Cpu0 : 0.3%us, 0.0%sy, 0.0%ni, 0.0%id, 99.7%wa, 0.0%hi, 0.0%si, 0.0%st <-- EBS subsystem is completely unreachable. I/O wait times are tanked across the board for me (I'm in US-EAST-1).
Ahh. Now that you mention it, I think I recall reading that before. It struck me as weird though because 1a was obviously the first one and 1e was recently added. So, would they rebalance my labels in that case?
Yeah, for me, 1d experiences the lowest load of all zones. According to the pricing history for spot instances, 1d experiences the fewest price spikes compared to 1a and 1b. I'd be interested to see if other users have noticed the same thing for their zones.
I find that random(5) is the best performing. For okay but consistent performance, random(5) is decent, but you should definitely avoid random(5) due to high load.
Well, they also return errors if a zone is out of capacity. That seems like it would guard against the issue a bit. But maybe they just don't want to have to field loads of questions about that.
I have instances in two different zones - both are down, although I don't know if AWS's randomization means that my 1a and 1d are actually located in the same logical zone.
The update I heard was (essentially) 'Another update from Amazon: Looks like it was a power issue for one facility that services a particular AZ in us-east-1, flipped to generator, now back on power and in recovery mode.'
Not really. Like MongoDB, the first four bytes of an ObjectId are a timestamp. That the timestamp is synced with other instances isn't paramount because the actual value of the timestamp does not matter. What does matter is that the timestamp is new and increasing every second. This is to retain sorting capabilities. With the 13 bits that represent the logical shard ID from this article, Instagram will guarantee uniqueness of an ID within the granularity of a second.
"What does matter is that the timestamp is new and increasing every second."
Right. I'm just sayin' that you have to be careful when you move data with a caveat like that. Moving the shard keyspace (the 13 bits) to a new machine that started generating ID's even one second behind (the first 4 bytes) would be troublesome, no?
Yep--definitely something to watch out for. At worst, though, you'd have a duplicate key when trying to insert, and can re-try without the risk of having a duplicate ID floating around your system.
The lower rotating 10 bits should give them a reasonable safety margin. If they're creating less than 128 entries in a particular shard per second (right now they're doing that across their entire datastore), their clocks would need to be out by 8 seconds to cause a problem.
They should definitely be monitoring their clocks though :)
Like StackExchange, I think it would make sense to take this idea and bring a more abstract platform together. Niche communities (such as Ruby on Rails and Founders) can be created based on community involvement and volunteer willingness to help. A premium model can surely follow for certain communities.
I'm assuming they're getting overwhelmed with traffic after being linked here and other high traffic properties. With only two volunteers on staff, there's only so much you can do. I am sure they are rapidly going to look into adding volunteers if the volume stays persistent (and/or hopefully grows even larger).
The major distinction here is voice is much more personal and one on one than IRC. IRC can be intimidating for a novice, and let's be quite frank, many times people's IRC persona does not reflect who they are in real life. As someone who's been contributing to major networks such as EFnet for many years now - I've learned IRC can be a great tool for learning, but it can also be downright aggressive and humiliating, particularly to the majority of users who this service would be targeting.
A voice on the other hand is more personal, synchronous and on-demand. I think there's value there and that it's possible to charge for that additional value.
chap, as I've mentioned before, I think this is yet another great way to contribute to open source. It's not always about writing code - projects like this are just as valuable as someone who works full time on documenting open source projects, writes code or creating user interfaces. thanks for a fresh idea!
I don't know Fred personally, but from following him on Twitter to being an avid reader of his blog, he comes off far from grumpy. Fred's successful/unsuccessful investments aside - he's been nothing but a class act in all of his talks, tweets, blog postings etc. I think there is a lot to learn from him on a myriad of topics including technology, business, venture capital and more. Pardon my ignorance, but this article is absurd and AdWeek should be ashamed of themselves for posting it.
