Editing Scalability (section)

==Horizontal (scale out) and vertical scaling (scale up){{Anchor|HORIZONTAL-SCALING|VERTICAL-SCALING|Horizontal and vertical scaling}}==
Resources fall into two broad categories: horizontal and vertical.<ref>{{cite conference|conference=2007 IEEE International Parallel and Distributed Processing Symposium|date=March 26, 2007|doi=10.1109/IPDPS.2007.370631|title=Scale-up x Scale-out: A Case Study using Nutch/Lucene|last1=Michael|first1=Maged|last2=Moreira|first2=Jose E.|last3=Shiloach|first3=Doron|last4=Wisniewski|first4=Robert W.|isbn=978-1-4244-0909-9|page=1}}</ref>

===Horizontal or scale out{{anchor|Horizontal}}===
Scaling horizontally (out/in) means adding or removing nodes, such as adding a new computer to a distributed software application. An example might involve scaling out from one web server to three. [[High-performance computing]] applications, such as [[seismic analysis]] and [[biotechnology]], scale workloads horizontally to support tasks that once would have required expensive [[supercomputer]]s. Other workloads, such as large social networks, exceed the capacity of the largest supercomputer and can only be handled by scalable systems. Exploiting this scalability requires software for efficient resource management and maintenance.<ref name="parallel_arch" />

===Vertical or scale up{{anchor|Vertical}}===
Scaling vertically (up/down) means adding resources to (or removing resources from) a single node, typically involving the addition of CPUs, memory or storage to a single computer.<ref name="parallel_arch" />

Benefits to scale-up include avoiding increased management complexity, more sophisticated programming to allocate tasks among resources and handling issues such as throughput, latency, and synchronization across nodes.  Moreover some [[Amdahl's law|applications do not scale horizontally]].