[v1,1/4] dts: improve starting and stopping interactive shells
Checks
Commit Message
From: Jeremy Spewock <jspewock@iol.unh.edu>
The InteractiveShell class currently relies on being cleaned up and
shutdown at the time of garbage collection, but this cleanup of the class
does no verification that the session is still running prior to cleanup.
So, if a user were to call this method themselves prior to garbage
collection, it would be called twice and throw an exception when the
desired behavior is to do nothing since the session is already cleaned
up. This is solved by using a weakref and a finalize class which
achieves the same result of calling the method at garbage collection,
but also ensures that it is called exactly once.
Additionally, this fixes issues regarding starting a primary DPDK
application while another is still cleaning up via a retry when starting
interactive shells. It also adds catch for attempting to send a command
to an interactive shell that is not running to create a more descriptive
error message.
Signed-off-by: Jeremy Spewock <jspewock@iol.unh.edu>
---
.../remote_session/interactive_shell.py | 51 ++++++++++++++++---
dts/framework/remote_session/testpmd_shell.py | 4 +-
2 files changed, 45 insertions(+), 10 deletions(-)
Comments
Looks good to me! Thank you for your work.
Reviewed-by: Luca Vizzarro <luca.vizzarro@arm.com>
Reviewed-by: Patrick Robb <probb@iol.unh.edu>
@@ -14,12 +14,14 @@
environment variable configure the timeout of getting the output from command execution.
"""
+import weakref
from abc import ABC
from pathlib import PurePath
from typing import Callable, ClassVar
from paramiko import Channel, SSHClient, channel # type: ignore[import]
+from framework.exception import InteractiveCommandExecutionError
from framework.logger import DTSLogger
from framework.settings import SETTINGS
@@ -32,6 +34,10 @@ class InteractiveShell(ABC):
and collecting input until reaching a certain prompt. All interactive applications
will use the same SSH connection, but each will create their own channel on that
session.
+
+ Attributes:
+ is_started: :data:`True` if the application has started successfully, :data:`False`
+ otherwise.
"""
_interactive_session: SSHClient
@@ -41,6 +47,7 @@ class InteractiveShell(ABC):
_logger: DTSLogger
_timeout: float
_app_args: str
+ _finalizer: weakref.finalize
#: Prompt to expect at the end of output when sending a command.
#: This is often overridden by subclasses.
@@ -58,6 +65,8 @@ class InteractiveShell(ABC):
#: for DPDK on the node will be prepended to the path to the executable.
dpdk_app: ClassVar[bool] = False
+ is_started: bool = False
+
def __init__(
self,
interactive_session: SSHClient,
@@ -93,17 +102,39 @@ def __init__(
def _start_application(self, get_privileged_command: Callable[[str], str] | None) -> None:
"""Starts a new interactive application based on the path to the app.
- This method is often overridden by subclasses as their process for
- starting may look different.
+ This method is often overridden by subclasses as their process for starting may look
+ different. Initialization of the shell on the host can be retried up to 5 times. This is
+ done because some DPDK applications need slightly more time after exiting their script to
+ clean up EAL before others can start.
+
+ When the application is started we also bind a class for finalization to this instance of
+ the shell to ensure proper cleanup of the application.
Args:
get_privileged_command: A function (but could be any callable) that produces
the version of the command with elevated privileges.
"""
+ self._finalizer = weakref.finalize(self, self._close)
+ max_retries = 5
+ self._ssh_channel.settimeout(1)
start_command = f"{self.path} {self._app_args}"
if get_privileged_command is not None:
start_command = get_privileged_command(start_command)
- self.send_command(start_command)
+ self.is_started = True
+ for retry in range(max_retries):
+ try:
+ self.send_command(start_command)
+ break
+ except TimeoutError:
+ self._logger.info(
+ "Interactive shell failed to start, retrying... "
+ f"({retry+1} out of {max_retries})"
+ )
+ else:
+ self._ssh_channel.settimeout(self._timeout)
+ self.is_started = False # update state on failure to start
+ raise InteractiveCommandExecutionError("Failed to start application.")
+ self._ssh_channel.settimeout(self._timeout)
def send_command(self, command: str, prompt: str | None = None) -> str:
"""Send `command` and get all output before the expected ending string.
@@ -125,6 +156,10 @@ def send_command(self, command: str, prompt: str | None = None) -> str:
Returns:
All output in the buffer before expected string.
"""
+ if not self.is_started:
+ raise InteractiveCommandExecutionError(
+ f"Cannot send command {command} to application because the shell is not running."
+ )
self._logger.info(f"Sending: '{command}'")
if prompt is None:
prompt = self._default_prompt
@@ -140,11 +175,11 @@ def send_command(self, command: str, prompt: str | None = None) -> str:
self._logger.debug(f"Got output: {out}")
return out
- def close(self) -> None:
- """Properly free all resources."""
+ def _close(self) -> None:
+ self.is_started = False
self._stdin.close()
self._ssh_channel.close()
- def __del__(self) -> None:
- """Make sure the session is properly closed before deleting the object."""
- self.close()
+ def close(self) -> None:
+ """Properly free all resources."""
+ self._finalizer()
@@ -227,10 +227,10 @@ def set_forward_mode(self, mode: TestPmdForwardingModes, verify: bool = True):
f"Test pmd failed to set fwd mode to {mode.value}"
)
- def close(self) -> None:
+ def _close(self) -> None:
"""Overrides :meth:`~.interactive_shell.close`."""
self.send_command("quit", "")
- return super().close()
+ return super()._close()
def get_capas_rxq(
self, supported_capabilities: MutableSet, unsupported_capabilities: MutableSet