Leonid Pershin
a563ae06c4
- Updated version number in pyproject.toml and __init__.py to 0.2.0. - Revised README.md to reflect the current state of the project, including usage instructions and setup steps. - Improved CLI documentation in cli.md, adding details about new commands and their functionalities. - Enhanced the quick start section in README.md for better clarity on initial setup. - Updated local folder documentation to clarify file handling and commands. - Added a new command for listing GPU flavors and improved error handling in the CLI. - Implemented a watchdog feature in the tunnel to manage server states effectively.
92 lines
2.9 KiB
Python
92 lines
2.9 KiB
Python
"""Grow data volume upward (Cinder extend + resize2fs on VM)."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import shlex
|
|
import time
|
|
from collections.abc import Callable
|
|
|
|
from gpu_rent.config import Config
|
|
from gpu_rent.errors import CloudError, GpuRentError
|
|
from gpu_rent.os_client import DATA_VOLUME_NAME, connect, find_volumes_by_name
|
|
from gpu_rent.ssh_ops import run_ssh
|
|
from gpu_rent.state import load_state, save_state
|
|
|
|
Log = Callable[[str], None]
|
|
|
|
_GROW_FS = r"""
|
|
set -euo pipefail
|
|
mnt=/mnt/swarm_data
|
|
src=$(findmnt -n -o SOURCE "$mnt" || true)
|
|
if [[ -z "$src" ]]; then
|
|
echo "data volume not mounted at $mnt"
|
|
exit 1
|
|
fi
|
|
if command -v resize2fs >/dev/null 2>&1; then
|
|
resize2fs "$src"
|
|
elif command -v xfs_growfs >/dev/null 2>&1; then
|
|
xfs_growfs "$mnt"
|
|
else
|
|
echo "нет resize2fs/xfs_growfs"
|
|
exit 1
|
|
fi
|
|
df -h "$mnt"
|
|
"""
|
|
|
|
|
|
def resize_data_volume(cfg: Config, new_gb: int, log: Log) -> None:
|
|
if new_gb < 1:
|
|
raise GpuRentError("--gb должен быть положительным")
|
|
state = load_state()
|
|
vol_id = state.data_volume_id
|
|
conn = connect(cfg)
|
|
if not vol_id:
|
|
found = find_volumes_by_name(conn, DATA_VOLUME_NAME)
|
|
if not found:
|
|
raise CloudError("нет data volume — сначала gpu-rent up")
|
|
vol_id = found[0].id
|
|
state.data_volume_id = vol_id
|
|
save_state(state)
|
|
|
|
vol = conn.block_storage.get_volume(vol_id)
|
|
current = int(getattr(vol, "size", 0) or 0)
|
|
if new_gb < current:
|
|
raise GpuRentError(
|
|
f"вниз нельзя: сейчас {current} GB, запрошено {new_gb} GB. "
|
|
"Selectel online resize только вверх."
|
|
)
|
|
if new_gb == current:
|
|
log(f"data volume уже {current} GB")
|
|
return
|
|
|
|
log(f"Cinder extend {vol_id}: {current} → {new_gb} GB")
|
|
try:
|
|
conn.block_storage.extend_volume(vol, new_gb)
|
|
except Exception:
|
|
try:
|
|
conn.block_storage.extend_volume(vol_id, new_gb)
|
|
except Exception as exc:
|
|
raise CloudError(f"extend volume: {exc}") from exc
|
|
|
|
deadline = time.time() + 600
|
|
while time.time() < deadline:
|
|
cur = conn.block_storage.get_volume(vol_id)
|
|
size = int(getattr(cur, "size", 0) or 0)
|
|
status = (getattr(cur, "status", "") or "").lower()
|
|
if size >= new_gb and status in {"available", "in-use"}:
|
|
log(f"volume size={size} status={status}")
|
|
break
|
|
time.sleep(5)
|
|
else:
|
|
raise CloudError("volume не вырос за 10 мин")
|
|
|
|
host = state.floating_ip
|
|
if not host:
|
|
log("нет FIP — FS на VM не расширяю; подними GPU и повтори resize2fs вручную")
|
|
return
|
|
|
|
log("resize2fs на /mnt/swarm_data…")
|
|
quoted = shlex.quote(_GROW_FS)
|
|
out = run_ssh(cfg, host, f"sudo -n bash -c {quoted}", timeout=180)
|
|
log(out.strip() or "FS grown")
|