Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 8 additions & 4 deletions colossalai/cli/launcher/multinode_runner.py
Original file line number Diff line number Diff line change
@@ -1,8 +1,10 @@
import fabric
from .hostinfo import HostInfo, HostInfoList
from multiprocessing import Pipe, Process
from multiprocessing import connection as mp_connection

import click
import fabric

from .hostinfo import HostInfo, HostInfoList


def run_on_host(hostinfo: HostInfo, workdir: str, recv_conn: mp_connection.Connection,
Expand Down Expand Up @@ -45,8 +47,10 @@ def run_on_host(hostinfo: HostInfo, workdir: str, recv_conn: mp_connection.Conne
# execute on the remote machine
fab_conn.run(cmds, hide=False)
send_conn.send('success')
except:
click.echo(f"Error: failed to run {cmds} on {hostinfo.hostname}")
except Exception as e:
click.echo(
f"Error: failed to run {cmds} on {hostinfo.hostname}, is localhost: {hostinfo.is_local_host}, exception: {e}"
)
send_conn.send('failure')

# shutdown
Expand Down