Update README.md

This commit is contained in:
2025-02-26 15:25:39 +07:00
parent d6acf632e3
commit baf1723a50
69 changed files with 5525 additions and 0 deletions

293
app/routers/logs.py Normal file
View File

@ -0,0 +1,293 @@
from fastapi import APIRouter, HTTPException, Query
from typing import List, Dict, Any, Optional
import logging
from app.services.nomad_client import NomadService
from app.services.config_service import ConfigService
# Configure logging
logger = logging.getLogger(__name__)
router = APIRouter()
nomad_service = NomadService()
config_service = ConfigService()
# More specific routes first
@router.get("/repository/{repository}")
async def get_repository_logs(
repository: str,
log_type: str = Query("stderr", description="Log type: stdout or stderr"),
limit: int = Query(1, description="Number of allocations to return logs for"),
plain_text: bool = Query(False, description="Return plain text logs instead of JSON")
):
"""Get logs for a repository's associated job."""
# Get the job info for the repository
job_info = config_service.get_job_from_repository(repository)
if not job_info:
raise HTTPException(status_code=404, detail=f"No job found for repository: {repository}")
job_id = job_info.get("job_id")
namespace = job_info.get("namespace")
logger.info(f"Getting logs for job {job_id} in namespace {namespace}")
# Create a custom service with the specific namespace if provided
custom_nomad = NomadService()
if namespace:
custom_nomad.namespace = namespace
# Get allocations for the job
allocations = custom_nomad.get_allocations(job_id)
if not allocations:
raise HTTPException(status_code=404, detail=f"No allocations found for job {job_id}")
logger.info(f"Found {len(allocations)} allocations for job {job_id}")
# Sort allocations by creation time (descending)
sorted_allocations = sorted(
allocations,
key=lambda a: a.get("CreateTime", 0),
reverse=True
)
# Limit the number of allocations
allocations_to_check = sorted_allocations[:limit]
# Also get the job info to determine task names
job = custom_nomad.get_job(job_id)
# Collect logs for each allocation and task
result = []
error_messages = []
for alloc in allocations_to_check:
# Use the full UUID of the allocation
alloc_id = alloc.get("ID")
if not alloc_id:
logger.warning(f"Allocation ID not found in allocation data")
error_messages.append("Allocation ID not found in allocation data")
continue
logger.info(f"Processing allocation {alloc_id} for job {job_id}")
# Get task name from the allocation's TaskStates
task_states = alloc.get("TaskStates", {})
if not task_states:
logger.warning(f"No task states found in allocation {alloc_id}")
error_messages.append(f"No task states found in allocation {alloc_id}")
for task_name, task_state in task_states.items():
try:
logger.info(f"Retrieving logs for allocation {alloc_id}, task {task_name}")
logs = custom_nomad.get_allocation_logs(alloc_id, task_name, log_type)
# Check if logs is an error message
if logs and isinstance(logs, str):
if logs.startswith("Error:") or logs.startswith("No "):
logger.warning(f"Error retrieving logs for {task_name}: {logs}")
error_messages.append(logs)
continue
# Only add if we got some logs
if logs:
result.append({
"alloc_id": alloc_id,
"task": task_name,
"type": log_type,
"create_time": alloc.get("CreateTime"),
"logs": logs
})
logger.info(f"Successfully retrieved logs for {task_name}")
else:
error_msg = f"No logs found for {task_name}"
logger.warning(error_msg)
error_messages.append(error_msg)
except Exception as e:
# Log but continue to try other tasks
error_msg = f"Failed to get logs for {alloc_id}/{task_name}: {str(e)}"
logger.error(error_msg)
error_messages.append(error_msg)
# Return as plain text if requested
if plain_text:
if not result:
if error_messages:
return f"No logs found for this job. Errors: {'; '.join(error_messages)}"
return "No logs found for this job"
return "\n\n".join([f"=== {r.get('task')} ===\n{r.get('logs')}" for r in result])
# Otherwise return as JSON
return {
"job_id": job_id,
"repository": repository,
"namespace": namespace,
"allocation_logs": result,
"errors": error_messages if error_messages else None
}
@router.get("/job/{job_id}")
async def get_job_logs(
job_id: str,
namespace: str = Query(None, description="Nomad namespace"),
log_type: str = Query("stderr", description="Log type: stdout or stderr"),
limit: int = Query(1, description="Number of allocations to return logs for"),
plain_text: bool = Query(False, description="Return plain text logs instead of JSON")
):
"""Get logs for the most recent allocations of a job."""
# Create a custom service with the specific namespace if provided
custom_nomad = NomadService()
if namespace:
custom_nomad.namespace = namespace
logger.info(f"Getting logs for job {job_id} in namespace {namespace}")
else:
logger.info(f"Getting logs for job {job_id} in default namespace")
# Get all allocations for the job
allocations = custom_nomad.get_allocations(job_id)
if not allocations:
raise HTTPException(status_code=404, detail=f"No allocations found for job {job_id}")
logger.info(f"Found {len(allocations)} allocations for job {job_id}")
# Sort allocations by creation time (descending)
sorted_allocations = sorted(
allocations,
key=lambda a: a.get("CreateTime", 0),
reverse=True
)
# Limit the number of allocations
allocations_to_check = sorted_allocations[:limit]
# Collect logs for each allocation and task
result = []
for alloc in allocations_to_check:
alloc_id = alloc.get("ID")
if not alloc_id:
logger.warning(f"Allocation ID not found in allocation data")
continue
logger.info(f"Processing allocation {alloc_id} for job {job_id}")
# Get task names from the allocation's TaskStates
task_states = alloc.get("TaskStates", {})
for task_name, task_state in task_states.items():
try:
logger.info(f"Retrieving logs for allocation {alloc_id}, task {task_name}")
logs = custom_nomad.get_allocation_logs(alloc_id, task_name, log_type)
# Only add if we got some logs and not an error message
if logs and not logs.startswith("No") and not logs.startswith("Error"):
result.append({
"alloc_id": alloc_id,
"task": task_name,
"type": log_type,
"create_time": alloc.get("CreateTime"),
"logs": logs
})
logger.info(f"Successfully retrieved logs for {task_name}")
else:
logger.warning(f"No logs found for {task_name}: {logs}")
except Exception as e:
# Log but continue to try other tasks
logger.error(f"Failed to get logs for {alloc_id}/{task_name}: {str(e)}")
# Return as plain text if requested
if plain_text:
if not result:
return "No logs found for this job"
return "\n\n".join([f"=== {r.get('task')} ===\n{r.get('logs')}" for r in result])
# Otherwise return as JSON
return {
"job_id": job_id,
"namespace": namespace,
"allocation_logs": result
}
@router.get("/latest/{job_id}")
async def get_latest_allocation_logs(
job_id: str,
log_type: str = Query("stderr", description="Log type: stdout or stderr"),
plain_text: bool = Query(False, description="Return plain text logs instead of JSON")
):
"""Get logs from the latest allocation of a job."""
# Get all allocations for the job
allocations = nomad_service.get_allocations(job_id)
if not allocations:
raise HTTPException(status_code=404, detail=f"No allocations found for job {job_id}")
# Sort allocations by creation time (descending)
sorted_allocations = sorted(
allocations,
key=lambda a: a.get("CreateTime", 0),
reverse=True
)
# Get the latest allocation
latest_alloc = sorted_allocations[0]
alloc_id = latest_alloc.get("ID")
# Get task group and task information
job = nomad_service.get_job(job_id)
task_groups = job.get("TaskGroups", [])
# Collect logs for each task in the latest allocation
result = []
for task_group in task_groups:
tasks = task_group.get("Tasks", [])
for task in tasks:
task_name = task.get("Name")
try:
logs = nomad_service.get_allocation_logs(alloc_id, task_name, log_type)
result.append({
"alloc_id": alloc_id,
"task": task_name,
"type": log_type,
"create_time": latest_alloc.get("CreateTime"),
"logs": logs
})
except Exception as e:
# Skip if logs cannot be retrieved for this task
pass
# Return as plain text if requested
if plain_text:
return "\n\n".join([f"=== {r['task']} ===\n{r['logs']}" for r in result])
# Otherwise return as JSON
return {
"job_id": job_id,
"latest_allocation": alloc_id,
"task_logs": result
}
@router.get("/build/{job_id}")
async def get_build_logs(job_id: str, plain_text: bool = Query(False)):
"""Get build logs for a job (usually stderr logs from the latest allocation)."""
# This is a convenience endpoint that returns stderr logs from the latest allocation
return await get_latest_allocation_logs(job_id, "stderr", plain_text)
# Generic allocation logs route last
@router.get("/allocation/{alloc_id}/{task}")
async def get_allocation_logs(
alloc_id: str,
task: str,
log_type: str = Query("stderr", description="Log type: stdout or stderr"),
plain_text: bool = Query(False, description="Return plain text logs instead of JSON")
):
"""Get logs for a specific allocation and task."""
# Validate log_type
if log_type not in ["stdout", "stderr"]:
raise HTTPException(status_code=400, detail="Log type must be stdout or stderr")
# Get logs from Nomad
logs = nomad_service.get_allocation_logs(alloc_id, task, log_type)
# Return as plain text if requested
if plain_text:
return logs
# Otherwise return as JSON
return {"alloc_id": alloc_id, "task": task, "type": log_type, "logs": logs}