Compare commits
41 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 86501fd486 | |||
| 192eea6e0c | |||
| 43fb838c9b | |||
| 54483653f9 | |||
| e47803b705 | |||
| 439d0d9af6 | |||
| 2242b5ddfe | |||
| 9d0f42d55c | |||
| 1da7b5f6e7 | |||
| 006f27f7d9 | |||
| 07422cd0a7 | |||
| de30b80219 | |||
| 7d96ca9fad | |||
| 9b940ebd19 | |||
| 6d4da1b7da | |||
| 1e7f1616aa | |||
| 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 |
124
CLAUDE.md
124
CLAUDE.md
@@ -144,6 +144,130 @@ 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 - Complete Disk Collector Rewrite:**
|
||||
|
||||
The current disk collector has grown complex with mixed legacy/auto-discovery approaches. Planning complete rewrite with clean, simple workflow supporting both physical drives and mergerfs pools.
|
||||
|
||||
**New Clean Architecture:**
|
||||
|
||||
**Discovery Workflow:**
|
||||
1. **`lsblk`** to detect all mount points and backing devices
|
||||
2. **`df`** to get filesystem usage for each mount point
|
||||
3. **Group by physical drive** (nvme0n1, sda, etc.)
|
||||
4. **Parse `/proc/mounts`** for mergerfs pools
|
||||
5. **Generate unified metrics** for both storage types
|
||||
|
||||
**Physical Drive Display:**
|
||||
```
|
||||
● nvme0n1:
|
||||
├─ ● Drive: T: 35°C W: 1%
|
||||
├─ ● Total: 23% 218.0GB/928.2GB
|
||||
├─ ● /boot: 11% 0.1GB/1.0GB
|
||||
└─ ● /: 23% 214.9GB/928.2GB
|
||||
```
|
||||
|
||||
**MergerFS Pool Display:**
|
||||
```
|
||||
● /srv/media (mergerfs):
|
||||
├─ ● Pool: 63% 2355.2GB/3686.4GB
|
||||
├─ Data Disks:
|
||||
│ ├─ ● sdb T: 24°C
|
||||
│ └─ ● sdd T: 27°C
|
||||
└─ ● sdc T: 24°C (parity)
|
||||
```
|
||||
|
||||
**Implementation Benefits:**
|
||||
- **Pure auto-discovery**: No configuration needed
|
||||
- **Clean code paths**: Single workflow for all storage types
|
||||
- **Consistent display**: Status icons on every line, no redundant text
|
||||
- **Simple pipeline**: lsblk → df → group → metrics
|
||||
- **Support for both**: Physical drives and mergerfs pools
|
||||
|
||||
## Important Communication Guidelines
|
||||
|
||||
Keep responses concise and focused. Avoid extensive implementation summaries unless requested.
|
||||
|
||||
230
Cargo.lock
generated
230
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 = "0.1.82"
|
||||
version = "0.1.125"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"chrono",
|
||||
@@ -292,7 +301,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "cm-dashboard-agent"
|
||||
version = "0.1.82"
|
||||
version = "0.1.125"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"async-trait",
|
||||
@@ -315,7 +324,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "cm-dashboard-shared"
|
||||
version = "0.1.82"
|
||||
version = "0.1.125"
|
||||
dependencies = [
|
||||
"chrono",
|
||||
"serde",
|
||||
@@ -503,9 +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"
|
||||
@@ -768,9 +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",
|
||||
@@ -781,9 +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",
|
||||
@@ -794,11 +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",
|
||||
@@ -809,42 +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",
|
||||
@@ -885,9 +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"
|
||||
@@ -897,9 +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"
|
||||
@@ -928,9 +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",
|
||||
@@ -988,9 +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"
|
||||
@@ -1104,6 +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"
|
||||
@@ -1112,15 +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",
|
||||
@@ -1150,9 +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",
|
||||
@@ -1262,36 +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",
|
||||
]
|
||||
@@ -1611,9 +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",
|
||||
@@ -1716,9 +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",
|
||||
@@ -1826,9 +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",
|
||||
@@ -1874,9 +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",
|
||||
@@ -2001,9 +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"
|
||||
@@ -2055,9 +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"
|
||||
@@ -2107,9 +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",
|
||||
@@ -2118,25 +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",
|
||||
@@ -2147,9 +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",
|
||||
@@ -2157,31 +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",
|
||||
@@ -2535,17 +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",
|
||||
@@ -2553,9 +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",
|
||||
@@ -2616,9 +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",
|
||||
@@ -2627,9 +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",
|
||||
@@ -2638,9 +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",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "cm-dashboard-agent"
|
||||
version = "0.1.83"
|
||||
version = "0.1.125"
|
||||
edition = "2021"
|
||||
|
||||
[dependencies]
|
||||
|
||||
@@ -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,
|
||||
}
|
||||
}
|
||||
@@ -379,6 +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() {
|
||||
@@ -412,6 +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>,
|
||||
}
|
||||
|
||||
|
||||
@@ -5,353 +5,159 @@ use cm_dashboard_shared::{Metric, MetricValue, Status, StatusTracker, Hysteresis
|
||||
use crate::config::DiskConfig;
|
||||
use std::process::Command;
|
||||
use std::time::Instant;
|
||||
use std::collections::HashMap;
|
||||
use tracing::debug;
|
||||
|
||||
use super::{Collector, CollectorError};
|
||||
|
||||
/// 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"
|
||||
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
|
||||
}
|
||||
|
||||
/// Information about an individual physical drive
|
||||
#[derive(Debug, Clone)]
|
||||
struct DriveInfo {
|
||||
device: String, // e.g., "sda", "nvme0n1"
|
||||
health_status: String, // e.g., "PASSED", "FAILED"
|
||||
temperature: Option<f32>, // e.g., 45.0°C
|
||||
wear_level: Option<f32>, // e.g., 12.0% (for SSDs)
|
||||
}
|
||||
|
||||
/// Disk usage collector for monitoring filesystem sizes
|
||||
/// Storage collector with clean architecture
|
||||
pub struct DiskCollector {
|
||||
config: DiskConfig,
|
||||
temperature_thresholds: HysteresisThresholds,
|
||||
detected_devices: std::collections::HashMap<String, Vec<String>>, // mount_point -> devices
|
||||
}
|
||||
|
||||
/// A physical drive with its filesystems
|
||||
#[derive(Debug, Clone)]
|
||||
struct PhysicalDrive {
|
||||
device: String, // e.g., "nvme0n1", "sda"
|
||||
filesystems: Vec<Filesystem>, // mounted filesystems on this drive
|
||||
temperature: Option<f32>, // drive temperature
|
||||
wear_level: Option<f32>, // SSD wear level
|
||||
health_status: String, // SMART health
|
||||
}
|
||||
|
||||
/// A mergerfs pool
|
||||
#[derive(Debug, Clone)]
|
||||
struct MergerfsPool {
|
||||
mount_point: String, // e.g., "/srv/media"
|
||||
total_bytes: u64, // pool total capacity
|
||||
used_bytes: u64, // pool used space
|
||||
data_drives: Vec<DriveInfo>, // data member drives
|
||||
parity_drives: Vec<DriveInfo>, // parity drives
|
||||
}
|
||||
|
||||
/// Individual filesystem on a drive
|
||||
#[derive(Debug, Clone)]
|
||||
struct Filesystem {
|
||||
mount_point: String, // e.g., "/", "/boot"
|
||||
total_bytes: u64, // filesystem capacity
|
||||
used_bytes: u64, // filesystem used space
|
||||
}
|
||||
|
||||
/// Drive information for pools
|
||||
#[derive(Debug, Clone)]
|
||||
struct DriveInfo {
|
||||
device: String, // e.g., "sdb", "sdc"
|
||||
mount_point: String, // e.g., "/mnt/disk1"
|
||||
temperature: Option<f32>, // drive temperature
|
||||
wear_level: Option<f32>, // SSD wear level
|
||||
health_status: String, // SMART health
|
||||
}
|
||||
|
||||
/// Discovered storage topology
|
||||
#[derive(Debug)]
|
||||
struct StorageTopology {
|
||||
physical_drives: Vec<PhysicalDrive>,
|
||||
mergerfs_pools: Vec<MergerfsPool>,
|
||||
}
|
||||
|
||||
impl DiskCollector {
|
||||
pub fn new(config: DiskConfig) -> Self {
|
||||
// Create hysteresis thresholds for disk temperature from config
|
||||
let temperature_thresholds = HysteresisThresholds::with_custom_gaps(
|
||||
config.temperature_warning_celsius,
|
||||
5.0, // 5°C gap for recovery
|
||||
5.0,
|
||||
config.temperature_critical_celsius,
|
||||
5.0, // 5°C gap for recovery
|
||||
5.0,
|
||||
);
|
||||
|
||||
// Detect devices for all configured filesystems at startup
|
||||
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);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Self {
|
||||
config,
|
||||
temperature_thresholds,
|
||||
detected_devices,
|
||||
}
|
||||
}
|
||||
|
||||
/// 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)
|
||||
/// Discover all storage using clean workflow: lsblk → df → group
|
||||
fn discover_storage(&self) -> Result<StorageTopology> {
|
||||
debug!("Starting storage discovery");
|
||||
|
||||
// Step 1: Get all mount points and their backing devices using lsblk
|
||||
let mount_devices = self.get_mount_devices()?;
|
||||
debug!("Found {} mount points", mount_devices.len());
|
||||
|
||||
// Step 2: Get filesystem usage for each mount point using df
|
||||
let filesystem_usage = self.get_filesystem_usage(&mount_devices)?;
|
||||
debug!("Got usage data for {} filesystems", filesystem_usage.len());
|
||||
|
||||
// Step 3: Detect mergerfs pools from /proc/mounts
|
||||
let mergerfs_pools = self.discover_mergerfs_pools()?;
|
||||
debug!("Found {} mergerfs pools", mergerfs_pools.len());
|
||||
|
||||
// Step 4: Group regular filesystems by physical drive
|
||||
let physical_drives = self.group_by_physical_drive(&mount_devices, &filesystem_usage, &mergerfs_pools)?;
|
||||
debug!("Grouped into {} physical drives", physical_drives.len());
|
||||
|
||||
Ok(StorageTopology {
|
||||
physical_drives,
|
||||
mergerfs_pools,
|
||||
})
|
||||
}
|
||||
|
||||
|
||||
/// Get configured storage pools with individual drive information
|
||||
fn get_configured_storage_pools(&self) -> Result<Vec<StoragePool>> {
|
||||
let mut storage_pools = Vec::new();
|
||||
|
||||
for fs_config in &self.config.filesystems {
|
||||
if !fs_config.monitor {
|
||||
continue;
|
||||
}
|
||||
|
||||
// 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
|
||||
};
|
||||
|
||||
// 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)?;
|
||||
|
||||
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(),
|
||||
size,
|
||||
used,
|
||||
available,
|
||||
usage_percent: usage_percent as f32,
|
||||
underlying_drives,
|
||||
});
|
||||
|
||||
debug!(
|
||||
"Storage pool '{}' ({}) at {} with {} detected drives",
|
||||
fs_config.name, fs_config.storage_type, fs_config.mount_point, device_names.len()
|
||||
);
|
||||
}
|
||||
Err(e) => {
|
||||
debug!(
|
||||
"Failed to get filesystem info for storage pool '{}': {}",
|
||||
fs_config.name, e
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Ok(storage_pools)
|
||||
}
|
||||
|
||||
/// 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();
|
||||
|
||||
for device_name in device_names {
|
||||
let device_path = format!("/dev/{}", device_name);
|
||||
|
||||
// Get SMART data for this drive
|
||||
let (health_status, temperature, wear_level) = self.get_smart_data(&device_path);
|
||||
|
||||
drives.push(DriveInfo {
|
||||
device: device_name.clone(),
|
||||
health_status: health_status.clone(),
|
||||
temperature,
|
||||
wear_level,
|
||||
});
|
||||
|
||||
debug!(
|
||||
"Drive info for {}: health={}, temp={:?}°C, wear={:?}%",
|
||||
device_name, health_status, temperature, wear_level
|
||||
);
|
||||
}
|
||||
|
||||
Ok(drives)
|
||||
}
|
||||
|
||||
/// Get SMART data for a drive (health, temperature, wear level)
|
||||
fn get_smart_data(&self, device_path: &str) -> (String, Option<f32>, Option<f32>) {
|
||||
// Try to get SMART data using smartctl
|
||||
let output = Command::new("sudo")
|
||||
.arg("smartctl")
|
||||
.arg("-a")
|
||||
.arg(device_path)
|
||||
.output();
|
||||
|
||||
match output {
|
||||
Ok(result) if result.status.success() => {
|
||||
let stdout = String::from_utf8_lossy(&result.stdout);
|
||||
|
||||
// Parse health status
|
||||
let health = if stdout.contains("PASSED") {
|
||||
"PASSED".to_string()
|
||||
} else if stdout.contains("FAILED") {
|
||||
"FAILED".to_string()
|
||||
} else {
|
||||
"UNKNOWN".to_string()
|
||||
};
|
||||
|
||||
// Parse temperature (look for various temperature indicators)
|
||||
let temperature = self.parse_temperature_from_smart(&stdout);
|
||||
|
||||
// Parse wear level (for SSDs)
|
||||
let wear_level = self.parse_wear_level_from_smart(&stdout);
|
||||
|
||||
(health, temperature, wear_level)
|
||||
}
|
||||
_ => {
|
||||
debug!("Failed to get SMART data for {}", device_path);
|
||||
("UNKNOWN".to_string(), None, None)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Parse temperature from SMART output
|
||||
fn parse_temperature_from_smart(&self, smart_output: &str) -> Option<f32> {
|
||||
for line in smart_output.lines() {
|
||||
// Look for temperature in various formats
|
||||
if line.contains("Temperature_Celsius") || line.contains("Temperature") {
|
||||
let parts: Vec<&str> = line.split_whitespace().collect();
|
||||
if parts.len() >= 10 {
|
||||
if let Ok(temp) = parts[9].parse::<f32>() {
|
||||
return Some(temp);
|
||||
}
|
||||
}
|
||||
}
|
||||
// NVMe drives might show temperature differently
|
||||
if line.contains("temperature:") {
|
||||
if let Some(temp_part) = line.split("temperature:").nth(1) {
|
||||
if let Some(temp_str) = temp_part.split_whitespace().next() {
|
||||
if let Ok(temp) = temp_str.parse::<f32>() {
|
||||
return Some(temp);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
None
|
||||
}
|
||||
|
||||
/// Parse wear level from SMART output (SSD wear leveling)
|
||||
/// Supports both NVMe and SATA SSD wear indicators
|
||||
fn parse_wear_level_from_smart(&self, smart_output: &str) -> Option<f32> {
|
||||
for line in smart_output.lines() {
|
||||
let line = line.trim();
|
||||
|
||||
// NVMe drives - direct percentage used
|
||||
if line.contains("Percentage Used:") {
|
||||
if let Some(wear_part) = line.split("Percentage Used:").nth(1) {
|
||||
if let Some(wear_str) = wear_part.split('%').next() {
|
||||
if let Ok(wear) = wear_str.trim().parse::<f32>() {
|
||||
return Some(wear);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// SATA SSD attributes - parse SMART table format
|
||||
// Format: ID ATTRIBUTE_NAME FLAG VALUE WORST THRESH TYPE UPDATED WHEN_FAILED RAW_VALUE
|
||||
let parts: Vec<&str> = line.split_whitespace().collect();
|
||||
if parts.len() >= 10 {
|
||||
// SSD Life Left / Percent Lifetime Remaining (higher = less wear)
|
||||
if line.contains("SSD_Life_Left") || line.contains("Percent_Lifetime_Remain") {
|
||||
if let Ok(remaining) = parts[3].parse::<f32>() { // VALUE column
|
||||
return Some(100.0 - remaining); // Convert remaining to used
|
||||
}
|
||||
}
|
||||
|
||||
// Media Wearout Indicator (lower = more wear, normalize to 0-100)
|
||||
if line.contains("Media_Wearout_Indicator") {
|
||||
if let Ok(remaining) = parts[3].parse::<f32>() { // VALUE column
|
||||
return Some(100.0 - remaining); // Convert remaining to used
|
||||
}
|
||||
}
|
||||
|
||||
// Wear Leveling Count (higher = less wear, but varies by manufacturer)
|
||||
if line.contains("Wear_Leveling_Count") {
|
||||
if let Ok(wear_count) = parts[3].parse::<f32>() { // VALUE column
|
||||
// Most SSDs: 100 = new, decreases with wear
|
||||
if wear_count <= 100.0 {
|
||||
return Some(100.0 - wear_count);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Total LBAs Written - calculate against typical endurance if available
|
||||
// This is more complex and manufacturer-specific, so we skip for now
|
||||
}
|
||||
}
|
||||
None
|
||||
}
|
||||
|
||||
/// Convert bytes to human-readable format
|
||||
fn bytes_to_human_readable(&self, bytes: u64) -> String {
|
||||
const UNITS: &[&str] = &["B", "K", "M", "G", "T"];
|
||||
let mut size = bytes as f64;
|
||||
let mut unit_index = 0;
|
||||
|
||||
while size >= 1024.0 && unit_index < UNITS.len() - 1 {
|
||||
size /= 1024.0;
|
||||
unit_index += 1;
|
||||
}
|
||||
|
||||
if unit_index == 0 {
|
||||
format!("{:.0}{}", size, UNITS[unit_index])
|
||||
} else {
|
||||
format!("{:.1}{}", size, UNITS[unit_index])
|
||||
}
|
||||
}
|
||||
|
||||
/// 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>> {
|
||||
/// Use lsblk to get mount points and their backing devices
|
||||
fn get_mount_devices(&self) -> Result<HashMap<String, String>> {
|
||||
let output = Command::new("lsblk")
|
||||
.args(&["-n", "-o", "NAME,MOUNTPOINT"])
|
||||
.output()?;
|
||||
|
||||
if !output.status.success() {
|
||||
return Ok(Vec::new());
|
||||
return Err(anyhow::anyhow!("lsblk command failed"));
|
||||
}
|
||||
|
||||
let mut mount_devices = HashMap::new();
|
||||
let output_str = String::from_utf8_lossy(&output.stdout);
|
||||
|
||||
for line in output_str.lines() {
|
||||
let parts: Vec<&str> = line.split_whitespace().collect();
|
||||
if parts.len() >= 2 && parts[1] == mount_point {
|
||||
// Remove tree symbols and extract device name (e.g., "├─nvme0n1p2" -> "nvme0n1p2")
|
||||
if parts.len() >= 2 {
|
||||
let device_name = parts[0]
|
||||
.trim_start_matches('├')
|
||||
.trim_start_matches('└')
|
||||
.trim_start_matches('─')
|
||||
.trim();
|
||||
.trim_start_matches(&['├', '└', '─', ' '][..]);
|
||||
let mount_point = parts[1];
|
||||
|
||||
// Extract base device name (e.g., "nvme0n1p2" -> "nvme0n1")
|
||||
if let Some(base_device) = Self::extract_base_device(device_name) {
|
||||
return Ok(vec![base_device]);
|
||||
// Skip unwanted mount points
|
||||
if self.should_skip_mount_point(mount_point) {
|
||||
continue;
|
||||
}
|
||||
|
||||
mount_devices.insert(mount_point.to_string(), device_name.to_string());
|
||||
}
|
||||
}
|
||||
|
||||
Ok(mount_devices)
|
||||
}
|
||||
|
||||
/// Check if we should skip this mount point
|
||||
fn should_skip_mount_point(&self, mount_point: &str) -> bool {
|
||||
let skip_prefixes = ["/proc", "/sys", "/dev", "/tmp", "/run"];
|
||||
skip_prefixes.iter().any(|prefix| mount_point.starts_with(prefix))
|
||||
}
|
||||
|
||||
/// Use df to get filesystem usage for mount points
|
||||
fn get_filesystem_usage(&self, mount_devices: &HashMap<String, String>) -> Result<HashMap<String, (u64, u64)>> {
|
||||
let mut filesystem_usage = HashMap::new();
|
||||
|
||||
for mount_point in mount_devices.keys() {
|
||||
match self.get_filesystem_info(mount_point) {
|
||||
Ok((total, used)) => {
|
||||
filesystem_usage.insert(mount_point.clone(), (total, used));
|
||||
}
|
||||
Err(e) => {
|
||||
debug!("Failed to get filesystem info for {}: {}", mount_point, e);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Ok(Vec::new())
|
||||
Ok(filesystem_usage)
|
||||
}
|
||||
|
||||
/// Extract base device name from partition (e.g., "nvme0n1p2" -> "nvme0n1", "sda1" -> "sda")
|
||||
fn extract_base_device(device_name: &str) -> Option<String> {
|
||||
// Handle NVMe devices (nvme0n1p1 -> nvme0n1)
|
||||
if device_name.starts_with("nvme") {
|
||||
if let Some(p_pos) = device_name.find('p') {
|
||||
return Some(device_name[..p_pos].to_string());
|
||||
}
|
||||
}
|
||||
|
||||
// Handle traditional devices (sda1 -> sda)
|
||||
if device_name.len() > 1 {
|
||||
let chars: Vec<char> = device_name.chars().collect();
|
||||
let mut end_idx = chars.len();
|
||||
|
||||
// Find where the device name ends and partition number begins
|
||||
for (i, &c) in chars.iter().enumerate().rev() {
|
||||
if !c.is_ascii_digit() {
|
||||
end_idx = i + 1;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
if end_idx > 0 && end_idx < chars.len() {
|
||||
return Some(chars[..end_idx].iter().collect());
|
||||
}
|
||||
}
|
||||
|
||||
// If no partition detected, return as-is
|
||||
Some(device_name.to_string())
|
||||
}
|
||||
|
||||
|
||||
/// Get filesystem info using df command
|
||||
fn get_filesystem_info(&self, path: &str) -> Result<(u64, u64)> {
|
||||
let output = Command::new("df")
|
||||
@@ -381,216 +187,782 @@ impl DiskCollector {
|
||||
Ok((total_bytes, used_bytes))
|
||||
}
|
||||
|
||||
/// Discover mergerfs pools from /proc/mounts
|
||||
fn discover_mergerfs_pools(&self) -> Result<Vec<MergerfsPool>> {
|
||||
let mounts_content = std::fs::read_to_string("/proc/mounts")?;
|
||||
let mut pools = Vec::new();
|
||||
|
||||
/// Parse size string (e.g., "120G", "45M") to GB value
|
||||
fn parse_size_to_gb(&self, size_str: &str) -> f32 {
|
||||
let size_str = size_str.trim();
|
||||
if size_str.is_empty() || size_str == "-" {
|
||||
return 0.0;
|
||||
}
|
||||
for line in mounts_content.lines() {
|
||||
let parts: Vec<&str> = line.split_whitespace().collect();
|
||||
if parts.len() >= 3 && parts[2] == "fuse.mergerfs" {
|
||||
let mount_point = parts[1].to_string();
|
||||
let device_sources = parts[0]; // e.g., "/mnt/disk1:/mnt/disk2"
|
||||
|
||||
// Extract numeric part and unit
|
||||
let (num_str, unit) = if let Some(last_char) = size_str.chars().last() {
|
||||
if last_char.is_alphabetic() {
|
||||
let num_part = &size_str[..size_str.len() - 1];
|
||||
let unit_part = &size_str[size_str.len() - 1..];
|
||||
(num_part, unit_part)
|
||||
} else {
|
||||
(size_str, "")
|
||||
// Get pool usage
|
||||
let (total_bytes, used_bytes) = self.get_filesystem_info(&mount_point)
|
||||
.unwrap_or((0, 0));
|
||||
|
||||
// Parse member paths - handle both full paths and numeric references
|
||||
let raw_paths: Vec<String> = device_sources
|
||||
.split(':')
|
||||
.map(|s| s.trim().to_string())
|
||||
.filter(|s| !s.is_empty())
|
||||
.collect();
|
||||
|
||||
// Convert numeric references to actual mount points if needed
|
||||
let mut member_paths = if raw_paths.iter().any(|path| !path.starts_with('/')) {
|
||||
// Handle numeric format like "1:2" by finding corresponding /mnt/disk* paths
|
||||
self.resolve_numeric_mergerfs_paths(&raw_paths)?
|
||||
} else {
|
||||
// Already full paths
|
||||
raw_paths
|
||||
};
|
||||
|
||||
// For SnapRAID setups, also include parity drives as part of the pool
|
||||
let snapraid_parity_paths = self.discover_snapraid_parity_drives()?;
|
||||
member_paths.extend(snapraid_parity_paths);
|
||||
|
||||
// Categorize as data vs parity drives
|
||||
let (data_drives, parity_drives) = match self.categorize_pool_drives(&member_paths) {
|
||||
Ok(drives) => drives,
|
||||
Err(e) => {
|
||||
debug!("Failed to categorize drives for pool {}: {}. Skipping.", mount_point, e);
|
||||
continue;
|
||||
}
|
||||
};
|
||||
|
||||
pools.push(MergerfsPool {
|
||||
mount_point,
|
||||
total_bytes,
|
||||
used_bytes,
|
||||
data_drives,
|
||||
parity_drives,
|
||||
});
|
||||
}
|
||||
} else {
|
||||
(size_str, "")
|
||||
};
|
||||
|
||||
let number: f32 = num_str.parse().unwrap_or(0.0);
|
||||
|
||||
match unit.to_uppercase().as_str() {
|
||||
"T" | "TB" => number * 1024.0,
|
||||
"G" | "GB" => number,
|
||||
"M" | "MB" => number / 1024.0,
|
||||
"K" | "KB" => number / (1024.0 * 1024.0),
|
||||
"B" | "" => number / (1024.0 * 1024.0 * 1024.0),
|
||||
_ => number, // Assume GB if unknown unit
|
||||
}
|
||||
|
||||
Ok(pools)
|
||||
}
|
||||
|
||||
/// Discover SnapRAID parity drives
|
||||
fn discover_snapraid_parity_drives(&self) -> Result<Vec<String>> {
|
||||
let mount_devices = self.get_mount_devices()?;
|
||||
let parity_paths: Vec<String> = mount_devices.keys()
|
||||
.filter(|path| path.contains("parity"))
|
||||
.cloned()
|
||||
.collect();
|
||||
Ok(parity_paths)
|
||||
}
|
||||
|
||||
/// Categorize pool member drives as data vs parity
|
||||
fn categorize_pool_drives(&self, member_paths: &[String]) -> Result<(Vec<DriveInfo>, Vec<DriveInfo>)> {
|
||||
let mut data_drives = Vec::new();
|
||||
let mut parity_drives = Vec::new();
|
||||
|
||||
for path in member_paths {
|
||||
let drive_info = self.get_drive_info_for_path(path)?;
|
||||
|
||||
// Heuristic: if path contains "parity", it's parity
|
||||
if path.to_lowercase().contains("parity") {
|
||||
parity_drives.push(drive_info);
|
||||
} else {
|
||||
data_drives.push(drive_info);
|
||||
}
|
||||
}
|
||||
|
||||
Ok((data_drives, parity_drives))
|
||||
}
|
||||
|
||||
/// Get drive information for a mount path
|
||||
fn get_drive_info_for_path(&self, path: &str) -> Result<DriveInfo> {
|
||||
// Use lsblk to find the backing device
|
||||
let output = Command::new("lsblk")
|
||||
.args(&["-n", "-o", "NAME,MOUNTPOINT"])
|
||||
.output()?;
|
||||
|
||||
let output_str = String::from_utf8_lossy(&output.stdout);
|
||||
let mut device = String::new();
|
||||
|
||||
for line in output_str.lines() {
|
||||
let parts: Vec<&str> = line.split_whitespace().collect();
|
||||
if parts.len() >= 2 && parts[1] == path {
|
||||
device = parts[0]
|
||||
.trim_start_matches('├')
|
||||
.trim_start_matches('└')
|
||||
.trim_start_matches('─')
|
||||
.trim()
|
||||
.to_string();
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
if device.is_empty() {
|
||||
return Err(anyhow::anyhow!("Could not find device for path {}", path));
|
||||
}
|
||||
|
||||
// Extract base device name (e.g., "sda1" -> "sda")
|
||||
let base_device = self.extract_base_device(&device);
|
||||
|
||||
// Get SMART data
|
||||
let (health, temperature, wear) = self.get_smart_data(&format!("/dev/{}", base_device));
|
||||
|
||||
Ok(DriveInfo {
|
||||
device: base_device,
|
||||
mount_point: path.to_string(),
|
||||
temperature,
|
||||
wear_level: wear,
|
||||
health_status: health,
|
||||
})
|
||||
}
|
||||
|
||||
/// Resolve numeric mergerfs references like "1:2" to actual mount paths
|
||||
fn resolve_numeric_mergerfs_paths(&self, numeric_refs: &[String]) -> Result<Vec<String>> {
|
||||
let mut resolved_paths = Vec::new();
|
||||
|
||||
// Get all mount points that look like /mnt/disk* or /mnt/parity*
|
||||
let mount_devices = self.get_mount_devices()?;
|
||||
let mut disk_mounts: Vec<String> = mount_devices.keys()
|
||||
.filter(|path| path.starts_with("/mnt/disk") || path.starts_with("/mnt/parity"))
|
||||
.cloned()
|
||||
.collect();
|
||||
disk_mounts.sort(); // Ensure consistent ordering
|
||||
|
||||
for num_ref in numeric_refs {
|
||||
if let Ok(index) = num_ref.parse::<usize>() {
|
||||
// Convert 1-based index to 0-based
|
||||
if index > 0 && index <= disk_mounts.len() {
|
||||
resolved_paths.push(disk_mounts[index - 1].clone());
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Fallback: if we couldn't resolve, return the original paths
|
||||
if resolved_paths.is_empty() {
|
||||
resolved_paths = numeric_refs.to_vec();
|
||||
}
|
||||
|
||||
Ok(resolved_paths)
|
||||
}
|
||||
|
||||
/// Extract base device name from partition (e.g., "nvme0n1p2" -> "nvme0n1", "sda1" -> "sda")
|
||||
fn extract_base_device(&self, device_name: &str) -> String {
|
||||
// Handle NVMe devices (nvme0n1p1 -> nvme0n1)
|
||||
if device_name.starts_with("nvme") {
|
||||
if let Some(p_pos) = device_name.find('p') {
|
||||
return device_name[..p_pos].to_string();
|
||||
}
|
||||
}
|
||||
|
||||
// Handle traditional devices (sda1 -> sda)
|
||||
if device_name.len() > 1 {
|
||||
let chars: Vec<char> = device_name.chars().collect();
|
||||
let mut end_idx = chars.len();
|
||||
|
||||
// Find where the device name ends and partition number begins
|
||||
for (i, &c) in chars.iter().enumerate().rev() {
|
||||
if !c.is_ascii_digit() {
|
||||
end_idx = i + 1;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
if end_idx > 0 && end_idx < chars.len() {
|
||||
return chars[..end_idx].iter().collect();
|
||||
}
|
||||
}
|
||||
|
||||
// If no partition detected, return as-is
|
||||
device_name.to_string()
|
||||
}
|
||||
|
||||
/// Group filesystems by physical drive (excluding mergerfs members)
|
||||
fn group_by_physical_drive(
|
||||
&self,
|
||||
mount_devices: &HashMap<String, String>,
|
||||
filesystem_usage: &HashMap<String, (u64, u64)>,
|
||||
mergerfs_pools: &[MergerfsPool]
|
||||
) -> Result<Vec<PhysicalDrive>> {
|
||||
let mut drive_groups: HashMap<String, Vec<Filesystem>> = HashMap::new();
|
||||
|
||||
// Get all mergerfs member paths to exclude them
|
||||
let mut mergerfs_members = std::collections::HashSet::new();
|
||||
for pool in mergerfs_pools {
|
||||
for drive in &pool.data_drives {
|
||||
mergerfs_members.insert(drive.mount_point.clone());
|
||||
}
|
||||
for drive in &pool.parity_drives {
|
||||
mergerfs_members.insert(drive.mount_point.clone());
|
||||
}
|
||||
}
|
||||
|
||||
// Group filesystems by base device
|
||||
for (mount_point, device) in mount_devices {
|
||||
// Skip mergerfs member mounts
|
||||
if mergerfs_members.contains(mount_point) {
|
||||
continue;
|
||||
}
|
||||
|
||||
let base_device = self.extract_base_device(device);
|
||||
|
||||
if let Some((total, used)) = filesystem_usage.get(mount_point) {
|
||||
let filesystem = Filesystem {
|
||||
mount_point: mount_point.clone(),
|
||||
total_bytes: *total,
|
||||
used_bytes: *used,
|
||||
};
|
||||
|
||||
drive_groups.entry(base_device).or_insert_with(Vec::new).push(filesystem);
|
||||
}
|
||||
}
|
||||
|
||||
// Convert to PhysicalDrive structs with SMART data
|
||||
let mut physical_drives = Vec::new();
|
||||
for (device, filesystems) in drive_groups {
|
||||
let (health, temperature, wear) = self.get_smart_data(&format!("/dev/{}", device));
|
||||
|
||||
physical_drives.push(PhysicalDrive {
|
||||
device,
|
||||
filesystems,
|
||||
temperature,
|
||||
wear_level: wear,
|
||||
health_status: health,
|
||||
});
|
||||
}
|
||||
|
||||
Ok(physical_drives)
|
||||
}
|
||||
|
||||
/// Get SMART data for a drive
|
||||
fn get_smart_data(&self, device_path: &str) -> (String, Option<f32>, Option<f32>) {
|
||||
let output = Command::new("sudo")
|
||||
.arg("smartctl")
|
||||
.arg("-a")
|
||||
.arg(device_path)
|
||||
.output();
|
||||
|
||||
match output {
|
||||
Ok(result) if result.status.success() => {
|
||||
let stdout = String::from_utf8_lossy(&result.stdout);
|
||||
|
||||
// Parse health status
|
||||
let health = if stdout.contains("PASSED") {
|
||||
"PASSED".to_string()
|
||||
} else if stdout.contains("FAILED") {
|
||||
"FAILED".to_string()
|
||||
} else {
|
||||
"UNKNOWN".to_string()
|
||||
};
|
||||
|
||||
// Parse temperature and wear level
|
||||
let temperature = self.parse_temperature_from_smart(&stdout);
|
||||
let wear_level = self.parse_wear_level_from_smart(&stdout);
|
||||
|
||||
(health, temperature, wear_level)
|
||||
}
|
||||
_ => {
|
||||
debug!("Failed to get SMART data for {}", device_path);
|
||||
("UNKNOWN".to_string(), None, None)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Parse temperature from SMART output
|
||||
fn parse_temperature_from_smart(&self, smart_output: &str) -> Option<f32> {
|
||||
for line in smart_output.lines() {
|
||||
if line.contains("Temperature_Celsius") || line.contains("Temperature") {
|
||||
let parts: Vec<&str> = line.split_whitespace().collect();
|
||||
if parts.len() >= 10 {
|
||||
if let Ok(temp) = parts[9].parse::<f32>() {
|
||||
return Some(temp);
|
||||
}
|
||||
}
|
||||
}
|
||||
if line.contains("temperature:") {
|
||||
if let Some(temp_part) = line.split("temperature:").nth(1) {
|
||||
if let Some(temp_str) = temp_part.split_whitespace().next() {
|
||||
if let Ok(temp) = temp_str.parse::<f32>() {
|
||||
return Some(temp);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
None
|
||||
}
|
||||
|
||||
/// Parse wear level from SMART output
|
||||
fn parse_wear_level_from_smart(&self, smart_output: &str) -> Option<f32> {
|
||||
for line in smart_output.lines() {
|
||||
if line.contains("Percentage Used:") {
|
||||
if let Some(wear_part) = line.split("Percentage Used:").nth(1) {
|
||||
if let Some(wear_str) = wear_part.split('%').next() {
|
||||
if let Ok(wear) = wear_str.trim().parse::<f32>() {
|
||||
return Some(wear);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
let parts: Vec<&str> = line.split_whitespace().collect();
|
||||
if parts.len() >= 10 {
|
||||
if line.contains("SSD_Life_Left") || line.contains("Percent_Lifetime_Remain") {
|
||||
if let Ok(remaining) = parts[3].parse::<f32>() {
|
||||
return Some(100.0 - remaining);
|
||||
}
|
||||
}
|
||||
if line.contains("Wear_Leveling_Count") {
|
||||
if let Ok(wear_count) = parts[3].parse::<f32>() {
|
||||
if wear_count <= 100.0 {
|
||||
return Some(100.0 - wear_count);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
None
|
||||
}
|
||||
|
||||
/// Calculate temperature status with hysteresis
|
||||
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)
|
||||
}
|
||||
|
||||
/// Convert bytes to human readable format
|
||||
fn bytes_to_human_readable(&self, bytes: u64) -> String {
|
||||
const UNITS: &[&str] = &["B", "K", "M", "G", "T"];
|
||||
let mut size = bytes as f64;
|
||||
let mut unit_index = 0;
|
||||
|
||||
while size >= 1024.0 && unit_index < UNITS.len() - 1 {
|
||||
size /= 1024.0;
|
||||
unit_index += 1;
|
||||
}
|
||||
|
||||
if unit_index == 0 {
|
||||
format!("{:.0}{}", size, UNITS[unit_index])
|
||||
} else {
|
||||
format!("{:.1}{}", size, UNITS[unit_index])
|
||||
}
|
||||
}
|
||||
|
||||
/// Convert bytes to gigabytes
|
||||
fn bytes_to_gb(&self, bytes: u64) -> f32 {
|
||||
bytes as f32 / (1024.0 * 1024.0 * 1024.0)
|
||||
}
|
||||
}
|
||||
|
||||
#[async_trait]
|
||||
impl Collector for DiskCollector {
|
||||
|
||||
async fn collect(&self, status_tracker: &mut StatusTracker) -> Result<Vec<Metric>, CollectorError> {
|
||||
let start_time = Instant::now();
|
||||
debug!("Collecting storage pool and individual drive metrics");
|
||||
debug!("Starting clean storage collection");
|
||||
|
||||
let mut metrics = Vec::new();
|
||||
let timestamp = chrono::Utc::now().timestamp() as u64;
|
||||
|
||||
// Get configured storage pools with individual drive data
|
||||
let storage_pools = match self.get_configured_storage_pools() {
|
||||
Ok(pools) => {
|
||||
debug!("Found {} storage pools", pools.len());
|
||||
pools
|
||||
}
|
||||
// Discover storage topology
|
||||
let topology = match self.discover_storage() {
|
||||
Ok(topology) => topology,
|
||||
Err(e) => {
|
||||
debug!("Failed to get storage pools: {}", e);
|
||||
Vec::new()
|
||||
tracing::error!("Storage discovery failed: {}", e);
|
||||
return Ok(metrics);
|
||||
}
|
||||
};
|
||||
|
||||
// Generate metrics for each storage pool and its underlying drives
|
||||
for storage_pool in &storage_pools {
|
||||
let timestamp = chrono::Utc::now().timestamp() as u64;
|
||||
// Generate metrics for physical drives
|
||||
for drive in &topology.physical_drives {
|
||||
self.generate_physical_drive_metrics(&mut metrics, drive, timestamp, status_tracker);
|
||||
}
|
||||
|
||||
// Storage pool overall metrics
|
||||
let pool_name = &storage_pool.name;
|
||||
// Generate metrics for mergerfs pools
|
||||
for pool in &topology.mergerfs_pools {
|
||||
self.generate_mergerfs_pool_metrics(&mut metrics, pool, timestamp, status_tracker);
|
||||
}
|
||||
|
||||
// Parse size strings to get actual values for calculations
|
||||
let size_gb = self.parse_size_to_gb(&storage_pool.size);
|
||||
let used_gb = self.parse_size_to_gb(&storage_pool.used);
|
||||
let avail_gb = self.parse_size_to_gb(&storage_pool.available);
|
||||
// Add total storage count
|
||||
let total_storage = topology.physical_drives.len() + topology.mergerfs_pools.len();
|
||||
metrics.push(Metric {
|
||||
name: "disk_count".to_string(),
|
||||
value: MetricValue::Integer(total_storage as i64),
|
||||
unit: None,
|
||||
description: Some(format!("Total storage: {} drives, {} pools", topology.physical_drives.len(), topology.mergerfs_pools.len())),
|
||||
status: Status::Ok,
|
||||
timestamp,
|
||||
});
|
||||
|
||||
// Calculate status based on configured thresholds
|
||||
let pool_status = if storage_pool.usage_percent >= self.config.usage_critical_percent {
|
||||
let collection_time = start_time.elapsed();
|
||||
debug!("Clean storage collection completed in {:?} with {} metrics", collection_time, metrics.len());
|
||||
|
||||
Ok(metrics)
|
||||
}
|
||||
}
|
||||
|
||||
impl DiskCollector {
|
||||
/// Generate metrics for a physical drive and its filesystems
|
||||
fn generate_physical_drive_metrics(
|
||||
&self,
|
||||
metrics: &mut Vec<Metric>,
|
||||
drive: &PhysicalDrive,
|
||||
timestamp: u64,
|
||||
status_tracker: &mut StatusTracker
|
||||
) {
|
||||
let drive_name = &drive.device;
|
||||
|
||||
// Calculate drive totals
|
||||
let total_capacity: u64 = drive.filesystems.iter().map(|fs| fs.total_bytes).sum();
|
||||
let total_used: u64 = drive.filesystems.iter().map(|fs| fs.used_bytes).sum();
|
||||
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 };
|
||||
|
||||
// Drive health status
|
||||
let health_status = if drive.health_status == "PASSED" { Status::Ok }
|
||||
else if drive.health_status == "FAILED" { Status::Critical }
|
||||
else { Status::Unknown };
|
||||
|
||||
// Usage status
|
||||
let usage_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
|
||||
};
|
||||
|
||||
let drive_status = if health_status == Status::Critical { Status::Critical } else { usage_status };
|
||||
|
||||
// Drive info metrics
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_health", drive_name),
|
||||
value: MetricValue::String(drive.health_status.clone()),
|
||||
unit: None,
|
||||
description: Some(format!("{}: {}", drive_name, drive.health_status)),
|
||||
status: health_status,
|
||||
timestamp,
|
||||
});
|
||||
|
||||
// Drive temperature
|
||||
if let Some(temp) = drive.temperature {
|
||||
let temp_status = self.calculate_temperature_status(
|
||||
&format!("disk_{}_temperature", drive_name), temp, status_tracker
|
||||
);
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_temperature", drive_name),
|
||||
value: MetricValue::Float(temp),
|
||||
unit: Some("°C".to_string()),
|
||||
description: Some(format!("{}: {:.0}°C", drive_name, temp)),
|
||||
status: temp_status,
|
||||
timestamp,
|
||||
});
|
||||
}
|
||||
|
||||
// Drive wear level
|
||||
if let Some(wear) = drive.wear_level {
|
||||
let wear_status = if wear >= self.config.wear_critical_percent { Status::Critical }
|
||||
else if wear >= self.config.wear_warning_percent { Status::Warning }
|
||||
else { Status::Ok };
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_wear_percent", drive_name),
|
||||
value: MetricValue::Float(wear),
|
||||
unit: Some("%".to_string()),
|
||||
description: Some(format!("{}: {:.0}% wear", drive_name, wear)),
|
||||
status: wear_status,
|
||||
timestamp,
|
||||
});
|
||||
}
|
||||
|
||||
// Drive capacity metrics
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_total_gb", drive_name),
|
||||
value: MetricValue::Float(self.bytes_to_gb(total_capacity)),
|
||||
unit: Some("GB".to_string()),
|
||||
description: Some(format!("{}: {}", drive_name, self.bytes_to_human_readable(total_capacity))),
|
||||
status: Status::Ok,
|
||||
timestamp,
|
||||
});
|
||||
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_used_gb", drive_name),
|
||||
value: MetricValue::Float(self.bytes_to_gb(total_used)),
|
||||
unit: Some("GB".to_string()),
|
||||
description: Some(format!("{}: {}", drive_name, self.bytes_to_human_readable(total_used))),
|
||||
status: drive_status.clone(),
|
||||
timestamp,
|
||||
});
|
||||
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_available_gb", drive_name),
|
||||
value: MetricValue::Float(self.bytes_to_gb(total_available)),
|
||||
unit: Some("GB".to_string()),
|
||||
description: Some(format!("{}: {}", drive_name, self.bytes_to_human_readable(total_available))),
|
||||
status: Status::Ok,
|
||||
timestamp,
|
||||
});
|
||||
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_usage_percent", drive_name),
|
||||
value: MetricValue::Float(usage_percent as f32),
|
||||
unit: Some("%".to_string()),
|
||||
description: Some(format!("{}: {:.1}%", drive_name, usage_percent)),
|
||||
status: drive_status,
|
||||
timestamp,
|
||||
});
|
||||
|
||||
// Pool type indicator
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_pool_type", drive_name),
|
||||
value: MetricValue::String(format!("drive ({})", drive.filesystems.len())),
|
||||
unit: None,
|
||||
description: Some(format!("Type: physical drive")),
|
||||
status: Status::Ok,
|
||||
timestamp,
|
||||
});
|
||||
|
||||
// Individual filesystem metrics
|
||||
for filesystem in &drive.filesystems {
|
||||
let fs_name = if filesystem.mount_point == "/" {
|
||||
"root".to_string()
|
||||
} else {
|
||||
filesystem.mount_point.trim_start_matches('/').replace('/', "_")
|
||||
};
|
||||
|
||||
let fs_usage_percent = if filesystem.total_bytes > 0 {
|
||||
(filesystem.used_bytes as f64 / filesystem.total_bytes as f64) * 100.0
|
||||
} else { 0.0 };
|
||||
|
||||
let fs_status = if fs_usage_percent >= self.config.usage_critical_percent as f64 {
|
||||
Status::Critical
|
||||
} else if storage_pool.usage_percent >= self.config.usage_warning_percent {
|
||||
} else if fs_usage_percent >= self.config.usage_warning_percent as f64 {
|
||||
Status::Warning
|
||||
} else {
|
||||
Status::Ok
|
||||
};
|
||||
|
||||
// Storage pool info metrics
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_mount_point", pool_name),
|
||||
value: MetricValue::String(storage_pool.mount_point.clone()),
|
||||
unit: None,
|
||||
description: Some(format!("Mount: {}", storage_pool.mount_point)),
|
||||
status: Status::Ok,
|
||||
timestamp,
|
||||
});
|
||||
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_filesystem", pool_name),
|
||||
value: MetricValue::String(storage_pool.filesystem.clone()),
|
||||
unit: None,
|
||||
description: Some(format!("FS: {}", storage_pool.filesystem)),
|
||||
status: Status::Ok,
|
||||
timestamp,
|
||||
});
|
||||
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_storage_type", pool_name),
|
||||
value: MetricValue::String(storage_pool.storage_type.clone()),
|
||||
unit: None,
|
||||
description: Some(format!("Type: {}", storage_pool.storage_type)),
|
||||
status: Status::Ok,
|
||||
timestamp,
|
||||
});
|
||||
|
||||
// Storage pool size metrics
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_total_gb", pool_name),
|
||||
value: MetricValue::Float(size_gb),
|
||||
unit: Some("GB".to_string()),
|
||||
description: Some(format!("Total: {}", storage_pool.size)),
|
||||
status: Status::Ok,
|
||||
timestamp,
|
||||
});
|
||||
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_used_gb", pool_name),
|
||||
value: MetricValue::Float(used_gb),
|
||||
unit: Some("GB".to_string()),
|
||||
description: Some(format!("Used: {}", storage_pool.used)),
|
||||
status: pool_status,
|
||||
timestamp,
|
||||
});
|
||||
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_available_gb", pool_name),
|
||||
value: MetricValue::Float(avail_gb),
|
||||
unit: Some("GB".to_string()),
|
||||
description: Some(format!("Available: {}", storage_pool.available)),
|
||||
status: Status::Ok,
|
||||
timestamp,
|
||||
});
|
||||
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_usage_percent", pool_name),
|
||||
value: MetricValue::Float(storage_pool.usage_percent),
|
||||
name: format!("disk_{}_fs_{}_usage_percent", drive_name, fs_name),
|
||||
value: MetricValue::Float(fs_usage_percent as f32),
|
||||
unit: Some("%".to_string()),
|
||||
description: Some(format!("Usage: {:.1}%", storage_pool.usage_percent)),
|
||||
status: pool_status,
|
||||
description: Some(format!("{}: {:.0}%", filesystem.mount_point, fs_usage_percent)),
|
||||
status: fs_status.clone(),
|
||||
timestamp,
|
||||
});
|
||||
|
||||
// Individual drive metrics for this storage pool
|
||||
for drive in &storage_pool.underlying_drives {
|
||||
// Drive health status
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_{}_health", pool_name, drive.device),
|
||||
value: MetricValue::String(drive.health_status.clone()),
|
||||
unit: None,
|
||||
description: Some(format!("{}: {}", drive.device, drive.health_status)),
|
||||
status: if drive.health_status == "PASSED" { Status::Ok }
|
||||
else if drive.health_status == "FAILED" { Status::Critical }
|
||||
else { Status::Unknown },
|
||||
timestamp,
|
||||
});
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_fs_{}_used_gb", drive_name, fs_name),
|
||||
value: MetricValue::Float(self.bytes_to_gb(filesystem.used_bytes)),
|
||||
unit: Some("GB".to_string()),
|
||||
description: Some(format!("{}: {}", filesystem.mount_point, self.bytes_to_human_readable(filesystem.used_bytes))),
|
||||
status: fs_status.clone(),
|
||||
timestamp,
|
||||
});
|
||||
|
||||
// Drive temperature
|
||||
if let Some(temp) = drive.temperature {
|
||||
let temp_status = self.calculate_temperature_status(
|
||||
&format!("disk_{}_{}_temperature", pool_name, drive.device),
|
||||
temp,
|
||||
status_tracker
|
||||
);
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_fs_{}_total_gb", drive_name, fs_name),
|
||||
value: MetricValue::Float(self.bytes_to_gb(filesystem.total_bytes)),
|
||||
unit: Some("GB".to_string()),
|
||||
description: Some(format!("{}: {}", filesystem.mount_point, self.bytes_to_human_readable(filesystem.total_bytes))),
|
||||
status: fs_status.clone(),
|
||||
timestamp,
|
||||
});
|
||||
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_{}_temperature", pool_name, drive.device),
|
||||
value: MetricValue::Float(temp),
|
||||
unit: Some("°C".to_string()),
|
||||
description: Some(format!("{}: {:.0}°C", drive.device, temp)),
|
||||
status: temp_status,
|
||||
timestamp,
|
||||
});
|
||||
}
|
||||
let fs_available = filesystem.total_bytes.saturating_sub(filesystem.used_bytes);
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_fs_{}_available_gb", drive_name, fs_name),
|
||||
value: MetricValue::Float(self.bytes_to_gb(fs_available)),
|
||||
unit: Some("GB".to_string()),
|
||||
description: Some(format!("{}: {}", filesystem.mount_point, self.bytes_to_human_readable(fs_available))),
|
||||
status: Status::Ok,
|
||||
timestamp,
|
||||
});
|
||||
|
||||
// Drive wear level (for SSDs)
|
||||
if let Some(wear) = drive.wear_level {
|
||||
let wear_status = if wear >= self.config.wear_critical_percent { Status::Critical }
|
||||
else if wear >= self.config.wear_warning_percent { Status::Warning }
|
||||
else { Status::Ok };
|
||||
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_{}_wear_percent", pool_name, drive.device),
|
||||
value: MetricValue::Float(wear),
|
||||
unit: Some("%".to_string()),
|
||||
description: Some(format!("{}: {:.0}% wear", drive.device, wear)),
|
||||
status: wear_status,
|
||||
timestamp,
|
||||
});
|
||||
}
|
||||
}
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_fs_{}_mount_point", drive_name, fs_name),
|
||||
value: MetricValue::String(filesystem.mount_point.clone()),
|
||||
unit: None,
|
||||
description: Some(format!("Mount: {}", filesystem.mount_point)),
|
||||
status: Status::Ok,
|
||||
timestamp,
|
||||
});
|
||||
}
|
||||
|
||||
// Add storage pool count metric
|
||||
metrics.push(Metric {
|
||||
name: "disk_count".to_string(),
|
||||
value: MetricValue::Integer(storage_pools.len() as i64),
|
||||
unit: None,
|
||||
description: Some(format!("Total storage pools: {}", storage_pools.len())),
|
||||
status: Status::Ok,
|
||||
timestamp: chrono::Utc::now().timestamp() as u64,
|
||||
});
|
||||
|
||||
|
||||
let collection_time = start_time.elapsed();
|
||||
debug!(
|
||||
"Multi-disk collection completed in {:?} with {} metrics",
|
||||
collection_time,
|
||||
metrics.len()
|
||||
);
|
||||
|
||||
Ok(metrics)
|
||||
}
|
||||
|
||||
/// Generate metrics for a mergerfs pool
|
||||
fn generate_mergerfs_pool_metrics(
|
||||
&self,
|
||||
metrics: &mut Vec<Metric>,
|
||||
pool: &MergerfsPool,
|
||||
timestamp: u64,
|
||||
status_tracker: &mut StatusTracker
|
||||
) {
|
||||
// Use consistent pool naming: extract mount point without leading slash
|
||||
let pool_name = if pool.mount_point == "/" {
|
||||
"root".to_string()
|
||||
} else {
|
||||
pool.mount_point.trim_start_matches('/').replace('/', "_")
|
||||
};
|
||||
|
||||
if pool_name.is_empty() {
|
||||
return;
|
||||
}
|
||||
|
||||
let usage_percent = if pool.total_bytes > 0 {
|
||||
(pool.used_bytes as f64 / pool.total_bytes as f64) * 100.0
|
||||
} else { 0.0 };
|
||||
|
||||
// Calculate pool health based on drive health
|
||||
let failed_data = pool.data_drives.iter()
|
||||
.filter(|d| d.health_status != "PASSED")
|
||||
.count();
|
||||
let failed_parity = pool.parity_drives.iter()
|
||||
.filter(|d| d.health_status != "PASSED")
|
||||
.count();
|
||||
|
||||
let pool_health = match (failed_data, failed_parity) {
|
||||
(0, 0) => Status::Ok,
|
||||
(1, 0) | (0, 1) => Status::Warning,
|
||||
_ => Status::Critical,
|
||||
};
|
||||
|
||||
let usage_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
|
||||
};
|
||||
|
||||
let pool_status = if pool_health == Status::Critical { Status::Critical } else { usage_status };
|
||||
|
||||
// Pool metrics
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_mount_point", pool_name),
|
||||
value: MetricValue::String(pool.mount_point.clone()),
|
||||
unit: None,
|
||||
description: Some(format!("Mount: {}", pool.mount_point)),
|
||||
status: Status::Ok,
|
||||
timestamp,
|
||||
});
|
||||
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_pool_type", pool_name),
|
||||
value: MetricValue::String(format!("mergerfs ({}+{})", pool.data_drives.len(), pool.parity_drives.len())),
|
||||
unit: None,
|
||||
description: Some("Type: mergerfs".to_string()),
|
||||
status: Status::Ok,
|
||||
timestamp,
|
||||
});
|
||||
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_pool_health", pool_name),
|
||||
value: MetricValue::String(match pool_health {
|
||||
Status::Ok => "healthy".to_string(),
|
||||
Status::Warning => "degraded".to_string(),
|
||||
Status::Critical => "critical".to_string(),
|
||||
_ => "unknown".to_string(),
|
||||
}),
|
||||
unit: None,
|
||||
description: Some("Pool health".to_string()),
|
||||
status: pool_health,
|
||||
timestamp,
|
||||
});
|
||||
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_total_gb", pool_name),
|
||||
value: MetricValue::Float(self.bytes_to_gb(pool.total_bytes)),
|
||||
unit: Some("GB".to_string()),
|
||||
description: Some(format!("Total: {}", self.bytes_to_human_readable(pool.total_bytes))),
|
||||
status: Status::Ok,
|
||||
timestamp,
|
||||
});
|
||||
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_used_gb", pool_name),
|
||||
value: MetricValue::Float(self.bytes_to_gb(pool.used_bytes)),
|
||||
unit: Some("GB".to_string()),
|
||||
description: Some(format!("Used: {}", self.bytes_to_human_readable(pool.used_bytes))),
|
||||
status: pool_status.clone(),
|
||||
timestamp,
|
||||
});
|
||||
|
||||
let available_bytes = pool.total_bytes.saturating_sub(pool.used_bytes);
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_available_gb", pool_name),
|
||||
value: MetricValue::Float(self.bytes_to_gb(available_bytes)),
|
||||
unit: Some("GB".to_string()),
|
||||
description: Some(format!("Available: {}", self.bytes_to_human_readable(available_bytes))),
|
||||
status: Status::Ok,
|
||||
timestamp,
|
||||
});
|
||||
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_usage_percent", pool_name),
|
||||
value: MetricValue::Float(usage_percent as f32),
|
||||
unit: Some("%".to_string()),
|
||||
description: Some(format!("Usage: {:.1}%", usage_percent)),
|
||||
status: pool_status,
|
||||
timestamp,
|
||||
});
|
||||
|
||||
// Individual drive metrics
|
||||
for drive in &pool.data_drives {
|
||||
self.generate_pool_drive_metrics(metrics, &pool_name, &drive.device, drive, timestamp, status_tracker);
|
||||
}
|
||||
|
||||
for drive in &pool.parity_drives {
|
||||
self.generate_pool_drive_metrics(metrics, &pool_name, &drive.device, drive, timestamp, status_tracker);
|
||||
}
|
||||
}
|
||||
|
||||
/// Generate metrics for drives in mergerfs pools
|
||||
fn generate_pool_drive_metrics(
|
||||
&self,
|
||||
metrics: &mut Vec<Metric>,
|
||||
pool_name: &str,
|
||||
drive_role: &str,
|
||||
drive: &DriveInfo,
|
||||
timestamp: u64,
|
||||
status_tracker: &mut StatusTracker
|
||||
) {
|
||||
let drive_health = if drive.health_status == "PASSED" { Status::Ok }
|
||||
else if drive.health_status == "FAILED" { Status::Critical }
|
||||
else { Status::Unknown };
|
||||
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_{}_health", pool_name, drive_role),
|
||||
value: MetricValue::String(drive.health_status.clone()),
|
||||
unit: None,
|
||||
description: Some(format!("{}: {}", drive.device, drive.health_status)),
|
||||
status: drive_health,
|
||||
timestamp,
|
||||
});
|
||||
|
||||
if let Some(temp) = drive.temperature {
|
||||
let temp_status = self.calculate_temperature_status(
|
||||
&format!("disk_{}_{}_temperature", pool_name, drive_role), temp, status_tracker
|
||||
);
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_{}_temperature", pool_name, drive_role),
|
||||
value: MetricValue::Float(temp),
|
||||
unit: Some("°C".to_string()),
|
||||
description: Some(format!("{}: {:.0}°C", drive.device, temp)),
|
||||
status: temp_status,
|
||||
timestamp,
|
||||
});
|
||||
}
|
||||
|
||||
if let Some(wear) = drive.wear_level {
|
||||
let wear_status = if wear >= self.config.wear_critical_percent { Status::Critical }
|
||||
else if wear >= self.config.wear_warning_percent { Status::Warning }
|
||||
else { Status::Ok };
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_{}_wear_percent", pool_name, drive_role),
|
||||
value: MetricValue::Float(wear),
|
||||
unit: Some("%".to_string()),
|
||||
description: Some(format!("{}: {:.0}% wear", drive.device, wear)),
|
||||
status: wear_status,
|
||||
timestamp,
|
||||
});
|
||||
}
|
||||
}
|
||||
}
|
||||
1327
agent/src/collectors/disk_old.rs
Normal file
1327
agent/src/collectors/disk_old.rs
Normal file
@@ -0,0 +1,1327 @@
|
||||
use anyhow::Result;
|
||||
use async_trait::async_trait;
|
||||
use cm_dashboard_shared::{Metric, MetricValue, Status, StatusTracker, HysteresisThresholds};
|
||||
|
||||
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"
|
||||
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
|
||||
#[derive(Debug, Clone)]
|
||||
struct DriveInfo {
|
||||
device: String, // e.g., "sda", "nvme0n1"
|
||||
health_status: String, // e.g., "PASSED", "FAILED"
|
||||
temperature: Option<f32>, // e.g., 45.0°C
|
||||
wear_level: Option<f32>, // e.g., 12.0% (for SSDs)
|
||||
}
|
||||
|
||||
/// Disk usage collector for monitoring filesystem sizes
|
||||
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 {
|
||||
pub fn new(config: DiskConfig) -> Self {
|
||||
// Create hysteresis thresholds for disk temperature from config
|
||||
let temperature_thresholds = HysteresisThresholds::with_custom_gaps(
|
||||
config.temperature_warning_celsius,
|
||||
5.0, // 5°C gap for recovery
|
||||
config.temperature_critical_celsius,
|
||||
5.0, // 5°C gap for recovery
|
||||
);
|
||||
|
||||
// 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();
|
||||
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);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Self {
|
||||
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 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 };
|
||||
|
||||
// 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 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(),
|
||||
pool_type: pool_type.clone(),
|
||||
size,
|
||||
used,
|
||||
available,
|
||||
usage_percent: usage_percent as f32,
|
||||
underlying_drives,
|
||||
pool_health,
|
||||
});
|
||||
|
||||
debug!(
|
||||
"Legacy configured storage pool '{}' ({:?}) at {} with {} drives, health: {:?}",
|
||||
fs_config.name, pool_type, fs_config.mount_point, drive_count, pool_health
|
||||
);
|
||||
}
|
||||
Err(e) => {
|
||||
debug!(
|
||||
"Failed to get filesystem info for storage pool '{}': {}",
|
||||
fs_config.name, e
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
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();
|
||||
|
||||
for device_name in device_names {
|
||||
let device_path = format!("/dev/{}", device_name);
|
||||
|
||||
// Get SMART data for this drive
|
||||
let (health_status, temperature, wear_level) = self.get_smart_data(&device_path);
|
||||
|
||||
drives.push(DriveInfo {
|
||||
device: device_name.clone(),
|
||||
health_status: health_status.clone(),
|
||||
temperature,
|
||||
wear_level,
|
||||
});
|
||||
|
||||
debug!(
|
||||
"Drive info for {}: health={}, temp={:?}°C, wear={:?}%",
|
||||
device_name, health_status, temperature, wear_level
|
||||
);
|
||||
}
|
||||
|
||||
Ok(drives)
|
||||
}
|
||||
|
||||
/// Get SMART data for a drive (health, temperature, wear level)
|
||||
fn get_smart_data(&self, device_path: &str) -> (String, Option<f32>, Option<f32>) {
|
||||
// Try to get SMART data using smartctl
|
||||
let output = Command::new("sudo")
|
||||
.arg("smartctl")
|
||||
.arg("-a")
|
||||
.arg(device_path)
|
||||
.output();
|
||||
|
||||
match output {
|
||||
Ok(result) if result.status.success() => {
|
||||
let stdout = String::from_utf8_lossy(&result.stdout);
|
||||
|
||||
// Parse health status
|
||||
let health = if stdout.contains("PASSED") {
|
||||
"PASSED".to_string()
|
||||
} else if stdout.contains("FAILED") {
|
||||
"FAILED".to_string()
|
||||
} else {
|
||||
"UNKNOWN".to_string()
|
||||
};
|
||||
|
||||
// Parse temperature (look for various temperature indicators)
|
||||
let temperature = self.parse_temperature_from_smart(&stdout);
|
||||
|
||||
// Parse wear level (for SSDs)
|
||||
let wear_level = self.parse_wear_level_from_smart(&stdout);
|
||||
|
||||
(health, temperature, wear_level)
|
||||
}
|
||||
_ => {
|
||||
debug!("Failed to get SMART data for {}", device_path);
|
||||
("UNKNOWN".to_string(), None, None)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Parse temperature from SMART output
|
||||
fn parse_temperature_from_smart(&self, smart_output: &str) -> Option<f32> {
|
||||
for line in smart_output.lines() {
|
||||
// Look for temperature in various formats
|
||||
if line.contains("Temperature_Celsius") || line.contains("Temperature") {
|
||||
let parts: Vec<&str> = line.split_whitespace().collect();
|
||||
if parts.len() >= 10 {
|
||||
if let Ok(temp) = parts[9].parse::<f32>() {
|
||||
return Some(temp);
|
||||
}
|
||||
}
|
||||
}
|
||||
// NVMe drives might show temperature differently
|
||||
if line.contains("temperature:") {
|
||||
if let Some(temp_part) = line.split("temperature:").nth(1) {
|
||||
if let Some(temp_str) = temp_part.split_whitespace().next() {
|
||||
if let Ok(temp) = temp_str.parse::<f32>() {
|
||||
return Some(temp);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
None
|
||||
}
|
||||
|
||||
/// Parse wear level from SMART output (SSD wear leveling)
|
||||
/// Supports both NVMe and SATA SSD wear indicators
|
||||
fn parse_wear_level_from_smart(&self, smart_output: &str) -> Option<f32> {
|
||||
for line in smart_output.lines() {
|
||||
let line = line.trim();
|
||||
|
||||
// NVMe drives - direct percentage used
|
||||
if line.contains("Percentage Used:") {
|
||||
if let Some(wear_part) = line.split("Percentage Used:").nth(1) {
|
||||
if let Some(wear_str) = wear_part.split('%').next() {
|
||||
if let Ok(wear) = wear_str.trim().parse::<f32>() {
|
||||
return Some(wear);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// SATA SSD attributes - parse SMART table format
|
||||
// Format: ID ATTRIBUTE_NAME FLAG VALUE WORST THRESH TYPE UPDATED WHEN_FAILED RAW_VALUE
|
||||
let parts: Vec<&str> = line.split_whitespace().collect();
|
||||
if parts.len() >= 10 {
|
||||
// SSD Life Left / Percent Lifetime Remaining (higher = less wear)
|
||||
if line.contains("SSD_Life_Left") || line.contains("Percent_Lifetime_Remain") {
|
||||
if let Ok(remaining) = parts[3].parse::<f32>() { // VALUE column
|
||||
return Some(100.0 - remaining); // Convert remaining to used
|
||||
}
|
||||
}
|
||||
|
||||
// Media Wearout Indicator (lower = more wear, normalize to 0-100)
|
||||
if line.contains("Media_Wearout_Indicator") {
|
||||
if let Ok(remaining) = parts[3].parse::<f32>() { // VALUE column
|
||||
return Some(100.0 - remaining); // Convert remaining to used
|
||||
}
|
||||
}
|
||||
|
||||
// Wear Leveling Count (higher = less wear, but varies by manufacturer)
|
||||
if line.contains("Wear_Leveling_Count") {
|
||||
if let Ok(wear_count) = parts[3].parse::<f32>() { // VALUE column
|
||||
// Most SSDs: 100 = new, decreases with wear
|
||||
if wear_count <= 100.0 {
|
||||
return Some(100.0 - wear_count);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Total LBAs Written - calculate against typical endurance if available
|
||||
// This is more complex and manufacturer-specific, so we skip for now
|
||||
}
|
||||
}
|
||||
None
|
||||
}
|
||||
|
||||
/// Convert bytes to human-readable format
|
||||
fn bytes_to_human_readable(&self, bytes: u64) -> String {
|
||||
const UNITS: &[&str] = &["B", "K", "M", "G", "T"];
|
||||
let mut size = bytes as f64;
|
||||
let mut unit_index = 0;
|
||||
|
||||
while size >= 1024.0 && unit_index < UNITS.len() - 1 {
|
||||
size /= 1024.0;
|
||||
unit_index += 1;
|
||||
}
|
||||
|
||||
if unit_index == 0 {
|
||||
format!("{:.0}{}", size, UNITS[unit_index])
|
||||
} else {
|
||||
format!("{:.1}{}", size, UNITS[unit_index])
|
||||
}
|
||||
}
|
||||
|
||||
/// 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")
|
||||
.args(&["-n", "-o", "NAME,MOUNTPOINT"])
|
||||
.output()?;
|
||||
|
||||
if !output.status.success() {
|
||||
return Ok(Vec::new());
|
||||
}
|
||||
|
||||
let output_str = String::from_utf8_lossy(&output.stdout);
|
||||
|
||||
for line in output_str.lines() {
|
||||
let parts: Vec<&str> = line.split_whitespace().collect();
|
||||
if parts.len() >= 2 && parts[1] == mount_point {
|
||||
// Remove tree symbols and extract device name (e.g., "├─nvme0n1p2" -> "nvme0n1p2")
|
||||
let device_name = parts[0]
|
||||
.trim_start_matches('├')
|
||||
.trim_start_matches('└')
|
||||
.trim_start_matches('─')
|
||||
.trim();
|
||||
|
||||
// Extract base device name (e.g., "nvme0n1p2" -> "nvme0n1")
|
||||
if let Some(base_device) = Self::extract_base_device(device_name) {
|
||||
return Ok(vec![base_device]);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Ok(Vec::new())
|
||||
}
|
||||
|
||||
/// Extract base device name from partition (e.g., "nvme0n1p2" -> "nvme0n1", "sda1" -> "sda")
|
||||
fn extract_base_device(device_name: &str) -> Option<String> {
|
||||
// Handle NVMe devices (nvme0n1p1 -> nvme0n1)
|
||||
if device_name.starts_with("nvme") {
|
||||
if let Some(p_pos) = device_name.find('p') {
|
||||
return Some(device_name[..p_pos].to_string());
|
||||
}
|
||||
}
|
||||
|
||||
// Handle traditional devices (sda1 -> sda)
|
||||
if device_name.len() > 1 {
|
||||
let chars: Vec<char> = device_name.chars().collect();
|
||||
let mut end_idx = chars.len();
|
||||
|
||||
// Find where the device name ends and partition number begins
|
||||
for (i, &c) in chars.iter().enumerate().rev() {
|
||||
if !c.is_ascii_digit() {
|
||||
end_idx = i + 1;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
if end_idx > 0 && end_idx < chars.len() {
|
||||
return Some(chars[..end_idx].iter().collect());
|
||||
}
|
||||
}
|
||||
|
||||
// If no partition detected, return as-is
|
||||
Some(device_name.to_string())
|
||||
}
|
||||
|
||||
|
||||
/// Get filesystem info using df command
|
||||
fn get_filesystem_info(&self, path: &str) -> Result<(u64, u64)> {
|
||||
let output = Command::new("df")
|
||||
.arg("--block-size=1")
|
||||
.arg(path)
|
||||
.output()?;
|
||||
|
||||
if !output.status.success() {
|
||||
return Err(anyhow::anyhow!("df command failed for {}", path));
|
||||
}
|
||||
|
||||
let output_str = String::from_utf8(output.stdout)?;
|
||||
let lines: Vec<&str> = output_str.lines().collect();
|
||||
|
||||
if lines.len() < 2 {
|
||||
return Err(anyhow::anyhow!("Unexpected df output format"));
|
||||
}
|
||||
|
||||
let fields: Vec<&str> = lines[1].split_whitespace().collect();
|
||||
if fields.len() < 4 {
|
||||
return Err(anyhow::anyhow!("Unexpected df fields count"));
|
||||
}
|
||||
|
||||
let total_bytes = fields[1].parse::<u64>()?;
|
||||
let used_bytes = fields[2].parse::<u64>()?;
|
||||
|
||||
Ok((total_bytes, used_bytes))
|
||||
}
|
||||
|
||||
|
||||
/// Parse size string (e.g., "120G", "45M") to GB value
|
||||
fn parse_size_to_gb(&self, size_str: &str) -> f32 {
|
||||
let size_str = size_str.trim();
|
||||
if size_str.is_empty() || size_str == "-" {
|
||||
return 0.0;
|
||||
}
|
||||
|
||||
// Extract numeric part and unit
|
||||
let (num_str, unit) = if let Some(last_char) = size_str.chars().last() {
|
||||
if last_char.is_alphabetic() {
|
||||
let num_part = &size_str[..size_str.len() - 1];
|
||||
let unit_part = &size_str[size_str.len() - 1..];
|
||||
(num_part, unit_part)
|
||||
} else {
|
||||
(size_str, "")
|
||||
}
|
||||
} else {
|
||||
(size_str, "")
|
||||
};
|
||||
|
||||
let number: f32 = num_str.parse().unwrap_or(0.0);
|
||||
|
||||
match unit.to_uppercase().as_str() {
|
||||
"T" | "TB" => number * 1024.0,
|
||||
"G" | "GB" => number,
|
||||
"M" | "MB" => number / 1024.0,
|
||||
"K" | "KB" => number / (1024.0 * 1024.0),
|
||||
"B" | "" => number / (1024.0 * 1024.0 * 1024.0),
|
||||
_ => number, // Assume GB if unknown unit
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[async_trait]
|
||||
impl Collector for DiskCollector {
|
||||
|
||||
async fn collect(&self, status_tracker: &mut StatusTracker) -> Result<Vec<Metric>, CollectorError> {
|
||||
let start_time = Instant::now();
|
||||
debug!("Collecting storage pool and individual drive metrics");
|
||||
|
||||
let mut metrics = Vec::new();
|
||||
|
||||
// Get configured storage pools with individual drive data
|
||||
let storage_pools = match self.get_configured_storage_pools() {
|
||||
Ok(pools) => {
|
||||
debug!("Found {} storage pools", pools.len());
|
||||
pools
|
||||
}
|
||||
Err(e) => {
|
||||
debug!("Failed to get storage pools: {}", e);
|
||||
Vec::new()
|
||||
}
|
||||
};
|
||||
|
||||
// Generate metrics for each storage pool and its underlying drives
|
||||
for storage_pool in &storage_pools {
|
||||
let timestamp = chrono::Utc::now().timestamp() as u64;
|
||||
|
||||
// Storage pool overall metrics
|
||||
let pool_name = &storage_pool.name;
|
||||
|
||||
// Parse size strings to get actual values for calculations
|
||||
let size_gb = self.parse_size_to_gb(&storage_pool.size);
|
||||
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 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
|
||||
} else {
|
||||
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),
|
||||
value: MetricValue::String(storage_pool.mount_point.clone()),
|
||||
unit: None,
|
||||
description: Some(format!("Mount: {}", storage_pool.mount_point)),
|
||||
status: Status::Ok,
|
||||
timestamp,
|
||||
});
|
||||
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_filesystem", pool_name),
|
||||
value: MetricValue::String(storage_pool.filesystem.clone()),
|
||||
unit: None,
|
||||
description: Some(format!("FS: {}", storage_pool.filesystem)),
|
||||
status: Status::Ok,
|
||||
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_{}_pool_type", pool_name),
|
||||
value: MetricValue::String(pool_type_str.clone()),
|
||||
unit: None,
|
||||
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),
|
||||
value: MetricValue::Float(size_gb),
|
||||
unit: Some("GB".to_string()),
|
||||
description: Some(format!("Total: {}", storage_pool.size)),
|
||||
status: Status::Ok,
|
||||
timestamp,
|
||||
});
|
||||
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_used_gb", pool_name),
|
||||
value: MetricValue::Float(used_gb),
|
||||
unit: Some("GB".to_string()),
|
||||
description: Some(format!("Used: {}", storage_pool.used)),
|
||||
status: pool_status,
|
||||
timestamp,
|
||||
});
|
||||
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_available_gb", pool_name),
|
||||
value: MetricValue::Float(avail_gb),
|
||||
unit: Some("GB".to_string()),
|
||||
description: Some(format!("Available: {}", storage_pool.available)),
|
||||
status: Status::Ok,
|
||||
timestamp,
|
||||
});
|
||||
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_usage_percent", pool_name),
|
||||
value: MetricValue::Float(storage_pool.usage_percent),
|
||||
unit: Some("%".to_string()),
|
||||
description: Some(format!("Usage: {:.1}%", storage_pool.usage_percent)),
|
||||
status: pool_status,
|
||||
timestamp,
|
||||
});
|
||||
|
||||
// Individual drive metrics for this storage pool
|
||||
for drive in &storage_pool.underlying_drives {
|
||||
// Drive health status
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_{}_health", pool_name, drive.device),
|
||||
value: MetricValue::String(drive.health_status.clone()),
|
||||
unit: None,
|
||||
description: Some(format!("{}: {}", drive.device, drive.health_status)),
|
||||
status: if drive.health_status == "PASSED" { Status::Ok }
|
||||
else if drive.health_status == "FAILED" { Status::Critical }
|
||||
else { Status::Unknown },
|
||||
timestamp,
|
||||
});
|
||||
|
||||
// Drive temperature
|
||||
if let Some(temp) = drive.temperature {
|
||||
let temp_status = self.calculate_temperature_status(
|
||||
&format!("disk_{}_{}_temperature", pool_name, drive.device),
|
||||
temp,
|
||||
status_tracker
|
||||
);
|
||||
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_{}_temperature", pool_name, drive.device),
|
||||
value: MetricValue::Float(temp),
|
||||
unit: Some("°C".to_string()),
|
||||
description: Some(format!("{}: {:.0}°C", drive.device, temp)),
|
||||
status: temp_status,
|
||||
timestamp,
|
||||
});
|
||||
}
|
||||
|
||||
// Drive wear level (for SSDs)
|
||||
if let Some(wear) = drive.wear_level {
|
||||
let wear_status = if wear >= self.config.wear_critical_percent { Status::Critical }
|
||||
else if wear >= self.config.wear_warning_percent { Status::Warning }
|
||||
else { Status::Ok };
|
||||
|
||||
metrics.push(Metric {
|
||||
name: format!("disk_{}_{}_wear_percent", pool_name, drive.device),
|
||||
value: MetricValue::Float(wear),
|
||||
unit: Some("%".to_string()),
|
||||
description: Some(format!("{}: {:.0}% wear", drive.device, wear)),
|
||||
status: wear_status,
|
||||
timestamp,
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
// 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
|
||||
metrics.push(Metric {
|
||||
name: "disk_count".to_string(),
|
||||
value: MetricValue::Integer(storage_pools.len() as i64),
|
||||
unit: None,
|
||||
description: Some(format!("Total storage pools: {}", storage_pools.len())),
|
||||
status: Status::Ok,
|
||||
timestamp: chrono::Utc::now().timestamp() as u64,
|
||||
});
|
||||
|
||||
|
||||
let collection_time = start_time.elapsed();
|
||||
debug!(
|
||||
"Multi-disk collection completed in {:?} with {} metrics",
|
||||
collection_time,
|
||||
metrics.len()
|
||||
);
|
||||
|
||||
Ok(metrics)
|
||||
}
|
||||
}
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "cm-dashboard"
|
||||
version = "0.1.83"
|
||||
version = "0.1.125"
|
||||
edition = "2021"
|
||||
|
||||
[dependencies]
|
||||
|
||||
@@ -55,8 +55,8 @@ pub struct SystemConfig {
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct SshConfig {
|
||||
pub rebuild_user: String,
|
||||
pub rebuild_alias: String,
|
||||
pub backup_alias: String,
|
||||
pub rebuild_cmd: String,
|
||||
pub service_manage_cmd: String,
|
||||
}
|
||||
|
||||
/// Service log file configuration per host
|
||||
|
||||
@@ -220,12 +220,12 @@ impl TuiApp {
|
||||
let connection_ip = self.get_connection_ip(&hostname);
|
||||
// Create command that shows logo, rebuilds, and waits for user input
|
||||
let logo_and_rebuild = format!(
|
||||
"bash -c 'cat << \"EOF\"\nNixOS System Rebuild\nTarget: {} ({})\n\nEOF\nssh -tt {}@{} \"bash -ic {}\"\necho\necho \"========================================\"\necho \"Rebuild completed. Press any key to close...\"\necho \"========================================\"\nread -n 1 -s\nexit'",
|
||||
"echo 'Rebuilding system: {} ({})' && ssh -tt {}@{} \"bash -ic '{}'\"",
|
||||
hostname,
|
||||
connection_ip,
|
||||
self.config.ssh.rebuild_user,
|
||||
connection_ip,
|
||||
self.config.ssh.rebuild_alias
|
||||
self.config.ssh.rebuild_cmd
|
||||
);
|
||||
|
||||
std::process::Command::new("tmux")
|
||||
@@ -244,12 +244,12 @@ impl TuiApp {
|
||||
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!(
|
||||
"bash -c 'cat << \"EOF\"\nBackup Operation\nTarget: {} ({})\n\nEOF\nssh -tt {}@{} \"bash -ic {}\"\necho\necho \"========================================\"\necho \"Backup completed. Press any key to close...\"\necho \"========================================\"\nread -n 1 -s\nexit'",
|
||||
"echo 'Running backup: {} ({})' && ssh -tt {}@{} \"bash -ic '{}'\"",
|
||||
hostname,
|
||||
connection_ip,
|
||||
self.config.ssh.rebuild_user,
|
||||
connection_ip,
|
||||
self.config.ssh.backup_alias
|
||||
format!("{} start borgbackup", self.config.ssh.service_manage_cmd)
|
||||
);
|
||||
|
||||
std::process::Command::new("tmux")
|
||||
@@ -267,13 +267,12 @@ impl TuiApp {
|
||||
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!(
|
||||
"bash -c 'cat << \"EOF\"\nService Start: {}\nTarget: {} ({})\n\nEOF\nssh -tt {}@{} \"echo \\\"Starting service and following logs (Ctrl+C to stop):\\\" && echo \\\"========================================\\\" && sudo systemctl start {} & sudo journalctl -fu {} --since='1 second ago' --no-pager\"\necho\necho \"========================================\"\necho \"Operation completed. Press any key to close...\"\necho \"========================================\"\nread -n 1 -s\nexit'",
|
||||
"echo 'Starting service: {} on {}' && ssh -tt {}@{} \"bash -ic '{} start {}'\"",
|
||||
service_name,
|
||||
hostname,
|
||||
connection_ip,
|
||||
self.config.ssh.rebuild_user,
|
||||
connection_ip,
|
||||
service_name,
|
||||
self.config.ssh.service_manage_cmd,
|
||||
service_name
|
||||
);
|
||||
|
||||
@@ -292,14 +291,12 @@ impl TuiApp {
|
||||
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!(
|
||||
"bash -c 'cat << \"EOF\"\nService Stop: {}.service\nTarget: {} ({})\n\nEOF\nssh -tt {}@{} \"echo \\\"Stopping service...\\\" && sudo systemctl stop {}.service && echo \\\"Service stopped! Final logs:\\\" && echo \\\"========================================\\\" && sudo journalctl -u {}.service --no-pager -n 10 && echo \\\"========================================\\\" && sudo systemctl status {}.service --no-pager -l\"\necho\necho \"========================================\"\necho \"Operation completed. Press any key to close...\"\necho \"========================================\"\nread -n 1 -s\nexit'",
|
||||
"echo 'Stopping service: {} on {}' && ssh -tt {}@{} \"bash -ic '{} stop {}'\"",
|
||||
service_name,
|
||||
hostname,
|
||||
connection_ip,
|
||||
self.config.ssh.rebuild_user,
|
||||
connection_ip,
|
||||
service_name,
|
||||
service_name,
|
||||
self.config.ssh.service_manage_cmd,
|
||||
service_name
|
||||
);
|
||||
|
||||
@@ -313,14 +310,15 @@ impl TuiApp {
|
||||
.ok(); // Ignore errors, tmux will handle them
|
||||
}
|
||||
}
|
||||
KeyCode::Char('J') => {
|
||||
// Show service logs via journalctl in tmux split window
|
||||
KeyCode::Char('L') => {
|
||||
// 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()) {
|
||||
let connection_ip = self.get_connection_ip(&hostname);
|
||||
let journalctl_command = format!(
|
||||
"bash -c \"ssh -tt {}@{} 'sudo journalctl -u {}.service -f --no-pager -n 50'; exit\"",
|
||||
let logs_command = format!(
|
||||
"ssh -tt {}@{} '{} logs {}'",
|
||||
self.config.ssh.rebuild_user,
|
||||
connection_ip,
|
||||
self.config.ssh.service_manage_cmd,
|
||||
service_name
|
||||
);
|
||||
|
||||
@@ -329,37 +327,11 @@ impl TuiApp {
|
||||
.arg("-v")
|
||||
.arg("-p")
|
||||
.arg("30")
|
||||
.arg(&journalctl_command)
|
||||
.arg(&logs_command)
|
||||
.spawn()
|
||||
.ok(); // Ignore errors, tmux will handle them
|
||||
}
|
||||
}
|
||||
KeyCode::Char('L') => {
|
||||
// Show custom service log file 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 connection_ip = self.get_connection_ip(&hostname);
|
||||
let tail_command = format!(
|
||||
"bash -c \"ssh -tt {}@{} 'sudo tail -n 50 -f {}'; exit\"",
|
||||
self.config.ssh.rebuild_user,
|
||||
connection_ip,
|
||||
log_config.log_file_path
|
||||
);
|
||||
|
||||
std::process::Command::new("tmux")
|
||||
.arg("split-window")
|
||||
.arg("-v")
|
||||
.arg("-p")
|
||||
.arg("30")
|
||||
.arg(&tail_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() {
|
||||
@@ -392,7 +364,8 @@ impl TuiApp {
|
||||
if let Some(hostname) = self.current_host.clone() {
|
||||
let connection_ip = self.get_connection_ip(&hostname);
|
||||
let ssh_command = format!(
|
||||
"ssh -tt {}@{}",
|
||||
"echo 'Opening SSH terminal to: {}' && ssh -tt {}@{}",
|
||||
hostname,
|
||||
self.config.ssh.rebuild_user,
|
||||
connection_ip
|
||||
);
|
||||
@@ -616,12 +589,13 @@ impl TuiApp {
|
||||
// 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]))
|
||||
@@ -693,35 +667,27 @@ impl TuiApp {
|
||||
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::Inactive => ok_count += 1, // Treat inactive as OK for aggregation
|
||||
Status::Unknown => {}, // Ignore unknown for aggregation
|
||||
Status::Offline => {}, // Ignore offline 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
|
||||
}
|
||||
}
|
||||
|
||||
@@ -745,9 +711,10 @@ impl TuiApp {
|
||||
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
|
||||
|
||||
@@ -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());
|
||||
}
|
||||
@@ -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));
|
||||
}
|
||||
|
||||
if let Some(wear) = self.backup_disk_wear_percent {
|
||||
sub_items.push(format!("Wear: {:.0}%", wear));
|
||||
}
|
||||
|
||||
// Usage as sub-item
|
||||
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())
|
||||
]));
|
||||
}
|
||||
}
|
||||
|
||||
@@ -209,36 +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)
|
||||
|
||||
@@ -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 {
|
||||
@@ -140,7 +153,9 @@ impl SystemWidget {
|
||||
"steampool" => "/mnt/steampool".to_string(),
|
||||
"steampool_1" => "/steampool_1".to_string(),
|
||||
"steampool_2" => "/steampool_2".to_string(),
|
||||
_ => format!("/{}", pool_name), // Default fallback
|
||||
// For device names (nvme0n1, sda, etc.), use the device name directly
|
||||
name if name.starts_with("nvme") || name.starts_with("sd") || name.starts_with("hd") => name.to_string(),
|
||||
_ => format!("/{}", pool_name), // Default fallback for mount-based pools
|
||||
}
|
||||
}
|
||||
|
||||
@@ -151,32 +166,50 @@ impl SystemWidget {
|
||||
for metric in metrics {
|
||||
if metric.name.starts_with("disk_") {
|
||||
if let Some(pool_name) = self.extract_pool_name(&metric.name) {
|
||||
let mount_point = self.get_mount_point_for_pool(&pool_name);
|
||||
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
|
||||
mount_point: self.get_mount_point_for_pool(&pool_name), // Default fallback
|
||||
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
|
||||
if metric.name.contains("_usage_percent") {
|
||||
if metric.name.contains("_usage_percent") && !metric.name.contains("_fs_") {
|
||||
// Only use drive-level metrics for pool totals, not filesystem metrics
|
||||
if let MetricValue::Float(usage) = metric.value {
|
||||
pool.usage_percent = Some(usage);
|
||||
pool.status = metric.status.clone();
|
||||
}
|
||||
} else if metric.name.contains("_used_gb") {
|
||||
} else if metric.name.contains("_used_gb") && !metric.name.contains("_fs_") {
|
||||
// Only use drive-level metrics for pool totals, not filesystem metrics
|
||||
if let MetricValue::Float(used) = metric.value {
|
||||
pool.used_gb = Some(used);
|
||||
}
|
||||
} else if metric.name.contains("_total_gb") {
|
||||
} else if metric.name.contains("_total_gb") && !metric.name.contains("_fs_") {
|
||||
// Only use drive-level metrics for pool totals, not filesystem metrics
|
||||
if let MetricValue::Float(total) = metric.value {
|
||||
pool.total_gb = Some(total);
|
||||
}
|
||||
} else if metric.name.contains("_mount_point") {
|
||||
if let MetricValue::String(mount_point) = &metric.value {
|
||||
pool.mount_point = mount_point.clone();
|
||||
}
|
||||
} 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 +250,91 @@ 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();
|
||||
}
|
||||
}
|
||||
_ => {}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -230,26 +348,39 @@ impl SystemWidget {
|
||||
|
||||
/// Extract pool name from disk metric name
|
||||
fn extract_pool_name(&self, metric_name: &str) -> Option<String> {
|
||||
// Pattern: disk_{pool_name}_{drive_name}_{metric_type}
|
||||
// Pattern: disk_{pool_name}_{various suffixes}
|
||||
// Since pool_name can contain underscores, work backwards from known metric suffixes
|
||||
if metric_name.starts_with("disk_") {
|
||||
// First try drive-specific metrics that have device names
|
||||
if let Some(suffix_pos) = metric_name.rfind("_temperature")
|
||||
.or_else(|| metric_name.rfind("_wear_percent"))
|
||||
.or_else(|| metric_name.rfind("_health")) {
|
||||
// Find the second-to-last underscore to get pool name
|
||||
let before_suffix = &metric_name[..suffix_pos];
|
||||
if let Some(drive_start) = before_suffix.rfind('_') {
|
||||
return Some(metric_name[5..drive_start].to_string()); // Skip "disk_"
|
||||
// Handle filesystem metrics: disk_{pool}_fs_{filesystem}_{metric}
|
||||
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
|
||||
// Handle pool-level metrics (usage_percent, used_gb, total_gb, mount_point, pool_type, pool_health)
|
||||
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"))
|
||||
.or_else(|| metric_name.rfind("_mount_point"))
|
||||
.or_else(|| metric_name.rfind("_pool_type"))
|
||||
.or_else(|| metric_name.rfind("_pool_health")) {
|
||||
return Some(metric_name[5..suffix_pos].to_string()); // Skip "disk_"
|
||||
}
|
||||
// Fallback to old behavior for unknown patterns
|
||||
// Handle drive-specific metrics: disk_{pool}_{drive}_{metric}
|
||||
else if let Some(suffix_pos) = metric_name.rfind("_temperature")
|
||||
.or_else(|| metric_name.rfind("_wear_percent"))
|
||||
.or_else(|| metric_name.rfind("_health")) {
|
||||
// For both mergerfs and physical drives: disk_{pool_name}_{drive_name}_{metric}
|
||||
// Extract pool name by finding the second-to-last underscore
|
||||
let before_suffix = &metric_name[..suffix_pos];
|
||||
if let Some(drive_start) = before_suffix.rfind('_') {
|
||||
if drive_start > 5 {
|
||||
return Some(metric_name[5..drive_start].to_string()); // Skip "disk_"
|
||||
}
|
||||
}
|
||||
}
|
||||
// Fallback: extract first component after disk_ prefix
|
||||
else if let Some(captures) = metric_name.strip_prefix("disk_") {
|
||||
if let Some(pos) = captures.find('_') {
|
||||
return Some(captures[..pos].to_string());
|
||||
@@ -259,16 +390,43 @@ 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) {
|
||||
// Extract filesystem name by removing suffix and underscore
|
||||
if let Some(underscore_pos) = after_fs.rfind(&format!("_{}", suffix)) {
|
||||
let fs_name = after_fs[..underscore_pos].to_string();
|
||||
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}
|
||||
// Now using actual device names like: disk_srv_media_sdb_temperature
|
||||
// Since pool_name can contain underscores, work backwards from known metric suffixes
|
||||
if metric_name.starts_with("disk_") {
|
||||
if let Some(suffix_pos) = metric_name.rfind("_temperature")
|
||||
.or_else(|| metric_name.rfind("_wear_percent"))
|
||||
.or_else(|| metric_name.rfind("_health")) {
|
||||
// Find the second-to-last underscore to get the drive name
|
||||
let before_suffix = &metric_name[..suffix_pos];
|
||||
|
||||
// Extract the last component as drive name (e.g., "sdb", "sdc", "nvme0n1")
|
||||
if let Some(drive_start) = before_suffix.rfind('_') {
|
||||
return Some(before_suffix[drive_start + 1..].to_string());
|
||||
}
|
||||
@@ -277,73 +435,191 @@ 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 { "├─" };
|
||||
// Skip pool health line as discussed - removed
|
||||
|
||||
let mut drive_info = Vec::new();
|
||||
if let Some(temp) = drive.temperature {
|
||||
drive_info.push(format!("T: {:.0}C", temp));
|
||||
// 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)
|
||||
}
|
||||
if let Some(wear) = drive.wear_percent {
|
||||
drive_info.push(format!("W: {:.0}%", wear));
|
||||
_ => "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.contains("mergerfs") && 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() {
|
||||
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, "│ ├─");
|
||||
}
|
||||
}
|
||||
}
|
||||
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));
|
||||
}
|
||||
// Show parity drives
|
||||
if !parity_drives.is_empty() {
|
||||
lines.push(Line::from(vec![
|
||||
Span::raw(" "),
|
||||
Span::styled("└─ ", Typography::tree()),
|
||||
Span::styled("Parity:", Typography::secondary()),
|
||||
]));
|
||||
|
||||
// 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));
|
||||
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 if pool.pool_type != "single" && pool.drives.len() > 1 {
|
||||
// Regular drive listing for non-mergerfs multi-drive 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));
|
||||
}
|
||||
|
||||
// Always show drive name with info, or just name if no info available
|
||||
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 {
|
||||
@@ -513,48 +789,9 @@ 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();
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "cm-dashboard-shared"
|
||||
version = "0.1.83"
|
||||
version = "0.1.125"
|
||||
edition = "2021"
|
||||
|
||||
[dependencies]
|
||||
|
||||
@@ -82,13 +82,13 @@ impl MetricValue {
|
||||
/// Health status for metrics
|
||||
#[derive(Debug, Clone, Copy, Serialize, Deserialize, PartialEq, Eq, PartialOrd, Ord)]
|
||||
pub enum Status {
|
||||
Inactive, // Lowest priority - treated as good
|
||||
Ok, // Second lowest - also good
|
||||
Unknown,
|
||||
Offline,
|
||||
Pending,
|
||||
Warning,
|
||||
Critical,
|
||||
Inactive, // Lowest priority
|
||||
Unknown, //
|
||||
Offline, //
|
||||
Pending, //
|
||||
Ok, // 5th place - good status has higher priority than unknown states
|
||||
Warning, //
|
||||
Critical, // Highest priority
|
||||
}
|
||||
|
||||
impl Status {
|
||||
|
||||
Reference in New Issue
Block a user