From: David Vorick <david.vorick@gmail•com>
To: Jared Lee Richardson <jaredr26@gmail•com>
Cc: Bitcoin Dev <bitcoin-dev@lists•linuxfoundation.org>
Subject: Re: [bitcoin-dev] Hard fork proposal from last week's meeting
Date: Fri, 31 Mar 2017 14:23:00 -0400 [thread overview]
Message-ID: <CAFVRnyr-Z9YWtT3r+7-fGejzgxKhH3-kQuo8JQFqKDpyZNBBdg@mail.gmail.com> (raw)
In-Reply-To: <CAD1TkXvmo8ygbFdPJxdiL5-QiN6+ujeSgOJ7_4eit43aZ2bzyg@mail.gmail.com>
[-- Attachment #1: Type: text/plain, Size: 3429 bytes --]
Sure, your math is pretty much entirely irrelevant because scaling systems
to massive sizes doesn't work that way.
At 400B transactions per year we're looking at block sizes of 4.5 GB, and a
database size of petabytes. How much RAM do you need to process blocks like
that? Can you fit that much RAM into a single machine? Okay, you can't fit
that much RAM into a single machine. So you have to rework the code to
operate on a computer cluster.
Already we've hit a significant problem. You aren't going to rewrite
Bitcoin to do block validation on a computer cluster overnight. Further,
are storage costs consistent when we're talking about setting up clusters?
Are bandwidth costs consistent when we're talking about setting up
clusters? Are RAM and CPU costs consistent when we're talking about setting
up clusters? No, they aren't. Clusters are a lot more expensive to set up
per-resource because they need to talk to eachother and synchronize with
eachother and you have a LOT more parts, so you have to build in
redundancies that aren't necessary in non-clusters.
Also worth pointing out that peak transaction volumes are typically 20-50x
the size of typical transaction volumes. So your cluster isn't going to
need to plan to handle 15k transactions per second, you're really looking
at more like 200k or even 500k transactions per second to handle
peak-volumes. And if it can't, you're still going to see full blocks.
You'd need a handful of experts just to maintain such a thing. Disks are
going to be failing every day when you are storing multiple PB, so you
can't just count a flat cost of $20/TB and expect that to work. You're
going to need redundancy and tolerance so that you don't lose the system
when a few of your hard drives all fail within minutes of eachother. And
you need a way to rebuild everything without taking the system offline.
This isn't even my area of expertise. I'm sure there are a dozen other
significant issues that one of the Visa architects could tell you about
when dealing with mission-critical data at this scale.
--------
Massive systems operate very differently and are much more costly per-unit
than tiny systems. Once we grow the blocksize large enough that a single
computer can't do all the processing all by itself we get into a world of
much harder, much more expensive scaling problems. Especially because we're
talking about a distributed system where the nodes don't even trust each
other. And transaction processing is largely non-parallel. You have to
check each transaction against each other transaction to make sure that
they aren't double spending eachother. This takes synchronization and
prevents 500 CPUs from all crunching the data concurrently. You have to be
a lot more clever than that to get things working and consistent.
When talking about scalability problems, you should ask yourself what other
systems in the world operate at the scales you are talking about. None of
them have cost structures in the 6 digit range, and I'd bet (without
actually knowing) that none of them have cost structures in the 7 digit
range either. In fact I know from working in a related industry that the
cost structures for the datacenters (plus the support engineers, plus the
software management, etc.) that do airline ticket processing are above $5
million per year for the larger airlines. Visa is probably even more
expensive than that (though I can only speculate).
[-- Attachment #2: Type: text/html, Size: 3691 bytes --]
next prev parent reply other threads:[~2017-03-31 18:23 UTC|newest]
Thread overview: 81+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-03-29 19:33 Daniele Pinna
2017-03-29 20:28 ` Peter R
2017-03-29 22:17 ` Jared Lee Richardson
2017-03-29 20:28 ` David Vorick
2017-03-29 22:08 ` Jared Lee Richardson
2017-03-30 7:11 ` Luv Khemani
2017-03-30 17:16 ` Jared Lee Richardson
2017-03-31 4:21 ` Luv Khemani
2017-03-31 5:28 ` Jared Lee Richardson
2017-03-31 8:19 ` Luv Khemani
2017-03-31 15:59 ` Jared Lee Richardson
2017-03-31 16:14 ` David Vorick
2017-03-31 16:46 ` Jared Lee Richardson
2017-03-31 18:23 ` David Vorick [this message]
2017-03-31 18:58 ` Eric Voskuil
2017-04-01 6:15 ` Jared Lee Richardson
-- strict thread matches above, loose matches on Subject: below --
2017-03-31 21:23 Rodney Morris
2017-03-31 23:13 ` Eric Voskuil
[not found] ` <CABerxhGeofH4iEonjB1xKOkHcEVJrR+D4QhHSw5cWYsjmW4JpQ@mail.gmail.com>
2017-04-01 1:41 ` Rodney Morris
2017-04-01 6:18 ` Jared Lee Richardson
2017-04-01 7:41 ` Eric Voskuil
[not found] ` <CAAt2M1_sHsCD_AX-vm-oy-4tY+dKoDAJhfVUc4tnoNBFn-a+Dg@mail.gmail.com>
[not found] ` <CAAt2M19Gt8PmcPUGUHKm2kpMskpN4soF6M-Rb46HazKMV2D9mg@mail.gmail.com>
2017-04-01 14:45 ` Natanael
[not found] ` <CAD1TkXusCe-O3CGQkXyRw_m3sXS9grGxMqkMk8dOvFNXeV5zGQ@mail.gmail.com>
2017-04-01 18:42 ` Jared Lee Richardson
[not found] ` <CAAt2M1_kuCBQWd9dis5UwJX8+XGVPjjiOA54aD74iS2L0cYcTQ@mail.gmail.com>
[not found] ` <CAAt2M19Nr2KdyRkM_arJ=LBnqDQQyLQ2QQ-UBC8=gFnemCdPMg@mail.gmail.com>
2017-04-01 13:26 ` Natanael
2017-03-29 19:50 Raystonn .
2017-03-30 10:34 ` Tom Zander
2017-03-30 11:19 ` David Vorick
2017-03-30 21:42 ` Jared Lee Richardson
2017-03-30 11:24 ` Aymeric Vitte
2017-03-28 19:56 Paul Iverson
2017-03-28 20:16 ` Pieter Wuille
2017-03-28 20:43 ` Tom Zander
2017-03-28 20:53 ` Alphonse Pace
2017-03-28 21:06 ` Luke Dashjr
2017-03-28 16:59 Wang Chun
2017-03-28 17:13 ` Matt Corallo
2017-03-29 8:45 ` Jared Lee Richardson
2017-03-28 17:23 ` Alphonse Pace
2017-03-28 17:31 ` Wang Chun
2017-03-28 17:33 ` Jeremy
2017-03-28 17:50 ` Douglas Roark
2017-03-28 17:33 ` Juan Garavaglia
2017-03-28 17:53 ` Alphonse Pace
2017-03-28 22:36 ` Juan Garavaglia
2017-03-29 2:59 ` Luv Khemani
2017-03-29 6:24 ` Emin Gün Sirer
2017-03-29 15:34 ` Johnson Lau
2017-04-01 16:15 ` Leandro Coutinho
2017-03-29 9:16 ` Jared Lee Richardson
2017-03-29 16:00 ` Aymeric Vitte
2017-03-28 17:34 ` Johnson Lau
2017-03-28 17:46 ` Luke Dashjr
2017-03-28 20:50 ` Tom Zander
2017-03-29 4:21 ` Johnson Lau
2017-03-28 20:48 ` Tom Zander
2017-03-29 6:32 ` Bram Cohen
2017-03-29 9:37 ` Jorge Timón
2017-03-29 19:07 ` Jared Lee Richardson
2017-04-02 19:02 ` Staf Verhaegen
2017-03-29 7:49 ` Martin Lízner
2017-03-29 15:57 ` David Vorick
2017-03-29 16:08 ` Aymeric Vitte
[not found] ` <CAFVRnyo1XGNbq_F8UfqqJWHCVH14iMCUMU-R5bOh+h3mtwSUJg@mail.gmail.com>
2017-03-29 16:18 ` David Vorick
2017-03-29 16:20 ` Andrew Johnson
2017-03-29 16:25 ` David Vorick
2017-03-29 16:41 ` Andrew Johnson
2017-03-29 17:14 ` Aymeric Vitte
2017-03-29 20:53 ` Jared Lee Richardson
2017-03-29 20:32 ` Jared Lee Richardson
2017-03-29 21:36 ` praxeology_guy
2017-03-29 22:33 ` Aymeric Vitte
2017-03-30 5:23 ` Ryan J Martin
2017-03-30 10:30 ` Tom Zander
2017-03-30 16:44 ` Jared Lee Richardson
2017-03-30 20:51 ` Jared Lee Richardson
2017-03-30 21:57 ` Tom Zander
[not found] ` <CAD1TkXvx=RKvjC8BUstwtQxUUQwG4eiU9XmF1wr=bU=xcVg5WQ@mail.gmail.com>
2017-03-30 10:13 ` Aymeric Vitte
2017-03-29 19:46 ` Jared Lee Richardson
2017-03-29 19:10 ` Jared Lee Richardson
2017-03-29 19:36 ` praxeology_guy
2017-04-02 19:12 ` Staf Verhaegen
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=CAFVRnyr-Z9YWtT3r+7-fGejzgxKhH3-kQuo8JQFqKDpyZNBBdg@mail.gmail.com \
--to=david.vorick@gmail$(echo .)com \
--cc=bitcoin-dev@lists$(echo .)linuxfoundation.org \
--cc=jaredr26@gmail$(echo .)com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox