狠狠撸shows by User: YuchenZhao2 / http://www.slideshare.net/images/logo.gif 狠狠撸shows by User: YuchenZhao2 / Mon, 05 Dec 2016 20:08:59 GMT 狠狠撸Share feed for 狠狠撸shows by User: YuchenZhao2 大数据场景下应用性能排查的智能根源分析 /YuchenZhao2/ss-69847999 archsummit2016-161205200859
随着应用场景的越来越复杂和微服务的兴起，各种软件系统、模块和服务产生的数据越来越多，应用性能正经历着大数据时代的来临，传统应用性能管理技术已经逐渐不能适应数据的增长以及业务需求。应用性能低下和应用出错已经成为困扰软件开发和运维人员最大的挑战之一。排查这类问题往往需要几个小时甚至几天的时间，严重影响了效率和商业业务。在本演讲中，我们将对应用性能中常见的半结构化数据进行详细的分析。针对这些数据类型，我们将阐述和展示智能根源分析(RCA)的方法，从而大大降低了应用性能排查的时间至几分钟甚至几秒钟，极大提高了软件开发和运维的效率和成本。 演讲提纲： 1. 应用性能（APM）中的大数据； 1.1 大数据场景； 1.2 应用性能排查的痛点； 2. 对半结构化数据的智能根源分析； 2.1 智能根源分析（RCA）案例； 2.2 系统设计； 2.3 在日志（Log）上的应用； 3. 总结和未来方向； 听众受益： 1.理解APM场景中大数据已经到来； 2.在大数据场景中，对应用性能中不同的数据类型如何处理； 3.在应用性能降低或出错时，如何迅速的智能化的找到真正原因。]]>
随着应用场景的越来越复杂和微服务的兴起，各种软件系统、模块和服务产生的数据越来越多，应用性能正经历着大数据时代的来临，传统应用性能管理技术已经逐渐不能适应数据的增长以及业务需求。应用性能低下和应用出错已经成为困扰软件开发和运维人员最大的挑战之一。排查这类问题往往需要几个小时甚至几天的时间，严重影响了效率和商业业务。在本演讲中，我们将对应用性能中常见的半结构化数据进行详细的分析。针对这些数据类型，我们将阐述和展示智能根源分析(RCA)的方法，从而大大降低了应用性能排查的时间至几分钟甚至几秒钟，极大提高了软件开发和运维的效率和成本。 演讲提纲： 1. 应用性能（APM）中的大数据； 1.1 大数据场景； 1.2 应用性能排查的痛点； 2. 对半结构化数据的智能根源分析； 2.1 智能根源分析（RCA）案例； 2.2 系统设计； 2.3 在日志（Log）上的应用； 3. 总结和未来方向； 听众受益： 1.理解APM场景中大数据已经到来； 2.在大数据场景中，对应用性能中不同的数据类型如何处理； 3.在应用性能降低或出错时，如何迅速的智能化的找到真正原因。]]> Mon, 05 Dec 2016 20:08:59 GMT /YuchenZhao2/ss-69847999 YuchenZhao2@slideshare.net(YuchenZhao2) 大数据场景下应用性能排查的智能根源分析 YuchenZhao2 随着应用场景的越来越复杂和微服务的兴起，各种软件系统、模块和服务产生的数据越来越多，应用性能正经历着大数据时代的来临，传统应用性能管理技术已经逐渐不能适应数据的增长以及业务需求。应用性能低下和应用出错已经成为困扰软件开发和运维人员最大的挑战之一。排查这类问题往往需要几个小时甚至几天的时间，严重影响了效率和商业业务。在本演讲中，我们将对应用性能中常见的半结构化数据进行详细的分析。针对这些数据类型，我们将阐述和展示智能根源分析(RCA)的方法，从而大大降低了应用性能排查的时间至几分钟甚至几秒钟，极大提高了软件开发和运维的效率和成本。 演讲提纲： 1. 应用性能（APM）中的大数据； 1.1 大数据场景； 1.2 应用性能排查的痛点； 2. 对半结构化数据的智能根源分析； 2.1 智能根源分析（RCA）案例； 2.2 系统设计； 2.3 在日志（Log）上的应用； 3. 总结和未来方向； 听众受益： 1.理解APM场景中大数据已经到来； 2.在大数据场景中，对应用性能中不同的数据类型如何处理； 3.在应用性能降低或出错时，如何迅速的智能化的找到真正原因。 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/archsummit2016-161205200859-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> 随着应用场景的越来越复杂和微服务的兴起，各种软件系统、模块和服务产生的数据越来越多，应用性能正经历着大数据时代的来临，传统应用性能管理技术已经逐渐不能适应数据的增长以及业务需求。应用性能低下和应用出错已经成为困扰软件开发和运维人员最大的挑战之一。排查这类问题往往需要几个小时甚至几天的时间，严重影响了效率和商业业务。在本演讲中，我们将对应用性能中常见的半结构化数据进行详细的分析。针对这些数据类型，我们将阐述和展示智能根源分析(RCA)的方法，从而大大降低了应用性能排查的时间至几分钟甚至几秒钟，极大提高了软件开发和运维的效率和成本。 演讲提纲： 1. 应用性能（APM）中的大数据； 1.1 大数据场景； 1.2 应用性能排查的痛点； 2. 对半结构化数据的智能根源分析； 2.1 智能根源分析（RCA）案例； 2.2 系统设计； 2.3 在日志（Log）上的应用； 3. 总结和未来方向； 听众受益： 1.理解APM场景中大数据已经到来； 2.在大数据场景中，对应用性能中不同的数据类型如何处理； 3.在应用性能降低或出错时，如何迅速的智能化的找到真正原因。
大数据场景下应用性能排查的智能根源分析 from Yuchen Zhao
]]> 460 3 https://cdn.slidesharecdn.com/ss_thumbnails/archsummit2016-161205200859-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Next Generation Intelligent APM: Pain Points, Trends and Solutions /slideshow/next-generation-intelligent-apm-pain-points-trends-and-solutions/65641466 nextgenerationintelligentapm-painpointstrendsandsolutions-appdstyle-160902203956
2016 APMCon Keynote, Beijing]]>
2016 APMCon Keynote, Beijing]]> Fri, 02 Sep 2016 20:39:56 GMT /slideshow/next-generation-intelligent-apm-pain-points-trends-and-solutions/65641466 YuchenZhao2@slideshare.net(YuchenZhao2) Next Generation Intelligent APM: Pain Points, Trends and Solutions YuchenZhao2 2016 APMCon Keynote, Beijing <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/nextgenerationintelligentapm-painpointstrendsandsolutions-appdstyle-160902203956-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> 2016 APMCon Keynote, Beijing
Next Generation Intelligent APM: Pain Points, Trends and Solutions from Yuchen Zhao
]]> 677 5 https://cdn.slidesharecdn.com/ss_thumbnails/nextgenerationintelligentapm-painpointstrendsandsolutions-appdstyle-160902203956-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Anomaly detection and root cause analysis in distributed application transactions /slideshow/anomaly-detection-and-root-cause-analysis-in-distributed-application-transactions/54003917 anomalydetectionandrootcauseanalysisindistributedapplicationtransactions-151016033459-lva1-app6892
Presentation slide deck for SF Big Analytics. As “software is eating the world”, we have seen an emergence of software-defined businesses and a radical digital disruption across almost all industries. Meanwhile, the application architecture is changing rapidly to cloud, NOSQL and abundant distributed services with a focus on big data. Since the application complexity is exploding, applications could easily lose control and their management, diagnosis and root cause analysis are particularly challenging. Simple questions such as “why and when the application crashed” or “why it works for some users but not for others” can be tricky to answer and investigate. In addition, the data collected by application performance monitoring (APM) products for analysis is complex, heterogeneous and often semi-structured. In this talk, Yuchen will share insights on building a powerful end-to-end machine learning system that collects application related data and provides insightful relevant fields analysis in addition to search and filtering. He will discuss details on field extraction, indexing, relevant field processing and dynamic baseline derivation. He will also demonstrate the effectiveness of various machine learning scoring algorithms. Real-world use cases show relevant fields analysis is effective to detect application anomalies and discover root causes of application incidents. ]]>
Presentation slide deck for SF Big Analytics. As “software is eating the world”, we have seen an emergence of software-defined businesses and a radical digital disruption across almost all industries. Meanwhile, the application architecture is changing rapidly to cloud, NOSQL and abundant distributed services with a focus on big data. Since the application complexity is exploding, applications could easily lose control and their management, diagnosis and root cause analysis are particularly challenging. Simple questions such as “why and when the application crashed” or “why it works for some users but not for others” can be tricky to answer and investigate. In addition, the data collected by application performance monitoring (APM) products for analysis is complex, heterogeneous and often semi-structured. In this talk, Yuchen will share insights on building a powerful end-to-end machine learning system that collects application related data and provides insightful relevant fields analysis in addition to search and filtering. He will discuss details on field extraction, indexing, relevant field processing and dynamic baseline derivation. He will also demonstrate the effectiveness of various machine learning scoring algorithms. Real-world use cases show relevant fields analysis is effective to detect application anomalies and discover root causes of application incidents. ]]> Fri, 16 Oct 2015 03:34:59 GMT /slideshow/anomaly-detection-and-root-cause-analysis-in-distributed-application-transactions/54003917 YuchenZhao2@slideshare.net(YuchenZhao2) Anomaly detection and root cause analysis in distributed application transactions YuchenZhao2 Presentation slide deck for SF Big Analytics. As “software is eating the world”, we have seen an emergence of software-defined businesses and a radical digital disruption across almost all industries. Meanwhile, the application architecture is changing rapidly to cloud, NOSQL and abundant distributed services with a focus on big data. Since the application complexity is exploding, applications could easily lose control and their management, diagnosis and root cause analysis are particularly challenging. Simple questions such as “why and when the application crashed” or “why it works for some users but not for others” can be tricky to answer and investigate. In addition, the data collected by application performance monitoring (APM) products for analysis is complex, heterogeneous and often semi-structured. In this talk, Yuchen will share insights on building a powerful end-to-end machine learning system that collects application related data and provides insightful relevant fields analysis in addition to search and filtering. He will discuss details on field extraction, indexing, relevant field processing and dynamic baseline derivation. He will also demonstrate the effectiveness of various machine learning scoring algorithms. Real-world use cases show relevant fields analysis is effective to detect application anomalies and discover root causes of application incidents. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/anomalydetectionandrootcauseanalysisindistributedapplicationtransactions-151016033459-lva1-app6892-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Presentation slide deck for SF Big Analytics. As “software is eating the world”, we have seen an emergence of software-defined businesses and a radical digital disruption across almost all industries. Meanwhile, the application architecture is changing rapidly to cloud, NOSQL and abundant distributed services with a focus on big data. Since the application complexity is exploding, applications could easily lose control and their management, diagnosis and root cause analysis are particularly challenging. Simple questions such as “why and when the application crashed” or “why it works for some users but not for others” can be tricky to answer and investigate. In addition, the data collected by application performance monitoring (APM) products for analysis is complex, heterogeneous and often semi-structured. In this talk, Yuchen will share insights on building a powerful end-to-end machine learning system that collects application related data and provides insightful relevant fields analysis in addition to search and filtering. He will discuss details on field extraction, indexing, relevant field processing and dynamic baseline derivation. He will also demonstrate the effectiveness of various machine learning scoring algorithms. Real-world use cases show relevant fields analysis is effective to detect application anomalies and discover root causes of application incidents.
Anomaly detection and root cause analysis in distributed application transactions from Yuchen Zhao
]]> 1517 5 https://cdn.slidesharecdn.com/ss_thumbnails/anomalydetectionandrootcauseanalysisindistributedapplicationtransactions-151016033459-lva1-app6892-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Data Science in Industry - Applying Machine Learning to Real-world Challenges /slideshow/data-science-in-industry-usu/47261087 datascienceinindustry-usu-150421165626-conversion-gate01
This slide deck gives an introduction on data science focusing on three most common tasks including regression, classification and clustering. Each task comes with a real world data science project to illustrate the concepts. This presentation was initially created for a one-hour guest lecture at Utah State University for teaching and education purposes.]]>
This slide deck gives an introduction on data science focusing on three most common tasks including regression, classification and clustering. Each task comes with a real world data science project to illustrate the concepts. This presentation was initially created for a one-hour guest lecture at Utah State University for teaching and education purposes.]]> Tue, 21 Apr 2015 16:56:26 GMT /slideshow/data-science-in-industry-usu/47261087 YuchenZhao2@slideshare.net(YuchenZhao2) Data Science in Industry - Applying Machine Learning to Real-world Challenges YuchenZhao2 This slide deck gives an introduction on data science focusing on three most common tasks including regression, classification and clustering. Each task comes with a real world data science project to illustrate the concepts. This presentation was initially created for a one-hour guest lecture at Utah State University for teaching and education purposes. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/datascienceinindustry-usu-150421165626-conversion-gate01-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> This slide deck gives an introduction on data science focusing on three most common tasks including regression, classification and clustering. Each task comes with a real world data science project to illustrate the concepts. This presentation was initially created for a one-hour guest lecture at Utah State University for teaching and education purposes.
Data Science in Industry - Applying Machine Learning to Real-world Challenges from Yuchen Zhao
]]> 1054 2 https://cdn.slidesharecdn.com/ss_thumbnails/datascienceinindustry-usu-150421165626-conversion-gate01-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 https://cdn.slidesharecdn.com/profile-photo-YuchenZhao2-48x48.jpg?cb=1605351348 9+ year R&D experience on large-scale data mining and machine learning engineering with big data (petabyte scale) hands-on experiences (e-commerece, social network, B2B, SaaS, etc.). ? Excellent coding skills: - Writing production code in Scala/Java/Python with a focus on large-scale real-time data science features, e.g. clustering, classification, anomaly detection, ranking, regression and recommendation. - I build things. Led, implemented and launched machine learning products/systems including relevant field analysis (recommendation), metric correlation analysis, auto regex generation, log clustering, etc. - 1st prize winner (2016, AppDynamics), Hackathon Judge (2013, Linkedin), 1s... http://www.cs.uic.edu/~yzhao https://cdn.slidesharecdn.com/ss_thumbnails/archsummit2016-161205200859-thumbnail.jpg?width=320&height=320&fit=bounds YuchenZhao2/ss-69847999 大数据场景下应用性能排查的智能根源分析 https://cdn.slidesharecdn.com/ss_thumbnails/nextgenerationintelligentapm-painpointstrendsandsolutions-appdstyle-160902203956-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/next-generation-intelligent-apm-pain-points-trends-and-solutions/65641466 Next Generation Intell... https://cdn.slidesharecdn.com/ss_thumbnails/anomalydetectionandrootcauseanalysisindistributedapplicationtransactions-151016033459-lva1-app6892-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/anomaly-detection-and-root-cause-analysis-in-distributed-application-transactions/54003917 Anomaly detection and ...