Knowledge

Shared-nothing architecture

Source 📝

41:
One alternative architecture is shared everything, in which requests are satisfied by arbitrary combinations of nodes. This may introduce contention, as multiple nodes may seek to update the same data at the same time. It also contrasts with
66:. A SN system typically partitions its data among many nodes. A refinement is to replicate commonly used but infrequently modified data across many nodes, allowing more requests to be resolved on a single node. 57:, allowing the overall system to continue operating despite failures in individual nodes and allowing individual nodes to upgrade hardware or software without a system-wide shutdown. 60:
A SN system can scale simply by adding nodes, since no central resource bottlenecks the system. In databases, a term for the part of a database on a single node is a
241: 219: 416: 357: 92:
systems, a shared-nothing implementation of hardware and software was released to market in 1976. Tandem Computers later released
38:. The intent is to eliminate contention among nodes. Nodes do not share (independently access) the same memory or storage. 358:"NonStop SQL, A Distributed, High-Performance, High-Availability Implementation of SQL, Tandem Technical Report TR-87.4" 78: 245: 333: 62: 115:
applications, although requests that require data from multiple nodes can dramatically reduce throughput.
411: 125: 89: 47: 141: 43: 54: 34:
in which each update request is satisfied by a single node (processor/memory/storage unit) in a
146: 31: 28: 192: 8: 74: 364: 268: 220:"The Advantages of a Shared Nothing Architecture for Truly Non-Disruptive Upgrades" 112: 86: 35: 105: 388: 162: 405: 389:"Article on Shared Nothing from the point of view of a Shared Nothing Vendor" 172: 197: 93: 135: 293: 177: 157: 182: 167: 130: 82: 187: 152: 334:"History of TANDEM COMPUTERS, INC. – FundingUniverse" 266: 316:Center Magazine: A Newsletter for Tandem Employees 96:, a shared-nothing relational database, in 1984. 403: 85:delivered the first SN database system in 1983. 111:Shared-nothing architectures are prevalent for 239: 16:Type of distributed computing architecture 269:"The Case for Shared Nothing Architecture" 81:used the term in a 1986 database paper. 240:Blankenhorn, Dana (February 27, 2006). 404: 242:"Shared nothing coming to open source" 217: 314:""Tandem History: An Introduction"". 13: 417:Distributed computing architecture 79:University of California, Berkeley 14: 428: 99: 381: 350: 326: 307: 286: 260: 233: 211: 104:Shared-nothing is popular for 1: 204: 267:Michael Stonebraker (1986). 7: 218:Wright, Dave (2014-09-17). 118: 21:shared-nothing architecture 10: 433: 126:NonStop_(server_computers) 69: 142:Byzantine fault tolerance 55:single points of failure 338:www.fundinguniverse.com 244:. ZDNet. Archived from 147:Distributed hash table 29:distributed computing 276:Database Engineering 193:Database scalability 138:(Shared Everything) 75:Michael Stonebraker 294:"Teradata History" 248:on October 4, 2012 412:Data partitioning 322:(1). Winter 1986. 424: 396: 395: 393: 385: 379: 378: 376: 375: 369: 363:. Archived from 362: 354: 348: 347: 345: 344: 330: 324: 323: 311: 305: 304: 302: 301: 290: 284: 283: 273: 264: 258: 257: 255: 253: 237: 231: 230: 228: 227: 215: 113:data warehousing 87:Tandem Computers 50:architectures. 36:computer cluster 432: 431: 427: 426: 425: 423: 422: 421: 402: 401: 400: 399: 391: 387: 386: 382: 373: 371: 367: 360: 356: 355: 351: 342: 340: 332: 331: 327: 313: 312: 308: 299: 297: 292: 291: 287: 271: 265: 261: 251: 249: 238: 234: 225: 223: 216: 212: 207: 202: 121: 106:web development 102: 72: 17: 12: 11: 5: 430: 420: 419: 414: 398: 397: 380: 349: 325: 306: 296:. Teradata.com 285: 259: 232: 209: 208: 206: 203: 201: 200: 195: 190: 185: 180: 175: 170: 165: 163:Grid computing 160: 155: 150: 144: 139: 133: 128: 122: 120: 117: 101: 98: 71: 68: 53:SN eliminates 15: 9: 6: 4: 3: 2: 429: 418: 415: 413: 410: 409: 407: 390: 384: 370:on 2012-03-16 366: 359: 353: 339: 335: 329: 321: 317: 310: 295: 289: 281: 277: 270: 263: 247: 243: 236: 221: 214: 210: 199: 196: 194: 191: 189: 186: 184: 181: 179: 176: 174: 173:MySQL Cluster 171: 169: 166: 164: 161: 159: 156: 154: 151: 148: 145: 143: 140: 137: 134: 132: 129: 127: 124: 123: 116: 114: 109: 107: 97: 95: 91: 88: 84: 80: 76: 67: 65: 64: 58: 56: 51: 49: 48:shared-memory 45: 39: 37: 33: 30: 26: 22: 383: 372:. Retrieved 365:the original 352: 341:. Retrieved 337: 328: 319: 315: 309: 298:. Retrieved 288: 279: 275: 262: 250:. Retrieved 246:the original 235: 224:. Retrieved 222:. netapp.com 213: 110: 103: 100:Applications 73: 61: 59: 52: 40: 32:architecture 24: 20: 18: 94:NonStop SQL 44:shared-disk 406:Categories 374:2012-10-11 343:2023-03-01 300:2013-06-16 226:2019-10-31 205:References 136:Oracle RAC 198:GlusterFS 178:Openstack 158:Greenplum 252:June 21, 183:ScyllaDB 168:InfiniDB 131:Teradata 119:See also 83:Teradata 188:Vertica 90:NonStop 77:at the 70:History 27:) is a 153:EXASOL 392:(PDF) 368:(PDF) 361:(PDF) 272:(PDF) 149:(DHT) 63:shard 282:(1). 254:2012 46:and 408:: 336:. 318:. 278:. 274:. 108:. 25:SN 19:A 394:. 377:. 346:. 320:6 303:. 280:9 256:. 229:. 23:(

Index

distributed computing
architecture
computer cluster
shared-disk
shared-memory
single points of failure
shard
Michael Stonebraker
University of California, Berkeley
Teradata
Tandem Computers
NonStop
NonStop SQL
web development
data warehousing
NonStop_(server_computers)
Teradata
Oracle RAC
Byzantine fault tolerance
Distributed hash table
EXASOL
Greenplum
Grid computing
InfiniDB
MySQL Cluster
Openstack
ScyllaDB
Vertica
Database scalability
GlusterFS

Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.