perf: build info log messages lazily so raising the log level actually saves work (#27837)

Raising GLOBAL_LOG_LEVEL to WARNING buys quieter output but not less work: 241 INFO call sites interpolate their payload into an f-string before the logging call gets to drop it. The heaviest is get_doc, which logs every chunk id and metadata dict in a collection, so on the full-context retrieval path that is the entire knowledge base, once per chat request.

That one line at WARNING, CPython 3.12:

| knowledge base | payload | before   | after   |
| -------------- | ------- | -------- | ------- |
| top-k of 3     | 1.2 kB  | 3.8 us   | 0.07 us |
| 500 chunks     | 201 kB  | 583.6 us | 0.08 us |
| 5000 chunks    | 2.0 MB  | 5.8 ms   | 0.15 us |

The lazy form log.info('query_doc:result %s %s', result.ids, result.metadatas) hands the payload to record.getMessage(), which the InterceptHandler only reaches once a record has passed the level check. Output at INFO is byte-identical. Two sites that already built their message eagerly, one str concat and one % operator, move to the same lazy form.
This commit is contained in:
Classic298 authored and GitHub committed 2026-08-02 15:39:10 -05:00
1 parent 52145eede9
commit 2d18727ab8
48 files changed
+297 -247

No files matched your search

+7 -7
View File
@@ -650,7 +650,7 @@ async def pull_model(
form_data['model'] = form_data.get('model', form_data.get('name'))
url = (await Config.get('ollama.base_urls', []))[url_idx]
log.info(f'url: {url}')
log.info('url: %s', url)
# Admins may pull from any registry
return await send_request(
@@ -881,7 +881,7 @@ async def embed(
if not await Config.get('ollama.enable'):
raise HTTPException(status_code=503, detail=ERROR_MESSAGES.OLLAMA_API_DISABLED)
log.info(f'generate_ollama_batch_embeddings {form_data}')
log.info('generate_ollama_batch_embeddings %s', form_data)
await check_model_access(user, await Models.get_model_by_id(form_data.model), BYPASS_MODEL_ACCESS_CONTROL)
await validate_ollama_backend_idx(request, form_data.model, url_idx, user)
@@ -932,7 +932,7 @@ async def embeddings(
if not await Config.get('ollama.enable'):
raise HTTPException(status_code=503, detail=ERROR_MESSAGES.OLLAMA_API_DISABLED)
log.info(f'generate_ollama_embeddings {form_data}')
log.info('generate_ollama_embeddings %s', form_data)
await check_model_access(user, await Models.get_model_by_id(form_data.model), BYPASS_MODEL_ACCESS_CONTROL)
await validate_ollama_backend_idx(request, form_data.model, url_idx, user)
@@ -1637,11 +1637,11 @@ async def upload_model(
async def file_process_stream():
nonlocal ollama_url
total_size = os.path.getsize(file_path)
log.info(f'Total Model Size: {total_size}')
log.info('Total Model Size: %s', total_size)
# Stage 2: hash the file and emit SSE progress
file_hash = await asyncio.to_thread(calculate_sha256, file_path, chunk_size)
log.info(f'Model Hash: {file_hash}')
log.info('Model Hash: %s', file_hash)
try:
bytes_read = 0
@@ -1675,13 +1675,13 @@ async def upload_model(
# Stage 4: create the model
model, _ext = os.path.splitext(filename)
log.info(f'Created Model: {model}')
log.info('Created Model: %s', model)
create_payload = {
'model': model,
'files': {filename: f'sha256:{file_hash}'},
}
log.info(f'Model Payload: {create_payload}')
log.info('Model Payload: %s', create_payload)
async with session.post(
f'{ollama_url}/api/create',