Friday, 13 May 2016

Rejoice: we have a new mayor!

So: we have a new mayor.

What's interesting about the results is the sheer number of people who turned out to vote -and the proportion of those voters who came out to vote out George. Given one of the aims of the mayoral program was to "increase engagement in local government", it has certainly met that goal, one way or another.

A lot of the city are clearly glad to see the back of GF. The big question is: which specific policies got people voting him out -or whether it was his general style of working: Unitarian decisions and dismissal of dissent- which got to people.

Marvin may end up following the Labour Party line -but that party does have a local organisation and many councillors -so there is a structure for propagating the issues and desires of part of the electorate up to the mayor's office.

He's promised to focus on those parts of the city which felt left behind, and address problems such as housing. Given the need to be seen to immediately fulfilling those promises, to deliver, expect work to start there. But given the lead time for such work, expect them to look for some low-hanging fruit elsewhere.

RPZ and 20 zones are in an interesting place here. They have proved controversial, especially the way the RPZs were rolled out. But at the same time, a lot of people in the zones are happy with the idea, albeit not the details: charges, times, disabled access. Tuning those is a simple way to be seen to be listening, without risking upsetting those in the core who are happy with them.

20 mph is also under threat. As with RPZ, the CAPEX is done: the signs and the paint. MR was not elected on a pro-speed platform and, with a large electorate within the inner city air quality "management" area, may be reluctant to upset those who see the benefit. Maybe he even recognises that trying to blame 20 mph for the city's transport woes is ridiculous. At the same time: the anti GF voters view it as part of the "war on motorists", and they will expect something in exchange for their vote.

The often cited proposal "make it purely round schools, hospitals and residential roads" will resurface, even if it misses out that most roads have residents, a continually jittering limit its actually harder to comply with, and that children walk and cycle to school on main roads too. Oh, and any changes to signage means more capital spending.

One tactic the mayor may try here is a discreet rollback of enforcement, though with the PCC being independent, that'll take negotiation.

The other pet peeve of the anti GF voters is all that money spent on cycling. Good news for them there: he didn't spend much. If you compare what Boris did in London over the last four years —the embankment, the bridges, Elephant and Castle— what Bristol got for their money is laughable. What is there? a segregated path that stops half way down Baldwin street and the continuing fiasco of that path near Bemmy.

The money, the effort, the time -and the road space- has gone into Metrobus, not bicycles. It's hard to see what worse MR could do here, short of taking away more space for BRT. We know someone still has their eye on the BBRP —fortunately the people of Easton love it enough to keep the buses out: if it was just the cyclists, it'd look like the M32, the centre and the Festival way do: roadworks for BRT.

Metrobus itself? Marvin supports it. Anyway, given how far it has gone, the current BRT fiasco routes may be considered too late to kill. All future work could be put on hold until it's seen how well it works out in budget as well a use. It would also have be on how well the Elf kingdom of Somerset and the Dwarf Mines of S. Gloucs step up to their bit. About what FirstBus and Wessex Bus deliver. And about whether well a transport authority spanning the CUBA region can kick FirstBus into the 21zt century: contactless payment for all journeys, tickets interchangeable with Wessex bus. It's even about FBus having buses waiting at Templemeads and Parkway for GWR trains from London.

Let's wait and see.

Monday, 2 May 2016

Where is our election coverage?

People come up to us and ask questions. Usually we like them to say "would you like some more beer?", rather than the more frequent question, "Are you aware of the national speed limit in this country, sir?".

Most recently, people have been asking: "where is your electoral coverage?"

Well, we've been primarily leaving it to other reporting outlets, specifically the Bristolian and Bristol 24/7. If people are putting effort in to analyse voting records, do interviews and organise hustings, that's enough.

A more relevant question people ask us is: who should we vote for?

As the people printing the ballots, we can say "you can't vote for UKIP on our photocopies as he falls off the end". Which is ironic as the spherical model of the earth is one of those sciency-things that UKIP candidates argue about, along with Climate Change and Newton's Laws of Motion (especially the bit that says the kinetic energy in a collision goes up with the square of the velocity).

Instead you get to make your mind up, noting that as Tony Dyer is the only one ever to have bought team members (including the late Chris Hutt) beer, he's got a head start.

What we recommend is you, the voter, place the following items in the order you feel is most important.

[ ] Right to speed at 35+ mph through the inner city
[ ] Right to park where you want in the city
[ ] Fundamental issues in society

The Fundamental issues in society box can include: education; housing; the central-government imposed austerity program and the fact that it will get worse; how and why so few people brought up in Bristol are in science and engineering jobs in north fringe technical companies, Bristol's Air Quality Management Area and other environmental issues; Firstbus & Metrobus. All the things that matter to those people who don't recognise that the choice between 20 mph and 30 mph is the most important issue facing the city today.

Then choose a politician that appears to prioritise issues in an order closest to your own. That's your first vote.

For the second vote you decide who you don't want in: Marvin or George —and vote for the other. Clear?

Saturday, 9 April 2016

The M32 picnic area

A known subversive, "Analogue Andy", has been praising the Frome Valley cycle route, saying it joins up communities where the M32 divides them.

Well, if the valley cycle route is of social benefit, it is purely because of the infrastructure improvements the M32 added

Look at this

An all-year, all-weather, family picnic area.

Not even the bearpit benches offer such a sheltered area to take the whole family, park near IKEA, then walk over here to enjoy the afternoon.

We would love to see any photos people have of this area in its heyday, when there were, presumably, many families, laughing kids playing, happy parents bringing flasks of tea from their Austin Morris cars to drink here.

Sadly, even this photo is a relic: the benches have been converted into a skateboard park. The right to have a picnic under the M32 has forever been stolen. Well, unless you have a tartan rug in your Austin Morris.

Thursday, 10 March 2016

CS11, the London Ringway and Hampstead

People paying attention to videos may note that more than one of our contributors have London accents. One actually has a South London accent, which is pretty shocking, but they've lived in the city long enough for it to no longer be something to apologise for. Another one of our team has a north-west london accent, the kind you'd get growing up in Camden and Brent. Their dark secret is even worse than having lived south of the Thames. They first went to school in Hampstead. (For locals, that little one opposite the tube station, under the everyman cinema, the one that still believes in hymns and things).

Eventually their parents saw the error of their ways and moved into West Hampstead, making their children walk to nearby ecoles. Under the gentle hand that was the Inner London Education Authority, swimming was taught at the nearest council pool: in primary school you got a coach. Come secondary school, they'd worked out a better solution: the kids were given the money to get the tube during lunch; if they made it to the swimming lesson they'd get the money to go home. This presented the children with two choices: take a tube from Kilburn to Swiss Cottage, or walk to the pool eating the bag of chips you'd just bought with the fare. Tough decision.

What was never considered was cycling from the school to the pool. Because that would involve negotiating the Swiss Cottage gyratory, a multilane mess which you had to cross to get to the pool or library, getting there along Finchley Road, the "A41" coming down off the M1 by way of Staples Corner and the North Circular. It was tube or foot.

In London: the tube is the mass form of transport for anyone near a station. It's why what zone you are in is a marker of house prices, "They can afford to live in Zone 2!"; distance from tube station advertised because it makes such a difference on your daily commute. Off-street parking? Maybe for those few houses that have it —but it's not useful for commuting anyway. Not only is there nowhere to park, and congestion fees to worry about —it's significantly slower than the tube.

Driving to work, at least if you work in Central London, is a minority form of commuting. That's even if you have a fancy job in the city: it's not that likely to have a parking space.

This is perhaps a reason for the volume of taxis in London, they're an exclusive form of travel for people who don't have parking spaces but can afford to sit in traffic jams. By outsourcing the sitting behind the wheel swearing to people from Essex, you can check emails on your phone, only at the cost of many pounds per journey.

The rise of cycling in London, then, is arguably a consequence of dissatisfaction with an overcrowded, expensive and unreliable tube, recognition that the bus service was worse, driving even more stupid and getting in a taxi a transport for the wealthy people with time on their hands.

Nowadays central London has a massive proportion of cycle commuters, those who are happy with a city worse to cycle in than Bristol, those who have learned all the back ways which are mostly survivable. When the new embankment and bridge segregated routes open, central London will show the rest of the UK cities how far they are behind, even Bristol, so proud of itself, can't do a pedestrian crossing of the Bearpit in less than a year, the Templemeads to Bemmy path is missing-considered-deceased, BRT2 has stolen bits of path and parkland, and then there's the centre and Baldwin Street. London is leading in both vision and execution. Which, when you consider the wanker in charge of it, quite saying something.

What London is doing is setting a baseline for the rest of Britain, for cycling and even, with Crossrail, what you can do for public transport. Bristol now needs to step up, making it pleasant to cycle across the city centre without you having to rehearse in your head a safe route and factoring in you won't have a clue what to do by The Centre, and that Templemeads hates cycling.

London needs to step up by moving out of the centre, to make it survivable to get in to the city, to make walking and cycling an option for people who live outside Zone 1. For a hint of the difficulties here, look at Vole O'Speed's coverage of Brent. As visitors to Brent with the "Love Bristol, Go Brent" campaign, we can assure people that he's actually upbeat about the prospects for cycling in Brent.

And Hampstead? With its primary school off a traffic jam of taxis? What hope does it have?

In CS11, it has the chance of a safe route to cycle from Swiss Cottage to the city centre, a feed in route for everyone in north west London. If you can get by bike to Swiss Cottage, you can carry on to your destination know that you'll be alive when you get there. Instead of having to text your loved ones "I'm at work, I'm fine!", you'd be able to text them "I'm on CS11, I'll live today!".

Except of course, the residents of St John's Wood don't want it, as it will make driving to Hampstead harder. And they are leading Britain's Backlash.

The comments are absolutely worth reading. Take this one from "Craig", resident of Hampstead village for nine year.

He is complaining that a cycle lane a mile away will devaluation the properties in Hampstead. That's an area where they are asking for £1.7M for a a flat, £3M for a house. So Craig, nine year resident, is worried that the resale value of his house will drop, by, what? a thousand pounds? Ten thousand? Because really it'd have to be a couple of hundred thousand pounds worth of devaluation.

And here's the irony. The sole reason that he has his £3.5M house is because in the 1970s, people fought to stop it having a motorway over it.

If the GLC had got its way then, the quaint little houses of Craig and others would be in the shadow on a par with London's Westway, a faint miasma of NOx and diesel particles infiltrating the house, adding extra flavour to the coffees their Nescafe-coffee pod cafe macchiatos, creating more traffic on every single road, and generally making the area even less pleasant to live in —as if having it full of people like Craig wasn't bad enough.

That was what London dodged: The ringway over Hampstead. Instead they got the status quo, which, with the vast cross-london school run, the emergence of diesel as the fuel of choice, killing those kids from NOx and lack of exercise. And yet these people don't want change —they expect to be able to drive round the city. First the school dropoff then on to the underground parking at Waitrose John Barnes, on to the gym for your spin class, up the road to pick up the children (Walk to school! Have them use public transport! Never!), then nip down to central london for a play or two, parking at westminster being outrageous, but well, so's the mortgage on a little Hampstead mews house, as is theatre tickets, what's another £30 on the evening —why, it's the amount of tip the au-pair would expect, isn't it?

Apparently there's a demonstration of support for the proposal on Friday, March 11. Us: we'd be more tempted to head to the anti demonstration to see who it is arguing against them —because they sound like the Donald Trump supporter of transport.

To close then, one last opposition comment: we can't have cycle paths in our cities because we have road, not canals.

If CS11 gets stopped, it'll because of people like this.

Monday, 7 March 2016

Bristol Drivers: always giving cyclists a hand

There are always complaints in the cycling community (all eight of them) about some war-on-cyclists taking place in Bristol. We know that's untrue: the war being conducted in Bristol is by cyclists, against Motorists!

Innocent motorists, we may add —law abiding, invariably polite and considerate.

Here we one such example, a BMW driver going out of their way to give the cyclist a helping hand up the road

See how they swerved to make sure they were able to help the cyclist? See how they carefully reached out and gently tried to assist the cyclist? Admittedly, they were try to help the cyclist fall over and injure themselves —but they were still trying to do their bit for a cycling city.

We've said before, that Bristol is split between those who like cycling and those who, well, hate it.

We suspect the driver of BMW MX64JWU may have been one of the people in the survey who expressed negative opinions about cycling. We may also suspect they aren't in favour of 20 mph limits.

Well, we always value those prepared to stand up for their principals, or here, lean out the window and try to push someone over for those same principals. We feel this driver should be congratulated with the publicity their action deserves. Does anyone know who they are?

Location: Horfield/Lockleaze border, Wordsworth Road.; that bit which the #24 bus covers.

Video from Dave Edmonds. See the BCyC facebook posting.

Tuesday, 1 March 2016

Where does Bristol's pollution come from?

20 mph is looking like one of the big manufactured controversy issues of the election. Not, say, library closures, or the sale of the Avonmouth ports and apparent abandonment of Avonmouth. No, 20 mph limits, along with parking restrictions. Who says the electorate isn't worrying about city wide issues?

One of the pro-speeding campaign claims is "20 mph causes pollution".

Bristol has a pollution problem. It has an Air Quality Management Area which covers the centre, and also follows the A38 and M32 out of town. And apparently even the council admits it is killing people.

Where is that pollution coming from? Well, for NOx, the nitrogen oxides which VW tried to cover up, it's coming from Diesel cars. Bristol's NOx problem would be significantly reduced if everyone driving diesel today switched to petrol. Not hybrid or electric: petrol would be a start, especially modern cars that turn off the engine when stopped. And with gearing such that they can cruise at 20 mph nicely.

What is that ratio of petrol:diesel in the city?

We have no data, though the council's ANPR camera arrays will have that information if they could sit down and analyse it. Otherwise, it's that same self-selecting short term surveys which we are always so disparaging of. Here's ours

This was taken by a tax dodger cycling up the shared use pavement on Bridge Valley Road. While most shared use pavements are technically, "bollocks", this one is worth using. The speed of the cyclist (4-6 mph) is at a significant different from that of the motor vehicles, so you will only get passed by everything. The speed limit here is 30 mph, its off the portway and cumberland basin flyover, drivers may not have seen a bicycle that morning and forgotten they exist. And there's almost never anyone walking. If there's a fault: pavement surface quality and sweeping; the usual.

Going up the hill on a bike, you can see the motor vehicles come in waves; a queue heading west from the cumberland basin builds up until there's a right turn light, then they set off. You get a minute or two of quiet, 30s of traffic, then repeated until you reach the top. The video shows one of the groups of cars and vans.

Let's look at engine type, confirming on the MOT checker site whenever the registration number was readable and it wasn't immediately obvious

  • white (VW?) van. Diesel
  • white van. Diesel
  • BMW 330d. Diesel. Passed MoT on Feb 22, 97K miles.
  • VW Passat. Only available in EURO-test-rigged diesel models. 100K miles on 16/11/15
  • Audi A6. Diesel
  • LGV. Diesel
  • Ice cream van. Diesel with dodgy fan belt.
  • white van. Diesel. 84K miles
  • Peugeot 308 Diesel. (Passed MoT on second attempt feb 17; 78K miles)
  • Mercedes SLK230K, petrol. 50K miles after 15 years of use.
  • Ice cream van. Diesel
11 vehicles; only one petrol engined. That's a ratio of 10:1.

As stated, this is a self-selected dataset, but even so, it didn't involve a cyclist going up and down the hill repeatedly until a group came by that were nearly all diesel. It was just the outlier. If one more petrol car had got through the ratio would have dropped to 5:1, awful, but not as bad.

We don't have any real datasets of the petrol/diesel ratio, and this being an out of rush hour measurement may show bias towards working vehicles over commuters (unless a lot of people go to work on an ice cream van, that is).  But it does point a lot of the blame at our NOx problem at Herr Doctor Diesel and his inventions.

This also means the mercedes owner has something to be smug about, as well as having a vehicle still worth more than the Peugeot or the Passat: every mile they've driven has chucked out a fraction of the pollution of the other vehicles, as well as only doing a quarter as many miles/year as the others. Too bad their wingmirrors cost so much to replace.

Wednesday, 17 February 2016

Costing out a 21st century police state

There's been lots of interesting coverage of the new Snooper's charter, with light blue touchpaper having a good summary of the fundamental civil liberties issues.

But we haven't seen much in the way of "how would an ISP implement this?"

Which means its up to us, implementers of a PCSO-state adjacent to the Bearpit, to look at how to build this. As proof we know what we are talking about, here is our 8TB JBOD storage infrastructure (running xubuntu server 14) with a Top of Rack (ToR) switch consisting of a netgear base station flashed to DD-WRT. Sticker some recruitment from "Google reliability engineering"

The new bill requires ISPs to store  an "Internet Connection Record (ICR)" of every connection, and allow government access to it on demand.

How would an ISP implement such a system?

First: What is an "Internet Connection Record (ICR)"? The bill has made up something which doesn't really exist and then told ISPs to maintain it.

It is probably a record recording: the originating IP address/port of a TCP connection, the destination IP/port, and the duration of the connection. "probably", because it uses the term "event"

7(9) In this Part “relevant communications data” means communications data which may be used to identify, or assist in identifying, any of the following—
(a) the sender or recipient of a communication (whether or not a person),
(b) the time or duration of a communication, 35
(c) the type, method or pattern, or fact, of communication,
(d) the telecommunication system (or any part of it) from, to or through which, or by means of which, a communication is or may be transmitted,
(e) the location of any such system, or 40
(f) the internet protocol address, or other identifier, of any apparatus to which a communication is transmitted for the purpose of obtaining access to, or running, a computer file or computer program.
In this subsection “identifier” means an identifier used to facilitate the transmission of a communication.

The GCHQ/Bristol university "Problem Book (redacted)" appears to cover this very problem in the "five alive" dataset of IP/IP communications (p70), with every communication record being a list of records of (start-time/8, source-IP/4, source port/2, dest-IP/4, dest port/2, protocol/2. [data size]/8). Using the byte size estimated in the /N values, that's 30 bytes per communication; with the move to IPv6 driven by mobile phones, you'd need 16 bytes per source and dest address, or 56 bytes/record. That's for every HTTP request, skype call, bittorrent block share, PS4 game setup. If they include DNS records, it's for every nslookup command issued.

That's a lot of data in a world of phones and home network connections.

How to store all of this?

We see a number of strategies

The "fuck off Theresa" strategy

Here your ISP implements "for security reasons" an isolated system which collects ICRs, but for which the only way to retrieve them is a 1970s-era punched card reader you have to actually walk to. If HMG asks for something, you say "next wednesday? Come on by. Bring your query on a prepared punched card and we'll have the printer ready for the output. Oh, and we'll bill you for the ink"

The problem here is on P135: "The Secretary of State may make regulations imposing specified obligations on 20 relevant operators, or relevant operators of a specified description.', which includes "obligations to provide facilities or services of a specified description;". You could offer "the fuck off then" system, and they'd say "no, we want this". The ISP would not get a choice in the matter.

The TalkTalk fiasco

A Linux server running MySQL with a front end of an unpatched PHP web application accessible on the open internet over an unencrypted HTTP connection.

MySQL does have the lowest cost/TB of storage out there, and while a single mysql server doesn't grow, you can scale via sharding; storing the mass surveillance records of a few tens of of thousands of users.


1. Doesn't handle the "list me everyone who used twitter between 9 and 9:30 query" without going through every single database and then aggregating the results, so pushing out a database query (SELECT * FROM icr WHERE icr.endpoint="" AND icr.time>21:00 and icr.time < 21:30), somehow merging them all.

2. Being people utterly out of their depth, that same web UI will be accessible from your customer billing form. That'll be a massive security disaster, unless the people breaking are a group like Anonymous, where it's more likely to be a contribution "; DROP * from USERS" or an attack on public targets (SELECT * FROM icr WHERE user="Theresa May")

The outsourced consultancy disaster

The design here is less a design than a process. Go to a global/national software consultancy (e.g. Capita). Give them lots of money. Wait. Eventually get some software that doesn't work very well, designed to run on very expensive hardware.

This is essentially how major government projects like Universal Credit and any NHS-wide computer systems turn out. The problem here is the "ocean boiling grand vision" along with an inability to adjust features to meet unrealistic deadlines, along with consultants who are too excited by the cash to point out the project is doomed. Oh, and politicians who stand up in parliament announce changes in plans and then keep pretending the project is on schedule.

With this strategy we'd have a police state that came in late and didn't work very well. But: we'd pay for it either via taxes or ISPs, and it will be expensive

Bring it to the Borg

The cloud approach.  All ICRs are Netflow records grabbed off the Cisco switches and buffered locally. Regularly they are pushed up to google cloud storage in bulk HTTPS PUT operations, so storing all your data in google's server farms. We'd duplicate it across sites for Disaster Recovery ("DR") , and host it in the zero-CO2 datacentres ("DCs") to help meet the COP21 commitments which Osborne is trying to pretend weren't made.

Those initial datasets could be converted to more compressed format, with some summary data pushed into the google BigTable database. Queries against the dataset "find everyone who used twitter and facebook yesterday" would be Google BigQuery queries.

This architecture would work, provided whoever wrote the capture, upload and query code knew what they were doing. Google would handle datacentre ops, bill your ISP or HMG by the petabyte of data stored and for the CPU load of the import/cleanup phase and the query execution.

This is the one we'd build. No upfront hardware CAPEX; operational costs O(records)+O(queries). As you get 1TB of free processing month, initial dev costs are relatively low too.

Would the government allow it? Unlikely. Google's nearest datacentres are in Ireland and Finland; all the data would be moved out of the UK and under the jurisdiction of others.

It's notable, however, that Amazon have a special datacentre in the US for Amazon GovCloud, which is is where federal agencies can keep data and run code. We aren't aware of a UK equivalent. They could do this, though presumably after discussing tax arrangements.

[BTW, if someone went this way, as costs are directly proportional to the number of records, you could hurt the telcos and government costs by generating as many records as you can. If every UDP packet kept a sender and destination, you could run something on all willing participant's machines to create costs. Even at pennies per gigabyte, you can ramp up the bills if you leave this code running flat out overnight. Just a thought]


The fallback design would be to use the open source Big Data stack; "Hadoop and Friends"

The netflow call records would be streamed into Apache Kafka streams, which would then store the data in Hadoop HDFS, or perhaps feed them through some initial streaming system for cleanup (storm, spark).

Summary information would go into a column database. Normally the checklist item would be HBase, but given this is a government project, the NSA implemented Accumulo would win out.

Assuming there's a way to submit remote queries, those queries need to be secured. We'd come to some arrangement with the government to say "here are the kerberos credentials you need" on a USB stick, restrict access to SPNEGO-authenticated callers over HTTPS and rely on the NSA having no back doors in Accumulo that they aren't willing to tell GCHQ about.

Cost: upfront CAPEX of the datacentre, operational costs: site, power, staff, cooling. ideally you'd host it somewhere with cool air and low cost zero-carbon power, which points us up a Scotland and NE england. Land, power and people are affordable, and before long you could have something on a par with Facebook Prineville, though not, notably, NSA Utah.

Being open source software, you don't actually have to pay anyone for it —if you take on the support costs yourselves. It's unlikely telcos will want to do this, so that needs to be covered too. Once you have enough Petabytes of data, the costs of this system is still likely to be less than with google or amazon.

Otherwise: software development costs atop this layer may be steep, especially if you don't have experience in this.

In fact: all of the strategies have software development costs, a cost which is the same for every telco, all implementing roughly the same application.

Which would leave the government to be in a very good position to walk up to all of them and say "we can provide the software for you —just run these servers with our code". That way they get to run precisely the software they want —and hook it up directly to their central systems in a way which they knows will work.

They could even say "we'll host your servers somewhere and provide the software". That would give the government direct access to the nominally independent telco-hosted datasets, when they were all really in the same big room, running the same application.

There you have it then: four real ways. Two disasters, two viable: one where you hand off the operational issues to Google or amazon in exchange for lots of cash, the other home-built on the open source Big Data stack for more upfront capital costs but lower long term storage & compute costs. And relying on GCHQ to provide the software layer.

The only one that would scale, technically and financially, without giving the Google or Amazon the data, would be Hadoop+Accumulo, with code the telcos probably aren't up to writing themselves.

How much would this cost?

Hardware: Facebook-based open compute servers.

These are never publicly quoted, as you have be shopping for $1M+ before the design starts to make sense; at that point you get off the web site and onto the phone.

Looking at the Penguin Computing icebreaker storage servers, holding 30 3.5" HDDs in a 2U system. with ~44 "rack units" of capacity in a normal rack, you get 22/per rack (we're leaving space for Top of Rack switches) == 660 disks.

With 4TB HDDs, you get 2.6 petabytes in a single rack. Heavy bastard with serious power budget, but compact enough that you can fit one in various telco sites, doing the initial storage/preprocess there before uploading to central facilities in off-peak times.

A 4TB HDD costs $115 from Amazon US; let's assume $75 for the OEM. You'd be paying $50K for those 550 disks. That's all. Servers, let's assume $1.5K for each chassis(*), 33K, so $82,500 per rack, excluding networking. Let's round that up to $100K.

We'd end up with a system whose pure hardware costs, the CAPEX, come in at $100K per 2.5 PB of storage. For 1MB USD you've got 25 PB. At, say, 60 bytes per record (==56 + 4), we'd get 426e9 records per rack. That's what's technically known as "a fuck of a lot of data". More subtly, if you look at the cost per record, in cents, its $0.000000234375. That's "a police state too cheap to meter" (**)

Which is what we are getting here. The big change isn't "the terrorists are using phones", or even "surveillance is getting harder than ever". It's "with the right technologies, we can record everything the population does for next to nothing"

Welcome to the future: privacy is over.

(*) Chassis costs depends very much on RAM and CPU; put in intel Xeon parts and lots of RAM and you'd be paying $8K/node, plus more in the leccy bill. That's what you'd expect to pay for the more compute-centric nodes, rather than the cold data storage, which is what we've costed out.

(**) These numbers seem to come in too low. Either there's a major underestimate of something, or the author should have used a spreadsheet rather than the calculator on their phone.