RustFS 1.0 GA releases a production-ready, Apache 2.0-licensed S3-compatible object store written in Rust, achieving 2.3× MinIO performance on 4KB objects via SIMD-accelerated erasure coding, io_uring zero-copy I/O, and a GC-free runtime, while adding built-in Iceberg REST Catalog (S3 Tables) for data-lake workloads.
Apache Paimon combines a lakehouse table format with an LSM-tree update engine to handle continuous updates, historical snapshots, and multi-engine access in real-time data warehouses, reducing the need for separate Kafka, Hive, and OLAP systems.
At Apache COC Asia 2026, Didi’s engineers presented three deep‑dive sessions covering the evolution of massive‑scale object storage with Ozone, cost‑effective lakehouse migration using Iceberg and real‑time ingestion, and AI‑friendly enhancements to the open‑source Seata project, detailing architectural choices, performance gains, and open‑source contributions.
This article (part 1) presents twelve high‑level interview questions from top tech firms covering the shift from AI‑Ready to Data‑Agent‑Ready data warehouses, AI‑centric metadata and lineage, lakehouse formats like Paimon, and key Iceberg features that empower AI‑driven analytics.
The article compares four emerging data‑lake‑for‑PostgreSQL solutions—Databricks LTAP, EDB Fusion Analytics, Snowflake pg_lake, and pgEdge's ColdFront—highlighting ColdFront's unique transparent Iceberg layer, writable cold data, DuckDB integration, and the strategic trade‑offs developers must weigh when choosing a modern OLTP/OLAP/AI architecture.
In the AI‑driven era, enterprises need a data foundation that supports both real‑time consumption and long‑term historical analysis, and the emerging "zero‑ETL" trend moves generic ingestion capabilities from external Flink/Spark jobs into a streamlined Kafka‑to‑Iceberg pipeline, reducing complexity while preserving low latency, consistency, schema evolution, CDC semantics and open‑ecosystem compatibility.
In the AI era, enterprises need a data foundation that supports both low‑latency streaming and long‑term analytics, and the combination of Kafka, Iceberg and object storage is emerging as a preferred solution; by moving ingestion capabilities closer to the message layer and eliminating external ETL jobs, a "zero‑ETL" approach reduces architectural complexity, improves consistency, and streamlines schema evolution and small‑file management.
StarRocks 4.1 introduces automatic multi‑tenant data management, large‑capacity tablets, second‑level schema evolution, enhanced cache observability, and deeper Iceberg support, addressing static data distribution, data skew, high repair costs and expertise requirements while delivering up to 1.86× higher throughput and dramatically lower latency in production workloads.
This article analytically compares three open table‑format projects—Paimon, Hudi, and Iceberg—examining how each addresses multimodal data lake challenges such as massive volume, sparse access patterns, and combined scalar‑vector retrieval, and provides concrete feature breakdowns and selection guidance.
This article presents a series of seven technical case studies—including Tencent Cloud’s Iceberg‑based batch‑stream integration, AI‑driven data governance with Apache Gravitino, Xiaohongshu’s lakehouse evolution, and a multimodal data‑lake solution—detailing challenges, architectural designs, implementation steps, performance results, and future directions.
This article analyzes why StarRocks multi-table joins on Paimon/Iceberg tables remain significantly slower than internal tables even after cache warming, detailing six root causes across storage format, data layout, caching, execution engine, metadata, and version management, plus four optimization strategies to narrow the gap.
Apache XTable introduces a lightweight metadata translation layer that decouples data storage from format metadata, enabling zero‑copy, omni‑directional conversion among Hudi, Iceberg, and Delta Lake, allowing organizations to write with one format and read with any engine without duplicating Parquet files.
This article series explores Tencent Cloud's Iceberg‑based batch‑stream integration, Apache Gravitino's unified metadata and lineage solution, Xiaohongshu's data‑architecture evolution for the Big AI Data era, and a practical Data+AI multimodal data‑lake implementation, highlighting challenges, architectural designs, and performance gains.
The article benchmarks StarRocks internal tables against Paimon and Iceberg lake tables using TPCH 100G, shows internal tables excel at real-time analytics while lake tables optimize cold storage cost and multi-engine sharing, and details optimization strategies (metadata, data cache, predicate pushdown) achieving 5-10x speedup, illustrated by a retail case study cutting query latency from seconds to milliseconds and storage cost by 65%.
Xiaomi’s data‑lake team explains how they tackled small‑file issues, unified metadata with Gravitino, migrated Hive to Iceberg and Fileset, leveraged JuiceFS for multi‑cloud storage, and combined Iceberg and Paimon to achieve cost‑effective, high‑performance batch and real‑time analytics.
Facing growing data demands in finance, we replaced two legacy synchronization pipelines with a unified, low‑latency architecture using BabelX Real‑Time, Flink CDC, Iceberg v2 and Paimon, achieving minute‑level data freshness, ten‑to‑thirty‑fold query speedups, reduced storage costs, and streamlined schema management across multiple business units.
After a weekend dive into Apache Hive’s official Wiki and GitHub, this article highlights Hive’s declining visibility compared to Spark and Flink, examines its 4.0 release’s major features—including Iceberg integration, enhanced ACID, cost‑based optimizer upgrades, and Ozone support—while reflecting on its role in modern data ecosystems.
This article examines how Xiaohongshu replaced its costly Lambda architecture with a real‑time lakehouse built on Iceberg, Paimon, Spark, and StarRocks, achieving minute‑level latency, higher data quality, lower resource consumption, and dramatically faster query performance.
Facing billions of daily logs and the need for minute‑level experiment metrics, Xiaohongshu partnered with Yunqi Tech to design a generic incremental‑compute solution that delivers near‑real‑time data warehousing with lower cost, higher accuracy, simplified pipelines, and improved query performance.
This article explains how Huawei's terminal cloud adopts the Apache Iceberg table format to efficiently manage large-scale datasets, detailing its architecture, feature engineering, merge operations, LSM-based storage, schema versioning, AB testing support, catalog enhancements, and future roadmap for full lifecycle data governance.
The article reports Xiaohongshu’s cancellation of the big‑small week schedule and non‑compete clause, then provides a collection of big‑data interview questions—including data governance, Iceberg metadata management, and lakehouse production best practices—along with concise answers and resources for candidates.
iQIYI transformed its real‑time data warehouse by replacing a costly Kafka‑based Lambda stack with a unified stream‑batch Iceberg lake, cutting storage expenses by 90%, halving compute costs, extending data retention, and delivering minute‑level freshness for 90% of use cases while preserving second‑level processing where needed.
The article details how Xiaohongshu's RedBI self‑service analytics platform transformed its architecture by integrating StarRocks and Iceberg, replacing ClickHouse‑based storage with Parquet, introducing DataCache, Z‑Order sorting and intelligent key selection, achieving a three‑fold P90 query speed improvement, sub‑10‑second latency, and halving storage consumption.
This presentation details Tencent's real‑time lakehouse architecture and the four key topics—lakehouse design, intelligent optimization services, scenario‑driven capabilities, and future outlook—covering components such as Spark, Flink, Iceberg, Auto‑Optimize Service, indexing, clustering, AutoEngine, and PyIceberg implementations.
This article presents Tencent's end‑to‑end real‑time lakehouse architecture, detailing its three‑layer design, the Auto Optimize Service modules such as compaction, indexing, clustering and engine acceleration, as well as scenario‑driven capabilities like multi‑stream joins, primary‑key tables, in‑place migration and PyIceberg support, and concludes with future optimization directions.
This presentation describes Tencent's real-time lakehouse architecture, including data lake compute, management, and storage layers, and details the intelligent optimization services—such as compaction, indexing, clustering, and auto-engine—designed to improve query performance, storage cost, and operational efficiency for large-scale data processing.
The article outlines Bilibili’s revamped recommendation data‑flow architecture that eliminates timing and calculation inconsistencies by snapshotting online features, unifying feature computation in a single C++ library accessed via JNI, and orchestrating label‑join and sample extraction through near‑line Kafka/Flink pipelines, with further performance gains and Iceberg‑based future extensions.
The article details Bilibili's comprehensive redesign of its tag system—including background challenges, architectural layers, technical upgrades like Iceberg integration and shard‑based ClickHouse writes, crowd selection methods, online service guarantees, performance metrics, and future plans—showcasing a data‑driven solution that boosts stability, speed, and business coverage.
Bilibili adopted Apache Gravitino as a unified metadata platform that decouples consumers, consolidates schemas and Fileset‑based unstructured data across heterogeneous sources, cuts metadata and storage costs, resolves inconsistencies, boosts Hive Metastore performance, and enables features such as Iceberg branching and future AI‑centric governance.
Tencent's advertising team replaced a traditional HDFS‑Hive warehouse with an Apache Iceberg‑based data lake, adding primary‑key tables, multi‑stream merging, adaptive compaction, and Spark SPJ optimizations to achieve minute‑level feature update latency, 10× back‑fill speed, and up to 60% storage savings.
Bilibili migrated its massive user‑behavior, commercial AI training, and database synchronization pipelines from Hive and Kafka to an Iceberg‑based streaming‑batch architecture, using Flink and the Magnus optimizer to achieve minute‑level freshness, reduce CPU and memory usage by about 20‑22 %, save roughly 3.55 M CNY annually, and dramatically improve query latency and join performance.
This article presents Bilibili's end‑to‑end exploration of a streaming‑batch unified data pipeline built on Apache Iceberg, detailing the original and iterated architectures for massive user behavior transmission, online AI training, DB synchronization, and dimension‑join, along with performance gains, cost savings, and future plans.
The article summarizes a roundtable discussion where experts compare four lake‑warehouse architectural patterns, explain their suitability for different business scenarios, contrast them with traditional data warehouses, and highlight practical considerations for choosing and evolving data platforms.
The rebuilt tag system introduces a three‑layer architecture, standard pipelines, Iceberg‑backed storage and custom ClickHouse sharding, a DSL for crowd selection, and a stateless online service, achieving 99.9% success, sub‑5 ms latency, and supporting thousands of tags across dozens of business scenarios while planning real‑time processing and automated lifecycle management.
Experts from Kuaishou, former Tencent, Ping An Insurance and others discuss data lake maturity, column‑level governance, resource management of unstructured data, and automated optimization techniques such as Iceberg small‑file merging, highlighting how these advances improve data quality and business decision‑making.
This article presents Tencent's real-time lakehouse architecture, detailing its three-layer design, the Auto Optimize Service with compaction, indexing, clustering and engine acceleration, scenario capabilities such as multi‑stream joins and in‑place migration, and outlines future optimization directions.
Magnus is Bilibili’s self‑developed intelligent service that continuously optimizes Iceberg tables by scheduling snapshot expiration, orphan‑file cleanup, manifest rewriting, and multi‑dimensional data optimizations—including small‑file merging, sorting, distribution, and index creation—while automatically recommending configurations from real‑time query logs, delivering over 99.9% task success and up to 30% scan‑data reduction.
DataFunSummit2024, co-hosted by Bilibili, convenes industry experts, scholars, and enterprise leaders across six forums to discuss next‑generation data architecture, showcasing Bilibili’s Iceberg‑based stream‑batch innovations, AI‑BI analytics, NoETL practices, and emerging alternatives to Lambda architecture.
Amid growing data demands, this article explains the data lake technology maturity curve, detailing lake‑warehouse architectural patterns, design principles, core functionalities, and the four leading open‑source solutions (Hudi, Iceberg, Delta Lake, Paimon) to guide enterprises in building flexible, scalable, and governed data platforms.
This article explains the data lake technology maturity curve, covering lake‑warehouse architecture patterns, design principles, core capabilities of major open‑source lake engines (Hudi, Iceberg, Delta Lake, Paimon), and practical application scenarios for modern data‑driven enterprises.
This article explains the rapid growth of data-driven businesses, the challenges of traditional data warehouses, and how modern data lake technologies such as Delta Lake, Hudi, Iceberg, and Paimon form a maturity curve that guides enterprises in architecture choices, design principles, core capabilities, and practical applications.
This article presents Xiaomi's real-time lakehouse architecture, outlines its current challenges, introduces Apache Paimon and several use‑case scenarios—including stream join optimization, streaming upserts, and lookup joins—while discussing expected benefits and future directions for a more efficient, unified data platform.
This article outlines practical approaches to data warehouse construction, covering dimensional modeling, layered architecture, capability development, real‑time and batch processing with technologies like Hive, Spark, Flink, Iceberg, and discusses governance, security, and future trends toward data value and real‑time metrics.
This article presents a comprehensive overview of Xiaomi's sales data warehouse, detailing its development history, dimensional modeling theory, multi‑layer architecture, Lambda design with batch and streaming processing, capability layers, security measures, and answers to common technical questions.
This article details Xiaomi's sales data warehouse development, covering its history, architecture, dimensional modeling, layer design, streaming‑batch integration, governance, security, and future directions, while also addressing practical Q&A on implementation challenges and best practices.
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.
This article describes Bilibili’s intelligent optimization project that automatically analyzes historical query workloads to configure multi‑dimensional sorting, various indexes, and pre‑aggregation on Iceberg tables, thereby reducing scan volume by 28% across dozens of tables and improving OLAP query latency.
This article shares Kangaroo Cloud's exploration and practice of a real-time data lake, covering background, data lake concepts, challenges, solution architecture using the Shuzhan platform with Iceberg/Hudi, CDC ingestion, small file handling, cross-cluster ingestion, materialized view acceleration, and future development plans.
This article presents OPPO's smart data lakehouse solution, describing its massive EB‑scale architecture, the integration of batch and streaming engines, the Glacier service for table management, schema‑adaptive ingestion, performance optimizations, and future technical road‑maps for unified data processing.
This article presents Tencent Game's comprehensive lakehouse integration practice, detailing the project background, storage‑compute separation, data layering, unified DDL/DML operations, performance optimizations, and future plans, illustrating how StarRocks, Iceberg, and Spark are combined to achieve scalable, cost‑effective analytics for massive game data.
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.
This article details Xiaomi’s practical deployment of Trino, covering its architectural role, core and extended capabilities, performance comparisons, integration with Iceberg and Spark, operational enhancements, multi‑cluster and ad‑hoc query scenarios, future cloud‑storage plans, and a Q&A session.
This article presents Xiaomi's sales data warehouse practice, detailing its evolution, positioning, dimensional modeling, layered architecture, Lambda design, Iceberg integration, capability building, security governance, and future directions toward data value and real‑time metrics.
This article introduces Xiaomi's sales data warehouse practices, covering its development history, positioning, architecture, dimensional modeling, layer theory, capability building, real‑time and batch processing using Lambda architecture, Iceberg, Flink, and Hologres, and discusses future trends and Q&A.
This article details Bilibili's implementation of an Iceberg‑based lakehouse platform that unifies storage and analytics, addressing Hive’s performance and latency issues through multidimensional sorting, various file‑level indexes, cube pre‑aggregation, star‑tree structures, and an automated Magnus service for intelligent optimization, achieving near‑second query responses.
This presentation introduces Iceberg's core capabilities, details Xiaomi's practical applications—including log ingestion, near‑real‑time warehousing, offline challenges, column‑level encryption, and Hive migration—and outlines future development directions such as materialized views and cloud migration, providing a comprehensive view of modern data‑lake engineering.
This article presents Bilibili's practical implementation of Trino within a lakehouse architecture, focusing on the compute engine placement, stability enhancements, and containerized deployment, while detailing indexing strategies, pre‑computation techniques, Iceberg metadata optimizations, and performance gains for large‑scale analytical queries.
This article explains how NetEase Yanxuan upgraded its legacy Lambda architecture to an Iceberg‑based batch‑stream unified platform, detailing the original data pipeline, the challenges faced, the evaluation of Iceberg versus Hudi and DeltaLake, and the concrete engineering optimizations and governance measures implemented to achieve lower latency and higher query performance.
The Venus log platform at iQiyi migrated from an ElasticSearch‑Kibana architecture to an Iceberg‑based data lake with Trino, cutting storage and compute costs by over 70%, boosting stability by 85%, and efficiently supporting billions of daily logs through write‑heavy, low‑query workloads.
The WeChat Experiment Platform migrated its 60,000 metric, 200,000 core, 30 PB plus data pipeline to an Iceberg based lakehouse, leveraging three layer metadata, fine grained partitioning, MERGE into writes, time travel snapshots and skew handling UDFs, which cut core time by 69%, saved ~100 PB storage, and reduced latency by up to 70%.
This note outlines how Hudi, Iceberg, and Paimon provide unified batch‑stream storage, UPSERT support, time‑travel capabilities, and lower development costs, enabling a streaming‑warehouse architecture that offers near‑real‑time latency, consistent semantics, persisted intermediate results, and easier historical data repair.
This article analyzes the rise of lake‑house architecture in the Hadoop ecosystem, compares the technical capabilities of Hudi, Iceberg and Delta Lake, details implementation enhancements such as MOR and multi‑writer support, showcases Flink integration, presents a real‑time marketing use case, and outlines future development directions.
This article presents a comprehensive overview of Impala's high‑performance MPP query engine, its architecture for data‑lake workloads, and detailed performance optimizations including Iceberg table format improvements, manifest caching, and various Codegen techniques such as asynchronous compilation and caching.
This article details Bilibili's evolution from the ClickHouse‑based Billions 2.0 log system to the Billions 3.0 architecture, explaining how they reduced storage costs, improved troubleshooting, adopted a lake‑house design with Iceberg on HDFS, leveraged ClickHouse for acceleration, and integrated Trino as the unified query engine.
By replacing the costly Lambda architecture with a unified data‑lake built on Iceberg and Flink CDC, the advertising team achieved minute‑level latency, strong consistency, and lower storage expenses, cutting end‑to‑end processing times from hours to a few minutes across budgeting, warehousing, OLAP and ETL workloads.
Bilibili evolved its log platform from ClickHouse‑based Billions 2.0 to Billions 3.0 lakehouse using Iceberg, HDFS, Trino, retaining ClickHouse for acceleration; this reduces storage cost by over 20%, improves observability, solves the compute‑storage mismatch, adds flexible indexing, and supports complex ETL while staying open‑source.
This article details Bilibili's implementation of a sub‑second response lakehouse platform using Apache Iceberg, covering background challenges, query acceleration techniques such as multi‑dimensional sorting, indexing, cube pre‑aggregation, and intelligent automated optimizations via the Magnus service, and reports current production metrics.
This article details iQIYI's adoption of Iceberg for its data lake, covering the OLAP architecture, reasons for a data lake, Iceberg's table format advantages over Hive, platform construction, streaming ingestion, query and performance optimizations, real‑world business deployments, and future plans.
This article presents a comprehensive overview of Iceberg MOR principles, Arctic‑based performance optimizations, benchmark evaluations using CH‑benchmark, and future roadmap items, highlighting how various file‑type strategies, self‑optimizing mechanisms, and task balancing improve real‑time data lake query efficiency.
This article details iQIYI's adoption of the Iceberg data lake, covering its OLAP architecture, reasons for a lake, Iceberg table format advantages over Hive, platform construction, extensive performance optimizations, and real‑world business use cases such as ad‑flow unification, log analysis, audit, and CDC pipelines.
This article details Bilibili's technical practice of constructing a millisecond‑response lake‑warehouse platform using Apache Iceberg, covering the background challenges, unified architecture, multi‑dimensional sorting and indexing for query acceleration, the Magnus service for intelligent optimization, and the current production deployment and performance metrics.
This article presents Xiaohongshu's design and implementation of a unified streaming‑batch storage system that integrates Lambda architecture, Kafka, Flink, Iceberg, and modern OLAP engines to solve real‑time data warehouse pain points and enable consistent, exactly‑once analytics across streaming and batch workloads.
This interview with NetEase data‑lake technology manager Ma Jin explains the distinction between data lakes and lakehouses, reviews the evolution of table‑format technologies such as Iceberg, Hudi and Delta Lake, evaluates feature maturity and performance trade‑offs, and discusses systematic versus non‑systematic adoption in enterprises.
This interview with NetEase’s data‑lake technology manager explores the distinction between data lakes and lakehouses, the evolution of table‑format technologies such as Iceberg, Hudi and Delta Lake, their maturity across key capabilities, and the practical adoption challenges faced by enterprises.
This article introduces the Iceberg table format, explains its core architecture and advantages such as transactionality, implicit partitioning and row‑level updates, details Xiaomi's practical deployments—including CDC pipelines, partition strategies, compaction services, and stream‑batch integration—and outlines future development directions.
This article details how NetEase Yanxuan transformed its data platform from a dual Lambda architecture to a unified batch‑stream solution built on Apache Iceberg, covering the original challenges, the evaluation of Iceberg versus Hudi and Delta Lake, implementation of stream‑batch pipelines, message ordering fixes, snapshot generation, and extensive table‑governance optimizations.
This article explains how Presto and Alluxio work together to query Iceberg tables, describes their architectures, deployment options, best‑practice recommendations such as using Iceberg native catalogs and local caches, and outlines future research directions for improving CPU usage and off‑heap caching.
This article explains the definition of data lakes (public‑cloud and non‑public‑cloud), outlines their key characteristics, presents three typical business scenarios—real‑time event analysis, change‑data analysis, and stream‑batch integration—summarizes required product features, evaluates open‑source lake formats, and details iQIYI's adoption of Apache Iceberg across multiple services to achieve low‑latency, large‑scale, cost‑effective analytics.
This article details Bilibili's 北极星 user behavior analysis platform, tracing its evolution from early Spark‑Jar models to Flink‑ClickHouse pipelines and Iceberg‑based full aggregation, and explains the technical solutions for event, retention, funnel, path analysis, data ingestion, cluster rebalancing, and performance optimizations that enable massive real‑time analytics on billions of daily events.
This article explains the challenges of a Lambda‑architecture data pipeline, introduces NetEase’s Arctic lakehouse built on Apache Iceberg, details its table‑store design, optimization cycles, consistency mechanisms, real‑time features, practical use cases, and future roadmap, highlighting its advantages over similar solutions.
This article presents a comprehensive overview of Iceberg's adoption in Huawei Terminal Cloud, covering its architectural overview, key features such as Git‑style data management, real‑time processing, acceleration layers, and future development directions, along with a Q&A session addressing performance and implementation details.
Bilibili’s PolarStar platform evolved from Spark‑based batch jobs to a Flink‑driven real‑time pipeline and finally to a unified Iceberg‑on‑ClickHouse model, cutting query latency to seconds, saving thousands of CPU cores and hundreds of gigabytes of Redis memory while enabling complex, near‑real‑time user‑behavior analyses and scalable data‑import, rebalancing, and compression optimizations.
This article presents Glacier, OPPO's intelligent data lake solution that builds on Iceberg Table Format to provide real‑time data ingestion, low‑latency queries, advanced indexing, and robust multi‑version management for both structured and unstructured data, tightly integrating with machine‑learning workflows.
The article details how Tencent Advertising re‑architected its massive log pipeline by consolidating heterogeneous real‑time and offline logs into an Iceberg‑based data lake, introducing multi‑level partitioning, Spark and Flink ingestion, and numerous performance and cost optimizations for scalable big‑data analytics.
This article explains how Alibaba Cloud EMR StarRocks extends data lake analytics to support Hive, Iceberg, and Hudi, detailing its architecture, Iceberg integration, performance gains over Trino, IO merging, lazy materialization, intelligent caching, and elastic compute capabilities for faster, unified, and cost‑effective queries.
This article introduces Iceberg’s table‑format fundamentals, details Xiaomi’s large‑scale deployment of Iceberg for CDC and log ingestion, explores their streaming‑batch integration experiments, outlines future roadmap items, and provides a comprehensive Q&A covering practical challenges and solutions.
This article presents an overview of the Iceberg table format, its core architecture and advantages, details Xiaomi’s large‑scale deployment and use cases, explores stream‑batch integration with Spark and Flink, outlines data correction methods, future plans, and answers common technical questions.
This article explains how to design and implement a cloud‑native Lakehouse using StarRocks and Tencent Cloud EMR, covering core technical requirements, a five‑layer architecture, data ingestion with Iceberg/Hudi, performance tricks like Z‑order clustering, cost‑control through elastic scaling, and the key product features of EMR StarRocks.
Bilibili’s new lake‑house platform, built on Trino and Iceberg, replaces Hive‑based pipelines by ingesting logs and DB data into Iceberg tables, applying advanced sorting, Z‑order/Hilbert clustering, bitmap and bloom indexes, virtual join columns and pre‑aggregation, enabling 70 000 daily queries on 2 PB with average scans of 2 GB and sub‑2‑second response times.
This article outlines the configuration settings for Apache Iceberg tables and catalogs on Hadoop, covering read and write properties, combine behavior for small HDFS files, reserved table properties, catalog lock options, and Hive Metastore connector Hadoop settings, supplemented with illustrative screenshots.
This article details how NetEase Yanxuan upgraded its legacy Lambda data pipeline to a unified batch‑stream architecture built on Apache Iceberg, covering the original challenges, the evaluation of Iceberg versus Hudi and DeltaLake, implementation specifics, table‑governance techniques, and future roadmap.
The article examines the open‑source release of Delta 2.0, compares its features and benchmark results with Iceberg and Hudi, discusses the core capabilities required by enterprises for a lakehouse architecture, and introduces the Arctic project as a multi‑engine streaming lake service.
The article reviews recent developments in data‑lake table formats—Delta Lake 2.0, Iceberg, and Hudi—examining their features, benchmark results, and ecosystem impact, and then introduces Arctic, an open‑source streaming lakehouse service built on Iceberg that aims to bridge batch‑stream gaps for enterprises.
This article details Bilibili's lakehouse implementation using Apache Iceberg and Alluxio, covering background challenges, architectural components, data organization techniques like Z‑order and bitmap indexes, performance benchmarks, and future optimization plans for large‑scale analytics.
This article provides a comprehensive tutorial on setting up Flink 1.11 with Iceberg 0.11.1, creating Hive catalogs, building databases and tables, inserting data, and exploring Iceberg components, file structures, partitioned tables, execution plans, and programmatic access via Scala.
The article uses an acorn‑moving analogy to highlight latency and traceability challenges in enterprise data warehouses, then explains offline versus real‑time approaches, compares Lambda and Kappa architectures, discusses Iceberg integration, and shares a detailed e‑commerce real‑time warehouse case study with optimization tips.
This article explains Bilibili's lake‑warehouse integrated architecture, describing how Iceberg, MagnuS, Trino, and Alluxio are used to achieve flexible data storage, high‑performance query acceleration, and automated indexing through Z‑Order, Hilbert curve, Bloom filter, and advanced BitMap techniques.
Bilibili’s lakehouse architecture merges Iceberg‑based data lake flexibility with data‑warehouse efficiency, using Kafka‑Flink real‑time ingestion, Spark offline loads, Trino queries, Alluxio caching, Z‑Order/Hilbert sorting, and enhanced BloomFilter and bitmap indexes to boost query speed up to tenfold while drastically cutting file reads.
This article details why Microvision adopted Apache Iceberg, how it replaces parts of their Lambda‑architecture data pipeline, the real‑time and offline use cases, table‑maintenance practices such as snapshot cleanup and small‑file merging, and lessons learned from the implementation.