Fix mojibake text and add md RAID checks

This commit is contained in:
2026-02-25 01:32:55 +03:00
parent 678332e6d0
commit efa5dd9644
3 changed files with 71 additions and 17 deletions

View File

@@ -67,7 +67,7 @@ async def snapshot_details(cb: CallbackQuery):
snap_id = cb.data.split(":", 1)[1] snap_id = cb.data.split(":", 1)[1]
await cb.answer("Loading snapshot…") await cb.answer("Loading snapshot…")
# получаем статистику snapshot # получаем статистику snapshot
rc, raw = await run_cmd( rc, raw = await run_cmd(
["restic", "stats", snap_id, "--json"], ["restic", "stats", snap_id, "--json"],
use_restic_env=True, use_restic_env=True,

View File

@@ -37,7 +37,7 @@ def _npm_api_base(cfg) -> str | None:
def health(cfg, container_map: dict | None = None) -> str: def health(cfg, container_map: dict | None = None) -> str:
lines = ["рџ©є Health check\n"] lines = ["🩺 Health check\n"]
thresholds = cfg.get("thresholds", {}) thresholds = cfg.get("thresholds", {})
disk_warn = int(thresholds.get("disk_warn", 80)) disk_warn = int(thresholds.get("disk_warn", 80))
load_warn = float(thresholds.get("load_warn", 2.0)) load_warn = float(thresholds.get("load_warn", 2.0))
@@ -45,9 +45,9 @@ def health(cfg, container_map: dict | None = None) -> str:
env = os.environ.copy() env = os.environ.copy()
env.update(RESTIC_ENV) env.update(RESTIC_ENV)
subprocess.check_output(["restic", "snapshots"], timeout=10, env=env) subprocess.check_output(["restic", "snapshots"], timeout=10, env=env)
lines.append("рџџў Backup repo reachable") lines.append("🟢 Backup repo reachable")
except Exception: except Exception:
lines.append("🔴 Backup repo unreachable") lines.append("🔴 Backup repo unreachable")
containers = container_map if container_map is not None else _containers_from_cfg(cfg) containers = container_map if container_map is not None else _containers_from_cfg(cfg)
for alias, real in containers.items(): for alias, real in containers.items():
@@ -55,20 +55,20 @@ def health(cfg, container_map: dict | None = None) -> str:
f"docker inspect -f '{{{{.State.Status}}}}' {real}" f"docker inspect -f '{{{{.State.Status}}}}' {real}"
) )
if out.strip() != "running": if out.strip() != "running":
lines.append(f"🔴 {alias} down") lines.append(f"🔴 {alias} down")
else: else:
lines.append(f"рџџў {alias} OK") lines.append(f"🟢 {alias} OK")
npm_cfg = cfg.get("npmplus", {}) npm_cfg = cfg.get("npmplus", {})
npm_base = _npm_api_base(cfg) npm_base = _npm_api_base(cfg)
if npm_base: if npm_base:
npm_status = _request_status(npm_base, npm_cfg.get("verify_tls", True)) npm_status = _request_status(npm_base, npm_cfg.get("verify_tls", True))
if npm_status == 200: if npm_status == 200:
lines.append("рџџў NPMplus API OK") lines.append("🟢 NPMplus API OK")
elif npm_status is None: elif npm_status is None:
lines.append("🔴 NPMplus API unreachable") lines.append("🔴 NPMplus API unreachable")
else: else:
lines.append(f"рџџЎ NPMplus API HTTP {npm_status}") lines.append(f"🟡 NPMplus API HTTP {npm_status}")
g_cfg = cfg.get("gitea", {}) g_cfg = cfg.get("gitea", {})
g_base = (g_cfg.get("base_url") or "").rstrip("/") g_base = (g_cfg.get("base_url") or "").rstrip("/")
@@ -84,22 +84,22 @@ def health(cfg, container_map: dict | None = None) -> str:
g_status = status g_status = status
break break
if g_status == 200: if g_status == 200:
lines.append("рџџў Gitea API OK") lines.append("🟢 Gitea API OK")
elif g_status is None: elif g_status is None:
lines.append("🔴 Gitea API unreachable") lines.append("🔴 Gitea API unreachable")
else: else:
lines.append(f"рџџЎ Gitea API HTTP {g_status}") lines.append(f"🟡 Gitea API HTTP {g_status}")
usage, mount = worst_disk_usage() usage, mount = worst_disk_usage()
if usage is None: if usage is None:
lines.append("вљ пёЏ Disk n/a") lines.append("⚠️ Disk n/a")
elif usage > disk_warn: elif usage > disk_warn:
lines.append(f"рџџЎ Disk {usage}% ({mount})") lines.append(f"🟡 Disk {usage}% ({mount})")
else: else:
lines.append(f"рџџў Disk {usage}% ({mount})") lines.append(f"🟢 Disk {usage}% ({mount})")
load = psutil.getloadavg()[0] load = psutil.getloadavg()[0]
lines.append(f"{'рџџў' if load < load_warn else 'рџџЎ'} Load {load}") lines.append(f"{'🟢' if load < load_warn else '🟡'} Load {load}")
return "\n".join(lines) return "\n".join(lines)

View File

@@ -82,6 +82,53 @@ def list_disks() -> list[str]:
return disks return disks
def list_md_arrays() -> list[str]:
out = _cmd("lsblk -dn -o NAME,TYPE")
arrays = []
for line in out.splitlines():
parts = line.split()
if len(parts) != 2:
continue
name, typ = parts
if typ == "raid" and name.startswith("md"):
arrays.append(f"/dev/{name}")
return arrays
def md_array_status(dev: str) -> str:
out = _cmd("cat /proc/mdstat")
if not out or "ERROR:" in out:
return "⚠️ n/a"
name = dev.rsplit("/", 1)[-1]
lines = out.splitlines()
header = None
idx = -1
for i, line in enumerate(lines):
s = line.strip()
if s.startswith(f"{name} :"):
header = s
idx = i
break
if not header:
return "⚠️ not found in /proc/mdstat"
if "inactive" in header:
return "🔴 inactive"
# Typical mdstat health marker: [UU] for healthy mirrors/raid members.
block = [header]
for line in lines[idx + 1:]:
if not line.strip():
break
block.append(line.strip())
block_text = " ".join(block)
if "[U_" in block_text or "[_U" in block_text:
return "🟡 degraded"
return "🟢 active"
def smart_health(dev: str) -> str: def smart_health(dev: str) -> str:
out = _cmd(f"smartctl -H {dev}") out = _cmd(f"smartctl -H {dev}")
@@ -138,8 +185,9 @@ def smart_last_test(dev: str) -> str:
def disks() -> str: def disks() -> str:
disks = list_disks() disks = list_disks()
md_arrays = list_md_arrays()
if not disks: if not disks and not md_arrays:
return "💽 Disks\n\n❌ No disks found" return "💽 Disks\n\n❌ No disks found"
lines = ["💽 Disks (SMART)\n"] lines = ["💽 Disks (SMART)\n"]
@@ -158,6 +206,12 @@ def disks() -> str:
lines.append(f"{icon} {d}{health}, 🌡 {temp}") lines.append(f"{icon} {d}{health}, 🌡 {temp}")
if md_arrays:
lines.append("")
lines.append("🧱 RAID (md)")
for md in md_arrays:
lines.append(f"{md}{md_array_status(md)}")
return "\n".join(lines) return "\n".join(lines)