The failure of AWS Tokyo led to the collapse of Chinese exchanges, why is Huobi so serious, and why is Binance down due to heavy traffic

Wu said the author | Colin Wu

Editor of this issue | Colin Wu

The old-fashioned "butterfly effect" story appeared in China's encryption industry on the evening of the 19th. Because of the power outage of the cooling system of the AWS Tokyo node, Huobi first experienced a serious network-wide downtime, and then Binance, Matcha, Coinex, KuCoin, etc. also experienced small-scale failures. It can be said that almost all Chinese exchanges have been affected. Influence.

At 10:00 p.m. Beijing time on the 19th, Huobi suddenly experienced a network failure, and users were kicked out of the login status, indicating that the network was not good. Huobi said that the login was affected due to a large-scale network failure in Zone C of Amazon Cloud Services, and it has been contacted and is currently being repaired, and the security of customer assets will not be affected.

At 11 o'clock, Binance, KuCoin, Matcha APP, Coinex, etc. also experienced freezes, but the impact was relatively small. The figure is a schematic diagram of the failure of the AWS node and the cause, and it is currently in the repair state. AWS discovered the problem at 11:00 p.m. Japan time on the 19th. The core reason was that the power outage of the cooling system caused the temperature to rise. Most of the problems were restored at 3:30 Japan time on the 20th, and almost all of them were restored at 5:30 on the 20th.

Binance announced that due to the AWS outage affecting our platform and many other exchanges, Binance temporarily suspended deposits, withdrawals, and fund transfers today from 1:13 AM to 4:52 AM Hong Kong time on the 29th.Although almost all Chinese exchanges have encountered failures, why Huobi is so serious, a Weibo netizen explained as follows, and this statement has also been recognized by relevant people.）

"The new CTO sacrificed high availability in pursuit of speed, and forced all services to be migrated to the single availability zone, which is the C zone of the failure. At the same time, there is no quick and effective emergency response plan. Once a single zone failure occurs, All services need to be migrated out, and the data needs to be rebuilt, which is very time-consuming." (Reference

Exclusive: Former Ali Executive Zhu Ye Appointed as Huobi's New CTO All Huobi Executives Expose for the First Time

Industry insiders pointed out that AWS Japan is the most expensive region in the Asia-Pacific region, and it is also an earthquake zone. It is not an appropriate choice to choose AWS Japan as the only available region. Objectively speaking, system availability, extreme transaction performance, and cost input are "impossible triangles", and the pursuit of speed at the expense of availability may lead to such results.

As Bitcoin and some mainstream currencies continued to soar on the evening of the 19th, investors who shorted contracts may suffer losses because they cannot cancel their orders. At present, except for Huobi, other exchanges have a smaller scope of failure, so there is not much compensation problem. Huobi said that it will definitely introduce a corresponding compensation plan. What is more special is that OKEx may have basically no failures in this incident because it mainly uses Alibaba Cloud servers in Hong Kong.

Before the failure, Binance suddenly announced the suspension of withdrawals of Ethereum and related tokens, which caused a lot of speculation and conspiracy theories, but quickly resumed withdrawals. The reason is currently unknown. However, Binance's relatively high frequency of downtime and failures has also attracted attention. What is the reason? Binance itself attributed it to excessive traffic, and CZ said that the number of new users reached 30,000 per day. However, some people also questioned that Binance’s profit in the last quarter was close to 1 billion US dollars, so it should not be reluctant to invest in technology.