Slashdot Mirror
Kevin Rose Load Tests Gmail
SishGupta writes "Load Testing Gmail - fillmybox@gmail.com
A few weeks ago, Kevin Rose of the The Screen Savers decided to load test Google's new email service, Gmail. He asked everyone to email him their favourite 5MB attachments to 'fillmybox@gmail.com.'
The test Gmail account is now 102% maxed out.
You can read about the test and the results at Kevin Rose.com (his weblog)."
Bet he wasn't expecting that!
And I was thinking the fact I was at 13% was quite impressive.
Jay | http://oldos.org
I've had little success with GMail's "auto ignore" option. Check this mozilla screengrab out:
http://etrade.malformed.org/Screenshot.png
With a gmail address of "fillmybox", I wonder what kind of file attachments he received!
Why does anyone listen to him...he's half security, half pirate, half hacker.
That's more then 100%!!!
~Eric
...may the Gmail privacy flaming begin!
The preceding message was based on actual events. Only the names, locations and events have been changed.
certainly an inventive way to get a response.
Why, just last night I wrote a little program that load tests Google.
Regards,
Arthur MyDoom, Jr.
"In spite of everything, I still believe that people are really good at heart." - Anne Frank
... since Google advertises the service as 1GB of email storage 1023MB is technically under the limit and not 102% of the limit.
His account maxed out at just under 1024 MB.
"Dave, I stand still--the conclusions jump to me!" - Bill McNeal, NewsRadio
Mod me down as flamebait if you really must, but what really was the point of this exercise ? I'm sure Google would find it an interesting test -assuming they've not already tried it themselves - but as the author says, he's never actually told anybody at google about it. It just doesn't strike me as particularly constructive...
Never, ever lose a file again. Ever.
is to let everyone on Slashdot have an account, at once.
--
# Canmephians for a better Linux Kernel
$Stalag99{"URL"}="http://stalag99.net";
...Kevin and co-host of the day finish talking about fillmybox@gmail.com and switch back over to Sarah for the news...
/me ROFL
Sarah: "Fill my box"
Kevin: "I will later"
Co-host of the day turns red.
Any words Kevin?
Im dreaming ofa big bndwdth, That can resist the
porn2.mog
porn3.mpg
Ahh.. gotta love when they put the offer out there for you.
Hmmm.
Haven't heard that from the wife in ages!
Thanks, folks, I'll be here all week! Tip your waitresses!
I received over 2,000 complaints from people who actually took the time to dig around and find my personal email address, I'm thinking we hit Gmail with around 50-75,000+, 5MB+ emails in a 10-15min window.
Think of all the spam that one of these accounts could hold. I propose testing Gmail's spam filters next: disseminate your Gmail addy to porn sites, and everywhere else it will likely be harvested by a spam bot. Sit back, and let the spam roll in. It should be interesting to see just how fast this sucker fills up with ads for penis enlargers.
I'm thinking we hit Gmail with around 50-75,000+, 5MB+ emails in a 10-15min window.
Hopefully google didn't take that personally.
I'd like to know if his theory about the compressed storage leading to a timeout condition is realistic.
That post would have sucked a whole lot less ass if I had entered my numbers right. 1 GiB is not 10^30 bytes, it's 2^30 bytes. My sincerest apologies for correcting you in a way that requires correction itself.
"You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
we all want to know how google does it, don't we?
here's what he thinks:
Google knows that 80% of mail messages are text, and we all know that text is highly compressible. That said, they probably only have around 2-300MB of storage allocated for each 1GB account (obviously this will fluctuate up to 1GB depending on the user's mail content). My take on this, is that they have a huge series of RAID arrays at their server farm. Every time an email comes in, it is compressed and stored in that users account on the RAID.
this should be closer to the truth: Venti: a new approach to archival storage
[beavisandbutthead]
uh huh huh
uh huh huh
"fill my box"
uh huh huh
[/beavisandbutthead]
>24 megabytes is a substantial difference for most email users.
It is if you have 10MB or 100MB,
but not when you have 1000 megabytes.
100K of memory was alot when all you had was 640K, but 100k is nothing to most users nowadays.
Verily.
Kind of poetic to see the complete definition of dookie on slashdot.
Real operations like America's funniest home videos presumably have their own mail servers, and thus can get dozens of gigabytes of email. I would assume so, anyway. I mean if I, as a college student, have the resources to do that, I'm sure any corporation does.
The question has finally been answered.
Why is Gmail the best free webmail?
ANSWER: Your inbox goes to 102%!!!
If you have kids named Arthur MyDoom, are you going to stick to the old standard (Arthur MyDoom the 3rd, the 4th, etc), or the new approach - Arthur MyDoom.B, Arthur MyDoom.C, Arthur MyDoom.D...?
I doubt that the space is all that the users care about. I was quite content with 5 megs of space until the spam-bots got a hold of my Yahoo account.
No, the real deal is archiving all of your old email and the ability to search through it all, as well as targeted advertising... I detest picture-advertising... most kinds, that is. pr0n's another story.
One of the other factors that makes the service so appealing to me is I trust Google, unlike Microsoft or Yahoo, to not sell my email address. When the company who gave you the email address is handing it out to the spammers (or spamming the box themselves), something is wrong.
- Yolegoman
What is the point in his test ? Did he think that Google hadn't done any testing at all ? Did he think that if a mailbox hit 100% something dreadful would happen ? Of course it's going to work just fine, 1Mb, 10Mb, 100Mb, 1000Mb or even 10,000Mb is just a tiny dribble in the ocean that is Googles' infrastructure. He's just looking for some kind of kudos ... "Hey dude I filled up my Gmail account!" "Wow! That's so ... so ... actually that's pretty lame .."
I signed up my GMail account to every Apple mailing list, mainly because I am a developer and want a searchable archive of exactly the mailing lists i want.
Seemed to be around about that time too. Maybe it was related. Some of the guys here at work were fine though. Maybe logins are always directed to a single server (not just the storage of the emails).
Anyone have a video clip of the segment I can host? _dan http://www.uneasysilence.com
If you have the clip e-mail me at admin (at) uneasysilence.com I would love to host it
_dan
http://www.uneasysilence.com
That great sigh of disappointment you hear is the sound of thousands of porn site administrators realizing that one of the gmail account names they really wanted has been taken...
-S
--- What parts of "shall make no law", "shall not be infringed", and "shall not be violated" don't you understand?
G4TechTV sux0rz. Curse you, Comcast! Curse you!
(Yeah, I know he's on KFI Radio here in LA. Whatever, I miss him on TSS.)
Knowledge is power. Knowledge shared is power multiplied.
The key is: Since there will be alot of users, compressing data is the key. Who cares if the uncompressed part is kept in memory or in /tmp ?
"...a generation of kids has grown up thinking Trance is the shittiest music since country and western." - Paul van Dyk
gspot@fillmybox.com sounds like a porn webmaster email. No wonder he wants all these attachments.
100K of memory was alot when all you had was 640K, but 100k is nothing to most users nowadays.
The memory analogy doesn't work. 100k of memory is nothing to users these days because it can barely hold the smallest of applications.
24 MB of mail storage, on the other hand, is still a lot since mail is still mostly text.
I'm Trappped at Berkeley.
done.
enjoy.
rob.
well, now we know that when you max out your gmail mailbox, you will no longer be able to send it mail.
/much/ more constructive use.
That's fantastic.
i would have put that account to
how much does this guy get paid?
The reason girls and Windows users don't understand UNIX is because all the documentation is in Man files.
send me your email addy to hollman2@gmail.com and I'll give you one.
consumer storage is cheep, yep. but in the datacenter where you have to consider backups, it's not as cheep as you would think. getting disk space (and hardware in general) in a datacenter is a comodity.
Now Kevin will have load tests for his web server too!
SIGFAULT
Thanks buddy.
Ryan
"One of the other factors that makes the service so appealing to me is I trust Google, unlike Microsoft or Yahoo, to not sell my email address. When the company who gave you the email address is handing it out to the spammers (or spamming the box themselves), something is wrong." What purpose would Yahoo have for selling e-mail addresses? They just route it into their bulk mail folder to be easily deleted anyway. Surely this isn't a long term advertising option. That's like paying for direct mailings, only to have the distributing company put them directly into the customers' trash cans on trash day.
Mod points are pointless when you browse at -1.
Nobody can read 1GB of text. Therefore the only way to use a gig of email is if either a) it isn't text, or b) you're not actually reading it.
For instance people getting MPEGs in the mail won't notice the difference between 1000MB and 1024MB. Similarly, people subscribed to a dozen mailinglists, hoping to use google to quickly find any message, won't notice the difference since a few days email will fill up the difference.
To make it really clear... say you can read 100 text emails a day. Now, if those emails are text they'll be about 5k, or around half a meg a day. So you're talking about six _years_ worth of email before you fill your box, with the extra 24MB getting you an extra month on your six years. For people getting ten text emails a day worth keeping, 1GB will probably hold enough email for life.
All good bugs need to be verified to make sure they realy exist. SO anyone want to give me a gmail invite so I can verify the login bug for the good of mankind?
I still have more fans than freaks. WTF is wrong with you people?
[Peter Griffin]
eh heh heh
eh heh heh
"fill my box"
eh heh heh
eh heh heh
"diarrhea"
eh heh heh
[/Peter Griffin]
Montreal - Best city to live in!
Here's the segment from g4techtv captured by me: http://www.members.shaw.ca/fog_dogg_69/fillmybox.w mv
SI rules. Of course it makes sense to have water freeze at 32 degrees instead of 0, and boil at 212 instead of 100... And why the hell would you want to mess with turning 1 kilometer into 1,000 meters, when you can turn 1 mile into 5,280 feet! And to realize that 1 liter is 1,000 milliliters is stupid, since we can instead make 1 gallon (US, liquid - or 0.86 gallon US dry - or 0.83 gallon UK) into 128 fl.oz. I rest my case.
Quidquid latine dictum sit, altum sonatur.
Buy Steampunk Clothing Online!
we would, but wouldnt you know it? last /i/ was aware, hotmail blocks gmail invites. it's a pisser, innit?
"Good night, good work, sleep well, I'll most likely kill you in the morning." - Dread Pirate Roberts
good point, i've just done the research :)
In that case, you can send it to my obscure isp address at hungyao@telus.net. Hopefully, they haven't done any funny business with blocking invites.
Thanks :)
Could any kind and generous slashdotter save me from yahoo mail with a gmail invite?
Yes, I know, -1 Offtopic, but I'd appreciate a hookup! ninenine_99@yahoo.com
Thanks!
Yeah...let me further your line of reasoning and say that there is no reason that we should have switched away from using base 1 for everything, since it's the first way, and every other approach is merely a redundant way to write it, and therefore part of the plot to lead to the eventual heat-death of the universe.
Computers use powers of two for every kind of calculation. The most important reason of all to do the measurements this way is because it's easier. It wasn't random, wasn't folly, wasn't totally rediculous.
The redefinition allows us to use the units in a calculable way. It also makes a kind of sense to redefine mega, giga, and tera in terms of base 2 because a byte is a base 2 unit. Why not just go all out when you're using them and make everything else base 2 as well? You may not that bits, which come out to a nice, round number in every number base, are measured in base 10. A terabit is 10^12 bits.
It's too much to ask that a microcontroller that reports usage have half of it's hardware devoted to base conversion, especially when the result may come out to some terrible fraction. To use your statement, I find that just because people are using mega, giga, and tera with the original meanings just because they're entrenched is folly at best and is better regarded as arrogant.
Mod me down and I will become more powerful than you can possibly imagine!
What would be really interesting now would be to know what exactly people sent him in those 5meg attachments.
http://www.popularculturegaming.com -- my blog about the culture of videogame players
Good test? Old news. A friend of mine, Milo, did this two weeks ago. I even submitted a Slashdot article. But it got rejected. Why? Some guy in the Netherlands isn't as important as the all mighty Kevin Rose of the Screen Savers I guess. :-\
You're right, I wouldn't steal a car. But if it were possible, I sure as hell would download one!
If you haven't already fulfilled this promise, I'd appreciate a Gmail account as well. AJYeary@yahoo.com. And yes, I know Yahoo filters Gmail invites as spam... Which means I'll be digging through my Bulk Mail folder for the next couple days!
~aj~
Would advertising it as 1 GB be then considered false?
Would you hold hard drive manufacturers accountable for false advertising then? Most advertise their drives in gigabytes, when they really equate to a base 10 conversion (think 1,000,000 kB for every gigabyte, as opposed to the actual 1,048,576 kB for every gigabyte).
http://it.slashdot.org/comments.pl?sid=115848&cid= 9808280
If I ever met someone who said or wrote "gibibyte" and "mibibyte" I would surely be inclined towards kicking them in the face and crotch.
That is some wholly ludicrous shit. Everyone knows it is thoroughly ridiculous. They sound like the squeaks of a retarded baby. ME BI BYTE! KI BI! GI BI!
To know the heinous nature of these words you must look at who benefits from them. It is clear that by redefining "gigabyte" the only people who benefit are hard drive manufacturers. In the ensuing confusion they can stop delivering anything like what they advertise and just make up the capacities of their drives. Recently I purchased two "160 gigabyte" hard drives. One of them was about 156 gigabytes while the other turned out to be about 149 gigabytes. I trust both my BIOS and my OS before I trust hard drive marketing and they say I'm getting a bit of the shaft. This is called deception. Lies. Widely agreed upon as immoral and harmful behavior. That is what "kibibyte" is all about.
Tim
Omnia vestra castrorum habetur nobis.
Like many computer users I have a couple of hotmail accounts for spam catching. I go in once a week and flush it out. I don't read any of it I just flush it out.
I created one address as a joke, I sent one mail, got the reaction I wanted, and promptly forgot about it. Well, when the week rolled around I check it and sure enough, it caught nearly as much spam as my advertised address. Some of it within hours of the creation.
But we all know what hotmail is for, don't we.
Garry AKA -Phoenix- Rising Above the Flames
Si hoc legere scis nimium eruditionis habes
The standard prefixes kibi, mebi, gibi, tebi, etc. mean the exact same thing when applied to ANY measure. That's the entire point of a standard, and the standard says 2^10, 2^20, 2^30, and 2^40, respectively.
So exactly what measures, other than units of computer storage, are you intending to apply these prefixes to?
If the answer is "none", then it's not a standard, it's a kludge.
...laporte junior? kevin rose needs to be stopped, he's following in the misinfo footsteps of his mentor mr Leo Laporte. I was so happy when when leo was canned but was sad to see they pulled a cheaper replacement (clone). G4-TECH TV needs to be turned back into a shop at home clone... it's dead to me now...
would be mighty fresh, wouldn't it. :D
----- Question authority, but not ours. Hate the man, but we're not him.
"Excuse me, and you are.."
"It's me! Dr. Rosenrose."
"Who?"
"Dr. Rosenpenis."
"I'm sorry, who did you say?"
"It's me, Kevin Rose Load."
It goes from God, to Jerry, to me.
I've done a little bit of my own stress testing. However, I've done it a little bit different. I wanted to see how Gmail handled huge conversations. I e-mailed my brother and we spammed each other back and forth in the same thread, seeing if we could influence the Ads. After a while we started adding more people to the conversation (our current test thread has nine people). We started out by hitting Reply All and saving the quotes from the previous e-mail. It became a huge list of >>> near the bottom and eventually Gmail clipped the messages. After a few hundred replies, opening the thread became slower and slower. When it reached 426 replies, it took me a week to finally get into it. With that I made one last reply and closed the thread. Hey, just out of curiosity, I opened the thread now and it loaded pretty easily. I wonder if they have optimized their behind the scenes engine to make it faster for large conversations. Maybe I'll continue the thread. Also, if you want to be part of the new test thread, just send an e-mail to adpowers@gmail.com.
Anyway, here is my Gmail stress test.
Also, you'll notice I have a few mailing lists on the side. I only read the Freenet one, but I subscribed to the Linux Kernel list and some others because I know them to be high traffic. Gmail is pretty impressive and they seem to be optimizing it even more.
What's so Flamebait about that? This guy does something that anyone with half a brain could have done (mind you, he needed the help of a national TV audience to do it, too) and it's news?
Heaven help us if he actually does something really notable. He'd probably get a free blowjob from CmdrTaco.
Game... blouses.
I guess "kev" is my hero now
The guy ran the *test* without informing Gmail people and his *promotion* resulted in Gmail receiving 70-80K 5MB mails in 10-15 minutes. Isn't that tantamount to a DDoS? Shouldn't the guy be booked for something?
PS - I RTFA
The Google Filesystem has a Blocksize of 64MB (see http://www.cs.rochester.edu/sosp2003/papers/p125-g hemawat.pdf for more information), so most likely the reason for the 1024MB of total size is, that the granularity of the quota system is 64MB too.
Hmm, /mnt/usb/emerg-mail-backup/2004.07.20 /mnt/usb/emerg-mail-backup/2004.07.21 /mnt/usb/emerg-mail-backup/2004.07.22 /mnt/usb/emerg-mail-backup/2004.07.23 /mnt/usb/emerg-mail-backup/2004.07.24 /mnt/usb/emerg-mail-backup/2004.07.25 /mnt/usb/emerg-mail-backup/2004.07.26 /mnt/usb/emerg-mail-backup/2004.07.27
;-)
2.8M
1.6M
1.6M
1.4M
1.5M
1.2M
1.6M
1.7M
Guess you're just more popular than me
gmail doesn't have terribly good support for export; I've seen a POP3 interface but it didn't work so well. I guess as it gets more popular the tools will improve.
The import tools are still fairly primitive too -- I found some emails took forever to import (invariably spam), with no skipping support.
Damn, and here I thought the speed limit on my commute was 61440 meters per hour. Drat! I guess I'll have to slow down to a paltry 60000.
Do daemons dream of electric sleep()?
I appreciate that gmail is in a test phase, but it sucks that this hack is wasting his account on a publicity stunt (don't for a second think it's more than that) when there are thousands of people begging for invites all over the world.
like me: matthyw at canoemail dot ca
Sorry. Lame begging aside, what does he think he's going to accomplish by this? It's basically an excuse to say something dirty over a public media stream.
I seriously hope you were joking with that post :-P
If enough people send each other copies of the "fill my gmail" video clip, will they fill gmail?
That selfish bastard:
"Proceeded to login with other Gmail accounts to ensure this was not a site wide problem. All other accounts worked fine."
He has multiple Gmail accounts, and I don't have a single one. Even more of a kick in the pants: The 3 variations of my e-mail name have already been taken on gmail.Please send me an invitation as well. Thanks!
I dunno... Kevin Rose's rambling explanation of GMail using a huge RAID array, and that business about copying your mail into "some type of RAM/solid state drive", and something about cron jobs sorting things out after a few days... I mean, does he actually know what he's talking about? (Being in the UK, I have never heard of him.)
Surely, for starters, they're using their Google File System to do the storage?
Totally untrue. Because most people have their email include the text from replies, so if you have lots of email conversations, its adding 5k to each email. the 4th email will be 20k. the 6th, 30k. It adds up fast.
Moo.
What kind of a person designs a website to show gray text on a black background? Is it his intent to make it as difficult as possible to read what he has to write?
The lessons of history teach us - if they teach us anything - that nobody learns the lessons that history teaches us.
Because Kevin Rose reminds me of those tech guys who solve stuff by rebooting first and then reloading the OS if that fails. I liked the show when it was Leo and Patrick. Mainly because these guys have been around and remember the old days. These new guys suck.
'Same speed C but faster'
Firkins, Furlongs, and Fortnights rule! And we thus eliminate the arbitrary seconds and use the more interesting microfortnights.
Dig the invite out of your sent mail and resend it manually. I haven't tested this, but it might work. If that fails, maybe use xrl.us or some other link shortener.
" (for example, I've heard people expressing their weight in kilograms, which is obviously absurd)"
Please explain to me since I'm not very good at recognizing obvious absurdities. And neither are many other people I guess, since it is usual to express one's weight in kilograms in many countries (Japan, for example). How are these people "misusing the unit"?
...that he gets to bang Sarah Lane.
(That said, you're right about him not really being a guru.)
"A great democracy must be progressive or it will soon cease to be a great democracy." --Theodore Roosevelt
thanks to a very kind soul, I have a gmail account now, so no need to send me any more :)
The reason girls and Windows users don't understand UNIX is because all the documentation is in Man files.
I am one of the developers for a SMTP server for a free mail provider so I have a bit of experience with this. In our case you can exceed your quota slightly in a couple of ways:
1) Sometimes a message comes in and the sending SMTP server didn't advertise the size of the message ahead of time, so it goes through the RCPT stage of sending a list of recipients for that message and you need to decide whether to accept or decline the message for each receiving user. In this case, because the length of the message is unknown until after the list is sent you don't know if it will cause the new message to exceed a particular users quota and therefore it is best to only reject delivery to people that have *already exceeded* their quota. This prevents you from having to accept the message and then queue up a bounce to send back to the sender. So for example someone with a 10MB quota and 8MB in their mailbox already, if they receive a 3MB attachment, could have 11MB of mail before the next message is rejected -- rather than accepting the message, seeing that it would exceed and having to ship it back to the sender.
2) In a distributed environment it is more efficient to update the mailbox size in batches rather than real-time, so there may be a few seconds or minutes lag between the time a message is received and the time it is incremented in their profile. Therefore someone with 8MB of mail might receive five 1MB attachments within a few seconds and have them all accepted before their totals are updated to show them as exceeding their quota.