The Day That Google Died
UPDATE: In a post on the Official Google Blog, Google describes the problem as a routing issue. Urs Hoelzle, senior vice president of operations, wrote that “an error in one of our systems caused us to direct some of our web traffic through Asia, which created a traffic jam. As a result, about 14% of our users experienced slow services or even interruptions.”
An unspecified technical problem prevented Google users all over the world from accessing their favorite Google services on Thursday morning, starting around 7:48 a.m. Pacific time. As fast as people could type out their quips and complaints, reports of problems with Google search, YouTube, Google Analytics, Google APIs, Google Docs, Google Maps and Google Reader came pouring in from Copenhagen to Venezuela. Google acknowledged “a problem” had affected “a small subset of users,” but as of 11 a.m. had not provided additional details.
Responding to some blog reports that the issue may have been related to AT&T’s network, John Britton, a spokesman for AT&T said Google’s problem was “not related to AT&T.”
Below is the timeline:
8:23 a.m. PST Google’s Apps Status Dashboard reported a glitch with Gmail that it said may have affected other services. “We’re aware of a problem with Google Mail affecting a small subset of users. The affected users are unable to access Google Mail. We will provide an update by May 14, 2009 10:00:00 AM UTC-7 detailing when we expect to resolve the problem. Please note that this resolution time is an estimate and may change.”
9:28 am. PST The company also posted this message on Twitter: “We’re aware some users are having trouble accessing some Google services. We’re looking into it, and we’ll update everyone soon.”
9:39 a.m. PST A new post on the Apps Status Dashboard said, “The problem with Google Mail should be resolved.”
9:50 a.m. PST Just Ping, a web-monitoring company reports the following packet losses from Google.com.:
Amsterdam 80% packets dropped; Austin, TX 80 %; Copenhagen, Denmark 100%; Haifa, Israel 80%, Hong Kong 70%; Krakow, Poland 70%; Lille, France 60%; Nagano, Japan 80%; New York 90%; Oslo, Norway 100%; Rio de Janeiro 60%; and Santa Clara, CA 10%;
10:33 a.m. PST Google posts this statement on Twitter and e-mails it to reporters: “The issue affecting some Google services has been resolved. We’re sorry for the inconvenience, and we’ll share more details soon.”
Here are some sample comments from Twitter’s #googlefail thread.
@swu how can I tell if the world is ending if I can’t google it?
@Rinze Google se madrileñiza
@mtigas First e-mail received post-#googlefail: “50% off Thousands of DVDs.” Great! I wonder if I ever needed Google & Gmail in the first place
@giyomu Google + Gmail + Googleapi down ? WTF ? Orange ? Probablement. #googlefail
@vulgrin wife’s email is fine, on same domain / account. I’m going to go apeshit if this doesn’t resolve itself soon
@amontag Minor anxiety attack over #googlefail over. Moving on with the day
@Google es a Internet lo que una hallaca a la navidad venezolana
@maxmerz Google lebt wieder. Gmail auch. Der Reader auch. Juchu.
@MickWest Google broke the internet!
Subscribe via RSS all feeds
Google might still be dying IMO: Why Twitter is changing search…
It came to me last night: Twitter is changing search.
Ok, everybody knows by now ? Yep, but the magnitude by which it’s happening doesn’t depend on Twitter itself and is by now irreversible.
Google isn’t actual anymore, because Google doesn’t get enough links from websites, blogs and wikis.
Google only gets shortened urls from Twitter, Jaiku, Identi.ca, Kwippy, Khaces, Meemi, Niimo, Watwet, etc.
It’s even becoming a trend to use these services for blog links, like they provide more and more information about the clickthrough rates and range.
I really like cli.gs map views about my microblog audience…
The problem Google has, is that it’s no longer the direct deliverer of traffic to sites, and that these site can ask them money for delivering the entire direct link.
Shortening sites could even blok access through search engine for their link or redirecting them to an interposed publicity before giving access to the site requested.
This means that they are now increasingly become the gatekeepers of information… and that has always been the place to be for any real gain.
Like by now there are some shortening services giving people some cash for using them, I believe someone has found this out and is exploiting the value generating model behind this gatekeepers function.