RELATED CONTENT
- A freak double failure in its data centers took Twitter down for around an hour on …
- A freak double failure in its data centers took Twitter down for around an hour on …
US spy master courts top hackers at Def Con
AFP News - 45 minutes agoGoogle seeks to close book in author copyright case
AFP News - 1 hour 16 minutes agoAnalysis: Internet stock collapse dents Silicon Valley
Reuters - 1 hour 33 minutes ago
A freak double failure in its data centers took Twitter down for around an hour on Thursday, leaving millions without updates from friends, celebrities and news providers a day ahead of the Olympics.
"We are sorry," said Mazen Rawashdeh, Twitter's vice president of engineering, in a message on the company's support blog.
"Many of you came to Twitter earlier today expecting, well, Twitter. Instead, between around 8:20 am and 9:00 am Pacific Time (1720 GMT to 1800 GMT), users around the world got zilch from us," he said.
The glitch was fixed by about 1925 GMT, according to Rawashdeh, but not before the outage had affected users around the world.
In a blog post, Rawashdeh explained that the blackout was triggered by a data center system and its backup system failing simultaneously.
"I wish I could say that today's outage could be explained by the Olympics or even a cascading buy," he said. "Instead, it was due to this infrastructural double-whammy."
Service was gradually restored and many users posted messages expressing relief in sarcastic terms.
"Wow. Wasn't sure I'd survive that @twitter outage. I even took to Facebook. Desperate times call for desperate measures. Thankful it's back," professional baseball player Michael Schlact tweeted.
Jason Carlin of Toronto tweeted: "Took time during the Twitter outage to explore some self-improvement."
"I've written two novels, learned Esperanto and knitted a sweater," he added.
Last month, the service was downed for several hours by what the company described as a "cascading bug," but the company said this time it had fallen victim to the double data center failure.
"Data centers are designed to be redundant: when one system fails, as everything does at one time or another, a parallel system takes over," Rawashdeh said in a message to users.
"What was noteworthy about today's outage was the coincidental failure of two parallel systems at nearly the same time.
But Rawashdeh promised that "we are investing aggressively in our systems to avoid this situation in the future."
In its early days, Twitter was notoriously unstable and would display a picture known as the "fail whale" on its home page when it experienced one of its frequent outages.
The service has become more reliable over the past couple of years, however, and down time is now infrequent.
At the Olympics, athletes are expected to share their Twitter handles, and tweet their experiences using the site.
Twitter, which allows its members to post brief comments, links or pictures, claims to have more than 140 million active users, with the largest number being in the United States.
A recent survey found one in seven Americans who go online use Twitter and eight percent do so every day.
The service has become more reliable over the past couple of years, however, and down time is now infrequent.
ReplyDelete水虫 | 爪水虫