by clicking on the page. A slider will appear, allowing you to adjust your zoom level. Return to the original size by clicking on the page again.
the page around when zoomed in by dragging it.
the zoom using the slider on the top right.
by clicking on the zoomed-in page.
by entering text in the search field and click on "In This Issue" or "All Issues" to search the current issue or the archive of back issues respectively.
by clicking on thumbnails to select pages, and then press the print button.
this publication and page.
displays a table of sections with thumbnails and descriptions.
displays thumbnails of every page in the issue. Click on a page to jump.
allows you to browse through every available issue.
GCN : June 2013
the large in ux of unstructured data and data without schemas. Examples include click streams, social media, log les, event data, mobility trends, sensor and machine data. . In-memory database systems: Provides a column-oriented relational database in large memory footprint systems for real-time database processing. This is especially suitable for low-latency environment and fast-results requirements. . Massively parallel processing (MPP) databases: Provides distributed database systems that have the ability to scale out as projects increase in size and number. CISCO S BIG DATA STRATEGY As Cisco evolves its big data strategy, it is focusing on three pillars: Increasingly the largest source of Big Data is machine-based data, with streams of information coming from sensors, mobile devices and other proliferating Internet-based systems. Cisco is a leader in interconnecting these machine-based Big Data sources. Cisco optimizes analytics software with its data center product portfolio, which includes Cisco Uni ed Computing System (UCS) and Nexus data center switches. Cisco's Open Partner Ecosystem includes Cloudera, Intel, MapR, Pivotal HD, Oracle, MarkLogic, and Actian Corp. In some cases, machine-based data is most valuable when it can be captured and analyzed as it is created, enabling organizations to make decisions in real time. Cisco connects data sources to analytic systems and delivers information to those who need it. Cisco offers a complete and integrated solution to address the full life cycle of enterprise Big Data requirements. These solutions consider current enterprise data architecture to incorporate Big Data and deliver business value. A typical lifecycle for Big Data has the following stages: Multi-site ingest, Shuf e and Output functions create large traf c volumes The collection of the data from diverse set of data sources as described above. The repository for the collected data. The right kind of data needs to be stored in the right repository. The analytics of the data in the repositories. The reporting and business intelligence for decision- making. NETWORK CONSIDERATIONS Cisco addresses ve key network considerations for big data: The failure of a networking device can affect multiple data nodes of a Big Data cluster. These events are critical factor in degradation of the cluster performance. Hence network availability and resiliency is key in a Big Data environment. A network that cannot handle bursts effectively will drop packets, so optimal buffering is needed in network devices to absorb bursts. Cisco Nexus switches and routers are integrated with Big Data architectures that employ buffer and queuing strategies that can handle bursts effectively. A good network design will consider the possibility of unacceptable congestion at critical points in the network under realistic loads. Network architectures that deliver a linear increase in oversubscription with each device failure are better than architectures that degrade dramatically during failures. Typical clusters are provisioned with one or two -GB uplinks per data node. The use of -Gbps server access is becoming increasingly common as the cluster nodes become more feature rich; Big Data software requires more bandwidth. In upcoming generation of Big Data cluster Gigabit Ethernet data node uplinks will be common practice. The latency contribution to the workload is much higher at the application level, contributed by the application logic (Java Virtual Machine software stack, socket-buffer, etc.) than network latency. Cisco provides low latency option for Big Data clusters that require low latency designs. NETWORK UNDERPINNINGS To understand the importance of the network infrastructure in Big Data projects, consider the work being done at the National Oceanic and Atmospheric Administration. NOAA's climate researchers rely on some of the most impressive high- performance computing systems in the world. For many years, researchers needed to work on site with those systems. But that is no longer the case. Several years ago, NOAA, working with network experts from Cisco, created the n-wave Network, a super-high-speed network infrastructure that gives NOAA SPONSORED CONTENT Relative Importance for Network Design Considerations Source: www.cisco.com/en/US/prod/collateral/ switches/ps9441/ps9670/white_paper_c11- 690561.html Availability and Resiliency Burst Handling and Queuing Oversubscription Ratio Data Node Network Speed Network Latency