web.eecs.umich.edu

web.eecs.umich.edu

The Google File System Sanjay Ghemawat, Howard Gobioff and Shun-Tak Leung Google Presented by Jiamin Huang EECS 582 W16 1 Problem

Component failures are the norm Files are huge Appends are common; random writes are rare Co-designing the applications and file system API increases flexibility 2 Architecture

3 Master Single master Metadata File and chunk namespaces Mapping from files to chunks Locations of each chunks replica Replicate using operation log

Read-only shadow masters 4 Master operations Namespace management using locks Place chunk replicas across racks Replicate chunks for higher availability Moves chunks around for disk space and load balancing

Garbage collection Deleted files Stale replicas 5 Chunkserver Multiple chunkservers Free to join and leave

Stores actual data Report chunk locations to master Checksums the data for integrity Replicated by the master 6 Interface Normal operations: create, delete, open, close, read, write

Additional operations Snapshot Create copy of file or directory tree Copy-on-write Record append Atomic Returns the offset to the client 7

System Interaction - Read 1.Client sends file name and chunk index to master Can be multiple chunks 2.Master returns replica locations May return locations for the next chunks 3.Client sends request to a chunkserver 4.Chunk servers returns the data

5.Further reads require no client-master interaction 8 System Interaction - Write 1.Master selects a primary chunkserver and grants a lease 2.Client asks master the location of primary and secondaries 3.Client pushes the data to all replicas

4.All replicas reply to the client 5.Client sends write request to primary 6.Primary executes request, forwards it to secondaries 7.Secondaries replay all mutations in the order of the 9 primary System Interaction - Append Same as write Primary pads the chunk if space is not enough and

client retries Each append is at most of the chunk size Large appends are broken into multiple operations 10 Consistency Model Consistency level Defined Consistent

Inconsistent Implications for applications Rely on appends rather than overwrites Checkpoint Use self-validating, self-identifying records 11 Evaluation - Micro-benchmarks

12 Evaluation - Real world clusters Cluster A Research and Development A few MBs to a few TBs of data Tasks run up to hours Cluster B

Production use Continuously generate and process multi-TB data Long running tasks 13 Storage and Metadata 14 Read/Write Rate

15 Recovery Time Kill one chunkserver 15000 chunks containing 600 GB data All chunks restored in 23.2 mins Kill two chunkservers Each with 16000 chunks and 660 GB data

Results in 266 single replicas Single replicas restored to at least 2x within 2 mins 16 Conclusion Some assumptions no longer hold Failures are normal Optimize for large files Optimize for appends

Fault tolerance Constant monitoring Replication Fast recovery 17 Flat Datacenter Storage (FDS) Bisection, high bandwidth network Flat storage model

Non-blocking API Single master, multiple tractservers Deterministic data placement Dynamic work allocation with small work unit Parallel writes to all replicas Parallel replication 18 Tachyon

Pushes lineage into the storage layer Lineage information is persisted before the actual data Asynchronous, selective checkpointing Leaves and hot files first Resource allocation based on job priority Uses client side caching to increase replication factor 19

Discussion How should the design be changed to handle small files? How to use multiple masters to avoid SPOF? How can consistency be improved? 20

Recently Viewed Presentations

  • Prevention of Sexual Harassment in the Workplace

    Prevention of Sexual Harassment in the Workplace

    City of Boca Raton 1998 Burlington Industries, Inc. v. Ellerth 1998 Quid Pro Quo Hostile Work Environment Quid Pro Quo sexual harassment occurs when: Employment decisions or expectations-hiring decisions, promotions, salary increases, work assignments or performance evaluations are based on...
  • Mod262 - Amazon Web Services

    Mod262 - Amazon Web Services

    Existing FM situation: Up to 200GWh/d capacity shortfall due to the rejection of NG's planning application for a PRI in Corse / Tirley area. Second Public Enquiry held July 2010 and awaiting Sec of State decision (DECC / C&LG joint...
  • Statewide Local Streets & Roads Needs Assessment Left

    Statewide Local Streets & Roads Needs Assessment Left

    [email protected] Greg Ray. 760 Mattie Rd. 805-773-4656. 1 applic. 318 first street. winters. 95694-1923. we rate by visual inspection developed in house. alligator cracking, ravelling, block cracking, spalling, contiunuous cracks, seam crack. not rated. visual inspection only. 9 10 7...
  • A B  B  C D  E  F G

    A B B C D E F G

    Arial MS Pゴシック Calibri Default Design PowerPoint Presentation PowerPoint Presentation PowerPoint Presentation PowerPoint Presentation PowerPoint Presentation PowerPoint Presentation PowerPoint Presentation PowerPoint Presentation PowerPoint Presentation PowerPoint Presentation PowerPoint ...
  • The Elizabethan Era A brief overview Renaissance French

    The Elizabethan Era A brief overview Renaissance French

    Sumptuary Laws. Used by Elizabeth's sister and father before her. Dictated what people could own, wear, use. Clear distinctions between classes. ... Elizabethan Dress. Elizabethan Dress. Women. Dressing could take as long as half an hour. Depended on age, social...
  • "The Seafarer""The Wanderer""The Wife's ... - PC\|MAC

    "The Seafarer""The Wanderer""The Wife's ... - PC\|MAC

    Answer these questions: What historical points are mentioned in the poem? How is the speaker affected by these historical points? How do you feel about the speaker and the events he or she experiences? Use at least two details from...
  • The Communicationby-Objectives Approach Chapter 3  Slide 1 Effective

    The Communicationby-Objectives Approach Chapter 3 Slide 1 Effective

    Section 2: Compose a Draft Choose Words That … Reflect the six Cs. Invoke the senses. Help form a mental picture. Support the message objective. Compose Construct Sentences Compose Construct the following types of sentences: Topic sentences Supporting sentences Concluding...
  • Chapter 4 - Promoting Aesthetic Experiences

    Chapter 4 - Promoting Aesthetic Experiences

    Chapter 3 The Concept of Aesthetics Aesthetics and the Quality of Learning Benefits of Aesthetic Sensitivity Aesthetic Experiences Benefits of Aesthetic Sensitivity Children learn taste and preference Encourages the creative process Develops sensitivity to problems Develops insight into one's world...