[HN Gopher] Colossus for Rapid Storage
       ___________________________________________________________________
        
       Colossus for Rapid Storage
        
       Was at the Google Next 2025 conference, and they've unveiled a
       zonal bucket version of GCS and what seems to be a gPRC interface
       over Google Colossus for Rapid Storage.
        
       Author : alobrah
       Score  : 228 points
       Date   : 2025-04-10 01:05 UTC (21 hours ago)
        
 (HTM) web link (cloud.google.com)
 (TXT) w3m dump (cloud.google.com)
        
       | alobrah wrote:
       | For some reason, text highlight didn't work, so here's the text-
       | highlighted link:
       | https://cloud.google.com/blog/products/compute/whats-new-wit...
        
         | xk3 wrote:
         | The gods strip off interesting bits of URLs when you submit it
        
           | dang wrote:
           | if you saw that code you wouldn't deify it
        
             | lazide wrote:
             | Moloch was also a god!
        
             | SweetLlamaMyth wrote:
             | It took me 4-5 attempts to not read:
             | 
             | > If you saw that code, you wouldn't _defy_ it
        
         | dang wrote:
         | That link doesn't work for me, so here's the relevant bit:
         | 
         |  _Rapid Storage: A new Cloud Storage zonal bucket that enables
         | you to colocate your primary storage with your TPUs or GPUs for
         | optimal utilization. It provides up to 20x faster random-read
         | data loading than a Cloud Storage regional bucket._
         | 
         | (Normally we wouldn't allow a post like this which cherry-picks
         | one bit of a larger article, but judging by the community
         | response it's clear that you've put your finger on something
         | important, so thanks! We're always game to suspend the rules
         | when doing so is interesting.)
        
           | alobrah wrote:
           | Apologies! First time making a post on hacker news, and I
           | thought this was really exciting news. FWIW, I talked to the
           | presenter after this was revealed during the NEXT conference
           | today, and he seems to have implied that zonal storage is
           | quite close to what Google seems to have with Colossus.
        
             | dang wrote:
             | Oh no, don't apologize - this was a case where you did
             | exactly the right thing and I'm glad you posted!
             | 
             | (I was just adding some explanation for more seasoned users
             | who might wonder why we were treating this a bit
             | differently.)
             | 
             | Also, welcome to posting on HN and we hope you'll continue!
        
           | noahl wrote:
           | There's now another blog post about Rapid storage
           | specifically: https://cloud.google.com/blog/products/storage-
           | data-transfer... . (That wasn't up yet when the original post
           | was made.)
        
             | dang wrote:
             | Ah excellent--that's what we were waiting for. I've changed
             | the URL to that from
             | https://cloud.google.com/blog/products/compute/whats-new-
             | wit... above. Thanks!
        
       | alobrah wrote:
       | FYI this was unveiled at the 2025 Google Next conference, and
       | they're apparently unveiling a gRPC client for Rapid Storage,
       | which appears to be a very thin wrapper over Colossus itself, as
       | this is just zonal storage.
        
         | jauntywundrkind wrote:
         | Struggling to find a definition, but seemingly zonal just means
         | there's a massive instance per cluster.
         | 
         | Did find some interesting recent (March 28th, 2025) reads
         | though!
         | 
         |  _Colossus under the hood: How we deliver SSD performance at
         | HDD prices_ https://cloud.google.com/blog/products/storage-
         | data-transfer...
         | 
         | I kind of thought you meant ZNS / https://zonedstorage.io/ at
         | first, or it's more recent better awesomer counterpart Host
         | Directed Placement (HDP). I wish someone would please please
         | advertize support for HDP, sounds like such a free win,
         | tackling so many write amplification issues for so little extra
         | complexity: just say which stream you want to write to, and
         | writes to that stream will go onto the same superblock. Duh,
         | simple, great.
        
           | re-thc wrote:
           | > Struggling to find a definition, but seemingly zonal just
           | means there's a massive instance per cluster.
           | 
           | There are a number of zones in a region. Region usually means
           | city. Zone can mean data center. Rarely just means some sort
           | of isolation (separate power / network).
        
           | bushbaba wrote:
           | It's GCP's answer to AWS S3 express zone
           | https://aws.amazon.com/s3/storage-classes/express-one-zone/
        
           | moandcompany wrote:
           | "Zonal" relates to the concept of "availability zones" which
           | are the next-smallest unit below a (physical) "region."
           | 
           | Most instances of a cloud ___ created in a region are
           | allocated and exist at the zonal level (i.e. a specific zone
           | of a region).
           | 
           | A physical "region" usually consists of three or more
           | availability zones, and each zone is physically separated
           | from other zones, limiting the potential for foreseeable
           | disaster events from affecting multiple zones simultaneously.
           | Zones are close enough networking-wise to have high
           | throughput and low latency interconnection, but not as fast
           | as same-rack, same-cluster communications.
           | 
           | Systems requiring high availability (or replication)
           | generally attain this by placing instances (or replicas) in
           | multiple availability zones.
           | 
           | Systems requiring high-availability generally start with
           | multi-zone replication, and Systems with even higher
           | availability requirements may use multi-region replication,
           | which comes at greater cost.
        
           | Dylan16807 wrote:
           | Delivering "HDD prices" is a bold claim there.
           | 
           | They charge $20/TB/month for basic cloud storage. You can
           | build storage servers for $20/TB flat. If you add 10% for
           | local parity, 15% free space, 5% in spare drives, and
           | $2000/rack/month overhead, then triple everything for
           | redundancy purposes, then over a 3 year period the price of
           | using your own hard drives is $115/TB and google's price is
           | $720. Over 5 years it's $145 versus $1200. And that's before
           | they charge you massive bandwidth fees.
        
             | saagarjha wrote:
             | You forgot paying yourself to set that up.
        
               | Dylan16807 wrote:
               | That's covered by the build and overhead numbers. But if
               | you want more on the build side, an extra $10k of labor
               | per rack of 9 servers only increases the cost per TB by
               | about $4.
        
               | concerndc1tizen wrote:
               | You're paying the same for "cloud engineers".
               | 
               | Also, don't forget the hidden cost/risk of giving a third
               | party full access to your data.
        
               | Sonnigeszeug wrote:
               | Clicking yourself a Bucket takes 5 Minutes.
               | 
               | Building a Server and keeping it secure and up-to-date
               | and fixing hardware issues, takes relevant time
        
             | Lex-2008 wrote:
             | I like your comparison with self-built storage, but
             | comparing $20/TB/month with other CLOUD offerings, we see:
             | 
             | * hetzner storage box starts from $4/month for 1TB, and
             | then goes down to $2.4/TB/month if you rent a 10TB box.
             | 
             | * mega starts from EUR10/month for 2TB, and goes down to
             | EUR2/TB/month if you get a 16TB plan
             | 
             | * backblaze costs (starts from?) $6/TB/month
             | 
             | I was looking for a cheap cloud storage recently, so have a
             | a list of these numbers :)
             | 
             | Moreover, these are not even the cheapest one. The cheapest
             | one I found had prices starting from $6.5 for 5TB, going
             | down to $0.64/TB/month for plans starting with 25TB (called
             | uloz, but I haven't tested them yet).
             | 
             | Also, looking at lowendbox you can find a VPS in Canada
             | with 2TB storage for $5/month and run whatever you want
             | there.
             | 
             | How all that compares to $20/TB/month?!
             | 
             | Please feel free to correct me if i'm comparing apples to
             | oranges, though. But I can't believe all of these offers
             | are scam or so-called "promotional" offers which cost
             | companies more than you pay for it.
        
               | ddorian43 wrote:
               | Of what you mentioned, only backblaze is similar (object
               | storage with S3-like API), all others are apples to
               | oranges.
        
               | Dylan16807 wrote:
               | You don't need very many terabytes to cover the labor
               | cost of installing and maintaining an S3-compatible
               | server program.
        
               | ksec wrote:
               | Thank You. So backblaze for $6/TB a month. I could have a
               | TB of Data backed up safely against file corruption? I
               | wonder how have I missed that.
               | 
               | Now you could use it with Synology NAS and it is a lot
               | cheaper than doing RAID 5 for ZFS / BTRFS with Muti
               | redundancy.
               | 
               | I wonder if there are any NAS that does that
               | automatically? Any drawbacks? Also wonder if the price
               | could go down to $5 / TB in a few years time.
        
               | ddorian43 wrote:
               | The price of Backblaze WAS $5 a few years ago and they
               | increased it to $6 (and added some free bandwidth).
        
               | Dylan16807 wrote:
               | I'm still annoyed they increased the price for B2. Maybe
               | "free" bandwidth gets people to use it more? But as far
               | as their costs go, between the time they launched at $5
               | and the time they upped it to $6, hard drives (and
               | servers full of hard drives) cost half as much per TB,
               | with 1/4 as many servers needed for the same number of
               | TB.
        
               | immibis wrote:
               | I get the impression that business has always been about
               | being the best schmoozer more than about having the best
               | product.
               | 
               | BTW at Hetzner you can rent _servers_ with very large
               | (hundred of TB) _non-redundant_ storage for an effective
               | price of about $1.50 /TB/month. If you want to build a
               | cloud storage product, that seems like a good starting
               | point - of course, once you take into account redundancy,
               | spare capacity, and paying yourself, the prices you
               | charge to your customers will end up closer to the price
               | of Backblaze at a minimum.
        
               | no_wizard wrote:
               | >I get the impression that business has always been about
               | being the best schmoozer more than about having the best
               | product
               | 
               | and thus, market efficiency feels like a myth. This feels
               | most true when it comes to cloud services. They're way
               | overpriced in multiple different common cases at the big
               | providers
        
               | singhrac wrote:
               | Yes, this is pretty much what Hetzner must have built
               | with their object storage - and they get to 5 EUR/month,
               | so really close to Backblaze pricing.
        
             | Twirrim wrote:
             | Leverage erasure encoding for durability and avoid both the
             | tripling and local parity. You'll get better durability
             | than 3x while only taking up significantly less than 2x the
             | space Backblaze open sourced their library and talk about
             | it here, https://www.backblaze.com/blog/Reed-Solomon. They
             | use a 17:20 ratio that'll get them 3 drive failure
             | resistance for just 1.17x stretch (ie a 100mb file gets
             | that resilient while taking up 117mb of space)
        
           | derefr wrote:
           | In Google Cloud parlance, "regional" usually means
           | "transparently master-master replicated across the
           | availability zones within a region", while "zonal" means "not
           | replicated, it just is where it is."
        
             | noahl wrote:
             | Slight nit: "zonal" doesn't necessarily mean "not
             | replicated", it means that the replicas could all be within
             | the same zone. That means they can share more points of
             | failure. (I don't know if there's an official definition of
             | zonal.)
             | 
             | NB: I am on the rapid storage team.
        
         | jeffbee wrote:
         | What on this page gives you that impression? Do I have to watch
         | the 2-hour video to learn this?
        
           | korkybuchek wrote:
           | Of course not. Gemini can summarize it for you.
        
             | CobrastanJorji wrote:
             | I mean, sure, it can easily provide quick text summaries of
             | this sort of thing, but I only consume ML summaries in the
             | forms of podcast discussions between two simulated pundits,
             | as God intended.
        
       | hiddencost wrote:
       | Hats off to whoever convinced management that selling Colossus
       | via cloud was Artificial Intelligence. Bravo.
        
         | eitally wrote:
         | I don't fault them for this at all. AI isn't possible without
         | the full infra stack, which clearly includes storage (and
         | compute, and networking, and data pipelining, and and and...).
         | There's an entire ecosystem of ISVs that only do one of these
         | things, very well (Pure Storage, for example, or Lamba or
         | Coreweave, or Confluent (Kafka + Flink with LLM integration).
         | While it might be more precisely accurate to state "AI
         | enabling" tech, I'll give them a pass.
        
           | rfoo wrote:
           | I think the joke here is that somehow management refused to
           | sell Colossus (which is such an obvious nice product just
           | like BigQuery) before and it takes "AI" to convince them.
        
             | derefr wrote:
             | > which is such an obvious nice product just like BigQuery
             | 
             | I always assumed (from outside Google) that the problem was
             | that Colossus had to make a "no malicious actors"
             | assumption in its design in order to make the
             | performance/scaling guarantees it does; and that therefore
             | just exposing it directly to the public would make it
             | possible for someone to DoS-attack the Colossus cluster.
             | 
             | My logic was that there's actually nothing forcing [the
             | public GCP service of] BigTable to require that a full copy
             | of the dataset be kept hot across the nodes, with pre-
             | reserved storage space -- rather than mostly decoupling
             | _origin storage_ from compute+ -- _unless_ it was to
             | prevent some DoS vector.
             | 
             | As for exactly what that DoS vector is... maybe
             | GC/compaction policy-engine logic? (AFAICT, Colossus has
             | pluggable "send compute to data" GC, which internal-
             | BigTable and GCS both use. But external-BigTable forces the
             | GC to be offloaded to the client [i.e. to the BigTable
             | compute nodes the user has allocated] so that the user
             | can't just load down the system with so many complex GC
             | policies that the DC-scale Colossus cluster itself starts
             | to fall behind its GC time budget.)
             | 
             | ---
             | 
             | + Where by "decouple storage from compute", I mean:
             | 
             | * Each compute node gets a fixed-sized DAS diskset, like
             | GCE local NVMe SSDs;
             | 
             | * each disk in that diskset gets partitioned up at some
             | fixed ratio, into two virtual disksets;
             | 
             | * one virtual diskset gets RAID6'ed or ZFS'ed together, and
             | is used as storage for non-Colossus-synced tablet-LDB
             | nursery level SSTs;
             | 
             | * the other virtual diskset gets RAID0'ed or LVM-JBOD-ed
             | together and is used as a bounded-size LFU read-through
             | cache of the Colossus-synced tablets -- just like BigQuery
             | compute nodes presumably have.
             | 
             | (AFAIK the LDB nursery levels _already_ get force-compacted
             | into  "full" [128MiB] Colossus-synced tablets after some
             | quite-short finality interval, so it's not like this
             | increases data loss likelihood by much. And BigTable
             | doesn't guarantee durability for non-replicated keys
             | anyway.)
        
               | rfoo wrote:
               | > a "no malicious actors" assumption in its design in
               | order to make the performance/scaling guarantees it does
               | 
               | Didn't think deep into it, could this be solved with
               | billing designs with more nuance?
        
         | klabb3 wrote:
         | That's an actually impressive level of spin. Flashback to when
         | shipping companies were slapping blockchain on international
         | container shipments.
        
           | Foobar8568 wrote:
           | Flashback to the cabbage on the Blockchain or when they
           | wanted to tag each fish caught in the wild as well for hu
           | traceability!
        
         | bushbaba wrote:
         | You gotta feed the GPUs & TPUs with enough data to avoid them
         | sitting idle. Which starts to become incredibly challenging
         | with latest gen GPU/TPU chips
        
         | re-thc wrote:
         | Everything is AI these days. Does it still need convincing?
        
           | CobrastanJorji wrote:
           | Ha, right after I read your comment, I looked at the bottom
           | of this Hacker News page and saw their "Join us for AI
           | Startup School" ad.
        
         | jeffbee wrote:
         | I would pay serious money if they sold CFS as a service but on
         | AWS.
        
           | immibis wrote:
           | Hi, I'm looking for a job. Are you willing to pay me serious
           | money to set up CFS as a service on your AWS?
        
             | jsnell wrote:
             | Obviously not, since you could not deliver it. It seems
             | that you maybe don't realize what CFS is in this context,
             | and are thinking of something else that you could just "set
             | up"?
             | 
             | What jeffbee is talking about is Google's proprietary
             | Colossus File System, and all its transitive dependencies.
        
               | immibis wrote:
               | I meant it sarcastically, but for "serious money" you can
               | have any software system you can dream of. You have to
               | dream of it, though - that's one of the hard parts.
               | 
               | It looks like every other clustered file system. What's
               | special about Google's Colossus?
        
               | noahl wrote:
               | There are some semantic differences compared to POSIX
               | filesystems. A couple big ones:                 - You can
               | only append to an object, and each object can only have
               | one writer at the time. This is useful for distributed
               | systems - you could have one process adding records to
               | the end of a log, and readers pulling new records from
               | the end.       - It's also possible to "finalize" an
               | object, meaning that it can't be appended to any more.
               | 
               | (I work on Rapid storage.)
        
         | CobrastanJorji wrote:
         | They're not saying that it's AI. They're saying it's for
         | customers who do AI. Training means lots and lots of reads from
         | a big data store, and if you're reading from, like, big Parquet
         | files, that probably means lots of random reads. This is for
         | that. Speedier data access, presumably at the cost of
         | durability and availability, which is probably a great trade-
         | off for people doing ML training jobs.
        
           | Zvez wrote:
           | calling everything 'for AI' is the new standard
           | 
           | >if you're reading from, like, big Parquet files, that
           | probably means lots of random reads
           | 
           | and it also usually means that you shouldn't use s3 in the
           | first place for workloads like this. Because they are usually
           | very inefficient comparing to distributed fs. Unless you have
           | some prefetch/cache layer, you will get both bad timings and
           | higher costs
        
             | CobrastanJorji wrote:
             | But a distributed FS is far more expensive than cloud blob
             | storage would be, and I can't imagine most workloads would
             | need the features of a POSIX filesystem.
        
       | acstorage wrote:
       | Similar to S3 express one zone
        
         | nodesocket wrote:
         | Is S3 Express One Zone performance greatly improved to standard
         | S3 like GCP rapid storage? My understanding is S3 Express One
         | Zone is just more cost effective.
         | 
         | > 20x faster random-read data loading than a Cloud Storage
         | regional bucket.
        
           | nodesocket wrote:
           | Update: Just read this article[1] which clarifies S3 Express
           | One Zone. Yes, performance is greatly improved, but actually
           | storage costs are 8x more than a standard S3 bucket. The
           | naming S3 Express One Zone is terrible and a bit misleading
           | on pricing changes.
           | 
           | [1] https://www.warpstream.com/blog/s3-express-is-all-you-
           | need
        
             | cowsandmilk wrote:
             | I understand your belief that One Zone implies less
             | expensive, but I'm staunchly in favor of them having it in
             | the name so people know that their data is in a single AZ.
             | The storage class succinctly summarizes faster with lower
             | availability.
        
               | nodesocket wrote:
               | Fair, how about instead of S3 Express they call it S3 Max
               | (One Zone). It doesn't take a rocket scientist to come up
               | with good product names, just copy Apple. Though I
               | suppose what happens when engineers are left up to the
               | marketing. :-)
        
               | onethumb wrote:
               | If Apple's so great at naming things, tell me (without
               | looking) which is bigger/better/faster for their CPUs:
               | Max or Ultra?
        
               | nodesocket wrote:
               | ha, ha, fair. Ultra. To be fair, I own a MacBook Pro M1
               | Max and Mac Mini M4 Pro and follow Apple products
               | closely.
        
               | onethumb wrote:
               | Yep, I love Apple, follow them closely, own a Mac Studio
               | with an M3 Ultra and a MacBook Pro with an M4 Max, and
               | it's still confusing. :)
               | 
               | I mean, surely a Mac Studio with an M4 Max must be the
               | best, right? It's an entire CPU generation ahead and it's
               | maximum! Of course, it's not... the M3 Ultra is the best.
               | 
               | Naming things is hard.
        
           | jashmatthews wrote:
           | AWS claims 10x lower latency but I haven't personally
           | checked.
        
           | dangoodmanUT wrote:
           | Yes, it's horribly more expensive... I think you are thinking
           | of one zone infrequent access
        
       | carbocation wrote:
       | This could actually speed up some of my scientific computing (in
       | some cases, data localization/delocalization is an important part
       | of overall instance run-time). I will be interested to try it.
        
       | bushbaba wrote:
       | Glad to see the zonal object store take off. Such massive
       | bandwidth speed will re define data analytics where 99% of all
       | queries able to run on a single node faster than what distributed
       | compute can offer.
        
       | pj_mukh wrote:
       | Super interesting! Rapid Storage especially, very useful, but
       | that first line:
       | 
       | "Today's innovation isn't born in a lab or at a drafting board;
       | it's built on the bedrock of AI infrastructure. "
       | 
       | Uhh..No. Even as an AI developer I can tell that is some AI Comms
       | person tripping over.
        
       | simonw wrote:
       | Everyone needs to learn to use a single, unique, unambiguous URL
       | for new product announcements like this.
       | 
       | Google aren't the only company that consistently mess this up,
       | but given how they built a 1.95 trillion company on top of
       | crawling URLs on the web they _really_ should have an internal
       | culture that values giving things unique URLs!
       | 
       | [I had to learn this lesson myself: I used to blog "weeknotes"
       | every week or two where I'd bundle all of my project
       | announcements together and it sucked not being able to link to
       | them as individual posts]
        
         | decimalenough wrote:
         | Google's not really at fault here: the OP submitted a link to
         | an article called "Introducing Ironwood TPUs and new
         | innovations in AI Hypercomputer" that happens to mention Rapid
         | Storage way down the page.
         | 
         | In case marketing seems to move faster than documentation
         | though, since I can't find any mention of this in the main GCS
         | docs. https://cloud.google.com/search?hl=en&q=rapid%20storage
        
           | alobrah wrote:
           | They revealed it's in private preview atm ;)
        
           | ncruces wrote:
           | It's down here too: https://cloud.google.com/products/storage
           | 
           | No link and no details though.
        
       | zifpanachr23 wrote:
       | Reading the press release about the "Hypercomputer" and I can't
       | tell what part of this is real and what part is marketing.
       | 
       | They say it comes in two configuration, 256 chips or 9,216 chips.
       | They also say that the maximal configuration of 9,216 chips
       | delivers 24x the compute power of the world's largest
       | supercomputer (which they say is called El Capitan). They say
       | that this comes to 42.6 exaFLOPs.
       | 
       | This implies that the 9,216 chip configuration doesn't actually
       | exist in any form in reality, or else it would now be the world's
       | largest supercomputer (by flops) by a huge margin.
       | 
       | Am I massively misunderstanding what the claims being made are
       | about the TPU and the 42.6 exaFLOPs? I feel like this would be
       | much bigger news if this was fully legit.
       | 
       | Edit: The flops being benchmarked are not the same as regular
       | supercomputer flops.
        
         | phonon wrote:
         | Supercomputers are measured based on 64 bit floating point
         | operations. Here they (inaptly) compared it to their 8 bit
         | floating point operations (which are only useful for AI
         | workloads).
        
           | zifpanachr23 wrote:
           | Gotcha. That makes a lot more sense. I was led to believe by
           | the wording of the comparison that they were the same
           | operations. Appreciate the explanation.
        
           | onlyrealcuzzo wrote:
           | Why is it inapt?
           | 
           | If all you care about is an 8-bit AI workload (there's
           | definitely a market for that), it's nice to have 24x the
           | speed.
        
             | remus wrote:
             | It's an apples to oranges comparison.
        
               | onlyrealcuzzo wrote:
               | It's apples to apples if you care about 8-bit (a lot of
               | people do these days).
               | 
               | AFAIK, there _wasn 't_ a faster 8-bit super computer to
               | compare to - which is why they made the comparison.
        
         | p_l wrote:
         | Also the set of supported/accelerated operations in the fastest
         | path is different no matter whether you use 8, 16, or 32bit
         | floats, thus the common use of "TOPS" as benchmark number
         | recently.
        
       | acstorage wrote:
       | If you want object storage faster than S3 Express One Zone or GCP
       | Rapid Storage without the zonal limitation check out ACS:
       | https://acceleratedcloudstorage.com
       | 
       | You can bring data in and out of the GPU quickly and improve
       | utilization.
        
       | EE84M3i wrote:
       | Is this related at all the the private invite only anywhere
       | caches? (or maybe they're GA now?)
       | 
       | https://cloud.google.com/storage/docs/anywhere-cache
        
         | leg wrote:
         | Anywhere Cache and Rapid Storage share some infrastructure
         | inside of GCS and both are good solutions for improving GCS
         | performance, but Anywhere Cache is an SSD cache in front of the
         | normal buckets while Rapid Storage is a new type of bucket.
         | 
         | (I work on Google storage)
        
           | minzi wrote:
           | Can you expand a bit on when it would make sense to use one
           | versus the other?
        
             | leg wrote:
             | Anywhere Cache shines in front of a multi-regional bucket.
             | Once the data is cached, there's no egress charges and
             | there's much better latency. This is great for someone who
             | looks for spot compute capacity to run computations
             | anywhere in the multi-region. It will also improve
             | performance in front of regional buckets but as a cache,
             | you'll see the difference between hits and misses.
             | 
             | Rapid Storage will have all of your data local and fast,
             | including writes. It also adds the ability to have fast
             | durable appends, which is something you can't get from the
             | standard buckets.
        
       | miroljub wrote:
       | Like with any other new Google product, better wait a few years
       | to see if it sticks before investing in its usage. In most cases,
       | you'd be better off searching for an alternative from the start.
        
       | davedx wrote:
       | Terrifyingly complicated and buzzword packed. I really don't know
       | what to make of any of this or what it does, and I work with AI
       | applications in my day job.
       | 
       | I'm guessing the $300 of Google Cloud credit offered in this
       | webpage wouldn't go very far using any of this stuff?
        
         | lysecret wrote:
         | You can try out everything for 300 dollars easily. Most
         | expensive thing you can do is get a server with 8 h200s and
         | spend 90 dollars an hour.
        
       | devops000 wrote:
       | Is it like PureStorage?
        
       | akshayshah wrote:
       | Very cool! This makes Google the only major cloud that has low-
       | latency single-zone object storage, standard regional object
       | storage, and transparently-replicated dual-region object storage
       | - all with the same API.
       | 
       | For infra systems, this is great: code against the GCS API, and
       | let the user choose the cost/latency/durability tradeoffs that
       | make sense for their use case.
        
         | dastbe wrote:
         | ?
         | 
         | s3: https://aws.amazon.com/pm/serv-s3
         | 
         | s3 express: https://aws.amazon.com/s3/storage-classes/express-
         | one-zone/
         | 
         | cross-region replication:
         | https://docs.aws.amazon.com/AmazonS3/latest/userguide/replic...
        
           | akshayshah wrote:
           | The cross-region replication I've seen for S3 (including the
           | link you've provided) is fundamentally different from a dual-
           | region GCS bucket. AWS is providing a way to automatically
           | copy objects between distinct buckets, while GCS is providing
           | a single bucket that spans multiple regions.
           | 
           | It's much, much easier to code against a dual-region GCS
           | bucket because the bucket namespace and object metadata are
           | strongly consistent across regions.
        
           | jeffbee wrote:
           | The semantics they are offering are very different from S3.
           | In Colossus a writer can make a durable 1-byte append and
           | other observers are able to reason about the commit point. S3
           | does not offer this property.
        
             | dastbe wrote:
             | Sure, but that's not what the parent said.
        
         | korkybuchek wrote:
         | > This makes Google the only major cloud that has low-latency
         | single-zone object storage, standard regional object storage,
         | 
         | Absurd claim. S3 Express launched last year.
        
           | akshayshah wrote:
           | Sure, but AFAIK S3's multi-region capabilities are quite far
           | behind GCS's.
           | 
           | S3 offers some multi-region replication facilities, but as
           | far as I've seen they all come at the cost of inconsistent
           | reads - which greatly complicates application code. GCS dual-
           | region buckets offer strongly consistent metadata reads
           | across multiple regions, transparently fetch data from the
           | source region where necessary, and offer clear SLAs for
           | replication. I don't think the S3 offerings are comparable.
           | But maybe I'm wrong - I'd love more competition here!
           | 
           | https://cloud.google.com/blog/products/storage-data-
           | transfer...
        
             | korkybuchek wrote:
             | > Sure, but AFAIK S3's multi-region capabilities are quite
             | far behind GCS's.
             | 
             | Entirely different claim.
        
               | akshayshah wrote:
               | I claimed that Google is the only major cloud provider
               | with all three of:
               | 
               | - single-zone object storage buckets
               | 
               | - regional object storage buckets
               | 
               | - transparently replicated, dual region object storage
               | buckets
               | 
               | I agree that AWS has two of the three. AFAIK AWS does not
               | have multi-region buckets - the closest they have is
               | canned replication between single-region buckets.
        
               | thayne wrote:
               | S3 doesn't have "transparently-replicated dual-region
               | object storage", which was part of the claim.
               | 
               | S3 does have replication, but it is far from transparent
               | and frought with gotchas.
               | 
               | And it certainly doesn't have all of that with a single
               | API.
        
           | grantwu wrote:
           | Isn't S3 Express not the same API? You have to use a
           | "directory bucket" which isn't an object store anymore, as it
           | has actual directories.
           | 
           | To be honest I'm not actually sure how different the API is.
           | I've never used it. I just frequently trip over the existence
           | of parallel APIs for directory buckets (when I'm doing
           | something niche, mostly; I think GetObject/PutObject are the
           | same.)
        
       | leg wrote:
       | There's a detailed blog post about Rapid Storage now available,
       | see https://news.ycombinator.com/item?id=43645309
       | 
       | (I work on Google storage)
        
         | dang wrote:
         | Thanks! I've changed the URL of the current thread and re-upped
         | this one. More at
         | https://news.ycombinator.com/item?id=43646209.
        
       | dang wrote:
       | (This was posted last night with
       | https://cloud.google.com/blog/products/compute/whats-new-wit...
       | above. We've changed the URL to the product-specific article.)
        
       | nashashmi wrote:
       | This link makes so much more sense than the previous link did.
       | 
       | SSDs with high random I/o speeds are a significant contributor to
       | the advantage. I think 20m writes per second are likely
       | distributed over a network of drives to make that kind of speed
       | possible.
        
       | steveBK123 wrote:
       | Had to go back to the classic microservices video as I was pretty
       | sure they used Colossus but it was actually Galactus & Omega
       | Star.
        
         | thethimble wrote:
         | This is what OP is referring to in case you haven't been
         | enlightened https://youtu.be/y8OnoxKotPQ?si=JAK5iPMcG1yoAhiT
        
       | __turbobrew__ wrote:
       | I want chubby as a service so I can throw etcd and zookeeper in
       | the trash.
        
       ___________________________________________________________________
       (page generated 2025-04-10 23:01 UTC)