🚀 Feature: Create dmesg enricher action#2037
🚀 Feature: Create dmesg enricher action#2037letho1608 wants to merge 1 commit intorobusta-dev:masterfrom
Conversation
Create a new action that executes dmesg on a node and returns the output as a FileBlock. This action should work for both NodeEvent and PodEvent, extracting node information from pods when necessary. Affected files: dmesg_enricher.py Signed-off-by: Le Quang Tho <92069270+letho1608@users.noreply.github.com>
|
|
WalkthroughA new Robusta action module has been added that implements dmesg enrichment functionality. The module defines parameters and two action handlers—one for NodeEvent and one for PodEvent—both executing dmesg commands on target nodes and attaching the output as file blocks. Changes
Sequence DiagramsequenceDiagram
participant Event as NodeEvent/PodEvent
participant Action as dmesg_enricher
participant Validator as Validation Logic
participant Executor as RobustaPod.exec_in_debugger_pod
participant Node as Target Node
participant Attachment as Event Enrichment
Event->>Action: Trigger with event & params
Action->>Validator: Extract & validate node
alt Node validation fails
Validator-->>Action: Node missing
Action-->>Event: Log error & return
else Node validation passes
Validator-->>Action: Node valid
Action->>Executor: Execute dmesg (timeout: 60s)
Executor->>Node: Run dmesg command
Node-->>Executor: Return output/error
alt Command fails
Executor-->>Action: Non-zero return code
Action-->>Event: Log failure with stderr
else Command succeeds
Executor-->>Action: Stdout output
Action->>Action: Optionally truncate to tail_lines
Action->>Attachment: Create FileBlock (dmesg.txt)
Attachment->>Event: Attach enriched block
Action-->>Event: Enrichment complete
end
end
Estimated code review effort🎯 2 (Simple) | ⏱️ ~8 minutes 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@playbooks/robusta_playbooks/dmesg_enricher.py`:
- Around line 57-62: The code incorrectly constructs NodeEvent with pod metadata
causing a TypeError; replace the synthetic NodeEvent creation with a real Node
lookup by calling Node.readNode(pod.spec.nodeName), then construct NodeEvent
with the returned Node object and the required named_sinks list before calling
dmesg_enricher(node_event, params); add error handling around Node.readNode to
catch lookup failures (log/skip/early return) so dmesg_enricher is only invoked
when a valid Node is obtained.
- Around line 23-34: The call to RobustaPod.exec_in_debugger_pod is using the
wrong signature and handling its return incorrectly: pass a valid pod_name
string as the first arg, then node_name as the second, and put "dmesg" (the
command) as the third arg to match exec_in_debugger_pod(pod_name, node_name,
cmd, ...); remove invalid kwargs override_container_name and command_timeout and
if needed use supported kwargs like debug_image or custom_annotations; treat the
function's return as a plain str (e.g., assign exec_output =
RobustaPod.exec_in_debugger_pod(...)) and replace the
return_code/.stderr/.stdout checks with a simple emptiness check and error log
(use logging.error with node_name and exec_output), then set output =
exec_output for downstream use (references: RobustaPod.exec_in_debugger_pod,
exec_result/exec_output, node_name, output, logging.error).
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 754e96df-8bda-4e39-b385-ff3900c14b09
📒 Files selected for processing (1)
playbooks/robusta_playbooks/dmesg_enricher.py
| exec_result = RobustaPod.exec_in_debugger_pod( | ||
| "dmesg", | ||
| node_name, | ||
| override_container_name="debug", | ||
| command_timeout=60, | ||
| ) | ||
|
|
||
| if exec_result.return_code != 0: | ||
| logging.error(f"dmesg failed on node {node_name}: {exec_result.stderr}") | ||
| return | ||
|
|
||
| output = exec_result.stdout |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
# Search for exec_in_debugger_pod definition and usage patterns
ast-grep --pattern $'def exec_in_debugger_pod($$$) {
$$$
}'
echo "---"
echo "Checking existing usages in playbooks:"
rg -n "exec_in_debugger_pod" --type py -C 3Repository: robusta-dev/robusta
Length of output: 6151
🏁 Script executed:
sed -n '318,345p' src/robusta/integrations/kubernetes/custom_models.pyRepository: robusta-dev/robusta
Length of output: 1014
Critical: exec_in_debugger_pod API mismatch causes runtime failure.
The method signature exec_in_debugger_pod(pod_name: str, node_name: str, cmd, ...) -> str confirms three critical issues:
- Wrong argument order:
"dmesg"is passed aspod_name(1st arg), but should be thecmd(3rd arg). - Missing pod_name argument: The first positional argument should be a pod identifier string.
- Invalid kwargs:
override_container_nameandcommand_timeoutare not valid parameters; onlydebug_imageandcustom_annotationsare supported. - Return type mismatch: The method returns
str(command output), not an object with.return_code,.stderr,.stdoutattributes. Lines 30-34 will fail when accessing these attributes.
🐛 Proposed fix aligning with the actual API
- exec_result = RobustaPod.exec_in_debugger_pod(
- "dmesg",
- node_name,
- override_container_name="debug",
- command_timeout=60,
- )
-
- if exec_result.return_code != 0:
- logging.error(f"dmesg failed on node {node_name}: {exec_result.stderr}")
- return
-
- output = exec_result.stdout
+ try:
+ output = RobustaPod.exec_in_debugger_pod(
+ pod_name="dmesg-debugger",
+ node_name=node_name,
+ cmd="dmesg",
+ )
+ except Exception as e:
+ logging.error(f"dmesg failed on node {node_name}: {e}")
+ return📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| exec_result = RobustaPod.exec_in_debugger_pod( | |
| "dmesg", | |
| node_name, | |
| override_container_name="debug", | |
| command_timeout=60, | |
| ) | |
| if exec_result.return_code != 0: | |
| logging.error(f"dmesg failed on node {node_name}: {exec_result.stderr}") | |
| return | |
| output = exec_result.stdout | |
| try: | |
| output = RobustaPod.exec_in_debugger_pod( | |
| pod_name="dmesg-debugger", | |
| node_name=node_name, | |
| cmd="dmesg", | |
| ) | |
| except Exception as e: | |
| logging.error(f"dmesg failed on node {node_name}: {e}") | |
| return |
🧰 Tools
🪛 Flake8 (7.3.0)
[error] 23-23: 'RobustaPod' may be undefined, or defined from star imports: robusta.api
(F405)
[error] 31-31: 'logging' may be undefined, or defined from star imports: robusta.api
(F405)
🪛 Ruff (0.15.7)
[error] 23-23: RobustaPod may be undefined, or defined from star imports
(F405)
[error] 31-31: logging may be undefined, or defined from star imports
(F405)
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@playbooks/robusta_playbooks/dmesg_enricher.py` around lines 23 - 34, The call
to RobustaPod.exec_in_debugger_pod is using the wrong signature and handling its
return incorrectly: pass a valid pod_name string as the first arg, then
node_name as the second, and put "dmesg" (the command) as the third arg to match
exec_in_debugger_pod(pod_name, node_name, cmd, ...); remove invalid kwargs
override_container_name and command_timeout and if needed use supported kwargs
like debug_image or custom_annotations; treat the function's return as a plain
str (e.g., assign exec_output = RobustaPod.exec_in_debugger_pod(...)) and
replace the return_code/.stderr/.stdout checks with a simple emptiness check and
error log (use logging.error with node_name and exec_output), then set output =
exec_output for downstream use (references: RobustaPod.exec_in_debugger_pod,
exec_result/exec_output, node_name, output, logging.error).
| node_event = NodeEvent( | ||
| metadata=pod.metadata, | ||
| involvedObject=pod, | ||
| nodeName=pod.spec.nodeName, | ||
| ) | ||
| dmesg_enricher(node_event, params) No newline at end of file |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
# Verify NodeEvent constructor and check how other playbooks create NodeEvent from pods
echo "=== NodeEvent class definition ==="
ast-grep --pattern $'class NodeEvent($$$):
def __init__($$$):
$$$
'
echo ""
echo "=== How other playbooks handle similar pod-to-node scenarios ==="
rg -n "NodeEvent\(" --type py -C 5 playbooks/Repository: robusta-dev/robusta
Length of output: 3569
🏁 Script executed:
#!/bin/bash
# Check PodEvent class and verify named_sinks attribute
echo "=== PodEvent class definition ==="
rg -n "class PodEvent" --type py -A 10 src/robusta/integrations/kubernetes/autogenerated/events.py | head -20
echo ""
echo "=== Check if PodEvent inherits named_sinks ==="
rg -n "class KubernetesResourceEvent" --type py -A 5 src/robusta/integrations/kubernetes/
echo ""
echo "=== Verify named_sinks usage in PodEvent context ==="
rg -n "named_sinks" --type py src/robusta/integrations/kubernetes/autogenerated/events.py | head -10Repository: robusta-dev/robusta
Length of output: 1818
Critical: NodeEvent constructor signature mismatch causes TypeError.
The NodeEvent.__init__ signature requires (obj: Node, named_sinks: List[str]), but the code passes metadata, involvedObject, and nodeName kwargs which do not exist in the constructor. This will raise a TypeError at runtime.
The current approach of synthesizing a NodeEvent from pod metadata cannot work. NodeEvent requires an actual Node object retrieved from the Kubernetes API, not pod metadata.
Use Node.readNode(pod.spec.nodeName) to fetch the real Node object:
Proposed fix
node_event = NodeEvent(
- metadata=pod.metadata,
- involvedObject=pod,
- nodeName=pod.spec.nodeName,
+ obj=Node.readNode(pod.spec.nodeName).obj,
+ named_sinks=event.named_sinks,
)
dmesg_enricher(node_event, params)Add error handling to gracefully handle Node lookup failures.
🧰 Tools
🪛 Flake8 (7.3.0)
[error] 57-57: 'NodeEvent' may be undefined, or defined from star imports: robusta.api
(F405)
🪛 Ruff (0.15.7)
[error] 57-57: NodeEvent may be undefined, or defined from star imports
(F405)
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@playbooks/robusta_playbooks/dmesg_enricher.py` around lines 57 - 62, The code
incorrectly constructs NodeEvent with pod metadata causing a TypeError; replace
the synthetic NodeEvent creation with a real Node lookup by calling
Node.readNode(pod.spec.nodeName), then construct NodeEvent with the returned
Node object and the required named_sinks list before calling
dmesg_enricher(node_event, params); add error handling around Node.readNode to
catch lookup failures (log/skip/early return) so dmesg_enricher is only invoked
when a valid Node is obtained.
2 participants
🚀 New Feature
Problem
Create a new action that executes dmesg on a node and returns the output as a FileBlock. This action should work for both NodeEvent and PodEvent, extracting node information from pods when necessary.
Severity:
mediumFile:
playbooks/robusta_playbooks/dmesg_enricher.pySolution
Create a new file with a function similar to node_bash_enricher but specifically for dmesg. The function should:
Changes
playbooks/robusta_playbooks/dmesg_enricher.py(new)Testing
Closes #549