Statements (59)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:cloud_storage
|
| gptkbp:architecture |
master-slave
|
| gptkbp:chunk_size |
64 MB
|
| gptkbp:client |
via API
|
| gptkbp:data_chunks |
stored on chunk servers
|
| gptkbp:designed_for |
large-scale data processing
large data processing Google's data-intensive applications |
| gptkbp:developed_by |
gptkb:Google
|
| gptkbp:features |
dynamic scaling
high availability high performance metadata management scalability robustness high throughput automatic recovery efficient data retrieval simple interface |
| https://www.w3.org/2000/01/rdf-schema#label |
Google File System
|
| gptkbp:influenced |
gptkb:Hadoop_Distributed_File_System
|
| gptkbp:inspired_by |
gptkb:Bigtable
|
| gptkbp:metadata |
stored on master node
|
| gptkbp:primary_use |
Google's internal applications
|
| gptkbp:provides |
data integrity
data processing capabilities fault tolerance load balancing data durability data accessibility high reliability data storage solutions streaming access efficient data access high throughput access |
| gptkbp:release_year |
gptkb:2003
|
| gptkbp:replication_factor |
default 3
|
| gptkbp:reprints |
yes
|
| gptkbp:supports |
data analytics
data sharing data transformation multi-tenancy multiple clients data redundancy data locality large files data versioning distributed applications large-scale data sets append operations |
| gptkbp:used_by |
gptkb:Map_Reduce
|
| gptkbp:uses |
checksums
distributed storage chunking networked storage write-once, read-many model |
| gptkbp:written_in |
gptkb:C++
|
| gptkbp:bfsParent |
gptkb:Bigtable
|
| gptkbp:bfsLayer |
5
|