||||
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_storage_type", pool_name),
|
||||
value: MetricValue::String(storage_pool.storage_type.clone()),
|
||||
name: format!("disk_{}_pool_type", pool_name),
|
||||
value: MetricValue::String(pool_type_str.clone()),
|
||||
unit: None,
|
||||
description: Some(format!("Type: {}", storage_pool.storage_type)),
|
||||
description: Some(format!("Type: {}", pool_type_str)),
|
||||
status: Status::Ok,
|
||||
timestamp,
|
||||
});
|
||||
|
||||
// Pool health status
|
||||
let health_str = match storage_pool.pool_health {
|
||||
PoolHealth::Healthy => "healthy",
|
||||
PoolHealth::Degraded => "degraded",
|
||||
PoolHealth::Critical => "critical",
|
||||
PoolHealth::Rebuilding => "rebuilding",
|
||||
PoolHealth::Unknown => "unknown",
|
||||
};
|
||||
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_pool_health", pool_name),
|
||||
value: MetricValue::String(health_str.to_string()),
|
||||
unit: None,
|
||||
description: Some(format!("Health: {}", health_str)),
|
||||
status: pool_status,
|
||||
timestamp,
|
||||
});
|
||||
|
||||
// Storage pool size metrics
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_total_gb", pool_name),
|
||||
@@ -570,6 +1229,79 @@ impl Collector for DiskCollector {
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
// Individual filesystem metrics for PhysicalDrive pools
|
||||
if let StoragePoolType::PhysicalDrive { filesystems } = &storage_pool.pool_type {
|
||||
for filesystem_mount in filesystems {
|
||||
if let Ok((total_bytes, used_bytes)) = self.get_filesystem_info(filesystem_mount) {
|
||||
let available_bytes = total_bytes - used_bytes;
|
||||
let usage_percent = if total_bytes > 0 {
|
||||
(used_bytes as f64 / total_bytes as f64) * 100.0
|
||||
} else { 0.0 };
|
||||
|
||||
let filesystem_name = if filesystem_mount == "/" {
|
||||
"root".to_string()
|
||||
} else {
|
||||
filesystem_mount.trim_start_matches('/').replace('/', "_")
|
||||
};
|
||||
|
||||
// Calculate filesystem status based on usage
|
||||
let fs_status = if usage_percent >= self.config.usage_critical_percent as f64 {
|
||||
Status::Critical
|
||||
} else if usage_percent >= self.config.usage_warning_percent as f64 {
|
||||
Status::Warning
|
||||
} else {
|
||||
Status::Ok
|
||||
};
|
||||
|
||||
// Filesystem usage metrics
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_fs_{}_usage_percent", pool_name, filesystem_name),
|
||||
value: MetricValue::Float(usage_percent as f32),
|
||||
unit: Some("%".to_string()),
|
||||
description: Some(format!("{}: {:.0}%", filesystem_mount, usage_percent)),
|
||||
status: fs_status.clone(),
|
||||
timestamp,
|
||||
});
|
||||
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_fs_{}_used_gb", pool_name, filesystem_name),
|
||||
value: MetricValue::Float(self.bytes_to_gb(used_bytes)),
|
||||
unit: Some("GB".to_string()),
|
||||
description: Some(format!("{}: {}GB used", filesystem_mount, self.bytes_to_human_readable(used_bytes))),
|
||||
status: Status::Ok,
|
||||
timestamp,
|
||||
});
|
||||
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_fs_{}_total_gb", pool_name, filesystem_name),
|
||||
value: MetricValue::Float(self.bytes_to_gb(total_bytes)),
|
||||
unit: Some("GB".to_string()),
|
||||
description: Some(format!("{}: {}GB total", filesystem_mount, self.bytes_to_human_readable(total_bytes))),
|
||||
status: Status::Ok,
|
||||
timestamp,
|
||||
});
|
||||
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_fs_{}_available_gb", pool_name, filesystem_name),
|
||||
value: MetricValue::Float(self.bytes_to_gb(available_bytes)),
|
||||
unit: Some("GB".to_string()),
|
||||
description: Some(format!("{}: {}GB available", filesystem_mount, self.bytes_to_human_readable(available_bytes))),
|
||||
status: Status::Ok,
|
||||
timestamp,
|
||||
});
|
||||
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_fs_{}_mount_point", pool_name, filesystem_name),
|
||||
value: MetricValue::String(filesystem_mount.clone()),
|
||||
unit: None,
|
||||
description: Some(format!("Mount: {}", filesystem_mount)),
|
||||
status: Status::Ok,
|
||||
timestamp,
|
||||
});
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Add storage pool count metric
|
||||
@@ -592,5 +1324,4 @@ impl Collector for DiskCollector {
|
||||
|
||||
Ok(metrics)
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
@@ -8,7 +8,6 @@ use tracing::debug;
|
||||
|
||||
use super::{Collector, CollectorError};
|
||||
use crate::config::SystemdConfig;
|
||||
use crate::service_tracker::UserStoppedServiceTracker;
|
||||
|
||||
/// Systemd collector for monitoring systemd services
|
||||
pub struct SystemdCollector {
|
||||
@@ -357,33 +356,15 @@ impl SystemdCollector {
|
||||
/// Calculate service status, taking user-stopped services into account
|
||||
fn calculate_service_status(&self, service_name: &str, active_status: &str) -> Status {
|
||||
match active_status.to_lowercase().as_str() {
|
||||
"active" => {
|
||||
// If service is now active and was marked as user-stopped, clear the flag
|
||||
if UserStoppedServiceTracker::is_service_user_stopped(service_name) {
|
||||
debug!("Service '{}' is now active - clearing user-stopped flag", service_name);
|
||||
// Note: We can't directly clear here because this is a read-only context
|
||||
// The agent will need to handle this differently
|
||||
}
|
||||
Status::Ok
|
||||
},
|
||||
"active" => Status::Ok,
|
||||
"inactive" | "dead" => {
|
||||
// Check if this service was stopped by user action
|
||||
if UserStoppedServiceTracker::is_service_user_stopped(service_name) {
|
||||
debug!("Service '{}' is inactive but marked as user-stopped - treating as OK", service_name);
|
||||
Status::Ok
|
||||
} else {
|
||||
Status::Warning
|
||||
}
|
||||
debug!("Service '{}' is inactive - treating as Inactive status", service_name);
|
||||
Status::Inactive
|
||||
},
|
||||
"failed" | "error" => Status::Critical,
|
||||
"activating" | "deactivating" | "reloading" | "start" | "stop" | "restart" => {
|
||||
// For user-stopped services that are transitioning, keep them as OK during transition
|
||||
if UserStoppedServiceTracker::is_service_user_stopped(service_name) {
|
||||
debug!("Service '{}' is transitioning but was user-stopped - treating as OK", service_name);
|
||||
Status::Ok
|
||||
} else {
|
||||
Status::Pending
|
||||
}
|
||||
debug!("Service '{}' is transitioning - treating as Pending", service_name);
|
||||
Status::Pending
|
||||
},
|
||||
_ => Status::Unknown,
|
||||
}
|
||||
|
||||
@@ -66,8 +66,6 @@ impl ZmqHandler {
|
||||
}
|
||||
|
||||
|
||||
/// Send heartbeat (placeholder for future use)
|
||||
|
||||
/// Try to receive a command (non-blocking)
|
||||
pub fn try_receive_command(&self) -> Result<Option<AgentCommand>> {
|
||||
match self.command_receiver.recv_bytes(zmq::DONTWAIT) {
|
||||
@@ -100,19 +98,4 @@ pub enum AgentCommand {
|
||||
ToggleCollector { name: String, enabled: bool },
|
||||
/// Request status/health check
|
||||
Ping,
|
||||
/// Control systemd service
|
||||
ServiceControl {
|
||||
service_name: String,
|
||||
action: ServiceAction,
|
||||
},
|
||||
}
|
||||
|
||||
/// Service control actions
|
||||
#[derive(Debug, Clone, serde::Deserialize, serde::Serialize)]
|
||||
pub enum ServiceAction {
|
||||
Start,
|
||||
Stop,
|
||||
Status,
|
||||
UserStart, // User-initiated start (clears user-stopped flag)
|
||||
UserStop, // User-initiated stop (marks as user-stopped)
|
||||
}
|
||||
|
||||
@@ -25,9 +25,10 @@ pub struct ZmqConfig {
|
||||
pub publisher_port: u16,
|
||||
pub command_port: u16,
|
||||
pub bind_address: String,
|
||||
pub timeout_ms: u64,
|
||||
pub heartbeat_interval_ms: u64,
|
||||
pub transmission_interval_seconds: u64,
|
||||
/// Heartbeat transmission interval in seconds for host connectivity detection
|
||||
#[serde(default = "default_heartbeat_interval_seconds")]
|
||||
pub heartbeat_interval_seconds: u64,
|
||||
}
|
||||
|
||||
/// Collector configuration
|
||||
@@ -146,9 +147,23 @@ pub struct NotificationConfig {
|
||||
pub rate_limit_minutes: u64,
|
||||
/// Email notification batching interval in seconds (default: 60)
|
||||
pub aggregation_interval_seconds: u64,
|
||||
/// List of metric names to exclude from email notifications
|
||||
#[serde(default)]
|
||||
pub exclude_email_metrics: Vec<String>,
|
||||
/// Path to maintenance mode file that suppresses email notifications when present
|
||||
#[serde(default = "default_maintenance_mode_file")]
|
||||
pub maintenance_mode_file: String,
|
||||
}
|
||||
|
||||
|
||||
fn default_heartbeat_interval_seconds() -> u64 {
|
||||
5
|
||||
}
|
||||
|
||||
fn default_maintenance_mode_file() -> String {
|
||||
"/tmp/cm-maintenance".to_string()
|
||||
}
|
||||
|
||||
impl AgentConfig {
|
||||
pub fn from_file<P: AsRef<Path>>(path: P) -> Result<Self> {
|
||||
loader::load_config(path)
|
||||
|
||||
@@ -19,10 +19,6 @@ pub fn validate_config(config: &AgentConfig) -> Result<()> {
|
||||
bail!("ZMQ bind address cannot be empty");
|
||||
}
|
||||
|
||||
if config.zmq.timeout_ms == 0 {
|
||||
bail!("ZMQ timeout cannot be 0");
|
||||
}
|
||||
|
||||
// Validate collection interval
|
||||
if config.collection_interval_seconds == 0 {
|
||||
bail!("Collection interval cannot be 0");
|
||||
|
||||
@@ -59,6 +59,6 @@ impl NotificationManager {
|
||||
}
|
||||
|
||||
fn is_maintenance_mode(&self) -> bool {
|
||||
std::fs::metadata("/tmp/cm-maintenance").is_ok()
|
||||
std::fs::metadata(&self.config.maintenance_mode_file).is_ok()
|
||||
}
|
||||
}
|
||||
@@ -90,14 +90,6 @@ impl UserStoppedServiceTracker {
|
||||
tracker
|
||||
}
|
||||
|
||||
/// Mark a service as user-stopped
|
||||
pub fn mark_user_stopped(&mut self, service_name: &str) -> Result<()> {
|
||||
info!("Marking service '{}' as user-stopped", service_name);
|
||||
self.user_stopped_services.insert(service_name.to_string());
|
||||
self.save_to_storage()?;
|
||||
debug!("Service '{}' marked as user-stopped and saved to storage", service_name);
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Clear user-stopped flag for a service (when user starts it)
|
||||
pub fn clear_user_stopped(&mut self, service_name: &str) -> Result<()> {
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "cm-dashboard"
|
||||
version = "0.1.51"
|
||||
version = "0.1.109"
|
||||
edition = "2021"
|
||||
|
||||
[dependencies]
|
||||
@@ -18,4 +18,5 @@ tracing-subscriber = { workspace = true }
|
||||
ratatui = { workspace = true }
|
||||
crossterm = { workspace = true }
|
||||
toml = { workspace = true }
|
||||
gethostname = { workspace = true }
|
||||
gethostname = { workspace = true }
|
||||
wake-on-lan = "0.2"
|
||||
@@ -9,20 +9,19 @@ use std::io;
|
||||
use std::time::{Duration, Instant};
|
||||
use tracing::{debug, error, info, warn};
|
||||
|
||||
use crate::communication::{AgentCommand, ServiceAction, ZmqCommandSender, ZmqConsumer};
|
||||
use crate::communication::{ZmqConsumer};
|
||||
use crate::config::DashboardConfig;
|
||||
use crate::metrics::MetricStore;
|
||||
use crate::ui::{TuiApp, UiCommand};
|
||||
use crate::ui::TuiApp;
|
||||
|
||||
pub struct Dashboard {
|
||||
zmq_consumer: ZmqConsumer,
|
||||
zmq_command_sender: ZmqCommandSender,
|
||||
metric_store: MetricStore,
|
||||
tui_app: Option<TuiApp>,
|
||||
terminal: Option<Terminal<CrosstermBackend<io::Stdout>>>,
|
||||
headless: bool,
|
||||
initial_commands_sent: std::collections::HashSet<String>,
|
||||
_config: DashboardConfig,
|
||||
config: DashboardConfig,
|
||||
}
|
||||
|
||||
impl Dashboard {
|
||||
@@ -58,20 +57,9 @@ impl Dashboard {
|
||||
}
|
||||
};
|
||||
|
||||
// Initialize ZMQ command sender
|
||||
let zmq_command_sender = match ZmqCommandSender::new(&config.zmq) {
|
||||
Ok(sender) => sender,
|
||||
Err(e) => {
|
||||
error!("Failed to initialize ZMQ command sender: {}", e);
|
||||
return Err(e);
|
||||
}
|
||||
};
|
||||
|
||||
// Connect to predefined hosts from configuration
|
||||
let hosts = config.hosts.predefined_hosts.clone();
|
||||
|
||||
// Try to connect to hosts but don't fail if none are available
|
||||
match zmq_consumer.connect_to_predefined_hosts(&hosts).await {
|
||||
match zmq_consumer.connect_to_predefined_hosts(&config.hosts).await {
|
||||
Ok(_) => info!("Successfully connected to ZMQ hosts"),
|
||||
Err(e) => {
|
||||
warn!(
|
||||
@@ -127,28 +115,23 @@ impl Dashboard {
|
||||
|
||||
Ok(Self {
|
||||
zmq_consumer,
|
||||
zmq_command_sender,
|
||||
metric_store,
|
||||
tui_app,
|
||||
terminal,
|
||||
headless,
|
||||
initial_commands_sent: std::collections::HashSet::new(),
|
||||
_config: config,
|
||||
config,
|
||||
})
|
||||
}
|
||||
|
||||
/// Send a command to a specific agent
|
||||
pub async fn send_command(&mut self, hostname: &str, command: AgentCommand) -> Result<()> {
|
||||
self.zmq_command_sender
|
||||
.send_command(hostname, command)
|
||||
.await
|
||||
}
|
||||
|
||||
pub async fn run(&mut self) -> Result<()> {
|
||||
info!("Starting dashboard main loop");
|
||||
|
||||
let mut last_metrics_check = Instant::now();
|
||||
let metrics_check_interval = Duration::from_millis(100); // Check for metrics every 100ms
|
||||
let mut last_heartbeat_check = Instant::now();
|
||||
let heartbeat_check_interval = Duration::from_secs(1); // Check for host connectivity every 1 second
|
||||
|
||||
loop {
|
||||
// Handle terminal events (keyboard input) only if not headless
|
||||
@@ -158,16 +141,10 @@ impl Dashboard {
|
||||
match event::read() {
|
||||
Ok(event) => {
|
||||
if let Some(ref mut tui_app) = self.tui_app {
|
||||
// Handle input and check for commands
|
||||
// Handle input
|
||||
match tui_app.handle_input(event) {
|
||||
Ok(Some(command)) => {
|
||||
// Execute the command
|
||||
if let Err(e) = self.execute_ui_command(command).await {
|
||||
error!("Failed to execute UI command: {}", e);
|
||||
}
|
||||
}
|
||||
Ok(None) => {
|
||||
// No command, check if we should quit
|
||||
Ok(_) => {
|
||||
// Check if we should quit
|
||||
if tui_app.should_quit() {
|
||||
info!("Quit requested, exiting dashboard");
|
||||
break;
|
||||
@@ -191,6 +168,17 @@ impl Dashboard {
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
// Render UI immediately after handling input for responsive feedback
|
||||
if let Some(ref mut terminal) = self.terminal {
|
||||
if let Some(ref mut tui_app) = self.tui_app {
|
||||
if let Err(e) = terminal.draw(|frame| {
|
||||
tui_app.render(frame, &self.metric_store);
|
||||
}) {
|
||||
error!("Error rendering TUI after input: {}", e);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Check for new metrics
|
||||
@@ -202,34 +190,18 @@ impl Dashboard {
|
||||
metric_message.metrics.len()
|
||||
);
|
||||
|
||||
// Check if this is the first time we've seen this host
|
||||
// Track first contact with host (no command needed - agent sends data every 2s)
|
||||
let is_new_host = !self
|
||||
.initial_commands_sent
|
||||
.contains(&metric_message.hostname);
|
||||
|
||||
if is_new_host {
|
||||
info!(
|
||||
"First contact with host {}, sending initial CollectNow command",
|
||||
"First contact with host {} - data will update automatically",
|
||||
metric_message.hostname
|
||||
);
|
||||
|
||||
// Send CollectNow command for immediate refresh
|
||||
if let Err(e) = self
|
||||
.send_command(&metric_message.hostname, AgentCommand::CollectNow)
|
||||
.await
|
||||
{
|
||||
error!(
|
||||
"Failed to send initial CollectNow command to {}: {}",
|
||||
metric_message.hostname, e
|
||||
);
|
||||
} else {
|
||||
info!(
|
||||
"✓ Sent initial CollectNow command to {}",
|
||||
metric_message.hostname
|
||||
);
|
||||
self.initial_commands_sent
|
||||
.insert(metric_message.hostname.clone());
|
||||
}
|
||||
self.initial_commands_sent
|
||||
.insert(metric_message.hostname.clone());
|
||||
}
|
||||
|
||||
// Update metric store
|
||||
@@ -243,14 +215,8 @@ impl Dashboard {
|
||||
}
|
||||
}
|
||||
|
||||
// Update TUI with new hosts and metrics (only if not headless)
|
||||
// Update TUI with new metrics (only if not headless)
|
||||
if let Some(ref mut tui_app) = self.tui_app {
|
||||
let connected_hosts = self
|
||||
.metric_store
|
||||
.get_connected_hosts(Duration::from_secs(30));
|
||||
|
||||
|
||||
tui_app.update_hosts(connected_hosts);
|
||||
tui_app.update_metrics(&self.metric_store);
|
||||
}
|
||||
}
|
||||
@@ -269,6 +235,20 @@ impl Dashboard {
|
||||
last_metrics_check = Instant::now();
|
||||
}
|
||||
|
||||
// Check for host connectivity changes (heartbeat timeouts) periodically
|
||||
if last_heartbeat_check.elapsed() >= heartbeat_check_interval {
|
||||
let timeout = Duration::from_secs(self.config.zmq.heartbeat_timeout_seconds);
|
||||
|
||||
// Clean up metrics for offline hosts
|
||||
self.metric_store.cleanup_offline_hosts(timeout);
|
||||
|
||||
if let Some(ref mut tui_app) = self.tui_app {
|
||||
let connected_hosts = self.metric_store.get_connected_hosts(timeout);
|
||||
tui_app.update_hosts(connected_hosts);
|
||||
}
|
||||
last_heartbeat_check = Instant::now();
|
||||
}
|
||||
|
||||
// Render TUI (only if not headless)
|
||||
if !self.headless {
|
||||
if let Some(ref mut terminal) = self.terminal {
|
||||
@@ -291,33 +271,6 @@ impl Dashboard {
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Execute a UI command by sending it to the appropriate agent
|
||||
async fn execute_ui_command(&self, command: UiCommand) -> Result<()> {
|
||||
match command {
|
||||
UiCommand::ServiceStart { hostname, service_name } => {
|
||||
info!("Sending user start command for service {} on {}", service_name, hostname);
|
||||
let agent_command = AgentCommand::ServiceControl {
|
||||
service_name: service_name.clone(),
|
||||
action: ServiceAction::UserStart,
|
||||
};
|
||||
self.zmq_command_sender.send_command(&hostname, agent_command).await?;
|
||||
}
|
||||
UiCommand::ServiceStop { hostname, service_name } => {
|
||||
info!("Sending user stop command for service {} on {}", service_name, hostname);
|
||||
let agent_command = AgentCommand::ServiceControl {
|
||||
service_name: service_name.clone(),
|
||||
action: ServiceAction::UserStop,
|
||||
};
|
||||
self.zmq_command_sender.send_command(&hostname, agent_command).await?;
|
||||
}
|
||||
UiCommand::TriggerBackup { hostname } => {
|
||||
info!("Trigger backup requested for {}", hostname);
|
||||
// TODO: Implement backup trigger command
|
||||
info!("Backup trigger not yet implemented");
|
||||
}
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
|
||||
@@ -5,40 +5,6 @@ use zmq::{Context, Socket, SocketType};
|
||||
|
||||
use crate::config::ZmqConfig;
|
||||
|
||||
/// Commands that can be sent to agents
|
||||
#[derive(Debug, Clone, serde::Deserialize, serde::Serialize)]
|
||||
pub enum AgentCommand {
|
||||
/// Request immediate metric collection
|
||||
CollectNow,
|
||||
/// Change collection interval
|
||||
SetInterval { seconds: u64 },
|
||||
/// Enable/disable a collector
|
||||
ToggleCollector { name: String, enabled: bool },
|
||||
/// Request status/health check
|
||||
Ping,
|
||||
/// Control systemd service
|
||||
ServiceControl {
|
||||
service_name: String,
|
||||
action: ServiceAction,
|
||||
},
|
||||
/// Rebuild NixOS system
|
||||
SystemRebuild {
|
||||
git_url: String,
|
||||
git_branch: String,
|
||||
working_dir: String,
|
||||
api_key_file: Option<String>,
|
||||
},
|
||||
}
|
||||
|
||||
/// Service control actions
|
||||
#[derive(Debug, Clone, serde::Deserialize, serde::Serialize)]
|
||||
pub enum ServiceAction {
|
||||
Start,
|
||||
Stop,
|
||||
Status,
|
||||
UserStart, // User-initiated start (clears user-stopped flag)
|
||||
UserStop, // User-initiated stop (marks as user-stopped)
|
||||
}
|
||||
|
||||
/// ZMQ consumer for receiving metrics from agents
|
||||
pub struct ZmqConsumer {
|
||||
@@ -84,13 +50,14 @@ impl ZmqConsumer {
|
||||
}
|
||||
}
|
||||
|
||||
/// Connect to predefined hosts
|
||||
pub async fn connect_to_predefined_hosts(&mut self, hosts: &[String]) -> Result<()> {
|
||||
|
||||
/// Connect to predefined hosts using their configuration
|
||||
pub async fn connect_to_predefined_hosts(&mut self, hosts: &std::collections::HashMap<String, crate::config::HostDetails>) -> Result<()> {
|
||||
let default_port = self.config.subscriber_ports[0];
|
||||
|
||||
for hostname in hosts {
|
||||
// Try to connect, but don't fail if some hosts are unreachable
|
||||
if let Err(e) = self.connect_to_host(hostname, default_port).await {
|
||||
for (hostname, host_details) in hosts {
|
||||
// Try to connect using configured IP, but don't fail if some hosts are unreachable
|
||||
if let Err(e) = self.connect_to_host_with_details(hostname, host_details, default_port).await {
|
||||
warn!("Could not connect to {}: {}", hostname, e);
|
||||
}
|
||||
}
|
||||
@@ -104,6 +71,15 @@ impl ZmqConsumer {
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Connect to a host using its configuration details
|
||||
pub async fn connect_to_host_with_details(&mut self, hostname: &str, host_details: &crate::config::HostDetails, port: u16) -> Result<()> {
|
||||
// Get primary connection IP only - no fallbacks
|
||||
let primary_ip = host_details.get_connection_ip(hostname);
|
||||
|
||||
// Connect directly without fallback attempts
|
||||
self.connect_to_host(&primary_ip, port).await
|
||||
}
|
||||
|
||||
/// Receive command output from any connected agent (non-blocking)
|
||||
pub async fn receive_command_output(&mut self) -> Result<Option<CommandOutputMessage>> {
|
||||
match self.subscriber.recv_bytes(zmq::DONTWAIT) {
|
||||
@@ -192,42 +168,3 @@ impl ZmqConsumer {
|
||||
}
|
||||
}
|
||||
|
||||
/// ZMQ command sender for sending commands to agents
|
||||
pub struct ZmqCommandSender {
|
||||
context: Context,
|
||||
}
|
||||
|
||||
impl ZmqCommandSender {
|
||||
pub fn new(_config: &ZmqConfig) -> Result<Self> {
|
||||
let context = Context::new();
|
||||
|
||||
info!("ZMQ command sender initialized");
|
||||
|
||||
Ok(Self { context })
|
||||
}
|
||||
|
||||
/// Send a command to a specific agent
|
||||
pub async fn send_command(&self, hostname: &str, command: AgentCommand) -> Result<()> {
|
||||
// Create a new PUSH socket for this command (ZMQ best practice)
|
||||
let socket = self.context.socket(SocketType::PUSH)?;
|
||||
|
||||
// Set socket options
|
||||
socket.set_linger(1000)?; // Wait up to 1 second on close
|
||||
socket.set_sndtimeo(5000)?; // 5 second send timeout
|
||||
|
||||
// Connect to agent's command port (6131)
|
||||
let address = format!("tcp://{}:6131", hostname);
|
||||
socket.connect(&address)?;
|
||||
|
||||
// Serialize command
|
||||
let serialized = serde_json::to_vec(&command)?;
|
||||
|
||||
// Send command
|
||||
socket.send(&serialized, 0)?;
|
||||
|
||||
info!("Sent command {:?} to agent at {}", command, hostname);
|
||||
|
||||
// Socket will be automatically closed when dropped
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
|
||||
@@ -6,7 +6,7 @@ use std::path::Path;
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct DashboardConfig {
|
||||
pub zmq: ZmqConfig,
|
||||
pub hosts: HostsConfig,
|
||||
pub hosts: std::collections::HashMap<String, HostDetails>,
|
||||
pub system: SystemConfig,
|
||||
pub ssh: SshConfig,
|
||||
pub service_logs: std::collections::HashMap<String, Vec<ServiceLogConfig>>,
|
||||
@@ -16,12 +16,30 @@ pub struct DashboardConfig {
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct ZmqConfig {
|
||||
pub subscriber_ports: Vec<u16>,
|
||||
/// Heartbeat timeout in seconds - hosts considered offline if no heartbeat received within this time
|
||||
#[serde(default = "default_heartbeat_timeout_seconds")]
|
||||
pub heartbeat_timeout_seconds: u64,
|
||||
}
|
||||
|
||||
/// Hosts configuration
|
||||
fn default_heartbeat_timeout_seconds() -> u64 {
|
||||
10 // Default to 10 seconds - allows for multiple missed heartbeats
|
||||
}
|
||||
|
||||
/// Individual host configuration details
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct HostsConfig {
|
||||
pub predefined_hosts: Vec<String>,
|
||||
pub struct HostDetails {
|
||||
pub mac_address: Option<String>,
|
||||
/// Primary IP address (local network)
|
||||
pub ip: Option<String>,
|
||||
}
|
||||
|
||||
|
||||
impl HostDetails {
|
||||
/// Get the IP address for connection (uses ip field or hostname as fallback)
|
||||
pub fn get_connection_ip(&self, hostname: &str) -> String {
|
||||
self.ip.as_ref().unwrap_or(&hostname.to_string()).clone()
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
/// System configuration
|
||||
@@ -33,11 +51,12 @@ pub struct SystemConfig {
|
||||
pub nixos_config_api_key_file: Option<String>,
|
||||
}
|
||||
|
||||
/// SSH configuration for rebuild operations
|
||||
/// SSH configuration for rebuild and backup operations
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct SshConfig {
|
||||
pub rebuild_user: String,
|
||||
pub rebuild_alias: String,
|
||||
pub rebuild_cmd: String,
|
||||
pub service_manage_cmd: String,
|
||||
}
|
||||
|
||||
/// Service log file configuration per host
|
||||
@@ -68,8 +87,3 @@ impl Default for ZmqConfig {
|
||||
}
|
||||
}
|
||||
|
||||
impl Default for HostsConfig {
|
||||
fn default() -> Self {
|
||||
panic!("Dashboard configuration must be loaded from file - no hardcoded defaults allowed")
|
||||
}
|
||||
}
|
||||
|
||||
@@ -11,8 +11,8 @@ pub struct MetricStore {
|
||||
current_metrics: HashMap<String, HashMap<String, Metric>>,
|
||||
/// Historical metrics for trending
|
||||
historical_metrics: HashMap<String, Vec<MetricDataPoint>>,
|
||||
/// Last update timestamp per host
|
||||
last_update: HashMap<String, Instant>,
|
||||
/// Last heartbeat timestamp per host
|
||||
last_heartbeat: HashMap<String, Instant>,
|
||||
/// Configuration
|
||||
max_metrics_per_host: usize,
|
||||
history_retention: Duration,
|
||||
@@ -23,7 +23,7 @@ impl MetricStore {
|
||||
Self {
|
||||
current_metrics: HashMap::new(),
|
||||
historical_metrics: HashMap::new(),
|
||||
last_update: HashMap::new(),
|
||||
last_heartbeat: HashMap::new(),
|
||||
max_metrics_per_host,
|
||||
history_retention: Duration::from_secs(history_retention_hours * 3600),
|
||||
}
|
||||
@@ -56,10 +56,13 @@ impl MetricStore {
|
||||
|
||||
// Add to history
|
||||
host_history.push(MetricDataPoint { received_at: now });
|
||||
}
|
||||
|
||||
// Update last update timestamp
|
||||
self.last_update.insert(hostname.to_string(), now);
|
||||
// Track heartbeat metrics for connectivity detection
|
||||
if metric_name == "agent_heartbeat" {
|
||||
self.last_heartbeat.insert(hostname.to_string(), now);
|
||||
debug!("Updated heartbeat for host {}", hostname);
|
||||
}
|
||||
}
|
||||
|
||||
// Get metrics count before cleanup
|
||||
let metrics_count = host_metrics.len();
|
||||
@@ -88,22 +91,46 @@ impl MetricStore {
|
||||
}
|
||||
}
|
||||
|
||||
/// Get connected hosts (hosts with recent updates)
|
||||
/// Get connected hosts (hosts with recent heartbeats)
|
||||
pub fn get_connected_hosts(&self, timeout: Duration) -> Vec<String> {
|
||||
let now = Instant::now();
|
||||
|
||||
self.last_update
|
||||
self.last_heartbeat
|
||||
.iter()
|
||||
.filter_map(|(hostname, &last_update)| {
|
||||
if now.duration_since(last_update) <= timeout {
|
||||
.filter_map(|(hostname, &last_heartbeat)| {
|
||||
if now.duration_since(last_heartbeat) <= timeout {
|
||||
Some(hostname.clone())
|
||||
} else {
|
||||
debug!("Host {} considered offline - last heartbeat was {:?} ago",
|
||||
hostname, now.duration_since(last_heartbeat));
|
||||
None
|
||||
}
|
||||
})
|
||||
.collect()
|
||||
}
|
||||
|
||||
/// Clean up data for offline hosts
|
||||
pub fn cleanup_offline_hosts(&mut self, timeout: Duration) {
|
||||
let now = Instant::now();
|
||||
let mut hosts_to_cleanup = Vec::new();
|
||||
|
||||
// Find hosts that are offline (no recent heartbeat)
|
||||
for (hostname, &last_heartbeat) in &self.last_heartbeat {
|
||||
if now.duration_since(last_heartbeat) > timeout {
|
||||
hosts_to_cleanup.push(hostname.clone());
|
||||
}
|
||||
}
|
||||
|
||||
// Clear metrics for offline hosts
|
||||
for hostname in hosts_to_cleanup {
|
||||
if let Some(metrics) = self.current_metrics.remove(&hostname) {
|
||||
info!("Cleared {} metrics for offline host: {}", metrics.len(), hostname);
|
||||
}
|
||||
// Keep heartbeat timestamp for reconnection detection
|
||||
// Don't remove from last_heartbeat to track when host was last seen
|
||||
}
|
||||
}
|
||||
|
||||
/// Cleanup old data and enforce limits
|
||||
fn cleanup_host_data(&mut self, hostname: &str) {
|
||||
let now = Instant::now();
|
||||
|
||||
@@ -9,32 +9,19 @@ use ratatui::{
|
||||
use std::collections::HashMap;
|
||||
use std::time::Instant;
|
||||
use tracing::info;
|
||||
use wake_on_lan::MagicPacket;
|
||||
|
||||
pub mod theme;
|
||||
pub mod widgets;
|
||||
|
||||
use crate::config::DashboardConfig;
|
||||
use crate::metrics::MetricStore;
|
||||
use cm_dashboard_shared::{Metric, Status};
|
||||
use cm_dashboard_shared::Status;
|
||||
use theme::{Components, Layout as ThemeLayout, Theme, Typography};
|
||||
use widgets::{BackupWidget, ServicesWidget, SystemWidget, Widget};
|
||||
|
||||
/// Commands that can be triggered from the UI
|
||||
#[derive(Debug, Clone)]
|
||||
pub enum UiCommand {
|
||||
ServiceStart { hostname: String, service_name: String },
|
||||
ServiceStop { hostname: String, service_name: String },
|
||||
TriggerBackup { hostname: String },
|
||||
}
|
||||
|
||||
|
||||
/// Types of commands for status tracking
|
||||
#[derive(Debug, Clone)]
|
||||
pub enum CommandType {
|
||||
ServiceStart,
|
||||
ServiceStop,
|
||||
BackupTrigger,
|
||||
}
|
||||
|
||||
/// Panel types for focus management
|
||||
|
||||
@@ -47,14 +34,8 @@ pub struct HostWidgets {
|
||||
pub services_widget: ServicesWidget,
|
||||
/// Backup widget state
|
||||
pub backup_widget: BackupWidget,
|
||||
/// Scroll offsets for each panel
|
||||
pub system_scroll_offset: usize,
|
||||
pub services_scroll_offset: usize,
|
||||
pub backup_scroll_offset: usize,
|
||||
/// Last update time for this host
|
||||
pub last_update: Option<Instant>,
|
||||
/// Pending service transitions for immediate visual feedback
|
||||
pub pending_service_transitions: HashMap<String, (CommandType, String, Instant)>, // service_name -> (command_type, original_status, start_time)
|
||||
}
|
||||
|
||||
impl HostWidgets {
|
||||
@@ -63,11 +44,7 @@ impl HostWidgets {
|
||||
system_widget: SystemWidget::new(),
|
||||
services_widget: ServicesWidget::new(),
|
||||
backup_widget: BackupWidget::new(),
|
||||
system_scroll_offset: 0,
|
||||
services_scroll_offset: 0,
|
||||
backup_scroll_offset: 0,
|
||||
last_update: None,
|
||||
pending_service_transitions: HashMap::new(),
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -89,19 +66,33 @@ pub struct TuiApp {
|
||||
user_navigated_away: bool,
|
||||
/// Dashboard configuration
|
||||
config: DashboardConfig,
|
||||
/// Cached localhost hostname to avoid repeated system calls
|
||||
localhost: String,
|
||||
}
|
||||
|
||||
impl TuiApp {
|
||||
pub fn new(config: DashboardConfig) -> Self {
|
||||
Self {
|
||||
let localhost = gethostname::gethostname().to_string_lossy().to_string();
|
||||
let mut app = Self {
|
||||
host_widgets: HashMap::new(),
|
||||
current_host: None,
|
||||
available_hosts: Vec::new(),
|
||||
available_hosts: config.hosts.keys().cloned().collect(),
|
||||
host_index: 0,
|
||||
should_quit: false,
|
||||
user_navigated_away: false,
|
||||
config,
|
||||
localhost,
|
||||
};
|
||||
|
||||
// Sort predefined hosts
|
||||
app.available_hosts.sort();
|
||||
|
||||
// Initialize with first host if available
|
||||
if !app.available_hosts.is_empty() {
|
||||
app.current_host = Some(app.available_hosts[0].clone());
|
||||
}
|
||||
|
||||
app
|
||||
}
|
||||
|
||||
/// Get or create host widgets for the given hostname
|
||||
@@ -120,34 +111,32 @@ impl TuiApp {
|
||||
// Only update widgets if we have metrics for this host
|
||||
let all_metrics = metric_store.get_metrics_for_host(&hostname);
|
||||
if !all_metrics.is_empty() {
|
||||
// Get metrics first while hostname is borrowed
|
||||
let cpu_metrics: Vec<&Metric> = all_metrics
|
||||
.iter()
|
||||
.filter(|m| {
|
||||
m.name.starts_with("cpu_")
|
||||
|| m.name.contains("c_state_")
|
||||
|| m.name.starts_with("process_top_")
|
||||
})
|
||||
.copied()
|
||||
.collect();
|
||||
let memory_metrics: Vec<&Metric> = all_metrics
|
||||
.iter()
|
||||
.filter(|m| m.name.starts_with("memory_") || m.name.starts_with("disk_tmp_"))
|
||||
.copied()
|
||||
.collect();
|
||||
let service_metrics: Vec<&Metric> = all_metrics
|
||||
.iter()
|
||||
.filter(|m| m.name.starts_with("service_"))
|
||||
.copied()
|
||||
.collect();
|
||||
let all_backup_metrics: Vec<&Metric> = all_metrics
|
||||
.iter()
|
||||
.filter(|m| m.name.starts_with("backup_"))
|
||||
.copied()
|
||||
.collect();
|
||||
// Single pass metric categorization for better performance
|
||||
let mut cpu_metrics = Vec::new();
|
||||
let mut memory_metrics = Vec::new();
|
||||
let mut service_metrics = Vec::new();
|
||||
let mut backup_metrics = Vec::new();
|
||||
let mut nixos_metrics = Vec::new();
|
||||
let mut disk_metrics = Vec::new();
|
||||
|
||||
for metric in all_metrics {
|
||||
if metric.name.starts_with("cpu_")
|
||||
|| metric.name.contains("c_state_")
|
||||
|| metric.name.starts_with("process_top_") {
|
||||
cpu_metrics.push(metric);
|
||||
} else if metric.name.starts_with("memory_") || metric.name.starts_with("disk_tmp_") {
|
||||
memory_metrics.push(metric);
|
||||
} else if metric.name.starts_with("service_") {
|
||||
service_metrics.push(metric);
|
||||
} else if metric.name.starts_with("backup_") {
|
||||
backup_metrics.push(metric);
|
||||
} else if metric.name == "system_nixos_build" || metric.name == "system_active_users" || metric.name == "agent_version" {
|
||||
nixos_metrics.push(metric);
|
||||
} else if metric.name.starts_with("disk_") {
|
||||
disk_metrics.push(metric);
|
||||
}
|
||||
}
|
||||
|
||||
// Clear completed transitions first
|
||||
self.clear_completed_transitions(&hostname, &service_metrics);
|
||||
|
||||
// Now get host widgets and update them
|
||||
let host_widgets = self.get_or_create_host_widgets(&hostname);
|
||||
@@ -155,21 +144,7 @@ impl TuiApp {
|
||||
// Collect all system metrics (CPU, memory, NixOS, disk/storage)
|
||||
let mut system_metrics = cpu_metrics;
|
||||
system_metrics.extend(memory_metrics);
|
||||
|
||||
// Add NixOS metrics - using exact matching for build display fix
|
||||
let nixos_metrics: Vec<&Metric> = all_metrics
|
||||
.iter()
|
||||
.filter(|m| m.name == "system_nixos_build" || m.name == "system_active_users" || m.name == "agent_version")
|
||||
.copied()
|
||||
.collect();
|
||||
system_metrics.extend(nixos_metrics);
|
||||
|
||||
// Add disk/storage metrics
|
||||
let disk_metrics: Vec<&Metric> = all_metrics
|
||||
.iter()
|
||||
.filter(|m| m.name.starts_with("disk_"))
|
||||
.copied()
|
||||
.collect();
|
||||
system_metrics.extend(disk_metrics);
|
||||
|
||||
host_widgets.system_widget.update_from_metrics(&system_metrics);
|
||||
@@ -178,7 +153,7 @@ impl TuiApp {
|
||||
.update_from_metrics(&service_metrics);
|
||||
host_widgets
|
||||
.backup_widget
|
||||
.update_from_metrics(&all_backup_metrics);
|
||||
.update_from_metrics(&backup_metrics);
|
||||
|
||||
host_widgets.last_update = Some(Instant::now());
|
||||
}
|
||||
@@ -186,30 +161,28 @@ impl TuiApp {
|
||||
}
|
||||
|
||||
/// Update available hosts with localhost prioritization
|
||||
pub fn update_hosts(&mut self, hosts: Vec<String>) {
|
||||
// Sort hosts alphabetically
|
||||
let mut sorted_hosts = hosts.clone();
|
||||
pub fn update_hosts(&mut self, discovered_hosts: Vec<String>) {
|
||||
// Start with configured hosts (always visible)
|
||||
let mut all_hosts: Vec<String> = self.config.hosts.keys().cloned().collect();
|
||||
|
||||
// Keep hosts that have pending transitions even if they're offline
|
||||
for (hostname, host_widgets) in &self.host_widgets {
|
||||
if !host_widgets.pending_service_transitions.is_empty() {
|
||||
if !sorted_hosts.contains(hostname) {
|
||||
sorted_hosts.push(hostname.clone());
|
||||
}
|
||||
// Add any discovered hosts that aren't already configured
|
||||
for host in discovered_hosts {
|
||||
if !all_hosts.contains(&host) {
|
||||
all_hosts.push(host);
|
||||
}
|
||||
}
|
||||
|
||||
sorted_hosts.sort();
|
||||
self.available_hosts = sorted_hosts;
|
||||
|
||||
all_hosts.sort();
|
||||
self.available_hosts = all_hosts;
|
||||
|
||||
// Get the current hostname (localhost) for auto-selection
|
||||
let localhost = gethostname::gethostname().to_string_lossy().to_string();
|
||||
if !self.available_hosts.is_empty() {
|
||||
if self.available_hosts.contains(&localhost) && !self.user_navigated_away {
|
||||
if self.available_hosts.contains(&self.localhost) && !self.user_navigated_away {
|
||||
// Localhost is available and user hasn't navigated away - switch to it
|
||||
self.current_host = Some(localhost.clone());
|
||||
self.current_host = Some(self.localhost.clone());
|
||||
// Find the actual index of localhost in the sorted list
|
||||
self.host_index = self.available_hosts.iter().position(|h| h == &localhost).unwrap_or(0);
|
||||
self.host_index = self.available_hosts.iter().position(|h| h == &self.localhost).unwrap_or(0);
|
||||
} else if self.current_host.is_none() {
|
||||
// No current host - select first available (which is localhost if available)
|
||||
self.current_host = Some(self.available_hosts[0].clone());
|
||||
@@ -229,7 +202,7 @@ impl TuiApp {
|
||||
}
|
||||
|
||||
/// Handle keyboard input
|
||||
pub fn handle_input(&mut self, event: Event) -> Result<Option<UiCommand>> {
|
||||
pub fn handle_input(&mut self, event: Event) -> Result<()> {
|
||||
if let Event::Key(key) = event {
|
||||
match key.code {
|
||||
KeyCode::Char('q') => {
|
||||
@@ -244,103 +217,167 @@ impl TuiApp {
|
||||
KeyCode::Char('r') => {
|
||||
// System rebuild command - works on any panel for current host
|
||||
if let Some(hostname) = self.current_host.clone() {
|
||||
// Create command that shows CM Dashboard logo and then rebuilds
|
||||
let connection_ip = self.get_connection_ip(&hostname);
|
||||
// Create command that shows logo, rebuilds, and waits for user input
|
||||
let logo_and_rebuild = format!(
|
||||
r"cat << 'EOF'
|
||||
NixOS System Rebuild
|
||||
Target: {}
|
||||
|
||||
EOF
|
||||
ssh -tt {}@{} 'bash -ic {}'",
|
||||
"echo 'Rebuilding system: {} ({})' && ssh -tt {}@{} \"bash -ic '{}'\"",
|
||||
hostname,
|
||||
connection_ip,
|
||||
self.config.ssh.rebuild_user,
|
||||
hostname,
|
||||
self.config.ssh.rebuild_alias
|
||||
connection_ip,
|
||||
self.config.ssh.rebuild_cmd
|
||||
);
|
||||
|
||||
std::process::Command::new("tmux")
|
||||
.arg("display-popup")
|
||||
.arg("-w")
|
||||
.arg("80%")
|
||||
.arg("-h")
|
||||
.arg("80%")
|
||||
.arg("split-window")
|
||||
.arg("-v")
|
||||
.arg("-p")
|
||||
.arg("30")
|
||||
.arg(&logo_and_rebuild)
|
||||
.spawn()
|
||||
.ok(); // Ignore errors, tmux will handle them
|
||||
}
|
||||
}
|
||||
KeyCode::Char('s') => {
|
||||
// Service start command
|
||||
if let (Some(service_name), Some(hostname)) = (self.get_selected_service(), self.current_host.clone()) {
|
||||
if self.start_command(&hostname, CommandType::ServiceStart, service_name.clone()) {
|
||||
return Ok(Some(UiCommand::ServiceStart { hostname, service_name }));
|
||||
}
|
||||
}
|
||||
}
|
||||
KeyCode::Char('S') => {
|
||||
// Service stop command
|
||||
if let (Some(service_name), Some(hostname)) = (self.get_selected_service(), self.current_host.clone()) {
|
||||
if self.start_command(&hostname, CommandType::ServiceStop, service_name.clone()) {
|
||||
return Ok(Some(UiCommand::ServiceStop { hostname, service_name }));
|
||||
}
|
||||
}
|
||||
}
|
||||
KeyCode::Char('J') => {
|
||||
// Show service logs via journalctl in tmux popup
|
||||
if let (Some(service_name), Some(hostname)) = (self.get_selected_service(), self.current_host.clone()) {
|
||||
let journalctl_command = format!(
|
||||
"ssh -tt {}@{} 'sudo journalctl -u {}.service -f --no-pager -n 50'",
|
||||
self.config.ssh.rebuild_user,
|
||||
KeyCode::Char('B') => {
|
||||
// Backup command - works on any panel for current host
|
||||
if let Some(hostname) = self.current_host.clone() {
|
||||
let connection_ip = self.get_connection_ip(&hostname);
|
||||
// Create command that shows logo, runs backup, and waits for user input
|
||||
let logo_and_backup = format!(
|
||||
"echo 'Running backup: {} ({})' && ssh -tt {}@{} \"bash -ic '{}'\"",
|
||||
hostname,
|
||||
connection_ip,
|
||||
self.config.ssh.rebuild_user,
|
||||
connection_ip,
|
||||
format!("{} start borgbackup", self.config.ssh.service_manage_cmd)
|
||||
);
|
||||
|
||||
std::process::Command::new("tmux")
|
||||
.arg("split-window")
|
||||
.arg("-v")
|
||||
.arg("-p")
|
||||
.arg("30")
|
||||
.arg(&logo_and_backup)
|
||||
.spawn()
|
||||
.ok(); // Ignore errors, tmux will handle them
|
||||
}
|
||||
}
|
||||
KeyCode::Char('s') => {
|
||||
// Service start command via SSH with progress display
|
||||
if let (Some(service_name), Some(hostname)) = (self.get_selected_service(), self.current_host.clone()) {
|
||||
let connection_ip = self.get_connection_ip(&hostname);
|
||||
let service_start_command = format!(
|
||||
"echo 'Starting service: {} on {}' && ssh -tt {}@{} \"bash -ic '{} start {}'\"",
|
||||
service_name,
|
||||
hostname,
|
||||
self.config.ssh.rebuild_user,
|
||||
connection_ip,
|
||||
self.config.ssh.service_manage_cmd,
|
||||
service_name
|
||||
);
|
||||
|
||||
std::process::Command::new("tmux")
|
||||
.arg("display-popup")
|
||||
.arg("-w")
|
||||
.arg("80%")
|
||||
.arg("-h")
|
||||
.arg("80%")
|
||||
.arg("-T")
|
||||
.arg(format!("Logs: {}", service_name))
|
||||
.arg(&journalctl_command)
|
||||
.arg("split-window")
|
||||
.arg("-v")
|
||||
.arg("-p")
|
||||
.arg("30")
|
||||
.arg(&service_start_command)
|
||||
.spawn()
|
||||
.ok(); // Ignore errors, tmux will handle them
|
||||
}
|
||||
}
|
||||
KeyCode::Char('S') => {
|
||||
// Service stop command via SSH with progress display
|
||||
if let (Some(service_name), Some(hostname)) = (self.get_selected_service(), self.current_host.clone()) {
|
||||
let connection_ip = self.get_connection_ip(&hostname);
|
||||
let service_stop_command = format!(
|
||||
"echo 'Stopping service: {} on {}' && ssh -tt {}@{} \"bash -ic '{} stop {}'\"",
|
||||
service_name,
|
||||
hostname,
|
||||
self.config.ssh.rebuild_user,
|
||||
connection_ip,
|
||||
self.config.ssh.service_manage_cmd,
|
||||
service_name
|
||||
);
|
||||
|
||||
std::process::Command::new("tmux")
|
||||
.arg("split-window")
|
||||
.arg("-v")
|
||||
.arg("-p")
|
||||
.arg("30")
|
||||
.arg(&service_stop_command)
|
||||
.spawn()
|
||||
.ok(); // Ignore errors, tmux will handle them
|
||||
}
|
||||
}
|
||||
KeyCode::Char('L') => {
|
||||
// Show custom service log file in tmux popup
|
||||
// Show service logs via service-manage script in tmux split window
|
||||
if let (Some(service_name), Some(hostname)) = (self.get_selected_service(), self.current_host.clone()) {
|
||||
// Check if this service has a custom log file configured
|
||||
if let Some(host_logs) = self.config.service_logs.get(&hostname) {
|
||||
if let Some(log_config) = host_logs.iter().find(|config| config.service_name == service_name) {
|
||||
let tail_command = format!(
|
||||
"ssh -tt {}@{} 'sudo tail -n 50 -f {}'",
|
||||
self.config.ssh.rebuild_user,
|
||||
hostname,
|
||||
log_config.log_file_path
|
||||
);
|
||||
|
||||
std::process::Command::new("tmux")
|
||||
.arg("display-popup")
|
||||
.arg("-w")
|
||||
.arg("80%")
|
||||
.arg("-h")
|
||||
.arg("80%")
|
||||
.arg("-T")
|
||||
.arg(format!("Custom Log: {}", service_name))
|
||||
.arg(&tail_command)
|
||||
.spawn()
|
||||
.ok(); // Ignore errors, tmux will handle them
|
||||
let connection_ip = self.get_connection_ip(&hostname);
|
||||
let logs_command = format!(
|
||||
"ssh -tt {}@{} '{} logs {}'",
|
||||
self.config.ssh.rebuild_user,
|
||||
connection_ip,
|
||||
self.config.ssh.service_manage_cmd,
|
||||
service_name
|
||||
);
|
||||
|
||||
std::process::Command::new("tmux")
|
||||
.arg("split-window")
|
||||
.arg("-v")
|
||||
.arg("-p")
|
||||
.arg("30")
|
||||
.arg(&logs_command)
|
||||
.spawn()
|
||||
.ok(); // Ignore errors, tmux will handle them
|
||||
}
|
||||
}
|
||||
KeyCode::Char('w') => {
|
||||
// Wake on LAN for offline hosts
|
||||
if let Some(hostname) = self.current_host.clone() {
|
||||
// Check if host has MAC address configured
|
||||
if let Some(host_details) = self.config.hosts.get(&hostname) {
|
||||
if let Some(mac_address) = &host_details.mac_address {
|
||||
// Parse MAC address and send WoL packet
|
||||
let mac_bytes = Self::parse_mac_address(mac_address);
|
||||
match mac_bytes {
|
||||
Ok(mac) => {
|
||||
match MagicPacket::new(&mac).send() {
|
||||
Ok(_) => {
|
||||
info!("WakeOnLAN packet sent successfully to {} ({})", hostname, mac_address);
|
||||
}
|
||||
Err(e) => {
|
||||
tracing::error!("Failed to send WakeOnLAN packet to {}: {}", hostname, e);
|
||||
}
|
||||
}
|
||||
}
|
||||
Err(_) => {
|
||||
tracing::error!("Invalid MAC address format for {}: {}", hostname, mac_address);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
KeyCode::Char('b') => {
|
||||
// Trigger backup
|
||||
KeyCode::Char('t') => {
|
||||
// Open SSH terminal session in tmux window
|
||||
if let Some(hostname) = self.current_host.clone() {
|
||||
self.start_command(&hostname, CommandType::BackupTrigger, hostname.clone());
|
||||
return Ok(Some(UiCommand::TriggerBackup { hostname }));
|
||||
let connection_ip = self.get_connection_ip(&hostname);
|
||||
let ssh_command = format!(
|
||||
"echo 'Opening SSH terminal to: {}' && ssh -tt {}@{}",
|
||||
hostname,
|
||||
self.config.ssh.rebuild_user,
|
||||
connection_ip
|
||||
);
|
||||
|
||||
std::process::Command::new("tmux")
|
||||
.arg("split-window")
|
||||
.arg("-v")
|
||||
.arg("-p")
|
||||
.arg("30") // Use 30% like other commands
|
||||
.arg(&ssh_command)
|
||||
.spawn()
|
||||
.ok(); // Ignore errors, tmux will handle them
|
||||
}
|
||||
}
|
||||
KeyCode::Tab => {
|
||||
@@ -368,7 +405,7 @@ ssh -tt {}@{} 'bash -ic {}'",
|
||||
_ => {}
|
||||
}
|
||||
}
|
||||
Ok(None)
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Navigate between hosts
|
||||
@@ -391,9 +428,8 @@ ssh -tt {}@{} 'bash -ic {}'",
|
||||
self.current_host = Some(self.available_hosts[self.host_index].clone());
|
||||
|
||||
// Check if user navigated away from localhost
|
||||
let localhost = gethostname::gethostname().to_string_lossy().to_string();
|
||||
if let Some(ref current) = self.current_host {
|
||||
if current != &localhost {
|
||||
if current != &self.localhost {
|
||||
self.user_navigated_away = true;
|
||||
} else {
|
||||
self.user_navigated_away = false; // User navigated back to localhost
|
||||
@@ -423,86 +459,8 @@ ssh -tt {}@{} 'bash -ic {}'",
|
||||
self.should_quit
|
||||
}
|
||||
|
||||
/// Get current service status for state-aware command validation
|
||||
fn get_current_service_status(&self, hostname: &str, service_name: &str) -> Option<String> {
|
||||
if let Some(host_widgets) = self.host_widgets.get(hostname) {
|
||||
return host_widgets.services_widget.get_service_status(service_name);
|
||||
}
|
||||
None
|
||||
}
|
||||
|
||||
/// Start command execution with immediate visual feedback
|
||||
pub fn start_command(&mut self, hostname: &str, command_type: CommandType, target: String) -> bool {
|
||||
// Get current service status to validate command
|
||||
let current_status = self.get_current_service_status(hostname, &target);
|
||||
|
||||
// Validate if command makes sense for current state
|
||||
let should_execute = match (&command_type, current_status.as_deref()) {
|
||||
(CommandType::ServiceStart, Some("inactive") | Some("failed") | Some("dead")) => true,
|
||||
(CommandType::ServiceStop, Some("active")) => true,
|
||||
(CommandType::ServiceStart, Some("active")) => {
|
||||
// Already running - don't execute
|
||||
false
|
||||
},
|
||||
(CommandType::ServiceStop, Some("inactive") | Some("failed") | Some("dead")) => {
|
||||
// Already stopped - don't execute
|
||||
false
|
||||
},
|
||||
(_, None) => {
|
||||
// Unknown service state - allow command to proceed
|
||||
true
|
||||
},
|
||||
_ => true, // Default: allow other combinations
|
||||
};
|
||||
|
||||
// ALWAYS store the pending transition for immediate visual feedback, even if we don't execute
|
||||
if let Some(host_widgets) = self.host_widgets.get_mut(hostname) {
|
||||
host_widgets.pending_service_transitions.insert(
|
||||
target.clone(),
|
||||
(command_type, current_status.unwrap_or_else(|| "unknown".to_string()), Instant::now())
|
||||
);
|
||||
}
|
||||
|
||||
should_execute
|
||||
}
|
||||
|
||||
/// Clear pending transitions when real status updates arrive or timeout
|
||||
fn clear_completed_transitions(&mut self, hostname: &str, service_metrics: &[&Metric]) {
|
||||
if let Some(host_widgets) = self.host_widgets.get_mut(hostname) {
|
||||
let mut completed_services = Vec::new();
|
||||
|
||||
// Check each pending transition to see if real status has changed
|
||||
for (service_name, (command_type, original_status, _start_time)) in &host_widgets.pending_service_transitions {
|
||||
|
||||
// Look for status metric for this service
|
||||
for metric in service_metrics {
|
||||
if metric.name == format!("service_{}_status", service_name) {
|
||||
let new_status = metric.value.as_string();
|
||||
|
||||
// Check if status has changed from original (command completed)
|
||||
if &new_status != original_status {
|
||||
// Verify it changed in the expected direction
|
||||
let expected_change = match command_type {
|
||||
CommandType::ServiceStart => &new_status == "active",
|
||||
CommandType::ServiceStop => &new_status != "active",
|
||||
_ => false,
|
||||
};
|
||||
|
||||
if expected_change {
|
||||
completed_services.push(service_name.clone());
|
||||
}
|
||||
}
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Remove completed transitions
|
||||
for service_name in completed_services {
|
||||
host_widgets.pending_service_transitions.remove(&service_name);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
@@ -537,6 +495,21 @@ ssh -tt {}@{} 'bash -ic {}'",
|
||||
])
|
||||
.split(main_chunks[1]); // main_chunks[1] is now the content area (between title and statusbar)
|
||||
|
||||
// Check if current host is offline
|
||||
let current_host_offline = if let Some(hostname) = self.current_host.clone() {
|
||||
self.calculate_host_status(&hostname, metric_store) == Status::Offline
|
||||
} else {
|
||||
true // No host selected is considered offline
|
||||
};
|
||||
|
||||
// If host is offline, render wake-up message instead of panels
|
||||
if current_host_offline {
|
||||
self.render_offline_host_message(frame, main_chunks[1]);
|
||||
self.render_btop_title(frame, main_chunks[0], metric_store);
|
||||
self.render_statusbar(frame, main_chunks[2]);
|
||||
return;
|
||||
}
|
||||
|
||||
// Check if backup panel should be shown
|
||||
let show_backup = if let Some(hostname) = self.current_host.clone() {
|
||||
let host_widgets = self.get_or_create_host_widgets(&hostname);
|
||||
@@ -575,14 +548,10 @@ ssh -tt {}@{} 'bash -ic {}'",
|
||||
// Render services widget for current host
|
||||
if let Some(hostname) = self.current_host.clone() {
|
||||
let is_focused = true; // Always show service selection
|
||||
let (scroll_offset, pending_transitions) = {
|
||||
let host_widgets = self.get_or_create_host_widgets(&hostname);
|
||||
(host_widgets.services_scroll_offset, host_widgets.pending_service_transitions.clone())
|
||||
};
|
||||
let host_widgets = self.get_or_create_host_widgets(&hostname);
|
||||
host_widgets
|
||||
.services_widget
|
||||
.render_with_transitions(frame, content_chunks[1], is_focused, scroll_offset, &pending_transitions); // Services takes full right side
|
||||
.render(frame, content_chunks[1], is_focused); // Services takes full right side
|
||||
}
|
||||
|
||||
// Render statusbar at the bottom
|
||||
@@ -604,11 +573,14 @@ ssh -tt {}@{} 'bash -ic {}'",
|
||||
return;
|
||||
}
|
||||
|
||||
// Calculate worst-case status across all hosts
|
||||
// Calculate worst-case status across all hosts (excluding offline)
|
||||
let mut worst_status = Status::Ok;
|
||||
for host in &self.available_hosts {
|
||||
let host_status = self.calculate_host_status(host, metric_store);
|
||||
worst_status = Status::aggregate(&[worst_status, host_status]);
|
||||
// Don't include offline hosts in status aggregation
|
||||
if host_status != Status::Offline {
|
||||
worst_status = Status::aggregate(&[worst_status, host_status]);
|
||||
}
|
||||
}
|
||||
|
||||
// Use the worst status color as background
|
||||
@@ -617,12 +589,13 @@ ssh -tt {}@{} 'bash -ic {}'",
|
||||
// Split the title bar into left and right sections
|
||||
let chunks = Layout::default()
|
||||
.direction(Direction::Horizontal)
|
||||
.constraints([Constraint::Length(15), Constraint::Min(0)])
|
||||
.constraints([Constraint::Length(22), Constraint::Min(0)])
|
||||
.split(area);
|
||||
|
||||
// Left side: "cm-dashboard" text
|
||||
// Left side: "cm-dashboard" text with version
|
||||
let title_text = format!(" cm-dashboard v{}", env!("CARGO_PKG_VERSION"));
|
||||
let left_span = Span::styled(
|
||||
" cm-dashboard",
|
||||
&title_text,
|
||||
Style::default().fg(Theme::background()).bg(background_color).add_modifier(Modifier::BOLD)
|
||||
);
|
||||
let left_title = Paragraph::new(Line::from(vec![left_span]))
|
||||
@@ -686,7 +659,7 @@ ssh -tt {}@{} 'bash -ic {}'",
|
||||
let metrics = metric_store.get_metrics_for_host(hostname);
|
||||
|
||||
if metrics.is_empty() {
|
||||
return Status::Unknown;
|
||||
return Status::Offline;
|
||||
}
|
||||
|
||||
// First check if we have the aggregated host status summary from the agent
|
||||
@@ -694,33 +667,27 @@ ssh -tt {}@{} 'bash -ic {}'",
|
||||
return host_summary_metric.status;
|
||||
}
|
||||
|
||||
// Fallback to old aggregation logic with proper Pending handling
|
||||
// Rewritten status aggregation - only Critical, Warning, or OK for top bar
|
||||
let mut has_critical = false;
|
||||
let mut has_warning = false;
|
||||
let mut has_pending = false;
|
||||
let mut ok_count = 0;
|
||||
|
||||
for metric in &metrics {
|
||||
match metric.status {
|
||||
Status::Critical => has_critical = true,
|
||||
Status::Warning => has_warning = true,
|
||||
Status::Pending => has_pending = true,
|
||||
Status::Ok => ok_count += 1,
|
||||
Status::Unknown => {} // Ignore unknown for aggregation
|
||||
// Treat all other statuses as OK for top bar aggregation
|
||||
Status::Ok | Status::Pending | Status::Inactive | Status::Unknown => {},
|
||||
Status::Offline => {}, // Ignore offline
|
||||
}
|
||||
}
|
||||
|
||||
// Priority order: Critical > Warning > Pending > Ok > Unknown
|
||||
// Only return Critical, Warning, or OK - no other statuses
|
||||
if has_critical {
|
||||
Status::Critical
|
||||
} else if has_warning {
|
||||
Status::Warning
|
||||
} else if has_pending {
|
||||
Status::Pending
|
||||
} else if ok_count > 0 {
|
||||
Status::Ok
|
||||
} else {
|
||||
Status::Unknown
|
||||
Status::Ok
|
||||
}
|
||||
}
|
||||
|
||||
@@ -744,9 +711,11 @@ ssh -tt {}@{} 'bash -ic {}'",
|
||||
shortcuts.push("Tab: Host".to_string());
|
||||
shortcuts.push("↑↓/jk: Select".to_string());
|
||||
shortcuts.push("r: Rebuild".to_string());
|
||||
shortcuts.push("B: Backup".to_string());
|
||||
shortcuts.push("s/S: Start/Stop".to_string());
|
||||
shortcuts.push("J: Logs".to_string());
|
||||
shortcuts.push("L: Custom".to_string());
|
||||
shortcuts.push("L: Logs".to_string());
|
||||
shortcuts.push("t: Terminal".to_string());
|
||||
shortcuts.push("w: Wake".to_string());
|
||||
|
||||
// Always show quit
|
||||
shortcuts.push("q: Quit".to_string());
|
||||
@@ -760,12 +729,10 @@ ssh -tt {}@{} 'bash -ic {}'",
|
||||
frame.render_widget(system_block, area);
|
||||
// Get current host widgets, create if none exist
|
||||
if let Some(hostname) = self.current_host.clone() {
|
||||
let scroll_offset = {
|
||||
let host_widgets = self.get_or_create_host_widgets(&hostname);
|
||||
host_widgets.system_scroll_offset
|
||||
};
|
||||
// Clone the config to avoid borrowing issues
|
||||
let config = self.config.clone();
|
||||
let host_widgets = self.get_or_create_host_widgets(&hostname);
|
||||
host_widgets.system_widget.render_with_scroll(frame, inner_area, scroll_offset, &hostname);
|
||||
host_widgets.system_widget.render(frame, inner_area, &hostname, Some(&config));
|
||||
}
|
||||
}
|
||||
|
||||
@@ -776,14 +743,105 @@ ssh -tt {}@{} 'bash -ic {}'",
|
||||
|
||||
// Get current host widgets for backup widget
|
||||
if let Some(hostname) = self.current_host.clone() {
|
||||
let scroll_offset = {
|
||||
let host_widgets = self.get_or_create_host_widgets(&hostname);
|
||||
host_widgets.backup_scroll_offset
|
||||
};
|
||||
let host_widgets = self.get_or_create_host_widgets(&hostname);
|
||||
host_widgets.backup_widget.render_with_scroll(frame, inner_area, scroll_offset);
|
||||
host_widgets.backup_widget.render(frame, inner_area);
|
||||
}
|
||||
}
|
||||
|
||||
/// Render offline host message with wake-up option
|
||||
fn render_offline_host_message(&self, frame: &mut Frame, area: Rect) {
|
||||
use ratatui::layout::Alignment;
|
||||
use ratatui::style::Modifier;
|
||||
use ratatui::text::{Line, Span};
|
||||
use ratatui::widgets::{Block, Borders, Paragraph};
|
||||
|
||||
// Get hostname for message
|
||||
let hostname = self.current_host.as_ref()
|
||||
.map(|h| h.as_str())
|
||||
.unwrap_or("Unknown");
|
||||
|
||||
// Check if host has MAC address for wake-on-LAN
|
||||
let has_mac = self.current_host.as_ref()
|
||||
.and_then(|hostname| self.config.hosts.get(hostname))
|
||||
.and_then(|details| details.mac_address.as_ref())
|
||||
.is_some();
|
||||
|
||||
// Create message content
|
||||
let mut lines = vec![
|
||||
Line::from(Span::styled(
|
||||
format!("Host '{}' is offline", hostname),
|
||||
Style::default().fg(Theme::muted_text()).add_modifier(Modifier::BOLD),
|
||||
)),
|
||||
Line::from(""),
|
||||
];
|
||||
|
||||
if has_mac {
|
||||
lines.push(Line::from(Span::styled(
|
||||
"Press 'w' to wake up host",
|
||||
Style::default().fg(Theme::primary_text()).add_modifier(Modifier::BOLD),
|
||||
)));
|
||||
} else {
|
||||
lines.push(Line::from(Span::styled(
|
||||
"No MAC address configured - cannot wake up",
|
||||
Style::default().fg(Theme::muted_text()),
|
||||
)));
|
||||
}
|
||||
|
||||
// Create centered message
|
||||
let message = Paragraph::new(lines)
|
||||
.block(Block::default()
|
||||
.borders(Borders::ALL)
|
||||
.border_style(Style::default().fg(Theme::muted_text()))
|
||||
.title(" Offline Host ")
|
||||
.title_style(Style::default().fg(Theme::muted_text()).add_modifier(Modifier::BOLD)))
|
||||
.style(Style::default().bg(Theme::background()).fg(Theme::primary_text()))
|
||||
.alignment(Alignment::Center);
|
||||
|
||||
// Center the message in the available area
|
||||
let popup_area = ratatui::layout::Layout::default()
|
||||
.direction(Direction::Vertical)
|
||||
.constraints([
|
||||
Constraint::Percentage(40),
|
||||
Constraint::Length(6),
|
||||
Constraint::Percentage(40),
|
||||
])
|
||||
.split(area)[1];
|
||||
|
||||
let popup_area = ratatui::layout::Layout::default()
|
||||
.direction(Direction::Horizontal)
|
||||
.constraints([
|
||||
Constraint::Percentage(25),
|
||||
Constraint::Percentage(50),
|
||||
Constraint::Percentage(25),
|
||||
])
|
||||
.split(popup_area)[1];
|
||||
|
||||
frame.render_widget(message, popup_area);
|
||||
}
|
||||
|
||||
/// Parse MAC address string (e.g., "AA:BB:CC:DD:EE:FF") to [u8; 6]
|
||||
/// Get the connection IP for a hostname based on host configuration
|
||||
fn get_connection_ip(&self, hostname: &str) -> String {
|
||||
if let Some(host_details) = self.config.hosts.get(hostname) {
|
||||
host_details.get_connection_ip(hostname)
|
||||
} else {
|
||||
hostname.to_string()
|
||||
}
|
||||
}
|
||||
|
||||
fn parse_mac_address(mac_str: &str) -> Result<[u8; 6], &'static str> {
|
||||
let parts: Vec<&str> = mac_str.split(':').collect();
|
||||
if parts.len() != 6 {
|
||||
return Err("MAC address must have 6 parts separated by colons");
|
||||
}
|
||||
|
||||
let mut mac = [0u8; 6];
|
||||
for (i, part) in parts.iter().enumerate() {
|
||||
match u8::from_str_radix(part, 16) {
|
||||
Ok(byte) => mac[i] = byte,
|
||||
Err(_) => return Err("Invalid hexadecimal byte in MAC address"),
|
||||
}
|
||||
}
|
||||
Ok(mac)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -143,10 +143,12 @@ impl Theme {
|
||||
pub fn status_color(status: Status) -> Color {
|
||||
match status {
|
||||
Status::Ok => Self::success(),
|
||||
Status::Inactive => Self::muted_text(), // Gray for inactive services in service list
|
||||
Status::Pending => Self::highlight(), // Blue for pending
|
||||
Status::Warning => Self::warning(),
|
||||
Status::Critical => Self::error(),
|
||||
Status::Unknown => Self::muted_text(),
|
||||
Status::Offline => Self::muted_text(), // Dark gray for offline
|
||||
}
|
||||
}
|
||||
|
||||
@@ -242,10 +244,12 @@ impl StatusIcons {
|
||||
pub fn get_icon(status: Status) -> &'static str {
|
||||
match status {
|
||||
Status::Ok => "●",
|
||||
Status::Inactive => "○", // Empty circle for inactive services
|
||||
Status::Pending => "◉", // Hollow circle for pending
|
||||
Status::Warning => "◐",
|
||||
Status::Critical => "◯",
|
||||
Status::Critical => "!",
|
||||
Status::Unknown => "?",
|
||||
Status::Offline => "○", // Empty circle for offline
|
||||
}
|
||||
}
|
||||
|
||||
@@ -254,10 +258,12 @@ impl StatusIcons {
|
||||
let icon = Self::get_icon(status);
|
||||
let status_color = match status {
|
||||
Status::Ok => Theme::success(), // Green
|
||||
Status::Inactive => Theme::muted_text(), // Gray for inactive services
|
||||
Status::Pending => Theme::highlight(), // Blue
|
||||
Status::Warning => Theme::warning(), // Yellow
|
||||
Status::Critical => Theme::error(), // Red
|
||||
Status::Unknown => Theme::muted_text(), // Gray
|
||||
Status::Offline => Theme::muted_text(), // Dark gray for offline
|
||||
};
|
||||
|
||||
vec![
|
||||
|
||||
@@ -30,6 +30,8 @@ pub struct BackupWidget {
|
||||
backup_disk_product_name: Option<String>,
|
||||
/// Backup disk serial number from SMART data
|
||||
backup_disk_serial_number: Option<String>,
|
||||
/// Backup disk wear percentage from SMART data
|
||||
backup_disk_wear_percent: Option<f32>,
|
||||
/// Backup disk filesystem label
|
||||
backup_disk_filesystem_label: Option<String>,
|
||||
/// Number of completed services
|
||||
@@ -65,6 +67,7 @@ impl BackupWidget {
|
||||
backup_disk_used_gb: None,
|
||||
backup_disk_product_name: None,
|
||||
backup_disk_serial_number: None,
|
||||
backup_disk_wear_percent: None,
|
||||
backup_disk_filesystem_label: None,
|
||||
services_completed_count: None,
|
||||
services_failed_count: None,
|
||||
@@ -197,6 +200,9 @@ impl Widget for BackupWidget {
|
||||
"backup_disk_serial_number" => {
|
||||
self.backup_disk_serial_number = Some(metric.value.as_string());
|
||||
}
|
||||
"backup_disk_wear_percent" => {
|
||||
self.backup_disk_wear_percent = metric.value.as_f32();
|
||||
}
|
||||
"backup_disk_filesystem_label" => {
|
||||
self.backup_disk_filesystem_label = Some(metric.value.as_string());
|
||||
}
|
||||
@@ -285,8 +291,8 @@ impl Widget for BackupWidget {
|
||||
}
|
||||
|
||||
impl BackupWidget {
|
||||
/// Render with scroll offset support
|
||||
pub fn render_with_scroll(&mut self, frame: &mut Frame, area: Rect, scroll_offset: usize) {
|
||||
/// Render backup widget
|
||||
pub fn render(&mut self, frame: &mut Frame, area: Rect) {
|
||||
let mut lines = Vec::new();
|
||||
|
||||
// Latest backup section
|
||||
@@ -328,21 +334,31 @@ impl BackupWidget {
|
||||
);
|
||||
lines.push(ratatui::text::Line::from(disk_spans));
|
||||
|
||||
// Serial number as sub-item
|
||||
// Collect sub-items to determine tree structure
|
||||
let mut sub_items = Vec::new();
|
||||
|
||||
if let Some(serial) = &self.backup_disk_serial_number {
|
||||
lines.push(ratatui::text::Line::from(vec![
|
||||
ratatui::text::Span::styled(" ├─ ", Typography::tree()),
|
||||
ratatui::text::Span::styled(format!("S/N: {}", serial), Typography::secondary())
|
||||
]));
|
||||
sub_items.push(format!("S/N: {}", serial));
|
||||
}
|
||||
|
||||
// Usage as sub-item
|
||||
|
||||
if let Some(wear) = self.backup_disk_wear_percent {
|
||||
sub_items.push(format!("Wear: {:.0}%", wear));
|
||||
}
|
||||
|
||||
if let (Some(used), Some(total)) = (self.backup_disk_used_gb, self.backup_disk_total_gb) {
|
||||
let used_str = Self::format_size_with_proper_units(used);
|
||||
let total_str = Self::format_size_with_proper_units(total);
|
||||
sub_items.push(format!("Usage: {}/{}", used_str, total_str));
|
||||
}
|
||||
|
||||
// Render sub-items with proper tree structure
|
||||
let num_items = sub_items.len();
|
||||
for (i, item) in sub_items.into_iter().enumerate() {
|
||||
let is_last = i == num_items - 1;
|
||||
let tree_char = if is_last { " └─ " } else { " ├─ " };
|
||||
lines.push(ratatui::text::Line::from(vec![
|
||||
ratatui::text::Span::styled(" └─ ", Typography::tree()),
|
||||
ratatui::text::Span::styled(format!("Usage: {}/{}", used_str, total_str), Typography::secondary())
|
||||
ratatui::text::Span::styled(tree_char, Typography::tree()),
|
||||
ratatui::text::Span::styled(item, Typography::secondary())
|
||||
]));
|
||||
}
|
||||
}
|
||||
@@ -366,42 +382,20 @@ impl BackupWidget {
|
||||
let total_lines = lines.len();
|
||||
let available_height = area.height as usize;
|
||||
|
||||
// Calculate scroll boundaries
|
||||
let max_scroll = if total_lines > available_height {
|
||||
total_lines - available_height
|
||||
} else {
|
||||
total_lines.saturating_sub(1)
|
||||
};
|
||||
let effective_scroll = scroll_offset.min(max_scroll);
|
||||
|
||||
// Apply scrolling if needed
|
||||
if scroll_offset > 0 || total_lines > available_height {
|
||||
// Show only what fits, with "X more below" if needed
|
||||
if total_lines > available_height {
|
||||
let lines_for_content = available_height.saturating_sub(1); // Reserve one line for "more below"
|
||||
let mut visible_lines: Vec<_> = lines
|
||||
.into_iter()
|
||||
.skip(effective_scroll)
|
||||
.take(available_height)
|
||||
.take(lines_for_content)
|
||||
.collect();
|
||||
|
||||
// Add scroll indicator if there are hidden lines
|
||||
if total_lines > available_height {
|
||||
let hidden_above = effective_scroll;
|
||||
let hidden_below = total_lines.saturating_sub(effective_scroll + available_height);
|
||||
|
||||
if (hidden_above > 0 || hidden_below > 0) && !visible_lines.is_empty() {
|
||||
let scroll_text = if hidden_above > 0 && hidden_below > 0 {
|
||||
format!("... {} above, {} below", hidden_above, hidden_below)
|
||||
} else if hidden_above > 0 {
|
||||
format!("... {} more above", hidden_above)
|
||||
} else {
|
||||
format!("... {} more below", hidden_below)
|
||||
};
|
||||
|
||||
// Replace last line with scroll indicator
|
||||
visible_lines.pop();
|
||||
visible_lines.push(ratatui::text::Line::from(vec![
|
||||
ratatui::text::Span::styled(scroll_text, Typography::muted())
|
||||
]));
|
||||
}
|
||||
let hidden_below = total_lines.saturating_sub(lines_for_content);
|
||||
if hidden_below > 0 {
|
||||
let more_line = ratatui::text::Line::from(vec![
|
||||
ratatui::text::Span::styled(format!("... {} more below", hidden_below), Typography::muted())
|
||||
]);
|
||||
visible_lines.push(more_line);
|
||||
}
|
||||
|
||||
let paragraph = Paragraph::new(ratatui::text::Text::from(visible_lines));
|
||||
|
||||
@@ -9,7 +9,6 @@ use tracing::debug;
|
||||
|
||||
use super::Widget;
|
||||
use crate::ui::theme::{Components, StatusIcons, Theme, Typography};
|
||||
use crate::ui::CommandType;
|
||||
use ratatui::style::Style;
|
||||
|
||||
/// Services widget displaying hierarchical systemd service statuses
|
||||
@@ -125,40 +124,14 @@ impl ServicesWidget {
|
||||
)
|
||||
}
|
||||
|
||||
/// Get status icon for service, considering pending transitions for visual feedback
|
||||
fn get_service_icon_and_status(&self, service_name: &str, info: &ServiceInfo, pending_transitions: &HashMap<String, (CommandType, String, std::time::Instant)>) -> (String, String, ratatui::prelude::Color) {
|
||||
// Check if this service has a pending transition
|
||||
if let Some((command_type, _original_status, _start_time)) = pending_transitions.get(service_name) {
|
||||
// Show transitional icons for pending commands
|
||||
let (icon, status_text) = match command_type {
|
||||
CommandType::ServiceStart => ("↑", "starting"),
|
||||
CommandType::ServiceStop => ("↓", "stopping"),
|
||||
_ => return (StatusIcons::get_icon(info.widget_status).to_string(), info.status.clone(), Theme::status_color(info.widget_status)), // Not a service command
|
||||
};
|
||||
return (icon.to_string(), status_text.to_string(), Theme::highlight());
|
||||
}
|
||||
|
||||
// Normal status display
|
||||
let icon = StatusIcons::get_icon(info.widget_status);
|
||||
let status_color = match info.widget_status {
|
||||
Status::Ok => Theme::success(),
|
||||
Status::Pending => Theme::highlight(),
|
||||
Status::Warning => Theme::warning(),
|
||||
Status::Critical => Theme::error(),
|
||||
Status::Unknown => Theme::muted_text(),
|
||||
};
|
||||
|
||||
(icon.to_string(), info.status.clone(), status_color)
|
||||
}
|
||||
|
||||
|
||||
/// Create spans for sub-service with icon next to name, considering pending transitions
|
||||
fn create_sub_service_spans_with_transitions(
|
||||
/// Create spans for sub-service with icon next to name
|
||||
fn create_sub_service_spans(
|
||||
&self,
|
||||
name: &str,
|
||||
info: &ServiceInfo,
|
||||
is_last: bool,
|
||||
pending_transitions: &HashMap<String, (CommandType, String, std::time::Instant)>,
|
||||
) -> Vec<ratatui::text::Span<'static>> {
|
||||
// Truncate long sub-service names to fit layout (accounting for indentation)
|
||||
let short_name = if name.len() > 18 {
|
||||
@@ -167,19 +140,28 @@ impl ServicesWidget {
|
||||
name.to_string()
|
||||
};
|
||||
|
||||
// Get status icon and text, considering pending transitions
|
||||
let (icon, mut status_str, status_color) = self.get_service_icon_and_status(name, info, pending_transitions);
|
||||
// Get status icon and text
|
||||
let icon = StatusIcons::get_icon(info.widget_status);
|
||||
let status_color = match info.widget_status {
|
||||
Status::Ok => Theme::success(),
|
||||
Status::Inactive => Theme::muted_text(),
|
||||
Status::Pending => Theme::highlight(),
|
||||
Status::Warning => Theme::warning(),
|
||||
Status::Critical => Theme::error(),
|
||||
Status::Unknown => Theme::muted_text(),
|
||||
Status::Offline => Theme::muted_text(),
|
||||
};
|
||||
|
||||
// For sub-services, prefer latency if available (unless transition is pending)
|
||||
if !pending_transitions.contains_key(name) {
|
||||
if let Some(latency) = info.latency_ms {
|
||||
status_str = if latency < 0.0 {
|
||||
"timeout".to_string()
|
||||
} else {
|
||||
format!("{:.0}ms", latency)
|
||||
};
|
||||
// For sub-services, prefer latency if available
|
||||
let status_str = if let Some(latency) = info.latency_ms {
|
||||
if latency < 0.0 {
|
||||
"timeout".to_string()
|
||||
} else {
|
||||
format!("{:.0}ms", latency)
|
||||
}
|
||||
}
|
||||
} else {
|
||||
info.status.clone()
|
||||
};
|
||||
let tree_symbol = if is_last { "└─" } else { "├─" };
|
||||
|
||||
vec![
|
||||
@@ -227,36 +209,13 @@ impl ServicesWidget {
|
||||
}
|
||||
|
||||
/// Get currently selected service name (for actions)
|
||||
/// Only returns parent service names since only parent services can be selected
|
||||
pub fn get_selected_service(&self) -> Option<String> {
|
||||
// Build the same display list to find the selected service
|
||||
let mut display_lines: Vec<(String, Status, bool, Option<(ServiceInfo, bool)>, String)> = Vec::new();
|
||||
|
||||
// Only parent services can be selected, so just get the parent service at selected_index
|
||||
let mut parent_services: Vec<_> = self.parent_services.iter().collect();
|
||||
parent_services.sort_by(|(a, _), (b, _)| a.cmp(b));
|
||||
|
||||
for (parent_name, parent_info) in parent_services {
|
||||
let parent_line = self.format_parent_service_line(parent_name, parent_info);
|
||||
display_lines.push((parent_line, parent_info.widget_status, false, None, parent_name.clone()));
|
||||
|
||||
if let Some(sub_list) = self.sub_services.get(parent_name) {
|
||||
let mut sorted_subs = sub_list.clone();
|
||||
sorted_subs.sort_by(|(a, _), (b, _)| a.cmp(b));
|
||||
|
||||
for (i, (sub_name, sub_info)) in sorted_subs.iter().enumerate() {
|
||||
let is_last_sub = i == sorted_subs.len() - 1;
|
||||
let full_sub_name = format!("{}_{}", parent_name, sub_name);
|
||||
display_lines.push((
|
||||
sub_name.clone(),
|
||||
sub_info.widget_status,
|
||||
true,
|
||||
Some((sub_info.clone(), is_last_sub)),
|
||||
full_sub_name,
|
||||
));
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
display_lines.get(self.selected_index).map(|(_, _, _, _, raw_name)| raw_name.clone())
|
||||
parent_services.get(self.selected_index).map(|(name, _)| name.to_string())
|
||||
}
|
||||
|
||||
/// Get total count of selectable services (parent services only, not sub-services)
|
||||
@@ -265,25 +224,6 @@ impl ServicesWidget {
|
||||
self.parent_services.len()
|
||||
}
|
||||
|
||||
/// Get current status of a specific service by name
|
||||
pub fn get_service_status(&self, service_name: &str) -> Option<String> {
|
||||
// Check if it's a parent service
|
||||
if let Some(parent_info) = self.parent_services.get(service_name) {
|
||||
return Some(parent_info.status.clone());
|
||||
}
|
||||
|
||||
// Check sub-services (format: parent_sub)
|
||||
for (parent_name, sub_list) in &self.sub_services {
|
||||
for (sub_name, sub_info) in sub_list {
|
||||
let full_sub_name = format!("{}_{}", parent_name, sub_name);
|
||||
if full_sub_name == service_name {
|
||||
return Some(sub_info.status.clone());
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
None
|
||||
}
|
||||
|
||||
/// Calculate which parent service index corresponds to a display line index
|
||||
fn calculate_parent_service_index(&self, display_line_index: &usize) -> usize {
|
||||
@@ -438,8 +378,8 @@ impl Widget for ServicesWidget {
|
||||
|
||||
impl ServicesWidget {
|
||||
|
||||
/// Render with focus, scroll, and pending transitions for visual feedback
|
||||
pub fn render_with_transitions(&mut self, frame: &mut Frame, area: Rect, is_focused: bool, scroll_offset: usize, pending_transitions: &HashMap<String, (CommandType, String, std::time::Instant)>) {
|
||||
/// Render with focus
|
||||
pub fn render(&mut self, frame: &mut Frame, area: Rect, is_focused: bool) {
|
||||
let services_block = Components::widget_block("services");
|
||||
let inner_area = services_block.inner(area);
|
||||
frame.render_widget(services_block, area);
|
||||
@@ -464,14 +404,14 @@ impl ServicesWidget {
|
||||
return;
|
||||
}
|
||||
|
||||
// Use the existing render logic but with pending transitions
|
||||
self.render_services_with_transitions(frame, content_chunks[1], is_focused, scroll_offset, pending_transitions);
|
||||
// Render the services list
|
||||
self.render_services(frame, content_chunks[1], is_focused);
|
||||
}
|
||||
|
||||
/// Render services list with pending transitions awareness
|
||||
fn render_services_with_transitions(&mut self, frame: &mut Frame, area: Rect, is_focused: bool, scroll_offset: usize, pending_transitions: &HashMap<String, (CommandType, String, std::time::Instant)>) {
|
||||
// Build hierarchical service list for display - include raw service name for pending transition lookups
|
||||
let mut display_lines: Vec<(String, Status, bool, Option<(ServiceInfo, bool)>, String)> = Vec::new(); // Added raw service name
|
||||
/// Render services list
|
||||
fn render_services(&mut self, frame: &mut Frame, area: Rect, is_focused: bool) {
|
||||
// Build hierarchical service list for display
|
||||
let mut display_lines: Vec<(String, Status, bool, Option<(ServiceInfo, bool)>)> = Vec::new();
|
||||
|
||||
// Sort parent services alphabetically for consistent order
|
||||
let mut parent_services: Vec<_> = self.parent_services.iter().collect();
|
||||
@@ -480,7 +420,7 @@ impl ServicesWidget {
|
||||
for (parent_name, parent_info) in parent_services {
|
||||
// Add parent service line
|
||||
let parent_line = self.format_parent_service_line(parent_name, parent_info);
|
||||
display_lines.push((parent_line, parent_info.widget_status, false, None, parent_name.clone())); // Include raw name
|
||||
display_lines.push((parent_line, parent_info.widget_status, false, None));
|
||||
|
||||
// Add sub-services for this parent (if any)
|
||||
if let Some(sub_list) = self.sub_services.get(parent_name) {
|
||||
@@ -490,49 +430,48 @@ impl ServicesWidget {
|
||||
|
||||
for (i, (sub_name, sub_info)) in sorted_subs.iter().enumerate() {
|
||||
let is_last_sub = i == sorted_subs.len() - 1;
|
||||
let full_sub_name = format!("{}_{}", parent_name, sub_name);
|
||||
// Store sub-service info for custom span rendering
|
||||
display_lines.push((
|
||||
sub_name.clone(),
|
||||
sub_info.widget_status,
|
||||
true,
|
||||
Some((sub_info.clone(), is_last_sub)),
|
||||
full_sub_name, // Raw service name for pending transition lookup
|
||||
)); // true = sub-service, with is_last info
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Apply scroll offset and render visible lines (same as existing logic)
|
||||
// Show only what fits, with "X more below" if needed
|
||||
let available_lines = area.height as usize;
|
||||
let total_lines = display_lines.len();
|
||||
|
||||
// Calculate scroll boundaries
|
||||
let max_scroll = if total_lines > available_lines {
|
||||
total_lines - available_lines
|
||||
// Reserve one line for "X more below" if needed
|
||||
let lines_for_content = if total_lines > available_lines {
|
||||
available_lines.saturating_sub(1)
|
||||
} else {
|
||||
total_lines.saturating_sub(1)
|
||||
available_lines
|
||||
};
|
||||
let effective_scroll = scroll_offset.min(max_scroll);
|
||||
|
||||
// Get visible lines after scrolling
|
||||
let visible_lines: Vec<_> = display_lines
|
||||
.iter()
|
||||
.skip(effective_scroll)
|
||||
.take(available_lines)
|
||||
.take(lines_for_content)
|
||||
.collect();
|
||||
|
||||
let hidden_below = total_lines.saturating_sub(lines_for_content);
|
||||
|
||||
let lines_to_show = visible_lines.len();
|
||||
|
||||
if lines_to_show > 0 {
|
||||
// Add space for "X more below" message if needed
|
||||
let total_chunks_needed = if hidden_below > 0 { lines_to_show + 1 } else { lines_to_show };
|
||||
let service_chunks = Layout::default()
|
||||
.direction(Direction::Vertical)
|
||||
.constraints(vec![Constraint::Length(1); lines_to_show])
|
||||
.constraints(vec![Constraint::Length(1); total_chunks_needed])
|
||||
.split(area);
|
||||
|
||||
for (i, (line_text, line_status, is_sub, sub_info, raw_service_name)) in visible_lines.iter().enumerate()
|
||||
for (i, (line_text, line_status, is_sub, sub_info)) in visible_lines.iter().enumerate()
|
||||
{
|
||||
let actual_index = effective_scroll + i; // Real index in the full list
|
||||
let actual_index = i; // Simple index since we're not scrolling
|
||||
|
||||
// Only parent services can be selected - calculate parent service index
|
||||
let is_selected = if !*is_sub {
|
||||
@@ -544,41 +483,16 @@ impl ServicesWidget {
|
||||
};
|
||||
|
||||
let mut spans = if *is_sub && sub_info.is_some() {
|
||||
// Use custom sub-service span creation WITH pending transitions
|
||||
// Use custom sub-service span creation
|
||||
let (service_info, is_last) = sub_info.as_ref().unwrap();
|
||||
self.create_sub_service_spans_with_transitions(line_text, service_info, *is_last, pending_transitions)
|
||||
self.create_sub_service_spans(line_text, service_info, *is_last)
|
||||
} else {
|
||||
// Parent services - check if this parent service has a pending transition using RAW service name
|
||||
if pending_transitions.contains_key(raw_service_name) {
|
||||
// Create spans with transitional status
|
||||
let (icon, status_text, _) = self.get_service_icon_and_status(raw_service_name, &ServiceInfo {
|
||||
status: "".to_string(),
|
||||
memory_mb: None,
|
||||
disk_gb: None,
|
||||
latency_ms: None,
|
||||
widget_status: *line_status
|
||||
}, pending_transitions);
|
||||
|
||||
// Use blue for transitional icons when not selected, background color when selected
|
||||
let icon_color = if is_selected && !*is_sub && is_focused {
|
||||
Theme::background() // Dark background color for visibility against blue selection
|
||||
} else {
|
||||
Theme::highlight() // Blue for normal case
|
||||
};
|
||||
|
||||
vec![
|
||||
ratatui::text::Span::styled(format!("{} ", icon), Style::default().fg(icon_color)),
|
||||
ratatui::text::Span::styled(line_text.clone(), Style::default().fg(Theme::primary_text())),
|
||||
ratatui::text::Span::styled(format!(" {}", status_text), Style::default().fg(icon_color)),
|
||||
]
|
||||
} else {
|
||||
StatusIcons::create_status_spans(*line_status, line_text)
|
||||
}
|
||||
// Parent services - use normal status spans
|
||||
StatusIcons::create_status_spans(*line_status, line_text)
|
||||
};
|
||||
|
||||
// Apply selection highlighting to parent services only, making icons background color when selected
|
||||
// Apply selection highlighting to parent services only
|
||||
// Only show selection when Services panel is focused
|
||||
// Show selection highlighting even when transitional icons are present
|
||||
if is_selected && !*is_sub && is_focused {
|
||||
for (i, span) in spans.iter_mut().enumerate() {
|
||||
if i == 0 {
|
||||
@@ -599,33 +513,12 @@ impl ServicesWidget {
|
||||
|
||||
frame.render_widget(service_para, service_chunks[i]);
|
||||
}
|
||||
}
|
||||
|
||||
// Show scroll indicator if there are more services than we can display (same as existing)
|
||||
if total_lines > available_lines {
|
||||
let hidden_above = effective_scroll;
|
||||
let hidden_below = total_lines.saturating_sub(effective_scroll + available_lines);
|
||||
|
||||
if hidden_above > 0 || hidden_below > 0 {
|
||||
let scroll_text = if hidden_above > 0 && hidden_below > 0 {
|
||||
format!("... {} above, {} below", hidden_above, hidden_below)
|
||||
} else if hidden_above > 0 {
|
||||
format!("... {} more above", hidden_above)
|
||||
} else {
|
||||
format!("... {} more below", hidden_below)
|
||||
};
|
||||
|
||||
if available_lines > 0 && lines_to_show > 0 {
|
||||
let last_line_area = Rect {
|
||||
x: area.x,
|
||||
y: area.y + (lines_to_show - 1) as u16,
|
||||
width: area.width,
|
||||
height: 1,
|
||||
};
|
||||
|
||||
let scroll_para = Paragraph::new(scroll_text).style(Typography::muted());
|
||||
frame.render_widget(scroll_para, last_line_area);
|
||||
}
|
||||
// Show "X more below" message if content was truncated
|
||||
if hidden_below > 0 {
|
||||
let more_text = format!("... {} more below", hidden_below);
|
||||
let more_para = Paragraph::new(more_text).style(Typography::muted());
|
||||
frame.render_widget(more_para, service_chunks[lines_to_show]);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -45,12 +45,15 @@ pub struct SystemWidget {
|
||||
struct StoragePool {
|
||||
name: String,
|
||||
mount_point: String,
|
||||
pool_type: String, // "Single", "Raid0", etc.
|
||||
pool_type: String, // "single", "mergerfs (2+1)", "RAID5 (3+1)", etc.
|
||||
pool_health: Option<String>, // "healthy", "degraded", "critical", "rebuilding"
|
||||
drives: Vec<StorageDrive>,
|
||||
filesystems: Vec<FileSystem>, // For physical drive pools: individual filesystem children
|
||||
usage_percent: Option<f32>,
|
||||
used_gb: Option<f32>,
|
||||
total_gb: Option<f32>,
|
||||
status: Status,
|
||||
health_status: Status, // Separate status for pool health vs usage
|
||||
}
|
||||
|
||||
#[derive(Clone)]
|
||||
@@ -61,6 +64,16 @@ struct StorageDrive {
|
||||
status: Status,
|
||||
}
|
||||
|
||||
#[derive(Clone)]
|
||||
struct FileSystem {
|
||||
mount_point: String,
|
||||
usage_percent: Option<f32>,
|
||||
used_gb: Option<f32>,
|
||||
total_gb: Option<f32>,
|
||||
available_gb: Option<f32>,
|
||||
status: Status,
|
||||
}
|
||||
|
||||
impl SystemWidget {
|
||||
pub fn new() -> Self {
|
||||
Self {
|
||||
@@ -155,12 +168,15 @@ impl SystemWidget {
|
||||
let pool = pools.entry(pool_name.clone()).or_insert_with(|| StoragePool {
|
||||
name: pool_name.clone(),
|
||||
mount_point: mount_point.clone(),
|
||||
pool_type: "Single".to_string(), // Default, could be enhanced
|
||||
pool_type: "single".to_string(), // Default, will be updated
|
||||
pool_health: None,
|
||||
drives: Vec::new(),
|
||||
filesystems: Vec::new(),
|
||||
usage_percent: None,
|
||||
used_gb: None,
|
||||
total_gb: None,
|
||||
status: Status::Unknown,
|
||||
health_status: Status::Unknown,
|
||||
});
|
||||
|
||||
// Parse different metric types
|
||||
@@ -177,6 +193,15 @@ impl SystemWidget {
|
||||
if let MetricValue::Float(total) = metric.value {
|
||||
pool.total_gb = Some(total);
|
||||
}
|
||||
} else if metric.name.contains("_pool_type") {
|
||||
if let MetricValue::String(pool_type) = &metric.value {
|
||||
pool.pool_type = pool_type.clone();
|
||||
}
|
||||
} else if metric.name.contains("_pool_health") {
|
||||
if let MetricValue::String(health) = &metric.value {
|
||||
pool.pool_health = Some(health.clone());
|
||||
pool.health_status = metric.status.clone();
|
||||
}
|
||||
} else if metric.name.contains("_temperature") {
|
||||
if let Some(drive_name) = self.extract_drive_name(&metric.name) {
|
||||
// Find existing drive or create new one
|
||||
@@ -217,6 +242,91 @@ impl SystemWidget {
|
||||
}
|
||||
}
|
||||
}
|
||||
} else if metric.name.contains("_fs_") {
|
||||
// Handle filesystem metrics for physical drive pools (disk_{pool}_fs_{fs_name}_{metric})
|
||||
if let (Some(fs_name), Some(metric_type)) = self.extract_filesystem_metric(&metric.name) {
|
||||
// Find or create filesystem entry
|
||||
let fs_exists = pool.filesystems.iter().any(|fs| {
|
||||
let fs_id = if fs.mount_point == "/" {
|
||||
"root".to_string()
|
||||
} else {
|
||||
fs.mount_point.trim_start_matches('/').replace('/', "_")
|
||||
};
|
||||
fs_id == fs_name
|
||||
});
|
||||
|
||||
if !fs_exists {
|
||||
// Create filesystem entry with correct mount point
|
||||
let mount_point = if metric_type == "mount_point" {
|
||||
if let MetricValue::String(mount) = &metric.value {
|
||||
mount.clone()
|
||||
} else {
|
||||
// Fallback: handle special cases
|
||||
if fs_name == "root" {
|
||||
"/".to_string()
|
||||
} else {
|
||||
format!("/{}", fs_name.replace('_', "/"))
|
||||
}
|
||||
}
|
||||
} else {
|
||||
// Fallback for non-mount_point metrics: generate mount point from fs_name
|
||||
if fs_name == "root" {
|
||||
"/".to_string()
|
||||
} else {
|
||||
format!("/{}", fs_name.replace('_', "/"))
|
||||
}
|
||||
};
|
||||
|
||||
pool.filesystems.push(FileSystem {
|
||||
mount_point,
|
||||
usage_percent: None,
|
||||
used_gb: None,
|
||||
total_gb: None,
|
||||
available_gb: None,
|
||||
status: Status::Unknown,
|
||||
});
|
||||
}
|
||||
|
||||
// Update the filesystem with the metric value
|
||||
if let Some(filesystem) = pool.filesystems.iter_mut().find(|fs| {
|
||||
let fs_id = if fs.mount_point == "/" {
|
||||
"root".to_string()
|
||||
} else {
|
||||
fs.mount_point.trim_start_matches('/').replace('/', "_")
|
||||
};
|
||||
fs_id == fs_name
|
||||
}) {
|
||||
match metric_type.as_str() {
|
||||
"usage_percent" => {
|
||||
if let MetricValue::Float(usage) = metric.value {
|
||||
filesystem.usage_percent = Some(usage);
|
||||
filesystem.status = metric.status.clone();
|
||||
}
|
||||
}
|
||||
"used_gb" => {
|
||||
if let MetricValue::Float(used) = metric.value {
|
||||
filesystem.used_gb = Some(used);
|
||||
}
|
||||
}
|
||||
"total_gb" => {
|
||||
if let MetricValue::Float(total) = metric.value {
|
||||
filesystem.total_gb = Some(total);
|
||||
}
|
||||
}
|
||||
"available_gb" => {
|
||||
if let MetricValue::Float(available) = metric.value {
|
||||
filesystem.available_gb = Some(available);
|
||||
}
|
||||
}
|
||||
"mount_point" => {
|
||||
if let MetricValue::String(mount) = &metric.value {
|
||||
filesystem.mount_point = mount.clone();
|
||||
}
|
||||
}
|
||||
_ => {}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -243,10 +353,17 @@ impl SystemWidget {
|
||||
return Some(metric_name[5..drive_start].to_string()); // Skip "disk_"
|
||||
}
|
||||
}
|
||||
// Handle filesystem metrics: disk_{pool}_fs_{filesystem}_{metric}
|
||||
else if metric_name.contains("_fs_") {
|
||||
if let Some(fs_pos) = metric_name.find("_fs_") {
|
||||
return Some(metric_name[5..fs_pos].to_string()); // Skip "disk_", extract pool name before "_fs_"
|
||||
}
|
||||
}
|
||||
// For pool-level metrics (usage_percent, used_gb, total_gb), take everything before the metric suffix
|
||||
else if let Some(suffix_pos) = metric_name.rfind("_usage_percent")
|
||||
.or_else(|| metric_name.rfind("_used_gb"))
|
||||
.or_else(|| metric_name.rfind("_total_gb")) {
|
||||
.or_else(|| metric_name.rfind("_total_gb"))
|
||||
.or_else(|| metric_name.rfind("_available_gb")) {
|
||||
return Some(metric_name[5..suffix_pos].to_string()); // Skip "disk_"
|
||||
}
|
||||
// Fallback to old behavior for unknown patterns
|
||||
@@ -259,6 +376,28 @@ impl SystemWidget {
|
||||
None
|
||||
}
|
||||
|
||||
/// Extract filesystem name and metric type from filesystem metric names
|
||||
/// Pattern: disk_{pool}_fs_{filesystem_name}_{metric_type}
|
||||
fn extract_filesystem_metric(&self, metric_name: &str) -> (Option<String>, Option<String>) {
|
||||
if metric_name.starts_with("disk_") && metric_name.contains("_fs_") {
|
||||
// Find the _fs_ part
|
||||
if let Some(fs_start) = metric_name.find("_fs_") {
|
||||
let after_fs = &metric_name[fs_start + 4..]; // Skip "_fs_"
|
||||
|
||||
// Look for known metric suffixes (these can contain underscores)
|
||||
let known_suffixes = ["usage_percent", "used_gb", "total_gb", "available_gb", "mount_point"];
|
||||
|
||||
for suffix in known_suffixes {
|
||||
if after_fs.ends_with(suffix) {
|
||||
let fs_name = after_fs[..after_fs.len() - suffix.len() - 1].to_string(); // Remove suffix + underscore
|
||||
return (Some(fs_name), Some(suffix.to_string()));
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
(None, None)
|
||||
}
|
||||
|
||||
/// Extract drive name from disk metric name
|
||||
fn extract_drive_name(&self, metric_name: &str) -> Option<String> {
|
||||
// Pattern: disk_{pool_name}_{drive_name}_{metric_type}
|
||||
@@ -277,73 +416,208 @@ impl SystemWidget {
|
||||
None
|
||||
}
|
||||
|
||||
/// Render storage section with tree structure
|
||||
/// Render storage section with enhanced tree structure
|
||||
fn render_storage(&self) -> Vec<Line<'_>> {
|
||||
let mut lines = Vec::new();
|
||||
|
||||
for pool in &self.storage_pools {
|
||||
// Pool header line
|
||||
let usage_text = match (pool.usage_percent, pool.used_gb, pool.total_gb) {
|
||||
(Some(pct), Some(used), Some(total)) => {
|
||||
format!("{:.0}% {:.1}GB/{:.1}GB", pct, used, total)
|
||||
}
|
||||
_ => "—% —GB/—GB".to_string(),
|
||||
};
|
||||
|
||||
let pool_label = if pool.pool_type.to_lowercase() == "single" {
|
||||
// Pool header line with type and health
|
||||
let pool_label = if pool.pool_type == "single" {
|
||||
format!("{}:", pool.mount_point)
|
||||
} else {
|
||||
format!("{} ({}):", pool.mount_point, pool.pool_type)
|
||||
};
|
||||
let pool_spans = StatusIcons::create_status_spans(
|
||||
pool.status.clone(),
|
||||
pool.health_status.clone(),
|
||||
&pool_label
|
||||
);
|
||||
lines.push(Line::from(pool_spans));
|
||||
|
||||
// Drive lines with tree structure
|
||||
let has_usage_line = pool.usage_percent.is_some();
|
||||
for (i, drive) in pool.drives.iter().enumerate() {
|
||||
let is_last_drive = i == pool.drives.len() - 1;
|
||||
let tree_symbol = if is_last_drive && !has_usage_line { "└─" } else { "├─" };
|
||||
|
||||
let mut drive_info = Vec::new();
|
||||
if let Some(temp) = drive.temperature {
|
||||
drive_info.push(format!("T: {:.0}C", temp));
|
||||
// Pool health line (for multi-disk pools)
|
||||
if pool.pool_type != "single" {
|
||||
if let Some(health) = &pool.pool_health {
|
||||
let health_text = match health.as_str() {
|
||||
"healthy" => format!("Pool Status: {} Healthy",
|
||||
if pool.drives.len() > 1 { format!("({} drives)", pool.drives.len()) } else { String::new() }),
|
||||
"degraded" => "Pool Status: ⚠ Degraded".to_string(),
|
||||
"critical" => "Pool Status: ✗ Critical".to_string(),
|
||||
"rebuilding" => "Pool Status: ⟳ Rebuilding".to_string(),
|
||||
_ => format!("Pool Status: ? {}", health),
|
||||
};
|
||||
|
||||
let mut health_spans = vec![
|
||||
Span::raw(" "),
|
||||
Span::styled("├─ ", Typography::tree()),
|
||||
];
|
||||
health_spans.extend(StatusIcons::create_status_spans(pool.health_status.clone(), &health_text));
|
||||
lines.push(Line::from(health_spans));
|
||||
}
|
||||
if let Some(wear) = drive.wear_percent {
|
||||
drive_info.push(format!("W: {:.0}%", wear));
|
||||
}
|
||||
let drive_text = if drive_info.is_empty() {
|
||||
drive.name.clone()
|
||||
} else {
|
||||
format!("{} {}", drive.name, drive_info.join(" • "))
|
||||
};
|
||||
|
||||
let mut drive_spans = vec![
|
||||
Span::raw(" "),
|
||||
Span::styled(tree_symbol, Typography::tree()),
|
||||
Span::raw(" "),
|
||||
];
|
||||
drive_spans.extend(StatusIcons::create_status_spans(drive.status.clone(), &drive_text));
|
||||
lines.push(Line::from(drive_spans));
|
||||
}
|
||||
|
||||
// Usage line
|
||||
if pool.usage_percent.is_some() {
|
||||
let tree_symbol = "└─";
|
||||
let mut usage_spans = vec![
|
||||
Span::raw(" "),
|
||||
Span::styled(tree_symbol, Typography::tree()),
|
||||
Span::raw(" "),
|
||||
];
|
||||
usage_spans.extend(StatusIcons::create_status_spans(pool.status.clone(), &usage_text));
|
||||
lines.push(Line::from(usage_spans));
|
||||
// Total usage line (always show for pools)
|
||||
let usage_text = match (pool.usage_percent, pool.used_gb, pool.total_gb) {
|
||||
(Some(pct), Some(used), Some(total)) => {
|
||||
format!("Total: {:.0}% {:.1}GB/{:.1}GB", pct, used, total)
|
||||
}
|
||||
_ => "Total: —% —GB/—GB".to_string(),
|
||||
};
|
||||
|
||||
let has_drives = !pool.drives.is_empty();
|
||||
let has_filesystems = !pool.filesystems.is_empty();
|
||||
let has_children = has_drives || has_filesystems;
|
||||
let tree_symbol = if has_children { "├─" } else { "└─" };
|
||||
let mut usage_spans = vec![
|
||||
Span::raw(" "),
|
||||
Span::styled(tree_symbol, Typography::tree()),
|
||||
Span::raw(" "),
|
||||
];
|
||||
usage_spans.extend(StatusIcons::create_status_spans(pool.status.clone(), &usage_text));
|
||||
lines.push(Line::from(usage_spans));
|
||||
|
||||
// Drive lines with enhanced grouping
|
||||
if pool.pool_type != "single" && pool.drives.len() > 1 {
|
||||
// Group drives by type for mergerfs pools
|
||||
let (data_drives, parity_drives): (Vec<_>, Vec<_>) = pool.drives.iter().enumerate()
|
||||
.partition(|(_, drive)| {
|
||||
// Simple heuristic: drives with 'parity' in name or sdc (common parity drive)
|
||||
!drive.name.to_lowercase().contains("parity") && drive.name != "sdc"
|
||||
});
|
||||
|
||||
// Show data drives
|
||||
if !data_drives.is_empty() && pool.pool_type.contains("mergerfs") {
|
||||
lines.push(Line::from(vec![
|
||||
Span::raw(" "),
|
||||
Span::styled("├─ ", Typography::tree()),
|
||||
Span::styled("Data Disks:", Typography::secondary()),
|
||||
]));
|
||||
|
||||
for (i, (_, drive)) in data_drives.iter().enumerate() {
|
||||
let is_last = i == data_drives.len() - 1;
|
||||
if is_last && parity_drives.is_empty() {
|
||||
self.render_drive_line(&mut lines, drive, "│ └─");
|
||||
} else {
|
||||
self.render_drive_line(&mut lines, drive, "│ ├─");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Show parity drives
|
||||
if !parity_drives.is_empty() && pool.pool_type.contains("mergerfs") {
|
||||
lines.push(Line::from(vec![
|
||||
Span::raw(" "),
|
||||
Span::styled("└─ ", Typography::tree()),
|
||||
Span::styled("Parity:", Typography::secondary()),
|
||||
]));
|
||||
|
||||
for (i, (_, drive)) in parity_drives.iter().enumerate() {
|
||||
let is_last = i == parity_drives.len() - 1;
|
||||
if is_last {
|
||||
self.render_drive_line(&mut lines, drive, " └─");
|
||||
} else {
|
||||
self.render_drive_line(&mut lines, drive, " ├─");
|
||||
}
|
||||
}
|
||||
} else {
|
||||
// Regular drive listing for non-mergerfs pools
|
||||
for (i, drive) in pool.drives.iter().enumerate() {
|
||||
let is_last = i == pool.drives.len() - 1;
|
||||
let tree_symbol = if is_last { "└─" } else { "├─" };
|
||||
self.render_drive_line(&mut lines, drive, tree_symbol);
|
||||
}
|
||||
}
|
||||
} else if pool.pool_type.starts_with("drive (") {
|
||||
// Physical drive pools: show drive info + filesystem children
|
||||
// First show drive information
|
||||
for drive in &pool.drives {
|
||||
let mut drive_info = Vec::new();
|
||||
if let Some(temp) = drive.temperature {
|
||||
drive_info.push(format!("T: {:.0}°C", temp));
|
||||
}
|
||||
if let Some(wear) = drive.wear_percent {
|
||||
drive_info.push(format!("W: {:.0}%", wear));
|
||||
}
|
||||
let drive_text = if drive_info.is_empty() {
|
||||
format!("Drive: {}", drive.name)
|
||||
} else {
|
||||
format!("Drive: {}", drive_info.join(" "))
|
||||
};
|
||||
|
||||
let has_filesystems = !pool.filesystems.is_empty();
|
||||
let tree_symbol = if has_filesystems { "├─" } else { "└─" };
|
||||
let mut drive_spans = vec![
|
||||
Span::raw(" "),
|
||||
Span::styled(tree_symbol, Typography::tree()),
|
||||
Span::raw(" "),
|
||||
];
|
||||
drive_spans.extend(StatusIcons::create_status_spans(drive.status.clone(), &drive_text));
|
||||
lines.push(Line::from(drive_spans));
|
||||
}
|
||||
|
||||
// Then show filesystem children
|
||||
for (i, filesystem) in pool.filesystems.iter().enumerate() {
|
||||
let is_last = i == pool.filesystems.len() - 1;
|
||||
let tree_symbol = if is_last { "└─" } else { "├─" };
|
||||
|
||||
let fs_text = match (filesystem.usage_percent, filesystem.used_gb, filesystem.total_gb) {
|
||||
(Some(pct), Some(used), Some(total)) => {
|
||||
format!("{}: {:.0}% {:.1}GB/{:.1}GB", filesystem.mount_point, pct, used, total)
|
||||
}
|
||||
(Some(pct), _, Some(total)) => {
|
||||
format!("{}: {:.0}% —GB/{:.1}GB", filesystem.mount_point, pct, total)
|
||||
}
|
||||
(Some(pct), _, _) => {
|
||||
format!("{}: {:.0}% —GB/—GB", filesystem.mount_point, pct)
|
||||
}
|
||||
(_, Some(used), Some(total)) => {
|
||||
format!("{}: —% {:.1}GB/{:.1}GB", filesystem.mount_point, used, total)
|
||||
}
|
||||
_ => format!("{}: —% —GB/—GB", filesystem.mount_point),
|
||||
};
|
||||
|
||||
let mut fs_spans = vec![
|
||||
Span::raw(" "),
|
||||
Span::styled(tree_symbol, Typography::tree()),
|
||||
Span::raw(" "),
|
||||
];
|
||||
fs_spans.extend(StatusIcons::create_status_spans(filesystem.status.clone(), &fs_text));
|
||||
lines.push(Line::from(fs_spans));
|
||||
}
|
||||
} else {
|
||||
// Single drive or simple pools
|
||||
for (i, drive) in pool.drives.iter().enumerate() {
|
||||
let is_last = i == pool.drives.len() - 1;
|
||||
let tree_symbol = if is_last { "└─" } else { "├─" };
|
||||
self.render_drive_line(&mut lines, drive, tree_symbol);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
lines
|
||||
}
|
||||
|
||||
/// Helper to render a single drive line
|
||||
fn render_drive_line<'a>(&self, lines: &mut Vec<Line<'a>>, drive: &StorageDrive, tree_symbol: &'a str) {
|
||||
let mut drive_info = Vec::new();
|
||||
if let Some(temp) = drive.temperature {
|
||||
drive_info.push(format!("T: {:.0}°C", temp));
|
||||
}
|
||||
if let Some(wear) = drive.wear_percent {
|
||||
drive_info.push(format!("W: {:.0}%", wear));
|
||||
}
|
||||
let drive_text = if drive_info.is_empty() {
|
||||
drive.name.clone()
|
||||
} else {
|
||||
format!("{} {}", drive.name, drive_info.join(" • "))
|
||||
};
|
||||
|
||||
let mut drive_spans = vec![
|
||||
Span::raw(" "),
|
||||
Span::styled(tree_symbol, Typography::tree()),
|
||||
Span::raw(" "),
|
||||
];
|
||||
drive_spans.extend(StatusIcons::create_status_spans(drive.status.clone(), &drive_text));
|
||||
lines.push(Line::from(drive_spans));
|
||||
}
|
||||
}
|
||||
|
||||
impl Widget for SystemWidget {
|
||||
@@ -438,8 +712,8 @@ impl Widget for SystemWidget {
|
||||
}
|
||||
|
||||
impl SystemWidget {
|
||||
/// Render with scroll offset support
|
||||
pub fn render_with_scroll(&mut self, frame: &mut Frame, area: Rect, scroll_offset: usize, hostname: &str) {
|
||||
/// Render system widget
|
||||
pub fn render(&mut self, frame: &mut Frame, area: Rect, hostname: &str, config: Option<&crate::config::DashboardConfig>) {
|
||||
let mut lines = Vec::new();
|
||||
|
||||
// NixOS section
|
||||
@@ -457,6 +731,16 @@ impl SystemWidget {
|
||||
Span::styled(format!("Agent: {}", agent_version_text), Typography::secondary())
|
||||
]));
|
||||
|
||||
// Display detected connection IP
|
||||
if let Some(config) = config {
|
||||
if let Some(host_details) = config.hosts.get(hostname) {
|
||||
let detected_ip = host_details.get_connection_ip(hostname);
|
||||
lines.push(Line::from(vec![
|
||||
Span::styled(format!("IP: {}", detected_ip), Typography::secondary())
|
||||
]));
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
// CPU section
|
||||
lines.push(Line::from(vec![
|
||||
@@ -503,69 +787,30 @@ impl SystemWidget {
|
||||
Span::styled("Storage:", Typography::widget_title())
|
||||
]));
|
||||
|
||||
// Storage items with overflow handling
|
||||
// Storage items - let main overflow logic handle truncation
|
||||
let storage_lines = self.render_storage();
|
||||
let remaining_space = area.height.saturating_sub(lines.len() as u16);
|
||||
|
||||
if storage_lines.len() <= remaining_space as usize {
|
||||
// All storage lines fit
|
||||
lines.extend(storage_lines);
|
||||
} else if remaining_space >= 2 {
|
||||
// Show what we can and add overflow indicator
|
||||
let lines_to_show = (remaining_space - 1) as usize; // Reserve 1 line for overflow
|
||||
lines.extend(storage_lines.iter().take(lines_to_show).cloned());
|
||||
|
||||
// Count hidden pools
|
||||
let mut hidden_pools = 0;
|
||||
let mut current_pool = String::new();
|
||||
for (i, line) in storage_lines.iter().enumerate() {
|
||||
if i >= lines_to_show {
|
||||
// Check if this line represents a new pool (no indentation)
|
||||
if let Some(first_span) = line.spans.first() {
|
||||
let text = first_span.content.as_ref();
|
||||
if !text.starts_with(" ") && text.contains(':') {
|
||||
let pool_name = text.split(':').next().unwrap_or("").trim();
|
||||
if pool_name != current_pool {
|
||||
hidden_pools += 1;
|
||||
current_pool = pool_name.to_string();
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if hidden_pools > 0 {
|
||||
let overflow_text = format!(
|
||||
"... and {} more pool{}",
|
||||
hidden_pools,
|
||||
if hidden_pools == 1 { "" } else { "s" }
|
||||
);
|
||||
lines.push(Line::from(vec![
|
||||
Span::styled(overflow_text, Typography::muted())
|
||||
]));
|
||||
}
|
||||
}
|
||||
lines.extend(storage_lines);
|
||||
|
||||
// Apply scroll offset
|
||||
let total_lines = lines.len();
|
||||
let available_height = area.height as usize;
|
||||
|
||||
// Always apply scrolling if scroll_offset > 0, even if content fits
|
||||
if scroll_offset > 0 || total_lines > available_height {
|
||||
let max_scroll = if total_lines > available_height {
|
||||
total_lines - available_height
|
||||
} else {
|
||||
total_lines.saturating_sub(1)
|
||||
};
|
||||
let effective_scroll = scroll_offset.min(max_scroll);
|
||||
|
||||
// Take only the visible portion after scrolling
|
||||
let visible_lines: Vec<Line> = lines
|
||||
// Show only what fits, with "X more below" if needed
|
||||
if total_lines > available_height {
|
||||
let lines_for_content = available_height.saturating_sub(1); // Reserve one line for "more below"
|
||||
let mut visible_lines: Vec<Line> = lines
|
||||
.into_iter()
|
||||
.skip(effective_scroll)
|
||||
.take(available_height)
|
||||
.take(lines_for_content)
|
||||
.collect();
|
||||
|
||||
|
||||
let hidden_below = total_lines.saturating_sub(lines_for_content);
|
||||
if hidden_below > 0 {
|
||||
let more_line = Line::from(vec![
|
||||
Span::styled(format!("... {} more below", hidden_below), Typography::muted())
|
||||
]);
|
||||
visible_lines.push(more_line);
|
||||
}
|
||||
|
||||
let paragraph = Paragraph::new(Text::from(visible_lines));
|
||||
frame.render_widget(paragraph, area);
|
||||
} else {
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "cm-dashboard-shared"
|
||||
version = "0.1.51"
|
||||
version = "0.1.109"
|
||||
edition = "2021"
|
||||
|
||||
[dependencies]
|
||||
|
||||
@@ -82,11 +82,13 @@ impl MetricValue {
|
||||
/// Health status for metrics
|
||||
#[derive(Debug, Clone, Copy, Serialize, Deserialize, PartialEq, Eq, PartialOrd, Ord)]
|
||||
pub enum Status {
|
||||
Ok,
|
||||
Pending,
|
||||
Warning,
|
||||
Critical,
|
||||
Unknown,
|
||||
Inactive, // Lowest priority
|
||||
Unknown, //
|
||||
Offline, //
|
||||
Pending, //
|
||||
Ok, // 5th place - good status has higher priority than unknown states
|
||||
Warning, //
|
||||
Critical, // Highest priority
|
||||
}
|
||||
|
||||
impl Status {
|
||||
@@ -180,6 +182,16 @@ impl HysteresisThresholds {
|
||||
Status::Ok
|
||||
}
|
||||
}
|
||||
Status::Inactive => {
|
||||
// Inactive services use normal thresholds like first measurement
|
||||
if value >= self.critical_high {
|
||||
Status::Critical
|
||||
} else if value >= self.warning_high {
|
||||
Status::Warning
|
||||
} else {
|
||||
Status::Ok
|
||||
}
|
||||
}
|
||||
Status::Pending => {
|
||||
// Service transitioning, use normal thresholds like first measurement
|
||||
if value >= self.critical_high {
|
||||
@@ -190,6 +202,16 @@ impl HysteresisThresholds {
|
||||
Status::Ok
|
||||
}
|
||||
}
|
||||
Status::Offline => {
|
||||
// Host coming back online, use normal thresholds like first measurement
|
||||
if value >= self.critical_high {
|
||||
Status::Critical
|
||||
} else if value >= self.warning_high {
|
||||
Status::Warning
|
||||
} else {
|
||||
Status::Ok
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user