On designing and deploying internet-scale services Export

@inproceedings{citeulike:3211366, abstract = {The system-to-administrator ratio is commonly used as a rough metric to understand administrative costs in high-scale services. With smaller, less automated services this ratio can be as low as 2:1, whereas on industry leading, highly automated services, we've seen ratios as high as 2, 500:1. Within Microsoft services, Autopilot [1] is often cited as the magic behind the success of the Windows Live Search team in achieving high system-to-administrator ratios. While autoadministration is important, the most important factor is actually the service itself. Is the service efficient to automate? Is it what we refer to more generally as operations-friendly? Services that are operations-friendly require little human intervention, and both detect and recover from all but the most obscure failures without administrative intervention. This paper summarizes the best practices accumulated over many years in scaling some of the largest services at MSN and Windows Live.}, address = {Berkeley, CA, USA}, author = {Hamilton, James}, booktitle = {LISA'07: Proceedings of the 21st conference on Large Installation System Administration Conference}, citeulike-article-id = {3211366}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1349444}, isbn = {978-1-59327-152-7}, keywords = {distributed, distribution, scalability, web}, location = {Dallas}, pages = {1--12}, posted-at = {2008-09-10 09:23:27}, priority = {2}, publisher = {USENIX Association}, title = {On designing and deploying internet-scale services}, url = {http://portal.acm.org/citation.cfm?id=1349444}, year = {2007} }

TY - CONF ID - citeulike:3211366 L3 - citeulike-article-id:3211366 N2 - The system-to-administrator ratio is commonly used as a rough metric to understand administrative costs in high-scale services. With smaller, less automated services this ratio can be as low as 2:1, whereas on industry leading, highly automated services, we've seen ratios as high as 2, 500:1. Within Microsoft services, Autopilot [1] is often cited as the magic behind the success of the Windows Live Search team in achieving high system-to-administrator ratios. While autoadministration is important, the most important factor is actually the service itself. Is the service efficient to automate? Is it what we refer to more generally as operations-friendly? Services that are operations-friendly require little human intervention, and both detect and recover from all but the most obscure failures without administrative intervention. This paper summarizes the best practices accumulated over many years in scaling some of the largest services at MSN and Windows Live. CY - Dallas SN - 978-1-59327-152-7 AD - Berkeley, CA, USA EP - 12 TI - On designing and deploying internet-scale services PB - USENIX Association T2 - LISA'07: Proceedings of the 21st conference on Large Installation System Administration Conference SP - 1 KW - distributed KW - distribution KW - scalability KW - web AU - Hamilton, James PY - 2007/// UR - http://portal.acm.org/citation.cfm?id=1349444 ER -