Author

iQIYI Technical Product Team

The technical product team of iQIYI

402

Articles

Likes

931

Views

Comments

Latest from iQIYI Technical Product Team

100 recent articles max

iQIYI Technical Product Team

Jun 14, 2024 · Operations

Stability Assurance Practices for the 2024 CCTV Spring Festival Gala Live Stream

The 2024 CCTV Spring Festival Gala live stream employed comprehensive stability assurance practices across signal encoding, CDN distribution, request handling, and playback—using multi‑source encoding, multi‑level origin redundancy, multi‑cluster HA, and P2P‑augmented delivery—to handle massive QPS spikes, ensure high availability, and provide a resilient, high‑quality viewing experience.

CDNP2PPerformance Testing

0 likes · 24 min read

Stability Assurance Practices for the 2024 CCTV Spring Festival Gala Live Stream

iQIYI Technical Product Team

Jun 7, 2024 · Cloud Computing

Systematic Management of Cloud Costs and Multi‑Cloud Billing Solutions

To tackle rising multi‑cloud expenses, the Resource Cost Center provides a unified billing platform that standardizes diverse vendor invoices via a common API, automates reconciliation, allocates costs by project tags, offers real‑time dashboards, and plans AI‑driven forecasting and budget alerts.

Cloud Cost ManagementMulti-Cloud Billingautomation

0 likes · 18 min read

Systematic Management of Cloud Costs and Multi‑Cloud Billing Solutions

iQIYI Technical Product Team

May 31, 2024 · Artificial Intelligence

How Opal Turns iQIYI’s ML Workflow into a Unified AI Platform

Opal is iQIYI's end‑to‑end machine‑learning platform that integrates feature production, sample construction, model training, and deployment with big‑data services, addressing duplicated effort, weak data processing, and fragmented pipelines to boost efficiency across recommendation, advertising, and risk‑control scenarios.

AI OperationsBig Data IntegrationDistributed Training

0 likes · 19 min read

How Opal Turns iQIYI’s ML Workflow into a Unified AI Platform

iQIYI Technical Product Team

May 24, 2024 · Operations

High Availability and Disaster Recovery Practices of iQIYI's Video Relay Service (VRS)

iQIYI’s Video Relay Service ensures uninterrupted video playback by employing a two‑region, three‑center hybrid cloud architecture, multi‑layer storage, cross‑AZ retry mechanisms, protective rate‑limiting and degradation paths, layered monitoring, and rigorous stress‑testing and chaos engineering to achieve high availability and disaster recovery.

Monitoringbackend architecturecloud-native

0 likes · 18 min read

High Availability and Disaster Recovery Practices of iQIYI's Video Relay Service (VRS)

iQIYI Technical Product Team

May 10, 2024 · Operations

Full‑Link Load Testing of iQIYI Playback Service: Process, Tools, and Outcomes

iQIYI implemented full‑link load testing of its playback service using LoadMaker for traffic generation and Rover for link control, mapping the topology, creating weighted user scenarios, and safely pressurizing production‑like environments, which validated multi‑times historical peak capacity, uncovered bottlenecks, and enabled several performance and disaster‑recovery improvements without impacting real users.

Load Testingcapacity planningiQIYI

0 likes · 10 min read

Full‑Link Load Testing of iQIYI Playback Service: Process, Tools, and Outcomes

iQIYI Technical Product Team

Apr 26, 2024 · Big Data

iQIYI Real-time Lakehouse: Stream‑Batch Unified Architecture

iQIYI replaced its costly Lambda architecture with a unified Iceberg‑based lakehouse that combines Flink streaming and batch processing, cutting data latency from hours to minutes, supporting thousands of tables via a multi‑table sink, guaranteeing completeness, and saving millions of RMB in operational costs.

FlinkIcebergStream-Batch Integration

0 likes · 18 min read

iQIYI Real-time Lakehouse: Stream‑Batch Unified Architecture

iQIYI Technical Product Team

Apr 19, 2024 · Databases

Root Cause Analysis of Redis Timeout in a Spring Cloud Service Using Lettuce and Netty

A Docker image upgrade reduced Netty EventLoop threads, causing a Pub/Sub listener’s blocking Future.get() to stall one thread, fill a Redis cluster connection’s receive buffer and trigger widespread Redis timeouts in the custom Lettuce cache framework, which were eliminated by increasing I/O threads or making the callback asynchronous.

DockerEventLoopLettuce

0 likes · 15 min read

Root Cause Analysis of Redis Timeout in a Spring Cloud Service Using Lettuce and Netty

iQIYI Technical Product Team

Apr 12, 2024 · Mobile Development

Performance Optimization Strategies for iQIYI Android App on Low-End Devices

iQIYI improves its Android app for low‑end phones by classifying devices, streamlining startup with task‑based scheduling and baseline profiles, reducing UI thread load through card layout hard‑coding, message queuing, effect degradation, and pre‑fetching data, while continuously monitoring performance to ensure faster, smoother user experiences.

AndroidBaseline ProfilesPerformance optimization

0 likes · 16 min read

Performance Optimization Strategies for iQIYI Android App on Low-End Devices

iQIYI Technical Product Team

Mar 15, 2024 · Artificial Intelligence

Optimizing GPU Inference for CTR Models: Kernel Fusion, Multi‑Stream Execution, and Batch Merging

By fusing sparse‑feature operators, enabling multi‑stream execution, consolidating data copies, and merging inference batches, iQIYI reduced GPU CTR model latency to CPU‑level, boosted throughput over sixfold, and cut operational costs by more than 40%, overcoming launch‑overhead bottlenecks.

CTRGPUTensorFlow

0 likes · 10 min read

Optimizing GPU Inference for CTR Models: Kernel Fusion, Multi‑Stream Execution, and Batch Merging

iQIYI Technical Product Team

Mar 8, 2024 · Big Data

Smooth Migration from Hive to Iceberg Data Lake at iQIYI: Architecture, Techniques, and Performance Evaluation

iQIYI migrated hundreds of petabytes of Hive tables to Apache Iceberg using dual‑write, in‑place, and CTAS strategies, combined with partition pruning, Bloom filters, and Trino/Alluxio optimizations, achieving up to 40% lower query latency, simplified pipelines, and faster, cost‑effective data lake operations.

HiveIcebergMigration

0 likes · 20 min read

Smooth Migration from Hive to Iceberg Data Lake at iQIYI: Architecture, Techniques, and Performance Evaluation