NewsData managementStrategyInfrastructure

According to a Google spokesperson, "Google's networking and data center infrastructures have not been materially affected by the [Japan] earthquake."

Indeed, the averaged response times of Google App Engine in the Asia-Oceania region on 12 March (the day after the Japan Earthquake struck) was 4.47 seconds -- the best recorded in the past 30 days. But note the huge variation of Google App Engine response times in different cities: Sydney (11.3 seconds), Tokyo (11.61 seconds), Mumbai (12.69 seconds), and Beijing (87.55 seconds), which 'averaged out' the figure at 14.02 seconds (See Figure 1).

(Source: CloudSleuth; annotations by Asia Cloud Forum staff)

Google declined to detail its disaster recovery measures in relation to the Japan earthquake, as "it is the company's policy not to comment specifically on data centers." According to the Google spokesperson, the company has been maintaining a "diverse networking and data center infrastructure which allows us to tolerate point failures without disruption to our overall service."

In terms of availability in the Asia-Oceania region, Google App Engine has the lowest overall availability among the 18 cloud service providers being monitored at CloudSleuth, averaging at 82.88% in the past 30 days. But note the huge variations among the four cities where CloudSleuth collected these rates of availability -- Tokyo (99.9%), Mumbai (100%), Sydney (99.88%), and Beijing (7.26%), which consistently remained 0% since 12 March (See Figure 2) (Contrast this with Microsoft Azure's 99.8% availability in Beijing in the past 30 days).