Open broadcast of the main hall HighLoad ++
Great news - just like last year we will broadcast the main HighLoad ++ hall with the most interesting reports for free!
Do not forget to click on " Remind ", as well as subscribe to our channel . We constantly post videos of our reports in it.
Only the main hall will be broadcasted in open access, if you want to see the remaining 9 halls , you can also purchase closed access .
The full schedule is available on the website ( PDF , HTML ), and we will tell you about the most interesting reports by rolling.
Life after sharding
November 8, 2:00 pm
Many people think that to create a good highload project you need to share the data in the right way and sleep peacefully, delivering the server as needed. In fact, only after sharding does the most interesting part begin, since after physical separation the data does not cease to be logically connected. Badoo's
Mikhail Kurmaev will talk about how they solved problems of this class with the MySQL database. It will be about both characteristic problems outside sharding, and the process of building it: processing of realtime events, queues in conditions of geographically separated data centers, and much more.
As I was a team leader, and now - the head of the direction
November 8, 11:00
In a report by Vitaliy Sharovatov from Badoo, he will talk about two topics: how does growth from team lead to department head look like, and how to choose a team lead for his replacement, to help him become effective.
We will talk a little about psychology, about the atmosphere in the team, mentoring, of course, about hiring and much more. From Vitaly’s speech you will learn how to:
- competently choose a team lead : based on what criteria, how to check how much a person can fit, how to sell the idea of a career change and fight against classic fears;
- help the chosen person to confidently get into the course of the matter and become as effective as possible, fight;
- monitor the situation in teams and keep your finger on the pulse;
- stop leading the team yourself , and how lead management differs from managing developers.
Headliner of 2017 Mikhail Sychev from Google with a report
Reconstruction YouTube.com - rewriting the second most popular site in the world
November 7, 13:00
I ’ll tell you why we decided (and only now) to switch to a client-side application, how we evaluate the performance of YouTube (and why “Time To Glass” and “Above the Fold” are just the beginning of the story), as front-end and back -end work together to achieve maximum productivity when business logic is designed for many dozens of customers.
We will discuss why we chose Polymer as the framework for the site (no, not only because Google made it), a new development platform based on it, A / B testing and “experiments” to evaluate changes and control user reactions, and what metrics do we pay attention to ...
Quality Control of Highly Loaded Systems
November 8, 12:00
Agree that it is unrealistic to build highly loaded systems blindly? How to build quality control when developing difficult services? What exactly should you pay attention to when testing performance? The topic of testing loaded systems has been covered at many conferences more than once; there are a bunch of articles, blog entries, instructions from vendors. A huge pile of information.
Without preparation in this abundance of tips and solutions, you can easily get confused and waste valuable time on testing and quality control for nothing. And you can listen to Andrey Drozdov with a story about how quality control of loaded systems in Avito works.
In his story, Andrey will tellhow to build a system of testing and quality control of services from scratch. Together with you we will listen about fault tolerance, automation, see what tools Avito uses and what they get. And we’ll see how correctly selected metrics and accurate accounting.
Effective use of ClickHouse
November 8, 15:00
ClickHouse is available in open-source for just over a year. During this time, experience has been gained in its use in Russian and foreign companies. In some of them, the data volumes and loads exceed those with which we deal in Yandex. Since ClickHouse is a specialized system, when using it, it is important to consider the features of its architecture.
In his report, Alexey Milovidov will talk about examples of typical errors when using ClickHouse, which can lead to inefficient operation. Case studies will show how the choice of a data processing scheme can change performance by orders of magnitude.
How to rewrite VK database from scratch and migrate to it without downtime
November 7, 18:00
For many years, personal messages on the social network VKontakte worked on the same self-written database. Over time, it became obsolete, making it difficult to introduce new functionality, and growing loads led to the fact that for the functioning of messaging, a huge number of servers began to be required .
Dmitry Egorov will tellabout how a new message storage system was developed from scratch and introduced over the course of 10 months, which removes many architectural restrictions and also has much greater productivity, which allowed the company to save millions of dollars! The report will discuss the architecture of both personal messaging engines, many optimizations, and the technically most difficult part is described in detail - migration without downtime.
That's all, we are going to Skolkovo for building, and we are waiting for you on the online broadcast :)
PS: By the way, NGENIX company delivers and accelerates the broadcast , for which many thanks to it! And the company's technical director Dmitry Krikov, together with Alexander Petrovsky from Mellanox, will read a report entitled " Disaggregation and openness in Ethernet networks " on HighLoad ++ .