• Stefy Lanza (nextime / spora )'s avatar
    ten connections is a browser's number, not a fan-out's (v0.3.101) · a90b93a2
    Stefy Lanza (nextime / spora ) authored
    One shared session serves every pod, and `requests`' stock adapter keeps ten
    connections per host. `ocr.max_concurrency` defaults to 64 and is 128 on the
    install this came from, so from the ELEVENTH concurrent page onward urllib3
    opened a connection, used it, found the pool full on release and threw it
    away:
    
        urllib3.connectionpool: Connection pool is full, discarding connection:
        194.68.245.54. Connection pool size: 10
    
    74 of those in five minutes — about fourteen a minute against one pod — while
    that run's health checks were timing out. Every discarded connection means the
    next page pays a full TLS handshake to a machine in another country: several
    round trips of latency each, and handshake CPU on the orchestrator at precisely
    the moment it is busiest. It does not CAUSE a slow run, but it multiplies one,
    and it is the part that is ours.
    
    The pool is now sized from the concurrency the install is configured for:
    `ocr.max_concurrency`, floored at 64 and capped at 256. Read at session
    creation rather than at import, because the config is not loaded when this
    module is imported — and because an operator raising max_concurrency should not
    have to know a connection pool exists. An idle connection costs a socket and
    nothing else, which is the cheap side of this trade.
    
    The adapter also carries the floor as its own default, so a `_PinnedAdapter`
    built anywhere cannot silently fall back to ten.
    
    Routing is deliberately unchanged: only https-to-a-bare-IP uses the pinned
    session, everything else still goes through `requests` untouched, so callers
    and tests that patch `requests.get` keep working.
    
    Not a fix for the slowness that exposed it. That host was running MariaDB at
    534% CPU, four Postgres parallel workers, and a backup that had been streaming
    over SFTP for three hours, against coderai's own 8.8% of one core out of
    sixteen — the orchestrator was waiting for a CPU, not using one.
    
    9 tests. Suite: 3151 passed, the same 13 known-stale failures.
    Co-Authored-By: 's avatarClaude Opus 5 <noreply@anthropic.com>
    Claude-Session: https://claude.ai/code/session_01KnfkxBpcZ1v6ypRFFyhrVM
    a90b93a2
Name
Last commit
Last update
..
conftest.py Loading commit data...
ocr_lane_stub_worker.py Loading commit data...
test_admin_auth.py Loading commit data...
test_admin_forward_auth.py Loading commit data...
test_admin_remote_ui.py Loading commit data...
test_adoption_matches_image_and_card.py Loading commit data...
test_audio_ml_backends.py Loading commit data...
test_audio_ml_endpoints.py Loading commit data...
test_autoupgrade.py Loading commit data...
test_autoupgrade_force_options.py Loading commit data...
test_autoupgrade_midnight_force.py Loading commit data...
test_autoupgrade_recovers_a_down_server.py Loading commit data...
test_autoupgrade_sees_training.py Loading commit data...
test_broker_config.py Loading commit data...
test_broker_dispatch.py Loading commit data...
test_broker_protocol.py Loading commit data...
test_broker_shutdown.py Loading commit data...
test_broker_streaming.py Loading commit data...
test_burst_placement.py Loading commit data...
test_character_studio_fetch.py Loading commit data...
test_chat_passthrough.py Loading commit data...
test_chunking.py Loading commit data...
test_cluster.py Loading commit data...
test_compose.py Loading commit data...
test_embed_long_input.py Loading commit data...
test_embedding_capability.py Loading commit data...
test_embedding_repo_file_detection.py Loading commit data...
test_field_report_fixes.py Loading commit data...
test_forward_auth_peer_trust.py Loading commit data...
test_front_api_auth.py Loading commit data...
test_front_inflight_leak.py Loading commit data...
test_front_ocr_swap_gate.py Loading commit data...
test_image_has_c_compiler.py Loading commit data...
test_ledger_out_of_band.py Loading commit data...
test_longcat_avatar_layout.py Loading commit data...
test_longcat_bsa.py Loading commit data...
test_longcat_cancellable.py Loading commit data...
test_longcat_checkpoint_resolve.py Loading commit data...
test_longcat_component_quant.py Loading commit data...
test_longcat_config_ui.py Loading commit data...
test_longcat_external_training.py Loading commit data...
test_longcat_int8_load.py Loading commit data...
test_longcat_lora.py Loading commit data...
test_longcat_orchestration.py Loading commit data...
test_longcat_packaging.py Loading commit data...
test_longcat_placement.py Loading commit data...
test_longcat_progress.py Loading commit data...
test_longcat_prompt_cache.py Loading commit data...
test_longcat_quantize.py Loading commit data...
test_longcat_scale.py Loading commit data...
test_longcat_tasks.py Loading commit data...
test_longcat_variants.py Loading commit data...
test_longcat_vendored_source.py Loading commit data...
test_longcat_venv_env.py Loading commit data...
test_longcat_vram_estimate.py Loading commit data...
test_longcat_worker.py Loading commit data...
test_manual_multimodal_test_client.py Loading commit data...
test_model_scan_cache.py Loading commit data...
test_models_context_window.py Loading commit data...
test_ocr_accent_repair.py Loading commit data...
test_ocr_blank_page.py Loading commit data...
test_ocr_chandra.py Loading commit data...
test_ocr_confidence.py Loading commit data...
test_ocr_degraded_retry.py Loading commit data...
test_ocr_detector_venv.py Loading commit data...
test_ocr_dual_mode.py Loading commit data...
test_ocr_fanout.py Loading commit data...
test_ocr_language.py Loading commit data...
test_ocr_olmocr.py Loading commit data...
test_ocr_raster_pool.py Loading commit data...
test_ocr_request_budgets.py Loading commit data...
test_ocr_resident_budget.py Loading commit data...
test_ocr_resume_engines.py Loading commit data...
test_ocr_resume_shared.py Loading commit data...
test_ocr_served_model.py Loading commit data...
test_ocr_token_trace.py Loading commit data...
test_ocr_unreadable_and_dpi.py Loading commit data...
test_ocr_vram_share_and_fallback.py Loading commit data...
test_ocr_window_published.py Loading commit data...
test_ocr_worker_lanes.py Loading commit data...
test_olmocr_pod_tls.py Loading commit data...
test_oom_priority.py Loading commit data...
test_pod_http_pool.py Loading commit data...
test_pod_log_drain.py Loading commit data...
test_pod_seed_model_type.py Loading commit data...
test_pod_teach_on_unknown_model.py Loading commit data...
test_pod_token_adoption_race.py Loading commit data...
test_pool_growth_adopts.py Loading commit data...
test_proxy_logprobs.py Loading commit data...
test_remote_execution.py Loading commit data...
test_remote_gateway_gate.py Loading commit data...
test_runpod_client_scale.py Loading commit data...
test_runpod_fleet_status.py Loading commit data...
test_runpod_grow_reason.py Loading commit data...
test_runpod_ocr_remotization.py Loading commit data...
test_runpod_placement.py Loading commit data...
test_runpod_pod_extra_args.py Loading commit data...
test_runpod_reaper_grace.py Loading commit data...
test_runpod_regional_volumes.py Loading commit data...
test_runpod_registry_heartbeat.py Loading commit data...
test_runpod_release_and_boot_cancel.py Loading commit data...
test_runpod_request_gpu_choice.py Loading commit data...
test_runpod_restart_orphans.py Loading commit data...
test_runpod_scale_down.py Loading commit data...
test_runpod_scale_out.py Loading commit data...
test_runpod_schedule_region_spend.py Loading commit data...
test_runpod_transient_api.py Loading commit data...
test_runpod_warm_floor_parallel.py Loading commit data...
test_runpod_warm_floor_rerent.py Loading commit data...
test_runpod_warmup.py Loading commit data...
test_shared_pool_adapter_identity.py Loading commit data...
test_studio_composed_surfaces.py Loading commit data...
test_surya_item_cap.py Loading commit data...
test_surya_loop_reported.py Loading commit data...
test_surya_retry_budget.py Loading commit data...
test_surya_runpod_fixes.py Loading commit data...
test_surya_thread_boundary.py Loading commit data...
test_text_lora_to_pod.py Loading commit data...
test_township_api_key.py Loading commit data...
test_township_clip_geometry.py Loading commit data...
test_township_longcat.py Loading commit data...
test_township_page_js.py Loading commit data...
test_township_templates.py Loading commit data...
test_township_video_dataset.py Loading commit data...
test_upgrade_launcher.py Loading commit data...
test_video_as_b64_scope.py Loading commit data...
test_video_geometry.py Loading commit data...
test_vllm_share_self_tuning.py Loading commit data...
test_vram_releasers.py Loading commit data...
test_weight_stores.py Loading commit data...
test_whisper_server_local_models.py Loading commit data...