Fabric computing orunified computing involves constructing acomputing fabric consisting of interconnected nodes that look like aweave or afabric when seen collectively from a distance.[1]
Usually the phrase refers to a consolidatedhigh-performance computing system consisting ofloosely coupledstorage,networking andparallel processing functions linked byhigh bandwidth interconnects (such as10 Gigabit Ethernet andInfiniBand)[2] but the term has also been used to describe platforms such as theAzure Services Platform andgrid computing in general (where the common theme is interconnected nodes that appear as a single logical unit).[3]
The fundamental components of fabrics are "nodes" (processor(s), memory, and/or peripherals) and "links" (functional connections between nodes).[2] While the term "fabric" has also been used in association withstorage area networks and withswitched fabricnetworking, the introduction ofcompute resources provides a complete "unified" computing system.[citation needed] Other terms used to describe such fabrics include "unified fabric",[4] "data center fabric" and "unified data center fabric".[5]
Ian Foster, director of the Computation Institute at the Argonne National Laboratory and University of Chicago suggested in 2007 thatgrid computing "fabrics" were "poised to become the underpinning for next-generation enterprise IT architectures and be used by a much greater part of many organizations".[6]
While the term has been in use since the mid to late 1990s[2] the growth ofcloud computing and Cisco's evangelism ofunified data center fabrics followed byunified computing (an evolutionarydata center architecture wherebyblade servers are integrated orunified with supportingnetwork andstorage infrastructure) starting March 2009 has renewed interest in the technology.[7][8]
There have been mixed reactions to Cisco's architecture, particularly from rivals who claim that these proprietary systems will lock out other vendors. Analysts claim that this "ambitious new direction" is "a big risk" as companies such asIBM andHP who have previously partnered withCisco ondata center projects (accounting for $2–3bn of Cisco's annual revenue) are now competing with them.[8][9]
In 2007, Wombat Financial Software launched the "Wombat Data Fabric," the first commercial off-the-shelf software platform providing high performance / low-latency RDMA-based messaging across an Infiniband switch.[10]
The main advantages of fabrics are that massive concurrent processing combined with a huge, tightly coupled address space makes it possible to solve huge computing problems (such as those presented by delivery ofcloud computing services); and that they are bothscalable and able to be dynamically reconfigured.[2]
Challenges include a non-linearly degrading performance curve, whereby adding resources does not linearly increase performance which is a common problem withparallel computing and maintainingsecurity.[2]
As of 2015[update] companies offering unified or fabric computing systems includeAvaya,Brocade,Cisco,Dell,[11] Egenera,HPE,IBM,Liquid Computing Corporation,TIBCO,Unisys, andXsigo Systems.[12][13]
According to Ian Foster, Director of the Computation Institute at the Argonne National Laboratory and University of Chicago, 'grid computing "fabrics" are now poised to become the underpinning for next-generation enterprise IT architectures and be used by a much greater part of many organizations.'