--- title: "Why distributed computing for big data" subject: "Big Data Technologies" chapter: 1 key: "semester_8/big_data_technologies:distributed-computing-necessary" source: https://www.bctengineer.com/q/semester_8/big_data_technologies/distributed-computing-necessary site: BCT Engineering --- # Why distributed computing for big data Big Data Technologies · Chapter 1: Introduction to Big Data - Asked in: 2075 Bhadra, 5 marks - Video: [Distributed Computing In Big Data Analytics](https://www.youtube.com/watch?v=jKeqlTOwMR8) — Hafsa Waheed - Answer checked by Claude Opus 5.5 (high effort) on 2026-10-14 - Page: https://www.bctengineer.com/q/semester_8/big_data_technologies/distributed-computing-necessary - Whole chapter: https://www.bctengineer.com/md/semester_8/big_data_technologies/chapter-1 ## Question Why distributed computing is necessary for big data? ## Short answer Distributed computing is essential because a single machine cannot store or process petabyte-scale data quickly. It splits data and tasks across many nodes, enabling parallel processing, fault tolerance through replication, low-cost horizontal scaling, and moving computation to data to save network bandwidth. ## Answer **Distributed computing** means splitting data and computation over many connected machines that work together as one system. It is necessary for big data because one computer cannot store or process data of such volume, speed and variety in reasonable time. #### Reasons 1. **Volume exceeds a single machine:** data is in terabytes to petabytes. One disk or server cannot hold it, but many commodity nodes together can. 2. **Processing speed:** reading 1 TB from one disk at about 100 MB/s takes around 3 hours. With 1000 disks reading in parallel it takes about 10 seconds. Parallel processing gives the speed-up. 3. **Scalability:** capacity grows cheaply by adding more commodity nodes (horizontal scaling) instead of buying a costly supercomputer, whose limit is fixed. 4. **Fault tolerance:** with thousands of machines, failures are normal. Data is replicated (e.g. three copies) and failed tasks are re-run elsewhere, so the system keeps working. 5. **Cost:** cheap commodity hardware is much less expensive than one high-end server. 6. **Data locality:** moving code to the data is cheaper than moving huge data to the code, which saves network bandwidth. 7. **Availability and reliability:** no single point of failure for the data, and the service stays up when some nodes are down. 8. **Variety and velocity:** different nodes can handle different data types, and streaming data can be ingested by many nodes at once. #### Example Google indexes billions of web pages. This is only possible by spreading storage (GFS) and computation (MapReduce) over thousands of machines. ## Check yourself The answer's key points as multiple-choice questions, with the correct option and why. 1. Reading 1 TB from one disk at about 100 MB/s takes about 3 hours. What happens with 1000 disks reading in parallel? A. It still takes about 3 hours B. It takes about 3 minutes C. It takes about 10 seconds D. It takes about 30 minutes Answer: C. Dividing the work over 1000 disks cuts the time by about 1000, from roughly 3 hours (10,000 s) to about 10 seconds. (Key point: Parallel processing speed-up) 2. Why is adding commodity nodes preferred to buying one supercomputer for big data? A. A supercomputer has no upper limit B. Commodity nodes give cheap capacity growth, while a supercomputer's limit is fixed and costly C. Commodity nodes never fail D. Supercomputers cannot store files Answer: B. Horizontal scaling grows capacity cheaply by adding nodes, whereas a single high-end server has a fixed limit and high cost. (Key point: Horizontal scaling and cost) 3. What does the principle of data locality say? A. Move huge data to the machine that holds the code B. Keep all data on one machine C. Copy all data to every node D. Move the code to the node that holds the data to save network bandwidth Answer: D. Moving code is cheaper than moving huge data, so computation is sent to where the data already is. (Key point: Data locality) ## Related in Big Data Technologies - [Data analytics process and distributed computing](https://www.bctengineer.com/question.md?key=semester_8%2Fbig_data_technologies%3Adata-analytics-distributed-role) — Big Data Technologies, chapter 1 - [Distributed system in big data example](https://www.bctengineer.com/question.md?key=semester_8%2Fbig_data_technologies%3Adistributed-system-example) — Big Data Technologies, chapter 1 - [Role of data scientist in big data](https://www.bctengineer.com/question.md?key=semester_8%2Fbig_data_technologies%3Arole-of-data-scientist) — Big Data Technologies, chapter 1, asked 2× - [Big data trends, challenges, characteristics](https://www.bctengineer.com/question.md?key=semester_8%2Fbig_data_technologies%3Abig-data-trends-challenges) — Big Data Technologies, chapter 1 - [Hybrid data in big data warehouse](https://www.bctengineer.com/question.md?key=semester_8%2Fbig_data_technologies%3Ahybrid-data-warehouse) — Big Data Technologies, chapter 1 - [Attributes of Big Data](https://www.bctengineer.com/question.md?key=semester_8%2Fbig_data_technologies%3Abig-data-attributes) — Big Data Technologies, chapter 1 ## Related in other subjects - [Big data and its processing](https://www.bctengineer.com/question.md?key=semester_8%2Finformation_system%3Abig-data-processing) — Information System, chapter 8