Cloudflare K2: serverless event streams (blog.cloudflare.com)
165 points by elffjs 8 hours ago
max8539 a minute ago
Cloudflare is catching up to be a full AWS/GCP/Azure. At start it was just a few services around but they are adding everything else
psanford 5 hours ago
Object store is quickly becoming the new core data substrate. Lets build kafka, but on s3. Lets build github, but on s3. It feels like we going to see more and more "object-store first" systems in the next few years.
I am excited about this future. Give me stateless servers and a storage bucket over having to manage systems with disks any day.
I do wonder if we will see an expansion of the s3 api to support more of these use cases. S3 added a janky file append operation to their new express-one-zone bucket type, and limited to 10k total file append operations. I wonder what else we will get in the next few years.
shye 3 hours ago
It makes perfect sense: it's a extremely reliable, infinitely-scalable, strongly consistent (in some implementation), cheap, and extremely simple to use key-value store. As such, it transparently solves a lot of the problems distributed systems have to be engineered around.
As long as you can run on a CSP, and can engineer around the high-ish latency (most business cases can), it's extremely expensive to try engineer around it.
khazit 4 hours ago
I still think S3 is underutilized.
The range of things you can do with blob storage and a (very simple) auth model are surprisingly broad.
We recently replaced our Docker container registry with S3 using a tiny tool [1] we built in-house. I think that even with current capabilities, we can still model a lot services as a very thin layer over object storage.
monster_truck 3 hours ago
From the opposite side of things, I feel the same about OPFS. Finally having something that performant that multiple workers can operate against in a browser is such a massive boon. You could plug something like that in to it locally with markedly less bullshit than you would have had to do previously with the other APIs.
deanputney 3 hours ago
I'm a little surprised the Docker CLI doesn't support this directly, since gcr.io works this way. Maybe there's a thin layer between the bucket and the CLI? Neat that you worked it out for the generic case.
khazit 2 hours ago
tomjen3 3 hours ago
That sounds really cool — I tend to agree with you that S3 and similar are underutilized, but I remember that essentially all of the providers charge for bandwidth measured in gigabytes and I'm like no. My consumer line is measured in megabits per second and if I have to pay for my data usage the way it's paid for in data centers it would be far more expensive. Somehow consumer ISPs, who have to pay for the lines, are cheaper than than the cloud providers.
khazit 2 hours ago
switchbak 3 hours ago
gbalduzzi 3 hours ago
TYPE_FASTER 2 hours ago
necubi 5 hours ago
Definitely agree that every data system that doesn't need <100ms latency is moving to object storage.
> I do wonder if we will see an expansion of the s3 api to support more of these use cases
This is actually an area where I think we have a big leg up on folks building on top of S3. My team (which built K2) sits next to the R2 team, and we have the opportunity to co-evolve the products in mutually beneficial ways.
sensodine an hour ago
> every data system that doesn't need <100ms latency is moving to object storage
I think the opportunity extends below 100ms too, particularly given the existence of faster object storage tiers like S3 express or more recently GCS rapid bucket (both only offering single-zone durability, so still need to do quorum writes to get region-level durability as with standard tiers).
One of the tensions of course is how long to linger before flushing to object storage - you have to trade off directly between latency and cost of your API ops for PUTs.
When building the serverless offering of s2.dev (which is in a similar space, full disclosure!), we designed around stateful backend processes capable of constantly flushing multi-tenant objects (i.e., containing records from many streams), allowing streams to offer low ack latencies (~50ms p99 from same region) without blowing up the unit economics.
Congrats on the launch btw!
someonebaggy an hour ago
How will you prevent this system from becoming a server with extra steps?
madjam002 2 hours ago
Came across this the other day which lets you run a etcd compatible API/Kubernetes on top of S3
Haven't tried it yet but looks nice for simpler K8s deployments
6thbit 5 hours ago
doesn't that make egress fees egregious? or still cheaper than disks?
cj 4 hours ago
You can download objects from S3 from EC2 without traversing the public internet using things like gateway endpoints [0] which avoids s3 egress fees. But doesn't avoid egress fees from EC2 to the end user.
[0] https://docs.aws.amazon.com/vpc/latest/privatelink/vpc-endpo...
someonebaggy an hour ago
they are indeed egregious, like, downloading all your data one time costs about three times as much as buying disks to store it.
vmg12 4 hours ago
This all depends on the cloud you are building on and if the data ever leaves the datacenter.
Onavo 5 hours ago
People like S3 because they have hard engineering guarantees around bit rot and work well as a high level abstraction of a network filesystem with all of the low level failure recovery built-in. You don't have to worry about doing your own RAID configs. The bigger question is whether non-AWS services can offer the same level of guarantees. I have heard horror stories for example when it comes to downtime on Hetzner's S3 object store.
I am currently using Cloudflare R2 right now and if you see their forums, there's always the occasional post about objects going missing.
someonebaggy an hour ago
I find that Ceph is pretty annoying to operate but if you do, it works fine. Keeps redundant copies of data on multiple disks, across multiple racks if your diversity is that wide. Supports erasure coding for effective redundancy less than 2x.
Don't go for the "object gateway" compatibility layer - just use raw Ceph if you're writing your own app.
sgt 4 hours ago
Meanwhile, just using disks and regular servers is still reliable and more so than ever, especially with some redundancy.
Consider your cloud costs.
shye 2 hours ago
necubi 6 hours ago
I'm the author of the post and tech lead for K2. Happy to answer any questions!
prasoontrivedi 8 minutes ago
Have I understood the pricing correctly? There's charges for data published and consumed per GB?
e1g 2 hours ago
I'm doing some testing, and while my writes are <1s, I'm seeing E2E delivery latency of p95=2.5s / p99=7.5s. Is this roughly expected?
samtp 3 hours ago
After reading the post, still don't fully understand when you would use CF Queues vs K2. Can you help to elaborate a bit more?
necubi 2 hours ago
Sure! There are definitely some overlapping use cases, and we've seen folks using/abusing queues for use cases that are more appropriate to something like k2.
Queues are great when you have a unit of work that needs to be completed, retried, and tracked individually. For example, a shop might need to call a payment processor API that can fail or timeout, and retry it until it succeeds, while polling on the frontend for the state of that particular message. With a queue, you can insert a message tracking that payment, and have a queue processor that keeps getting sent it until it succeeds or has failed too many times.
In a queue each item is its own thing that's important to someone, and queues give you APIs to interact with that particular item.
K2 is for moving large volumes of data around. Pricing is per GB, not per message. Records are produced and consumed in bulk, and what matters is that all records are processed, but no one is querying the state of a particular record. K2 also supports multiple consumers for the same record, and long term retention. For example, all of your applications may emit events when things happen, and those events need to be read by an alerting system, a system that durably stores them, and a system that uses them to build ML features.
harikb 6 minutes ago
hasyimibhar an hour ago
Queues are for actions (do this), K2/event streams are for events (this happened).
aniketsauravv 5 hours ago
Great product, congratulation on launch. Are you using this internally in any way?
necubi 5 hours ago
Yes! We originally built K2 to serve as the ingestion layer for Basin Pipelines [0], our stream processing product. We have a number of other teams building new products on top of it at the moment which I can't talk about yet :)
vira28 2 hours ago
I wonder how many of data infra startups are wrapper on top of S3.
Also, the boundary between OLTP and OLAP is blurring every day.
For folks who want an off shelf version of this you may be interested in https://github.com/viggy28/streambed
(Disclaimer: I am one of the committers)
someonebaggy an hour ago
Hasn't it always been blurred? SQL supports OLAP and OLTP queries on the same database in the same language. They're different workload types in the way that "servers" and "GUIs" are two different types of software.
alexpotato 2 hours ago
LinkTree is a billion dollar business and it's basically a key value store.
addisonj 4 hours ago
Congrats on the launch! Stream/event-based system are really powerful, but they are also just pretty complex, in no small part because the modeling of streams for most people today is really modeling Kafka topic/partitions which has a whole bunch of foot-guns and complexity. Making the individual stream really cheap and easy is a big simplification, especially if flexibly consuming a stream for both ordered and unordered use-cases is made simple. This looks to work for unordered, be curious to see how the managed dividing the work for the mentioned key-based ordering.
someonebaggy an hour ago
Kafka works the way it does for a reason. I don't see how Cloudflare can avoid the same fundamental limits that Kafka faces.
mrkeen an hour ago
To support the ordered use-case, put events on the same topic-partition. To support the unordered use-case, don't.
wg0 2 hours ago
Has anyone built anything on top of D1 + Durable objects for multi tenancy? How has been the experience?
eivindga 3 hours ago
Congratulations on the launch! Looks very interesting indeed!
As someone who enjoys writing Kafka streams applications I am also looking forward to the day you support the Kafka APIs.
Having a cost efficient fully serverless Kafka compatible service would be great, and something I think many businesses would find useful.
Great work!
sarkarghya 2 hours ago
i think nats jetstream is superoverlooked in this space. the amount of throughput is more then enough for any medium scale enterprise as long as you know what you are doing
kirillkosolapov 4 hours ago
How does this solution differ from AutoMQ and WarpStream? I’ve worked with one of them, and it is indeed a serverless solution built on top of S3.
As far as I know, Kafka itself already supports offloading some data to S3 for long-term storage.
Based on the articles—which I didn't fully grasp—I’m wondering if there are additional benefits mentioned, such as multi-region distribution (though I find it hard to imagine how that would be implemented).
hasyimibhar 2 hours ago
It’s built for Cloudflare ecosystem, IMO using K2 on its own doesn’t make sense. I’ve worked with a startup that uses Cloudflare for everything except for Kafka. If K2 were to exist back then, I’m pretty sure they would have used it.
alanfranz an hour ago
Kafka also has inkless with diskless topics that run off object storage!
senderista 3 hours ago
Not a single mention of AWS Kinesis? That seems like the closest competitor.
aero142 28 minutes ago
This is specifically targeting edge. Kinesis is single region AFAIK, so I think Kinesis and Kafka are very similar and K2 is built on their S3 equivalent to make it globally distributed.
senderista 3 hours ago
Minor correction: it is not true that no major object stores support appends--Azure Blob Storage has from the beginning.
loufe 6 hours ago
If I was a serious Cloudflare customer I would be seriously concerned about the security of my infrastructure with them. Yes LLMs can code fast but this is an almost frenetic pace of releasing new products, all with fewer staff.
owenthejumper 4 hours ago
They've always been this fast. The trick is that they release beta products a lot. Kind of classic "lean" (does anyone remember that?)
My bigger concern would be their increasing grip on a lot of the market, and eventually becoming a monopoly (or part of the big tech "duopoly")
sssilver 4 hours ago
> eventually becoming a monopoly (or part of the big tech "duopoly")
At this point this has already effectively happened. The average person doesn't realize the extent of it, because the products Cloudflare builds are inherently transparent to the average consumer.
genxy 3 hours ago
wqtz 4 hours ago
I trust that this is not the case. Check out both the authors. Micah's company was acquired by Cloudflare, and both of these guys actually bring good expertise around this area.
The question is less about "vibe coding" the product, and more about how their acquired teams function. For most products they have released so far, they are backed by a company they acqui-hired. They will usually rebrand the product and absorb the team.
You would not be surprised if this release was from a product for a startup company rather than a large enterprise company.
Cloudflare hired a bunch of folks for sure, but they also fired a lot of folks. What they are doing these days is building products by buying out entire companies, giving them nearly independent authority to build a product like they would build a company.
vmg12 6 hours ago
They are working on a set of primitives that make building this kind of software easier. With AI, runtimes matter more than ever and languages matter less.
threatofrain 6 hours ago
I find this release relieving because it fills a hole that was really needed. Another hole would be a proper database and improvements to D1.
NicoJuicy 6 hours ago
That's just perception. At the same time they were hiring 1 k. People and hired 2 k. People the year before ( interns).
There was just more news about it than with other companies ( I think they let go about 2 k. People a year ago).
( Not saying it's good, just a little perception balance)
hack1312 3 hours ago
It hasn’t even been 6 months since they fired 20%
thepaulmcbride 5 hours ago
This sounds like a super interesting product, but I'm always reluctant to build on anything that isn't a portable industry standard.
ameliaquining 5 hours ago
Presumably the Kafka-compatible API that they say is in the works will address this?
necubi 5 hours ago
Yep. I'm not personally a huge fan of the kafka API — I think it's simultaneously too low level for normal users and too high level to deeply integrate into other systems (like stream processing engines), and requires a complex client library to use effectively.
We went with a simpler and more user friendly consume API, that also allows much higher levels of read parallelism (particularly important if you're using something like Workers, which parallelize well but aren't very powerful individually).
But we know many companies are invested in the Kafka ecosystem, and we want to provide an easy on (and if necessary, off) ramp for them.
theredsix 6 hours ago
What's the benefits of this over traditional GKE pub/sub, kafka or another queuing service?
necubi 5 hours ago
Google PubSub is a great product. The primary benefit of K2 is cost, particularly for longer retention periods. Being backed by object storage means that we can store data extremely cheaply compared to disk backed solution, and we pass that on in our pricing.
Compared to self-hosted or cloud-hosted Kafka (e.g., Amazon MSK or Confluent), K2 is much cheaper, and fully serverless. There are no clusters to manage or scale, and consistent performance even as you vastly increase the amount of data.
The main downside is produce (and end to end) latency is higher (around 1s p99) than systems that rely on local disk replication, like Kafka.
So it's great if you're trying to move a huge amount of data around, or for use cases where cost is more important than latency.
bonesss 3 hours ago
Having built a hobo version of something similar (serving a minimal subset of the Kafka API on top of CosmoDB): there’s also the hybrid scenario where the cheap serverless streams are used for scalability and broadcast while a low-latency core is maintained on sharply reduced compute resources. An 80/20 approach that saves a lot and, in our case, reduced cluster (mis)management risks at the same time.
In our case BLOB and large document transfers were handled in parallel, merging them together through object storage is a highly appealing package. Great work!
freakynit 5 hours ago
Ha setup and management is costly. K2 relieves you off that by charging you 0.04/0.04/GB read/write and 0.02/GB/month storage. Pretty useful if your volume is not into multi-GB's a month. GKE pub/sub seems pretty costly by comparison.
ipkstef 5 hours ago
i was trying to understand why i would use this over their current offerings of queues, and im really sick so my brain isn't working. so i ran it through ai
You need... | Use
-------------------------------------------------------|-------
“Make sure this job gets done” | Queue
retries / dead-letter handling | Queue
delayed jobs | Queue
distribute jobs among workers | Queue
“Record that this event happened” | K2
multiple independent systems reading the same events | K2
replay old events | K2
ordered event streams | K2
Kafka-like architecture | K2