Bing is comprised of ~300 petabytes of data

Microsoft has just taken to the stage at NA TechEd and is wasting no time by letting out some impressive statistics including that Bing is currently composed of nearly 300 petabytes of data and the service is writing nearly 1 terabyte of data each day. 

This massive amount of data goes to show that creating a search engine, is not an easy task. Gathering this amount of information is surely critical to delivering accurate and the best possible search results on the first query. Microsoft also said that Bing is now running on Server 2012 RC, which was announced previously, but wanted to hit home that Microsoft battle tests all of its products before pushing them out in to the field. 

As we progress through TechEd, expect to hear a lot more about how Microsoft services are "re-defining" the market as the company is pushing out new products such as Server 2012. Neowin is down on the ground floor at TechEd and has a few interviews lined up with folks from Microsoft and Nokia, stick around as the fun is only getting started. 

Report a problem with article
Previous Story

Watch Microsoft's NA TechEd keynote live

Next Story

Over 900,000 Android devices now activated per day

24 Comments

Commenting is disabled on this article.

theyarecomingforyou said,
Did anyone else read the title as 'compromised' rather than 'comprised"? I'm so used to reading about security scares.

True... for a moment I did it.....

theyarecomingforyou said,
Did anyone else read the title as 'compromised' rather than 'comprised"? I'm so used to reading about security scares.

Same bro!

It's ridiculous what our eyes have been trained for and now hardly will let go of that and let us read the actual title.
It took me reading a bit of the article to actually get the headline

GS:mac

I don't see the big deal that Microsoft are running Bing on 2012 RC... it's not like anyone actually uses that search engine anyway!

PhilUK said,
I don't see the big deal that Microsoft are running Bing on 2012 RC... it's not like anyone actually uses that search engine anyway!

i use it daily

PhilUK said,
I don't see the big deal that Microsoft are running Bing on 2012 RC... it's not like anyone actually uses that search engine anyway!

It's my main search engine.

*ahum* 13% market share *ahum*

Even if it was just a database they would mostly be references of metatags and what not. Its not like they have a COPY of every website on the planet.

xbamaris said,
I don't exactly understand WHY they have so much data.

I think it has to do with features such as 'cached version' of webpages and, more so, the cached video previews Bing Video search has (you can preview a video by moving your mouse over it). The latter probably takes quite a bit of storage space.

xbamaris said,
Even if it was just a database they would mostly be references of metatags and what not. Its not like they have a COPY of every website on the planet.

They will have copies of all the pages they've crawled, otherwise how would they be able to look them up so quickly when they do a search? Searching is done on far more than just meta tags.

keyboardP said,

I think it has to do with features such as 'cached version' of webpages and, more so, the cached video previews Bing Video search has (you can preview a video by moving your mouse over it). The latter probably takes quite a bit of storage space.

Don't forget maps, probably makes up the largest chunk of the data.