• Dar itself is both a library (with C++ and Python bindings) for interacting with data, and a CLI tool (dar itself).
• Alongside this, there is an ecosystem of tools around dar, including GUIs for multiple platforms, backup scripts, and FUSE implementations.
• Dar is like tar in that it can read and write files sequentially if desired. Dar archives can be streamed, just like tar archives. But dar takes it further; if you have dar_slave on the remote end, random access is possible over ssh (dramatically speeding up certain operations).
• Dar is like zip in that a dar archive contains a central directory (called a catalog) which permits random access to the contents of an archive. In other words, you don t have to read an entire archive to extract just one file (assuming the archive is on disk or something that itself permits random access). Also, dar can compress each file individually, rather than the tar approach of compressing the archive as a whole. This increases archive performance (dar knows not to try to compress already-compressed data), boosts restore resilience (corruption of one part of an archive doesn t invalidate the entire rest of it), and boosts restore performance (permitting random access).
• Dar can split an archive into multiple pieces called slices, and it can even split member files among the slices. The catalog contains information allowing you to know which slice(s) a given file is saved in.
• The catalog can also be saved off in a file of its own (dar calls this an isolated catalog ). Isolated catalogs record just metadata about files archived.
• dar_manager can assemble a database by reading archives or isolated catalogs, letting you know where files are stored and facilitating restores using the minimal number of discs.
• Dar supports differential/incremental backups, which record changes since the last backup. These backups record not just additions, but also deletions. dar can optionally use rsync-style binary deltas to minimize the space needed to record changes. Dar does not suffer from GNU tar s data loss bug with incrementals.
• Dar can slice and dice archives like Perl does strings. The usage notes page shows how you can merge archives, create decremental archives (where the full backup always reflects the current state of the system, and incrementals go backwards in time instead of forwards), etc. You can change the compression algorithm on an existing archive, re-slice it, etc.
• Dar is extremely careful about preserving all metadata: hard links, sparse files, symlinks, timestamps (including subsecond resolution), EAs, POSIX ACLs, resource forks on Mac, detecting files being modified while being read, etc. It makes a nice way to copy directories, sort of similar to rsync -avxHAXS.

• $SOURCEDIR is the directory being backed up
• $DRIVE is the directory for backups to be stored in. Since dar can split by a specified size, I don t need to make separate filesystems to simulate the separate drive experience as I did with git-annex.
• $CATDIR will hold isolated catalogs
• $DARDB points to the dar_manager database

• verbose does what you expect
• create selects the operation mode (like tar -c) and gives the archive basename
• on-fly-isolate says to write an isolated catalog as well, right while making the archive. You can always create an isolated catalog later (which is fast, since it only needs to read the last bits of the last slice) but it s more convenient to do it now, so we do. We give the base name for the isolated catalog also.
• slice 400M says to split the archive, and create slices 400MB each.
• min-digits 2 pertains to naming files. Without it, dar would create files named bak1.dar.1, bak1.dar.2, bak1.dar.10, etc. dar works fine with this, but it can be annoying in ls. This is just convenience for humans.
• pause tells dar to pause after writing each slice. This would let us swap drives, burn discs, etc. I do this for demonstration purposes only; it isn t strictly necessary in this situation. For a more powerful option, dar also supports execute, which can run commands after each slice.
• fs-root gives the path to actually back up.

• Renamed a file to file01-unchanged
• Deleted a file
• Copied /bin/cp to a file named cp

1. A file that was not changed from the initial backup. Its presence was simply noted, but because we re doing an incremental, the data wasn t saved.
2. A file that is saved in this incremental, on slice 1.
3. The two deleted files

• Use dar to simply extract each archive in order. It will handle deletions, renames, etc. along the way.
• Use dar_manager with the backup database to do manage the process. It may be somewhat more efficient, as it won t bother to restore files that will later be modified or deleted.

• Air quality is acknowledged as important, but monitoring it is not an urgent or pressing problem for most people.
• Most of the value is seen in the hardware rather than the software service.

Survey The first piece of research I undertook was a survey covering three topics: views on indoor air quality, how respondents currently monitor indoor air quality and the desired features, including price, for a CO2 monitor. The survey was distributed to my extended personal network via social media, email and word of mouth. I offered respondents the opportunity to win a year of free monitoring as an incentive and received just under 70 responses overall - the lucky winner of that prize was Sam H of Auckland whose shiny new CO2 monitor will be in the mail shortly.

Views on indoor air quality

• Nearly all respondents strongly agreed that clean, fresh indoor air is important for avoiding sickness and enabling our best work, learning and general cognitive performance, with not a single negative response.
• 25% of respondents indicated they did not have a good understanding of the quality of the indoor air they were breathing versus 43% who indicated they had a good understanding of their indoor air quality.
• Nearly 70% of respondents agreed (and greater than 40% strongly agreed) that real-time monitoring is beneficial and worth investing time and money in providing, with a similar distribution of responses agreeing it should be required in all shared indoor spaces.

Current ventilation monitoring approaches

• For the home setting, using our senses was the most common method of understanding air quality, and only 6% of respondents were unhappy with their ability to monitor ventilation at home.
• At work, trusting the owner of the building to monitor ventilation was the most common method, although using our senses and some personally collected data also featured for 20% of respondents. While the majority of respondents saw some room for improvement here, less than 20% of respondents were unsatisfied with the ability to monitor ventilation at work.
• In shared public spaces using our senses and trusting the owner were equally popular with very little use of any data reported. The majority of respondents (40%) were unsatisfied with this situation with 34% seeing some room for improvement and very few being satisfied overall.

CO2 monitoring product features

• A screen and WiFi were both strongly supported features with less than 10% of respondents seeing them as irrelevant and a large majority of answers skewing towards essential.
• Coloured lights providing a quick indication were not viewed as important by 13% of respondents and while the majority of answers were towards essential there was also a large (22%) set of respondents who were indifferent to this feature.
• The ability to access measurements and reports via a web interface was very mixed. Around 20% of respondents reported the feature as irrelevant, 20% essential with the majority seeing it as useful but mot essential.
• Almost all respondents strongly indicated that additional air quality metrics beyond CO2 were important to collect.
• Respondents mostly indicated the proposed prices are too high (64%), with essentially no responses suggesting they were too low and the balance (43%) in the middle. Only 5% of respondents indicated a preference for a rental option over a straight purchase.

Advertising In parallel with the survey, I worked with my cousin who runs a marketing agency, The Asset, to place some Facebook ads aiming to systematically evaluate what combination of images and text would draw the best response. It s been an interesting process - despite working for Google for 15 years, I know relatively little about the day to day practice of online advertising! I think we re about 50% of the way through that process of systematically building a funnel of traffic, it s been a steep learning curve and its clear there s significantly more thought and time that would need to be invested into this were it to be the primary driver of sales for a business. It s interested to see how what resonates or doesn t resonate with the audience is often completely different to what I expect, confirming the importance of having a process to evaluate and tweak how the advertising runs. After just under 2 weeks of advertising with a daily budget in the $20 - $30 range, my ads have had just under 17k impressions by 10k distinct people resulting in 76 visits to the co2mon.nz website, and zero sales. The ads themselves received 233 clicks, so there s clearly a lot of room for further improvement and revision of the ad text itself to present a more compelling message. Unfortunately the most common response and feedback to the ads themselves has been comments arguing that CO2 is wonderful, climate change is invented and all our problems would be solved if we had more CO2 everywhere. Tedious to deal with, but also useful reminder about awareness and interest in the problem to contrast with the results from the survey of my extended personal network!

Feedback from other conversations In addition to the survey and advertising I ve had conversations with some local air conditioning and ventilation businesses as well as a commercial building management firm - all providing similar feedback to the results from the survey - acknowledgement that air quality is important and relatively immaturely measured currently, but low urgency or pain to change or remedy that situation. Another interesting point that s come up in conversations with various small business owners is what to do if or when the monitoring shows a ventilation problem? The obvious answer of opening the windows more does not seem to be particularly well received. Without a compelling solution to offer to the potential problem that the monitoring might reveal I often sense a reluctance from people to invest too much time and money in something which may create a problem in a space they don t currently see as urgent.

Conclusions The responses are interesting and surprising to me a in a few ways (no interest in rental, favouring web interface over app), but at the end of the day lead to the two conclusions described above: Air quality is acknowledged as important, but monitoring it is not an urgent or pressing problem for most people. At home and work the majority of people are OK with relying on their senses or trusting someone else to maintain ventilation. They wouldn t object to improvements, but the feedback is that ventilation monitoring is not a problem people are actively looking to solve. The number of people who do see this as an urgent enough problem to invest money into solving is low - even within the biased sample of my extended network. There is a stronger set of evidence for the problem being seen as more urgent by the users of shared public spaces - but I ve not been able to find any evidence that the owners and managers of those spaces feel the same urgency or duty of care towards their users to invest in this space. Most of the opportunity is in the hardware rather than the software service. This signal comes through in the feedback on the pricing (preferring outright purchase vs rental), but it s also been directly expressed in the free-form comments and other conversations I ve had and the the relative importance given to the physical product features over the web/app interfaces in the survey results.

Wrap Up I m glad I finally spent the time doing this research, particularly the survey, these are good lessons to learn, even if I should have taken the time to learn them a year ago - so I can write that reminder (do your research before building a product) down as a key outcome of this process too! Stay tuned for more details on the other work I ve been doing recently on the hardware side of co2mon.nz and what these results mean for my overall plans. As always, I d love to hear from you if these results give you ideas or questions you d like to discuss.

But DNSSEC will save us from the evil CA ecosystem! Historically, the strongest motivation for DNSSEC has not been the direct security benefits themselves (which as explained above are minimal compared to what TLS provides), but in the new capabilities and use-cases that could be enabled if DNS were able to provide integrity and trusted data to applications. Specifically, the promise of DNS-based Authentication of Named Entities (DANE) is that with DNSSEC we can be free of the X.509 certificate authority ecosystem and along with it the expensive certificate issuance racket and dubious trust properties that have long been its most distinguishing features. Ten years ago this was an extremely compelling proposition with significant potential to improve the Internet. That potential has gone unfulfilled. Instead of maturing as deployments progressed and associated operational experience was gained, DNSSEC has been beset by the discovery of issue after issue. Each of these has necessitated further changes and additions to the protocol, increasing complexity and deployment cost. For many zones, including significant zones like google.com (where I led the attempt to evaluate and deploy DNSSEC in the mid 2010s), it is simply infeasible to deploy the protocol at all, let alone in a reliable and dependable manner. While DNSSEC maturation and deployment has been languishing, the TLS ecosystem has been steadily and impressively improving. Thanks to the efforts of many individuals and companies, although still founded on the use of a set of root certificate authorities, the TLS and CA ecosystem today features transparency, validation and multi-party accountability that comprehensively build trust in the ability to depend and rely upon the security guarantees that TLS provides. When you use TLS today, you benefit from:

• Free/cheap issuance from a number of different certificate authorities.
• Regular, automated issuance/renewal via the ACME protocol.
• Visibility into who has issued certificates for your domain and when through Certificate Transparency logs.
• Confidence that certificates issued without certificate transparency (and therefore lacking an SCT) will not be accepted by the leading modern browsers.
• The use of modern cryptographic protocols as a baseline, with a plausible and compelling story for how these can be steadily and promptly updated over time.

DNSSEC with DANE can match the TLS ecosystem on the first benefit (up front price) and perhaps makes the second benefit moot, but has no ability to match any of the other transparency and accountability measures that today s TLS ecosystem offers. If your ZSK is stolen, or a parent zone is compromised or coerced, validly signed TLSA records for a forged certificate can be produced and spoofed to users under attack with minimal chances of detection. Finally, in terms of overall trust in the roots of the system, the CA/Browser forum requirements continue to improve the accountability and transparency of TLS certificate authorities, significantly reducing the ability for any single actor (say a nefarious government) to subvert the system. The DNS root has a well established transparent multi-party system for establishing trust in the DNSSEC root itself, but at the TLD level, almost intentionally thanks to the hierarchical nature of DNS, DNSSEC has multiple single points of control (or coercion) which exist outside of any formal system of transparency or accountability. We ve moved from DANE being a potential improvement in security over TLS when it was first proposed, to being a definite regression from what TLS provides today. That s not to say that TLS is perfect, but given where we re at, we ll get a better security return from further investment and improvements in the TLS ecosystem than we will from trying to fix DNSSEC.

But TLS is not ubiquitous for non-HTTP applications The arguments above are most compelling when applied to the web-based HTTP-oriented ecosystem which has driven most of the TLS improvements we ve seen to date. Non-HTTP protocols are lagging in adoption of many of the improvements and best practices TLS has on the web. Some claim this need to provide a solution for non-HTTP, non-web applications provides a motivation to continue pushing DNSSEC deployment. I disagree, I think it provides a motivation to instead double-down on moving those applications to TLS. TLS as the new TCP. The problem is that costs of deploying and operating DNSSEC are largely fixed regardless of how many protocols you are intending to protect with it, and worse, the negative side-effects of DNSSEC deployment can and will easily spill over to affect zones and protocols that don t want or need DNSSEC s protection. To justify continued DNSSEC deployment and operation in this context means using a smaller set of benefits (just for the non-HTTP applications) to justify the already high costs of deploying DNSSEC itself, plus the cost of the risk that DNSSEC poses to the reliability to your websites. I don t see how that equation can ever balance, particularly when you evaluate it against the much lower costs of just turning on TLS for the rest of your non-HTTP protocols instead of deploying DNSSEC. MTA-STS is a worked example of how this can be achieved. If you re still not convinced, consider that even DNS itself is considering moving to TLS (via DoT and DoH) in order to add the confidentiality/privacy attributes the protocol currently lacks. I m not a huge fan of the latency implications of these approaches, but the ongoing discussion shows that clever solutions and mitigations for that may exist. DoT/DoH solve distinct problems from DNSSEC and in principle should be used in combination with it, but in a world where DNS itself is relying on TLS and therefore has eliminated the majority of spoofing and cache poisoning attacks through DoT/DoH deployment the benefit side of the DNSSEC equation gets smaller and smaller still while the costs remain the same.

OK, but better software or more careful operations can reduce DNSSEC s cost Some see the current DNSSEC costs simply as teething problems that will reduce as the software and tooling matures to provide more automation of the risky processes and operational teams learn from their mistakes or opt to simply transfer the risk by outsourcing the management and complexity to larger providers to take care of. I don t find these arguments compelling. We ve already had 15+ years to develop improved software for DNSSEC without success. What s changed that we should expect a better outcome this year or next? Nothing. Even if we did have better software or outsourced operations, the approach is still only hiding the costs behind automation or transferring the risk to another organisation. That may appear to work in the short-term, but eventually when the time comes to upgrade the software, migrate between providers or change registrars the debt will come due and incidents will occur. The problem is the complexity of the protocol itself. No amount of software improvement or outsourcing addresses that. After 15+ years of trying, I think it s worth considering that combining cryptography, caching and distributed consensus, some of the most fundamental and complex computer science problems, into a slow-moving and hard to evolve low-level infrastructure protocol while appropriately balancing security, performance and reliability appears to be beyond our collective ability. That doesn t have to be the end of the world, the improvements achieved in the TLS ecosystem over the same time frame provide a positive counter example - perhaps DNSSEC is simply focusing our attention at the wrong layer of the stack. Ideally secure DNS data would be something we could have, but if the complexity of DNSSEC is the price we have to pay to achieve it, I m out. I would rather opt to remain with the simpler yet insecure DNS protocol and compensate for its short comings at higher transport or application layers where experience shows we are able to more rapidly improve and develop our security capabilities.

Summing up For the vast majority of domains and use-cases there is simply no net benefit to deploying DNSSEC in 2023. I d even go so far as to say that if you ve already signed your zones, you should (carefully) move them back to being unsigned - you ll reduce the complexity of your operating environment and lower your risk of availability loss triggered by DNS. Your users will thank you. The threats that DNSSEC defends against are already amply defended by the now mature and still improving TLS ecosystem at the application layer, and investing in further improvements here carries far more return than deployment of DNSSEC. For TLDs, like .nz whose outage triggered this post, DNSSEC is not going anywhere and investment in mitigating its complexities and risks is an unfortunate burden that must be shouldered. While the full incident report of what went wrong with .nz is not yet available, the interim report already hints at some useful insights. It is important that InternetNZ publishes a full and comprehensive review so that the full set of learnings and improvements this incident can provide can be fully realised by .nz and other TLD operators stuck with the unenviable task of trying to safely operate DNSSEC.

Postscript After taking a few days to draft and edit this post, I ve just stumbled across a presentation from the well respected Geoff Huston at last weeks RIPE86 meeting. I ve only had time to skim the slides (video here) - they don t seem to disagree with my thinking regarding the futility of the current state of DNSSEC, but also contain some interesting ideas for what it might take for DNSSEC to become a compelling proposition. Probably worth a read/watch!

Changes in RcppArmadillo version 0.12.4.0.0 (2023-05-26)

• Upgraded to Armadillo release 12.4.0 (Cortisol Profusion Redux)
  • Added norm2est() for finding fast estimates of matrix 2-norm (spectral norm)
  • Added vecnorm() for obtaining the vector norm of each row or column of a matrix

This post by Dirk Eddelbuettel originated on his Thinking inside the box blog. Please report excessive re-aggregation in third-party for-profit settings.

Error updating ForwardingRule: googleapi: Error 400: Invalid value for field 'target.target':
'<https://www.googleapis.com/compute/v1/projects/mydumbproject/regions/europe-west1/serviceAttachments/
k8s1-sa-xyz-abc>'. Unexpected resource collection 'serviceAttachments'., invalid

resource "terraform_data" "replacement"  
    input = var.gcp_psc_data["target"]
 
resource "google_compute_forwarding_rule" "this"  
    count   = length(var.gcp_psc_data["target"]) > 0 ? 1 : 0
    name    = "$ var.gcp_psc_name -psc"
    region  = var.gcp_region
    project = var.gcp_project
    target                = var.gcp_psc_data["target"]
    load_balancing_scheme = "" # need to override EXTERNAL default when target is a service attachment
    network               = var.gcp_network
    ip_address            = google_compute_address.this.id
    lifecycle  
        replace_triggered_by = [
            terraform_data.replacement
        ]
     
 

# get post ID and word count
SELECT id, LENGTH(post_content) - LENGTH(REPLACE(REPLACE(REPLACE(REPLACE(post_content, "\r", ""), "\n", ""), "\t", ""), " ", "")) + 1 AS wordcount FROM wp_posts where post_status = 'publish' and post_type='post';
# get average word count
SELECT avg(LENGTH(post_content) - LENGTH(REPLACE(REPLACE(REPLACE(REPLACE(post_content, "\r", ""), "\n", ""), "\t", ""), " ", "")) + 1) FROM wp_posts where post_status = 'publish' and post_type='post';
# get the first posts by length
SELECT id, LENGTH(post_content) - LENGTH(REPLACE(REPLACE(REPLACE(REPLACE(post_content, "\r", ""), "\n", ""), "\t", ""), " ", "")) + 1 AS wordcount, post_content FROM wp_posts where post_status = 'publish' and post_type='post' ORDER BY wordcount limit 10;
# get a count of the posts less than 312 words
SELECT count(*) from wp_posts where (LENGTH(post_content) - LENGTH(REPLACE(REPLACE(REPLACE(REPLACE(post_content, "\r", ""), "\n", ""), "\t", ""), " ", "")) + 1) < 312 and post_status = 'publish' and post_type='post';
# get a count of all posts
select count(*) from wp_posts where post_status = 'publish' and post_type='post';

• [1] https://idiallo.com/blog/wordcount-in-mysql

2022-08-20 coffee
    liabilities:creditcard             -3
    liabilities:jon:expenses:coffee     3

    alias /^liabilities:jon(.*)$/ = liabilities:jon

2022-08-20 coffee
    liabilities:creditcard             -3
    liabilities:jon                     3

hledger reg -f family/2023-back.journal liabilities:jon: -O csv \
        jon/import/family/liabilities.csv

"55","2022-08-20","","coffee","liabilities:jon:expenses:coffee","  3.00","  3.00"

2022-08-20 coffee
    liabilities:jon:expenses:coffee     3
    liabilities:family                 -3

    alias /^liabilities.jon:/ =

2022-08-20 coffee
    expenses:coffee                     3
    liabilities:family                 -3

Changes in version 0.0.5 (2023-04-19)

• Calendars routines for Australia, Denmark, New Zealand, Turkey and the US have been updated from QuantLib 1.30.
• Support for 'Australia/ASX' has been added.
• Added demo showing all US holidays in current year

> print(Reduce(cbind, Map(makeHol, cals)))
           LiborImpact NYSE GovernmentBond NERC FederalReserve
2023-01-02        TRUE TRUE           TRUE TRUE           TRUE
2023-01-16        TRUE TRUE           TRUE   NA           TRUE
2023-02-20        TRUE TRUE           TRUE   NA           TRUE
2023-04-07          NA TRUE             NA   NA             NA
2023-05-29        TRUE TRUE           TRUE TRUE           TRUE
2023-06-19        TRUE TRUE           TRUE   NA           TRUE
2023-07-04        TRUE TRUE           TRUE TRUE           TRUE
2023-09-04        TRUE TRUE           TRUE TRUE           TRUE
2023-10-09        TRUE   NA           TRUE   NA           TRUE
2023-11-10        TRUE   NA             NA   NA             NA
2023-11-23        TRUE TRUE           TRUE TRUE           TRUE
2023-12-25        TRUE TRUE           TRUE TRUE           TRUE
> 

This post by Dirk Eddelbuettel originated on his Thinking inside the box blog. Please report excessive re-aggregation in third-party for-profit settings.

My journey to ventilation monitoring I started looking into ventilation monitoring in detail last year when I wanted to ensure that the classrooms of our local primary school were well ventilated during the Omicron outbreak. That research revealed that the existing products on offer were challenging to deploy in a school environment from a cost perspective while also not providing perfect functionality. I built and deployed a set of monitors to our local school, along with a corresponding set of software and web services that provide management of the monitors and visibility into the collected data and trends. The benefit of the monitoring is evident - CO2 concentration drops immediately after a notification occurs, indicating the intended action of increasing ventilation is taking place. Initially this occurred more frequently, but over time low concentrations of CO2, indicating good ventilation levels, are regularly achieved across the school day thanks to simple changes in routine being established, such as leaving windows cracked open. As the benefits of the project to the school became clear, my ambition and vision for ventilation monitoring grew from wanting to see my children learn in a safe and effective environment to desiring safe and effective learning, working, living and social spaces for everyone.

co2mon.nz: Ventilation monitoring as a service prototype co2mon.nz is the service that I have launched to explore this opportunity. Based on the same hardware and software that I used for the school deployment I am selling both a physical CO2 monitor and an ongoing subscription service for the management and monitoring. Together, the monitor and software provide an effective and affordable path to understanding indoor air quality and ventilation status that anyone can use.

CO2 monitor The CO2 monitor hardware and firmware are based on Oliver Seiler s design using a Sensirion SCD40 module for CO2 measurement and providing immediate in-room feedback via an on-monitor screen as well as a red/orange/green traffic light . In addition to the immediate feedback provided by the monitor itself, a WiFi connection can be configured allowing every measurement to be reported back to the supporting monitoring and management service. At the current prototype stage, I am building all the hardware, 3D printing the plastic cases and assembling the circuit board from purchased components through a production line in my home workshop. The monitor is powered via a standard USB cable and wall adaptor for simplicity. The first batch of monitors I built have been operating smoothly for nearly a year now. Further refinement and development of the design is required but already I am impressed with the potential this combination of easily accessible components provides to enable widespread adoption and deployment of ventilation monitoring.

Monitoring and management service The web service provides a historical record of CO2 levels from each monitor through a set of graphs and other dashboards and allows for this data to be shared or published. This is useful both for providing visibility into ventilation status to those not directly present in the space (e.g. across an entire school) and to allow insights into trends and patterns in ventilation to be observed and acted upon. When I began the project I approached the software side as an opportunity to explore the real-world equivalents of many of the internal tools and components that I was used to using within Google. That s been a fun process, even though it means I ve invested far more time on the software than the current number of customers or business state can really justify. Communication with the monitors occurs via MQTT into a custom Go service responsible for maintaining the fleet and exposing the measurement data to Prometheus which acts as the storage layer. A second service (based on the Buffalo web framework) is responsible for serving the web interface containing the dashboards and configuration options. Alongside these core components another small Golang service manages a private X509 certificate authority to provide monitor identity and encryption of the measurement data and an automated pipeline of scripts and triggers takes care of firmware provisioning, sensor calibration and burn-in/failure testing when building batches of monitors. While simple, the design is easy to manage and could scale to support many, many more monitors without significant effort. I m hosting the infrastructure on AWS, which I ve found pleasant and easy to use, and while not a typical choice, I m very pleased with the performance and flexibility that Prometheus offers as a data storage layer.

Areas of development The prototype has been effective in proving the feasibility of offering ventilation monitoring as a service, but to evolve the prototype into an actual business is going to require further effort in the following areas:

Finding product market fit I m confident that what co2mon.nz is offering could provide a useful and needed service for many small business owners and numerous others, but the question of whether it s sufficiently compelling that a sizeable group of customers see enough value that they re willing to regularly pay for it and therefore sustain a business providing the service is not yet proven. While initial feedback on the idea has been positive, much of it has been from family and friends and I ve spent more time building the software (which has been fun and educational) than I have talking to actual potential customers and understanding their needs and wants. This is a classic trap that technical founders fall into, and I m guilty despite my best intentions it s comfortable and easy for me to work on the parts where I have existing experience and neglect putting time into the customer-facing sales, marketing and research which are more uncomfortable, new and challenging!

Scaling monitor production Scaling from the current prototype batches I have built to even modest levels (e.g. hundreds) of sales will require outsourcing. There are several potential New Zealand and overseas providers I can work with which look very promising, but will require iteration of the hardware design (e.g. to remove through-hole components which add complexity and expense to the PCB assembly process). The lead times I ve been quoted for working with these outsourced providers are in the order of 1-2 months per batch, and on top of this there are a number of other risks in terms of component availability and regulatory compliance that may add additional delays or time to resolve, particularly as my experience leans towards the software rather than the hardware. It seems counter-intuitive to worry about how to scale to meet demand that doesn t yet provably exist, but given the potentially long lead times involved in establishing outsourced production I think it s worth taking some risk in starting this journey early.

Next steps My aim now is to intentionally change my focus from the software to learning about the market and finding the right product to offer via two channels:

1. Via online marketing, to reach a wide range of potential customers and allow rapid iteration and testing of a variety of product/service combinations, including referral options for existing customers.
2. In-person with small businesses in my local area to seek out direct feedback and thoughts on the general issue of ventilation monitoring and the specific service I m offering.

One concrete possibility I m keen to test via both channels is a simple monthly price for the combined service, rather than purchasing a monitor and separate software subscription. This has the potential to be both simpler to market and explain to customers, while also opening the possibility of short-term rental or evaluation to customers who are not willing to make a long-term investment or commitment. In parallel to the customer-focused discovery work, but as an explicit lower priority, I ll order an initial small batch of outsourced monitors to begin gaining experience with that process accepting the risk that the time and cost may turn out to be wasted if the product is wrong or not a good match for customers needs.

Once Upon a Tome: The Misadventures of a Rare Bookseller, wherein the theory of the profession is partially explained, with a variety of insufficient examples, by Oliver Darkshire. Interspersed with several diverting FOOTNOTES of a comical nature, ably ILLUSTRATED by Rohan Eason, PUBLISHED by W.W. Norton, and humbly proposed to the consideration of the public in this YEAR 2023

CUSTOMER: oh thank heavens I have been searching for a rare book expert with the knowledge to solve my complex problem ME (extremely and unhelpfully specialized): ok well the words are usually on the inside and I can see that's true here, so that's a good start I find I know lots of things until anyone asks me about it or there is a question to answer, at which point I know nothing, I am a void, a tragic bucket of ignorance

The hardest part, though, lies in recording precisely in what ways a book has survived the ravages of time. An entire lexicon of book-related terminology has evolved over hundreds of years for exactly this purpose terminology that means absolutely nothing to the average observer. It's traditional to adopt this baroque language when describing your books, for two reasons. The first is that the specific language of the book trade allows you to be exceedingly accurate and precise without using hundreds of words, and the second is that the elegance of it serves to dull the blow a little. Most rare books come with some minor defects, but that doesn't mean one has to be rude about it.

The Suited Gentlemen turn up annually, smartly dressed in matching suits and asking to see any material we have on Ayn Rand. Faces usually obscured by large dark glasses, they move without making a sound, and only travel in pairs. Sometimes they will bark out a laugh at nothing in particular, as if mimicking what they think humans do.

The book rest where the bible would be held (leaving arms free for gesticulation) was carved into the shape of a huge wooden eagle. I m given to understand this is the kind of eloquent and confusing metaphor one expects in a place of worship, as the talons of the divine descend from above in a flurry of wings and death, but it seemed to alarm people to come face to face with the beaked fury of God as they entered the bookshop.

Changes in RcppArmadillo version 0.12.2.0.0 (2023-04-04)

• Upgraded to Armadillo release 12.2.0 (Cortisol Profusion Deluxe)
  • more efficient use of FFTW3 by fft() and ifft()
  • faster in-place element-wise multiplication of sparse matrices by dense matrices
  • added spsolve_factoriser class to allow reuse of sparse matrix factorisation for solving systems of linear equations

This post by Dirk Eddelbuettel originated on his Thinking inside the box blog. Please report excessive re-aggregation in third-party for-profit settings.

The importance of indoor air quality Clean, fresh air is fundamental to life and health. That might sound obvious, but unfortunately being obvious is not enough to ensure the air we breathe is in fact always clean and healthy. Repeated studies have revealed that in many cases the air you re breathing at school, in the bus or at work and probably also at home falls well below the ideal of what clean, fresh air should be. Unclean air has potential long-term health impacts and has also been shown to lower cognitive performance impacting the ability to learn and work as well as increasing the risk of transmission of respiratory illnesses like Covid-19 and the flu. Ventilation (replacing old stale air with clean fresh air) is the most effective and economical method of improving and maintaining high indoor air quality. Most New Zealand buildings (including schools and houses) are designed to rely on manual ventilation (opening windows), while newer buildings, often including larger or commercial buildings may use mechanical ventilation involving fans and ducts. Mechanical ventilation including filtration may also be required in situations where the outdoor air is not clean and fresh such as in a city or next to a busy intersection.

Observing the invisible Overall air quality is a complex topic involving many contributing factors, many of which are invisible and not perceptible to us until well after adverse effects or irritation occur. This complexity and lack of visible signal is a large contributing factor to the ignorance and lack of attention towards indoor air quality that is prevalent in most buildings and indoor spaces today. Our attention is biased towards the risks that we can see, and this default bias has not been helped by hesitation and resistance to the idea that aerosol transmission and air quality is an important factor in preventing disease transmission that has only recently started to change. Zeynep Tufekci has a great overview that provides fascinating context for how an overreaction to the early incorrect theories of bad air and miasma causing disease contributed to aerosol transmission and air quality being incorrectly neglected for so long. Correcting this history of inattention to indoor air quality is going to take time and effort, but one significant step that we can take to help start the journey to ensuring all indoor spaces have clean, healthy air is to make the invisible part visible. The concentration of carbon dioxide (CO2) in a space is an incredibly effective and easy to measure proxy for the ventilation of a space. The atmospheric background level of CO2 is around 420 parts per million (ppm), while our exhaled breath has concentrations as high as 40,000 ppm. Without effective ventilation, one or more people breathing in an enclosed space will rapidly lead to an observable increase in CO2 concentration, which in turn provides a signal that the ventilation is insufficient and needs to be improved. Monitoring CO2 and improving ventilation is not a panacea for all possible air quality issues, but for the majority of buildings and indoor spaces, using CO2 as a proxy for ventilation and increasing ventilation when CO2 levels rise above recommended levels is a simple, effective and achievable approach that will deliver improvements in cognitive performance and reduction in the risk of disease transmission with few, if any, downsides or risks. See this Public Health Communication Centre briefing for a more detailed explanation.

Adding clean air to our hygiene practices We have well established expectations of hygiene for the food we eat and the water we drink and these expectations are codified in regulations that ensure those providing these services do so in a way that gives us confidence that we re not going to be at risk of illness. You may recall seeing food grade ratings prominently displayed on the walls of restaurants and cafes that you visit as an example of this. Why should the air we breathe be treated any differently? I think there is a strong argument that indoor air quality deserves regulation, both of the absolute quality of the air and ensuring that the practices and achieved air quality are clearly advertised and available. Ventilation monitoring via measurement of CO2 concentration provides an effective and achievable method that can be used to achieve this, and countries like Belgium and Japan are already starting to regulate indoor air quality. In the UK, the independent SAGE group of scientists has published Scores on the Doors , a proposal which demonstrates how CO2 monitoring can be helpful in providing information about the air quality of indoor spaces. Unfortunately there is no movement in any of these directions in New Zealand yet, and no sign that regulation or even a basic campaign to raise awareness of ventilation and air quality is even being planned. This is disappointing, but even if such work was planned, it would still require appropriate ventilation monitoring products and services to enable it, and while there are some options available, it is not a fully solved space yet.

Existing ventilation monitoring options Until recently the available offerings for ventilation monitoring have sat at two distinct ends of the price and quality spectrum:

• Handheld air quality meters advertised as measuring CO2, but in reality reporting only an approximation. These meters do not contain actual CO2 sensors, and only approximate CO2 levels based on measurements of other components of the air. While cheap (often less than $100), these meters are not useful for providing reliable data that can be systematically used to assess and improve ventilation and should be avoided.
• High-end building management systems (BMS), and industrial measurement products targeted at large buildings such as offices or commercial applications such as food production. These systems require specialist installation, often integrated with large whole-building air conditioning systems. These systems, if appropriately configured, can be a great solution for the types of buildings and spaces that can afford them, but by their nature and cost, they do not offer a solution for the majority of smaller buildings and indoor spaces where we tend to spend a lot of our time.

Over the last few years a growing number of companies have developed products that fit in between the unreliable air quality meters and the expensive BMS/industrial measurement products. Promising NZ-based options in this space include Air Suite, Tether and Monkeytronics. These products are wall mountable, resemble a smoke alarm and utilise a WiFi network to report their measurements to a supporting web service. Pricing varies between $200 and $300 ex GST per unit. Aranet, while not NZ based, provides a handheld monitor the Aranet4 Home, which is well regarded for quality and accuracy. Aranet4 Home devices are the most expensive in this space, retailing at $386 ex GST and offer a clunkier and less convenient set of connectivity options via a Bluetooth connection to an associated phone. To obtain similar reporting functionality to the other products requires upgrading to their Pro model and purchasing a separate base station at a combined cost of $1255 ex GST. Outside the commercial product offerings are a number of open source DIY options, which can be built by anyone with basic electronics knowledge. AirGradient is a leading example based in Thailand, and within New Zealand Oliver Seiler s CO2 Monitor provides similar functionality. These open source options have a parts cost in the $100-$150 range, depending on volume built and provide high-quality measurements via trusted CO2 sensors while also offering huge flexibility in terms of how they operate, interact with users and potential supporting web services.

An opportunity: Small businesses and organisations While a growing number of high-quality CO2 monitors has the potential to help drive increased adoption of ventilation monitoring, the plethora of small businesses and organisations that own, operate and manage many of the indoor spaces we visit on a day-to-day basis do not appear to be well served by these existing products. To deploy ventilation monitoring a small business or organisation needs to first become aware of the need or demand for it, and then have a simple and easy path to acquire and install the monitor and access the data. Little to no marketing or demand generation appears to be targeted towards this market from the existing businesses and tellingly, several of the products are not directly available for sale, requiring interaction with a salesperson to purchase. This indicates a focus on selling to larger customers who have a campus or portfolio of buildings and will purchase in larger quantities than the typical small business or organisation will. Small businesses and organisations are likely to occupy smaller buildings and spaces where manual ventilation is the prevalent method of improving and maintaining air quality. Maintaining clean, fresh air via manual ventilation requires the occupants of the space to receive an obvious and straightforward signal when action (opening windows, etc) is required. While the products above all tend to provide some form of local feedback and display in the room, the indication provided and notification of when to take action is less obvious and prominent than would be ideal in a situation where manual ventilation is being relied upon. Informally testing this opportunity with family and friends running small businesses over the last few months has resulted in promising feedback. One particular success story was the discovery of a fresh air duct on the air conditioning unit in a small office that had never been connected to the outside air and was simply recirculating air from the ceiling space back into an office! The resulting stuffiness and poor air quality had been noticed, but without the clear indication from the CO2 monitor that the air conditioning was actually making things worse, rather than better, the underlying issue had not been understood. With the issue fixed and the duct now connected, that business is now enjoying much more productive and healthy working conditions.

Next steps Many small businesses and organisations are likely to have poor air quality and opportunities for improvement similar to the example above that are waiting to be found and fixed, and the existing products available are neither focused or ideal for the needs of this market. I have spent some time over the past six months building a basic CO2 monitoring service that I have used to deploy ventilation monitoring to our local school, and a few other local businesses. There are a number of challenges that still need to be addressed in order to scale the business up, but I think there is a reasonable chance that I can build a viable business that offers an attractive and useful solution that would accelerate the deployment of ventilation monitoring for small businesses and organisations. In an upcoming post, I will explain the foundations of the service that I have built to date, the challenges that need to be overcome and how I plan to evolve the service from the current prototype into a sustainable, bootstrapped business.

Advice for buyers Those are things I wish I would have known before buying:

1. consider buying 4 USB-C expansion cards, or at least a mix of 4 USB-A or USB-C cards, as they use less power than other cards and you do want to fill those expansion slots otherwise they snag around and feel insecure
2. you will likely need a dock or at least a USB hub if you want a two-monitor setup, otherwise you'll run out of ports
3. you have to do some serious tuning to get proper (10h+ idle, 10 days suspend) power savings
4. in particular, beware that the HDMI, DisplayPort and particularly the SSD and MicroSD cards take a significant amount power, even when sleeping, up to 2-6W for the latter two
5. beware that the MicroSD card is what it says: Micro, normal SD cards won't fit, and while there might be full sized one eventually, it's currently only at the prototyping stage
6. the Framework monitor has an unusual aspect ratio (3:2): I like it (and it matches classic and digital photography aspect ratio), but it might surprise you

Current status I have the framework! It's setup with a fresh new Debian bookworm installation. I've ran through a large number of tests and burn in. I have decided to use the Framework as my daily driver, and had to buy a USB-C dock to get my two monitors connected, which was own adventure. Update: Framework just (2023-03-23) just announced a whole bunch of new stuff:

• AMD Ryzen 7040 and 13th gen Intel board
• 16" laptop version (pre-order) with an expansion "bay" for an upgradeable graphics module which could also fit M.2 storage
• audio expansion card, since the 16 laptop doesn't have a combo jack
• official mainboard case (back-ordered)
• official battery case (no site yet)
• new bezel colors, including transluscent, green, purple and red (back-ordered)
• new, louder (80dB) speakers
• new 61Wh battery
• matte display
• new hinge

The recording is available in this video and it's not your typical keynote. It starts ~25 minutes late, audio is crap, lightning and camera are crap, clapping seems to be from whatever staff they managed to get together in a room, decor is bizarre, colors are shit. It's amazing.

Specifications Those are the specifications of the 12th gen, in general terms. Your build will of course vary according to your needs.

• CPU: i5-1240P, i7-1260P, or i7-1280P (Up to 4.4-4.8 GHz, 4+8 cores), Iris Xe graphics
• Storage: 250-4000GB NVMe (or bring your own)
• Memory: 8-64GB DDR4-3200 (or bring your own)
• WiFi 6e (AX210, vPro optional, or bring your own)
• 296.63mm X 228.98mm X 15.85mm, 1.3Kg
• 13.5" display, 3:2 ratio, 2256px X 1504px, 100% sRGB, >400 nit
• 4 x USB-C user-selectable expansion ports, including
  • USB-C
  • USB-A
  • HDMI
  • DP
  • Ethernet
  • MicroSD
  • 250-1000GB SSD
• 3.5mm combo headphone jack
• Kill switches for microphone and camera
• Battery: 55Wh
• Camera: 1080p 60fps
• Biometrics: Fingerprint Reader
• Backlit keyboard
• Power Adapter: 60W USB-C (or bring your own)
• ships with a screwdriver/spludger
• 1 year warranty
• base price: 1000$CAD, but doesn't give you much, typical builds around 1500-2000$CAD

Actual build This is the actual build I ordered. Amounts in CAD. (1CAD = ~0.75EUR/USD.)

Base configuration

• CPU: Intel Core i5-1240P (AKA Alder Lake P 8 4.4GHz P-threads, 8 3.2GHz E-threads, 16 total, 28-64W), 1079$
• Memory: 16GB (1 x 16GB) DDR4-3200, 104$

Customization

• Keyboard: US English, included

Expansion Cards

• 2 USB-C $24
• 3 USB-A $36
• 2 HDMI $50
• 1 DP $50
• 1 MicroSD $25
• 1 Storage 1TB $199
• Sub-total: 384$

Accessories

• Power Adapter - US/Canada $64.00

Total

• Before tax: 1606$
• After tax and duties: 1847$
• Free shipping

Quick evaluation This is basically the TL;DR: here, just focusing on broad pros/cons of the laptop.

Pros

• easily repairable (complete with QR codes pointing to repair guides!), the 11th gen received a 10/10 score from ifixit.com, which they call "exceedingly rare", the 12th gen has a similar hardware design and would probably rate similarly
• replaceable motherboard!!! can be reused as a NUC-like device, with a 3d-printed case, 12th gen board can be bought standalone and retrofitted into an 11th gen case
• not a passing fad: they made a first laptop with the 11th gen Intel chipset in 2021, and a second motherboard with the 12th Intel chipset in 2022
• four modular USB-C ports which can fit HDMI, USB-C (pass-through, can provide power on both sides), USB-A, DisplayPort, MicroSD, external storage (250GB, 1TB), active modding community
• nice power led indicating power level (charging, charged, etc) when plugged
• test account on fwupd.org, "expressed interest to port to coreboot" (according to the Fedora developer) and are testing firmware updates over fwupd, present on LVFS testing, but including for the 12th gen, latest BIOS (3.06) was shipped through LVFS
• excellent documentation of the (proprietary) BIOS
• explicit Linux support with install guides, although you'll have to live with a bit of proprietary firmware, and not everything works correctly
• the 11th gen had good reviews: Ars Technica, Fedora developer, iFixit teardown, phoronix, amazing keyboard and touch pad, according to Linux After Dark, most exciting laptops I've ever broken (Cory Doctorow) ; more critical review from an OpenBSD developer
• the EC (Embedded Controller) is open source so of course people are hacking at it, some documentation on what's possible (e.g. changing LED colors, fan curves, etc), see also

Cons

• the 11th gen is out of stock, except for the higher-end CPUs, which are much less affordable (700$+)
• the 12th gen has compatibility issues with Debian, followup in the DebianOn page, but basically: brightness hotkeys, power management, wifi, the webcam is okay even though the chipset is the infamous alder lake because it does not have the fancy camera; most issues currently seem solvable, and upstream is working with mainline to get their shit working
• 12th gen might have issues with thunderbolt docks
• they used to have some difficulty keeping up with the orders: first two batches shipped, third batch sold out, fourth batch should have shipped in October 2021. they generally seem to keep up with shipping. update (august 2022): they rolled out a second line of laptops (12th gen), first batch shipped, second batch shipped late, September 2022 batch was generally on time, see this spreadsheet for a crowdsourced effort to track those supply chain issues seem to be under control as of early 2023. I got the Ethernet expansion card shipped within a week.
• compared to my previous laptop (Purism Librem 13v4), it feels strangely bulkier and heavier; it's actually lighter than the purism (1.3kg vs 1.4kg) and thinner (15.85mm vs 18mm) but the design of the Purism laptop (tapered edges) makes it feel thinner
• no space for a 2.5" drive
• rather bright LED around power button, but can be dimmed in the BIOS (not low enough to my taste) I got used to it
• fan quiet when idle, but can be noisy when running, for example if you max a CPU for a while
• battery described as "mediocre" by Ars Technica (above), confirmed poor in my tests (see below)
• no RJ-45 port, and attempts at designing ones are failing because the modular plugs are too thin to fit (according to Linux After Dark), so unlikely to have one in the future Update: they cracked that nut and ship an 2.5 gbps Ethernet expansion card with a realtek chipset, without any firmware blob
• a bit pricey for the performance, especially when compared to the competition (e.g. Dell XPS, Apple M1)
• 12th gen Intel has glitchy graphics, seems like Intel hasn't fully landed proper Linux support for that chipset yet

Initial hardware setup A breeze.

Accessing the board The internals are accessed through five TorX screws, but there's a nice screwdriver/spudger that works well enough. The screws actually hold in place so you can't even lose them. The first setup is a bit counter-intuitive coming from the Librem laptop, as I expected the back cover to lift and give me access to the internals. But instead the screws is release the keyboard and touch pad assembly, so you actually need to flip the laptop back upright and lift the assembly off to get access to the internals. Kind of scary. I also actually unplugged a connector in lifting the assembly because I lifted it towards the monitor, while you actually need to lift it to the right. Thankfully, the connector didn't break, it just snapped off and I could plug it back in, no harm done. Once there, everything is well indicated, with QR codes all over the place supposedly leading to online instructions.

Bad QR codes Unfortunately, the QR codes I tested (in the expansion card slot, the memory slot and CPU slots) did not actually work so I wonder how useful those actually are. After all, they need to point to something and that means a URL, a running website that will answer those requests forever. I bet those will break sooner than later and in fact, as far as I can tell, they just don't work at all. I prefer the approach taken by the MNT reform here which designed (with the 100 rabbits folks) an actual paper handbook (PDF). The first QR code that's immediately visible from the back of the laptop, in an expansion cord slot, is a 404. It seems to be some serial number URL, but I can't actually tell because, well, the page is a 404. I was expecting that bar code to lead me to an introduction page, something like "how to setup your Framework laptop". Support actually confirmed that it should point a quickstart guide. But in a bizarre twist, they somehow sent me the URL with the plus (+) signs escaped, like this:

https://guides.frame.work/Guide/Framework\+Laptop\+DIY\+Edition\+Quick\+Start\+Guide/57

... which Firefox immediately transforms in:

https://guides.frame.work/Guide/Framework/+Laptop/+DIY/+Edition/+Quick/+Start/+Guide/57

I'm puzzled as to why they would send the URL that way, the proper URL is of course:

https://guides.frame.work/Guide/Framework+Laptop+DIY+Edition+Quick+Start+Guide/57

(They have also "let the team know about this for feedback and help resolve the problem with the link" which is a support code word for "ha-ha! nope! not my problem right now!" Trust me, I know, my own code word is "can you please make a ticket?")

Seating disks and memory The "DIY" kit doesn't actually have that much of a setup. If you bought RAM, it's shipped outside the laptop in a little plastic case, so you just seat it in as usual. Then you insert your NVMe drive, and, if that's your fancy, you also install your own mPCI WiFi card. If you ordered one (which was my case), it's pre-installed. Closing the laptop is also kind of amazing, because the keyboard assembly snaps into place with magnets. I have actually used the laptop with the keyboard unscrewed as I was putting the drives in and out, and it actually works fine (and will probably void your warranty, so don't do that). (But you can.) (But don't, really.)

Hardware review

Keyboard and touch pad The keyboard feels nice, for a laptop. I'm used to mechanical keyboard and I'm rather violent with those poor things. Yet the key travel is nice and it's clickety enough that I don't feel too disoriented. At first, I felt the keyboard as being more laggy than my normal workstation setup, but it turned out this was a graphics driver issues. After enabling a composition manager, everything feels snappy. The touch pad feels good. The double-finger scroll works well enough, and I don't have to wonder too much where the middle button is, it just works. Taps don't work, out of the box: that needs to be enabled in Xorg, with something like this:

cat > /etc/X11/xorg.conf.d/40-libinput.conf <<EOF
Section "InputClass"
      Identifier "libinput touch pad catchall"
      MatchIsTouchpad "on"
      MatchDevicePath "/dev/input/event*"
      Driver "libinput"
      Option "Tapping" "on"
      Option "TappingButtonMap" "lmr"
EndSection
EOF

But be aware that once you enable that tapping, you'll need to deal with palm detection... So I have not actually enabled this in the end.

Power button The power button is a little dangerous. It's quite easy to hit, as it's right next to one expansion card where you are likely to plug in a cable power. And because the expansion cards are kind of hard to remove, you might squeeze the laptop (and the power key) when trying to remove the expansion card next to the power button. So obviously, don't do that. But that's not very helpful. An alternative is to make the power button do something else. With systemd-managed systems, it's actually quite easy. Add a HandlePowerKey stanza to (say) /etc/systemd/logind.conf.d/power-suspends.conf:

[Login]
HandlePowerKey=suspend
HandlePowerKeyLongPress=poweroff

You might have to create the directory first:

mkdir /etc/systemd/logind.conf.d/

Then restart logind:

systemctl restart systemd-logind

And the power button will suspend! Long-press to power off doesn't actually work as the laptop immediately suspends... Note that there's probably half a dozen other ways of doing this, see this, this, or that.

Special keybindings There is a series of "hidden" (as in: not labeled on the key) keybindings related to the fn keybinding that I actually find quite useful.

Key	Equivalent	Effect	Command
p	Pause	lock screen	xset s activate
b	Break	?	?
k	ScrLk	switch keyboard layout	N/A

It looks like those are defined in the microcontroller so it would be possible to add some. For example, the SysRq key is almost bound to fn s in there. Note that most other shortcuts like this are clearly documented (volume, brightness, etc). One key that's less obvious is F12 that only has the Framework logo on it. That actually calls the keysym XF86AudioMedia which, interestingly, does absolutely nothing here. By default, on Windows, it opens your browser to the Framework website and, on Linux, your "default media player". The keyboard backlight can be cycled with fn-space. The dimmer version is dim enough, and the keybinding is easy to find in the dark. A skinny elephant would be performed with alt PrtScr (above F11) KEY, so for example alt fn F11 b should do a hard reset. This comment suggests you need to hold the fn only if "function lock" is on, but that's actually the opposite of my experience. Out of the box, some of the fn keys don't work. Mute, volume up/down, brightness, monitor changes, and the airplane mode key all do basically nothing. They don't send proper keysyms to Xorg at all. This is a known problem and it's related to the fact that the laptop has light sensors to adjust the brightness automatically. Somehow some of those keys (e.g. the brightness controls) are supposed to show up as a different input device, but don't seem to work correctly. It seems like the solution is for the Framework team to write a driver specifically for this, but so far no progress since July 2022. In the meantime, the fancy functionality can be supposedly disabled with:

echo 'blacklist hid_sensor_hub'   sudo tee /etc/modprobe.d/framework-als-blacklist.conf

... and a reboot. This solution is also documented in the upstream guide. Note that there's another solution flying around that fixes this by changing permissions on the input device but I haven't tested that or seen confirmation it works.

Kill switches The Framework has two "kill switches": one for the camera and the other for the microphone. The camera one actually disconnects the USB device when turned off, and the mic one seems to cut the circuit. It doesn't show up as muted, it just stops feeding the sound. Both kill switches are around the main camera, on top of the monitor, and quite discreet. Then turn "red" when enabled (i.e. "red" means "turned off").

Monitor The monitor looks pretty good to my untrained eyes. I have yet to do photography work on it, but some photos I looked at look sharp and the colors are bright and lively. The blacks are dark and the screen is bright. I have yet to use it in full sunlight. The dimmed light is very dim, which I like.

Screen backlight I bind brightness keys to xbacklight in i3, but out of the box I get this error:

sep 29 22:09:14 angela i3[5661]: No outputs have backlight property

It just requires this blob in /etc/X11/xorg.conf.d/backlight.conf:

Section "Device"
    Identifier  "Card0"
    Driver      "intel"
    Option      "Backlight"  "intel_backlight"
EndSection

This way I can control the actual backlight power with the brightness keys, and they do significantly reduce power usage.

Multiple monitor support I have been able to hook up my two old monitors to the HDMI and DisplayPort expansion cards on the laptop. The lid closes without suspending the machine, and everything works great. I actually run out of ports, even with a 4-port USB-A hub, which gives me a total of 7 ports:

1. power (USB-C)
2. monitor 1 (DisplayPort)
3. monitor 2 (HDMI)
4. USB-A hub, which adds:
5. keyboard (USB-A)
6. mouse (USB-A)
7. Yubikey
8. external sound card

Now the latter, I might be able to get rid of if I switch to a combo-jack headset, which I do have (and still need to test). But still, this is a problem. I'll probably need a powered USB-C dock and better monitors, possibly with some Thunderbolt chaining, to save yet more ports. But that means more money into this setup, argh. And figuring out my monitor situation is the kind of thing I'm not that big of a fan of. And neither is shopping for USB-C (or is it Thunderbolt?) hubs. My normal autorandr setup doesn't work: I have tried saving a profile and it doesn't get autodetected, so I also first need to do:

autorandr -l framework-external-dual-lg-acer

The magic:

autorandr -l horizontal

... also works well. The worst problem with those monitors right now is that they have a radically smaller resolution than the main screen on the laptop, which means I need to reset the font scaling to normal every time I switch back and forth between those monitors and the laptop, which means I actually need to do this:

autorandr -l horizontal &&
eho Xft.dpi: 96   xrdb -merge &&
systemctl restart terminal xcolortaillog background-image emacs &&
i3-msg restart

Kind of disruptive.

Expansion ports I ordered a total of 10 expansion ports. I did manage to initialize the 1TB drive as an encrypted storage, mostly to keep photos as this is something that takes a massive amount of space (500GB and counting) and that I (unfortunately) don't work on very often (but still carry around). The expansion ports are fancy and nice, but not actually that convenient. They're a bit hard to take out: you really need to crimp your fingernails on there and pull hard to take them out. There's a little button next to them to release, I think, but at first it feels a little scary to pull those pucks out of there. You get used to it though, and it's one of those things you can do without looking eventually. There's only four expansion ports. Once you have two monitors, the drive, and power plugged in, bam, you're out of ports; there's nowhere to plug my Yubikey. So if this is going to be my daily driver, with a dual monitor setup, I will need a dock, which means more crap firmware and uncertainty, which isn't great. There are actually plans to make a dual-USB card, but that is blocked on designing an actual board for this. I can't wait to see more expansion ports produced. There's a ethernet expansion card which quickly went out of stock basically the day it was announced, but was eventually restocked. I would like to see a proper SD-card reader. There's a MicroSD card reader, but that obviously doesn't work for normal SD cards, which would be more broadly compatible anyways (because you can have a MicroSD to SD card adapter, but I have never heard of the reverse). Someone actually found a SD card reader that fits and then someone else managed to cram it in a 3D printed case, which is kind of amazing. Still, I really like that idea that I can carry all those little adapters in a pouch when I travel and can basically do anything I want. It does mean I need to shuffle through them to find the right one which is a little annoying. I have an elastic band to keep them lined up so that all the ports show the same side, to make it easier to find the right one. But that quickly gets undone and instead I have a pouch full of expansion cards. Another awesome thing with the expansion cards is that they don't just work on the laptop: anything that takes USB-C can take those cards, which means you can use it to connect an SD card to your phone, for backups, for example. Heck, you could even connect an external display to your phone that way, assuming that's supported by your phone of course (and it probably isn't). The expansion ports do take up some power, even when idle. See the power management section below, and particularly the power usage tests for details.

USB-C charging One thing that is really a game changer for me is USB-C charging. It's hard to overstate how convenient this is. I often have a USB-C cable lying around to charge my phone, and I can just grab that thing and pop it in my laptop. And while it will obviously not charge as fast as the provided charger, it will stop draining the battery at least. (As I wrote this, I had the laptop plugged in the Samsung charger that came with a phone, and it was telling me it would take 6 hours to charge the remaining 15%. With the provided charger, that flew down to 15 minutes. Similarly, I can power the laptop from the power grommet on my desk, reducing clutter as I have that single wire out there instead of the bulky power adapter.) I also really like the idea that I can charge my laptop with a power bank or, heck, with my phone, if push comes to shove. (And vice-versa!) This is awesome. And it works from any of the expansion ports, of course. There's a little led next to the expansion ports as well, which indicate the charge status:

• red/amber: charging
• white: charged
• off: unplugged

I couldn't find documentation about this, but the forum answered. This is something of a recurring theme with the Framework. While it has a good knowledge base and repair/setup guides (and the forum is awesome) but it doesn't have a good "owner manual" that shows you the different parts of the laptop and what they do. Again, something the MNT reform did well. Another thing that people are asking about is an external sleep indicator: because the power LED is on the main keyboard assembly, you don't actually see whether the device is active or not when the lid is closed. Finally, I wondered what happens when you plug in multiple power sources and it turns out the charge controller is actually pretty smart: it will pick the best power source and use it. The only downside is it can't use multiple power sources, but that seems like a bit much to ask.

Multimedia and other devices Those things also work:

• webcam: splendid, best webcam I've ever had (but my standards are really low)
• onboard mic: works well, good gain (maybe a bit much)
• onboard speakers: sound okay, a little metal-ish, loud enough to be annoying, see this thread for benchmarks, apparently pretty good speakers
• combo jack: works, with slight hiss, see below

There's also a light sensor, but it conflicts with the keyboard brightness controls (see above). There's also an accelerometer, but it's off by default and will be removed from future builds.

Combo jack mic tests The Framework laptop ships with a combo jack on the left side, which allows you to plug in a CTIA (source) headset. In human terms, it's a device that has both a stereo output and a mono input, typically a headset or ear buds with a microphone somewhere. It works, which is better than the Purism (which only had audio out), but is on par for the course for that kind of onboard hardware. Because of electrical interference, such sound cards very often get lots of noise from the board. With a Jabra Evolve 40, the built-in USB sound card generates basically zero noise on silence (invisible down to -60dB in Audacity) while plugging it in directly generates a solid -30dB hiss. There is a noise-reduction system in that sound card, but the difference is still quite striking. On a comparable setup (curie, a 2017 Intel NUC), there is also a his with the Jabra headset, but it's quieter, more in the order of -40/-50 dB, a noticeable difference. Interestingly, testing with my Mee Audio Pro M6 earbuds leads to a little more hiss on curie, more on the -35/-40 dB range, close to the Framework. Also note that another sound card, the Antlion USB adapter that comes with the ModMic 4, also gives me pretty close to silence on a quiet recording, picking up less than -50dB of background noise. It's actually probably picking up the fans in the office, which do make audible noises. In other words, the hiss of the sound card built in the Framework laptop is so loud that it makes more noise than the quiet fans in the office. Or, another way to put it is that two USB sound cards (the Jabra and the Antlion) are able to pick up ambient noise in my office but not the Framework laptop. See also my audio page.

Performance tests

Compiling Linux 5.19.11 On a single core, compiling the Debian version of the Linux kernel takes around 100 minutes:

5411.85user 673.33system 1:37:46elapsed 103%CPU (0avgtext+0avgdata 831700maxresident)k
10594704inputs+87448000outputs (9131major+410636783minor)pagefaults 0swaps

This was using 16 watts of power, with full screen brightness. With all 16 cores (make -j16), it takes less than 25 minutes:

19251.06user 2467.47system 24:13.07elapsed 1494%CPU (0avgtext+0avgdata 831676maxresident)k
8321856inputs+87427848outputs (30792major+409145263minor)pagefaults 0swaps

I had to plug the normal power supply after a few minutes because battery would actually run out using my desk's power grommet (34 watts). During compilation, fans were spinning really hard, quite noisy, but not painfully so. The laptop was sucking 55 watts of power, steadily:

  Time    User  Nice   Sys  Idle    IO  Run Ctxt/s  IRQ/s Fork Exec Exit  Watts
-------- ----- ----- ----- ----- ----- ---- ------ ------ ---- ---- ---- ------
 Average  87.9   0.0  10.7   1.4   0.1 17.8 6583.6 5054.3 233.0 223.9 233.1  55.96
 GeoMean  87.9   0.0  10.6   1.2   0.0 17.6 6427.8 5048.1 227.6 218.7 227.7  55.96
  StdDev   1.4   0.0   1.2   0.6   0.2  3.0 1436.8  255.5 50.0 47.5 49.7   0.20
-------- ----- ----- ----- ----- ----- ---- ------ ------ ---- ---- ---- ------
 Minimum  85.0   0.0   7.8   0.5   0.0 13.0 3594.0 4638.0 117.0 111.0 120.0  55.52
 Maximum  90.8   0.0  12.9   3.5   0.8 38.0 10174.0 5901.0 374.0 362.0 375.0  56.41
-------- ----- ----- ----- ----- ----- ---- ------ ------ ---- ---- ---- ------
Summary:
CPU:  55.96 Watts on average with standard deviation 0.20
Note: power read from RAPL domains: package-0, uncore, package-0, core, psys.
These readings do not cover all the hardware in this device.

memtest86+ I ran Memtest86+ v6.00b3. It shows something like this:

Memtest86+ v6.00b3        12th Gen Intel(R) Core(TM) i5-1240P
CLK/Temp: 2112MHz    78/78 C   Pass  2% #
L1 Cache:   48KB    414 GB/s   Test 46% ##################
L2 Cache: 1.25MB    118 GB/s   Test #3 [Moving inversions, 1s & 0s] 
L3 Cache:   12MB     43 GB/s   Testing: 16GB - 18GB [1GB of 15.7GB]
Memory  :  15.7GB  14.9 GB/s   Pattern: 
--------------------------------------------------------------------------------
CPU: 4P+8E-Cores (16T)    SMP: 8T (PAR))    Time:  0:27:23  Status: Pass     \
RAM: 1600MHz (DDR4-3200) CAS 22-22-22-51    Pass:  1        Errors: 0
--------------------------------------------------------------------------------
Memory SPD Information
----------------------
 - Slot 2: 16GB DDR-4-3200 - Crucial CT16G4SFRA32A.C16FP (2022-W23)
                          Framework FRANMACP04
 <ESC> Exit  <F1> Configuration  <Space> Scroll Lock            6.00.unknown.x64

So about 30 minutes for a full 16GB memory test.

Software setup Once I had everything in the hardware setup, I figured, voil , I'm done, I'm just going to boot this beautiful machine and I can get back to work. I don't understand why I am so na ve some times. It's mind boggling. Obviously, it didn't happen that way at all, and I spent the best of the three following days tinkering with the laptop.

Secure boot and EFI First, I couldn't boot off of the NVMe drive I transferred from the previous laptop (the Purism) and the BIOS was not very helpful: it was just complaining about not finding any boot device, without dropping me in the real BIOS. At first, I thought it was a problem with my NVMe drive, because it's not listed in the compatible SSD drives from upstream. But I figured out how to enter BIOS (press F2 manically, of course), which showed the NVMe drive was actually detected. It just didn't boot, because it was an old (2010!!) Debian install without EFI. So from there, I disabled secure boot, and booted a grml image to try to recover. And by "boot" I mean, I managed to get to the grml boot loader which promptly failed to load its own root file system somehow. I still have to investigate exactly what happened there, but it failed some time after the initrd load with:

Unable to find medium containing a live file system

This, it turns out, was fixed in Debian lately, so a daily GRML build will not have this problems. The upcoming 2022 release (likely 2022.10 or 2022.11) will also get the fix. I did manage to boot the development version of the Debian installer which was a surprisingly good experience: it mounted the encrypted drives and did everything pretty smoothly. It even offered me to reinstall the boot loader, but that ultimately (and correctly, as it turns out) failed because I didn't have a /boot/efi partition. At this point, I realized there was no easy way out of this, and I just proceeded to completely reinstall Debian. I had a spare NVMe drive lying around (backups FTW!) so I just swapped that in, rebooted in the Debian installer, and did a clean install. I wanted to switch to bookworm anyways, so I guess that's done too.

Storage limitations Another thing that happened during setup is that I tried to copy over the internal 2.5" SSD drive from the Purism to the Framework 1TB expansion card. There's no 2.5" slot in the new laptop, so that's pretty much the only option for storage expansion. I was tired and did something wrong. I ended up wiping the partition table on the original 2.5" drive. Oops. It might be recoverable, but just restoring the partition table didn't work either, so I'm not sure how I recover the data there. Normally, everything on my laptops and workstations is designed to be disposable, so that wasn't that big of a problem. I did manage to recover most of the data thanks to git-annex reinit, but that was a little hairy.

Bootstrapping Puppet Once I had some networking, I had to install all the packages I needed. The time I spent setting up my workstations with Puppet has finally paid off. What I actually did was to restore two critical directories:

/etc/ssh
/var/lib/puppet

So that I would keep the previous machine's identity. That way I could contact the Puppet server and install whatever was missing. I used my Puppet optimization trick to do a batch install and then I had a good base setup, although not exactly as it was before. 1700 packages were installed manually on angela before the reinstall, and not in Puppet. I did not inspect each one individually, but I did go through /etc and copied over more SSH keys, for backups and SMTP over SSH.

LVFS support It looks like there's support for the (de-facto) standard LVFS firmware update system. At least I was able to update the UEFI firmware with a simple:

apt install fwupd-amd64-signed
fwupdmgr refresh
fwupdmgr get-updates
fwupdmgr update

Nice. The 12th gen BIOS updates, currently (January 2023) beta, can be deployed through LVFS with:

fwupdmgr enable-remote lvfs-testing
echo 'DisableCapsuleUpdateOnDisk=true' >> /etc/fwupd/uefi_capsule.conf 
fwupdmgr update

Those instructions come from the beta forum post. I performed the BIOS update on 2023-01-16T16:00-0500.

Resolution tweaks The Framework laptop resolution (2256px X 1504px) is big enough to give you a pretty small font size, so welcome to the marvelous world of "scaling". The Debian wiki page has a few tricks for this.

Console This will make the console and grub fonts more readable:

cat >> /etc/default/console-setup <<EOF
FONTFACE="Terminus"
FONTSIZE=32x16
EOF
echo GRUB_GFXMODE=1024x768 >> /etc/default/grub
update-grub

Xorg Adding this to your .Xresources will make everything look much bigger:

! 1.5*96
Xft.dpi: 144

Apparently, some of this can also help:

! These might also be useful depending on your monitor and personal preference:
Xft.autohint: 0
Xft.lcdfilter:  lcddefault
Xft.hintstyle:  hintfull
Xft.hinting: 1
Xft.antialias: 1
Xft.rgba: rgb

It my experience it also makes things look a little fuzzier, which is frustrating because you have this awesome monitor but everything looks out of focus. Just bumping Xft.dpi by a 1.5 factor looks good to me. The Debian Wiki has a page on HiDPI, but it's not as good as the Arch Wiki, where the above blurb comes from. I am not using the latter because I suspect it's causing some of the "fuzziness". TODO: find the equivalent of this GNOME hack in i3? (gsettings set org.gnome.mutter experimental-features "['scale-monitor-framebuffer']"), taken from this Framework guide

Issues

BIOS configuration The Framework BIOS has some minor issues. One issue I personally encountered is that I had disabled Quick boot and Quiet boot in the BIOS to diagnose the above boot issues. This, in turn, triggers a bug where the BIOS boot manager (F12) would just hang completely. It would also fail to boot from an external USB drive. The current fix (as of BIOS 3.03) is to re-enable both Quick boot and Quiet boot. Presumably this is something that will get fixed in a future BIOS update. Note that the following keybindings are active in the BIOS POST check:

Key	Meaning
F2	Enter BIOS setup menu
F12	Enter BIOS boot manager
Delete	Enter BIOS setup menu

WiFi compatibility issues I couldn't make WiFi work at first. Obviously, the default Debian installer doesn't ship with proprietary firmware (although that might change soon) so the WiFi card didn't work out of the box. But even after copying the firmware through a USB stick, I couldn't quite manage to find the right combination of ip/iw/wpa-supplicant (yes, after repeatedly copying a bunch more packages over to get those bootstrapped). (Next time I should probably try something like this post.) Thankfully, I had a little USB-C dongle with a RJ-45 jack lying around. That also required a firmware blob, but it was a single package to copy over, and with that loaded, I had network. Eventually, I did managed to make WiFi work; the problem was more on the side of "I forgot how to configure a WPA network by hand from the commandline" than anything else. NetworkManager worked fine and got WiFi working correctly. Note that this is with Debian bookworm, which has the 5.19 Linux kernel, and with the firmware-nonfree (firmware-iwlwifi, specifically) package.

Battery life I was having between about 7 hours of battery on the Purism Librem 13v4, and that's after a year or two of battery life. Now, I still have about 7 hours of battery life, which is nicer than my old ThinkPad X220 (20 minutes!) but really, it's not that good for a new generation laptop. The 12th generation Intel chipset probably improved things compared to the previous one Framework laptop, but I don't have a 11th gen Framework to compare with). (Note that those are estimates from my status bar, not wall clock measurements. They should still be comparable between the Purism and Framework, that said.) The battery life doesn't seem up to, say, Dell XPS 13, ThinkPad X1, and of course not the Apple M1, where I would expect 10+ hours of battery life out of the box. That said, I do get those kind estimates when the machine is fully charged and idle. In fact, when everything is quiet and nothing is plugged in, I get dozens of hours of battery life estimated (I've seen 25h!). So power usage fluctuates quite a bit depending on usage, which I guess is expected. Concretely, so far, light web browsing, reading emails and writing notes in Emacs (e.g. this file) takes about 8W of power:

Time    User  Nice   Sys  Idle    IO  Run Ctxt/s  IRQ/s Fork Exec Exit  Watts
-------- ----- ----- ----- ----- ----- ---- ------ ------ ---- ---- ---- ------
 Average   1.7   0.0   0.5  97.6   0.2  1.2 4684.9 1985.2 126.6 39.1 128.0   7.57
 GeoMean   1.4   0.0   0.4  97.6   0.1  1.2 4416.6 1734.5 111.6 27.9 113.3   7.54
  StdDev   1.0   0.2   0.2   1.2   0.0  0.5 1584.7 1058.3 82.1 44.0 80.2   0.71
-------- ----- ----- ----- ----- ----- ---- ------ ------ ---- ---- ---- ------
 Minimum   0.2   0.0   0.2  94.9   0.1  1.0 2242.0  698.2 82.0 17.0 82.0   6.36
 Maximum   4.1   1.1   1.0  99.4   0.2  3.0 8687.4 4445.1 463.0 249.0 449.0   9.10
-------- ----- ----- ----- ----- ----- ---- ------ ------ ---- ---- ---- ------
Summary:
System:   7.57 Watts on average with standard deviation 0.71

Expansion cards matter a lot in the battery life (see below for a thorough discussion), my normal setup is 2xUSB-C and 1xUSB-A (yes, with an empty slot, and yes, to save power). Interestingly, playing a video in a (720p) window in a window takes up more power (10.5W) than in full screen (9.5W) but I blame that on my desktop setup (i3 + compton)... Not sure if mpv hits the VA-API, maybe not in windowed mode. Similar results with 1080p, interestingly, except the window struggles to keep up altogether. Full screen playback takes a relatively comfortable 9.5W, which means a solid 5h+ of playback, which is fine by me. Fooling around the web, small edits, youtube-dl, and I'm at around 80% battery after about an hour, with an estimated 5h left, which is a little disappointing. I had a 7h remaining estimate before I started goofing around Discourse, so I suspect the website is a pretty big battery drain, actually. I see about 10-12 W, while I was probably at half that (6-8W) just playing music with mpv in the background... In other words, it looks like editing posts in Discourse with Firefox takes a solid 4-6W of power. Amazing and gross. (When writing about abusive power usage generates more power usage, is that an heisenbug? Or schr dinbug?)

Power management Compared to the Purism Librem 13v4, the ongoing power usage seems to be slightly better. An anecdotal metric is that the Purism would take 800mA idle, while the more powerful Framework manages a little over 500mA as I'm typing this, fluctuating between 450 and 600mA. That is without any active expansion card, except the storage. Those numbers come from the output of tlp-stat -b and, unfortunately, the "ampere" unit makes it quite hard to compare those, because voltage is not necessarily the same between the two platforms.

• TODO: review Arch Linux's tips on power saving
• TODO: i915 driver has a lot of parameters, including some about power saving, see, again, the arch wiki, and particularly enable_fbc=1

TL:DR; power management on the laptop is an issue, but there's various tweaks you can make to improve it. Try:

• powertop --auto-tune
• apt install tlp && systemctl enable tlp
• nvme.noacpi=1 mem_sleep_default=deep on the kernel command line may help with standby power usage
• keep only USB-C expansion cards plugged in, all others suck power even when idle
• consider upgrading the BIOS to latest beta (3.06 at the time of writing), unverified power savings
• latest Linux kernels (6.2) promise power savings as well (unverified)

Update: also try to follow the official optimization guide. It was made for Ubuntu but will probably also work for your distribution of choice with a few tweaks. They recommend using tlpui but it's not packaged in Debian. There is, however, a Flatpak release. In my case, it resulted in the following diff to tlp.conf: tlp.patch.

Background on CPU architecture There were power problems in the 11th gen Framework laptop, according to this report from Linux After Dark, so the issues with power management on the Framework are not new. The 12th generation Intel CPU (AKA "Alder Lake") is a big-little architecture with "power-saving" and "performance" cores. There used to be performance problems introduced by the scheduler in Linux 5.16 but those were eventually fixed in 5.18, which uses Intel's hardware as an "intelligent, low-latency hardware-assisted scheduler". According to Phoronix, the 5.19 release improved the power saving, at the cost of some penalty cost. There were also patch series to make the scheduler configurable, but it doesn't look those have been merged as of 5.19. There was also a session about this at the 2022 Linux Plumbers, but they stopped short of talking more about the specific problems Linux is facing in Alder lake:

Specifically, the kernel's energy-aware scheduling heuristics don't work well on those CPUs. A number of features present there complicate the energy picture; these include SMT, Intel's "turbo boost" mode, and the CPU's internal power-management mechanisms. For many workloads, running on an ostensibly more power-hungry Pcore can be more efficient than using an Ecore. Time for discussion of the problem was lacking, though, and the session came to a close.

All this to say that the 12gen Intel line shipped with this Framework series should have better power management thanks to its power-saving cores. And Linux has had the scheduler changes to make use of this (but maybe is still having trouble). In any case, this might not be the source of power management problems on my laptop, quite the opposite. Also note that the firmware updates for various chipsets are supposed to improve things eventually. On the other hand, The Verge simply declared the whole P-series a mistake...

Attempts at improving power usage I did try to follow some of the tips in this forum post. The tricks powertop --auto-tune and tlp's PCIE_ASPM_ON_BAT=powersupersave basically did nothing: I was stuck at 10W power usage in powertop (600+mA in tlp-stat). Apparently, I should be able to reach the C8 CPU power state (or even C9, C10) in powertop, but I seem to be stock at C7. (Although I'm not sure how to read that tab in powertop: in the Core(HW) column there's only C3/C6/C7 states, and most cores are 85% in C7 or maybe C6. But the next column over does show many CPUs in C10 states... As it turns out, the graphics card actually takes up a good chunk of power unless proper power management is enabled (see below). After tweaking this, I did manage to get down to around 7W power usage in powertop. Expansion cards actually do take up power, and so does the screen, obviously. The fully-lit screen takes a solid 2-3W of power compared to the fully dimmed screen. When removing all expansion cards and making the laptop idle, I can spin it down to 4 watts power usage at the moment, and an amazing 2 watts when the screen turned off.

Caveats Abusive (10W+) power usage that I initially found could be a problem with my desktop configuration: I have this silly status bar that updates every second and probably causes redraws... The CPU certainly doesn't seem to spin down below 1GHz. Also note that this is with an actual desktop running with everything: it could very well be that some things (I'm looking at you Signal Desktop) take up unreasonable amount of power on their own (hello, 1W/electron, sheesh). Syncthing and containerd (Docker!) also seem to take a good 500mW just sitting there. Beyond my desktop configuration, this could, of course, be a Debian-specific problem; your favorite distribution might be better at power management.

Idle power usage tests Some expansion cards waste energy, even when unused. Here is a summary of the findings from the powerstat page. I also include other devices tested in this page for completeness:

Device	Minimum	Average	Max	Stdev	Note
Screen, 100%	2.4W	2.6W	2.8W	N/A
Screen, 1%	30mW	140mW	250mW	N/A
Backlight 1	290mW	?	?	?	fairly small, all things considered
Backlight 2	890mW	1.2W	3W?	460mW?	geometric progression
Backlight 3	1.69W	1.5W	1.8W?	390mW?	significant power use
Radios	100mW	250mW	N/A	N/A
USB-C	N/A	N/A	N/A	N/A	negligible power drain
USB-A	10mW	10mW	?	10mW	almost negligible
DisplayPort	300mW	390mW	600mW	N/A	not passive
HDMI	380mW	440mW	1W?	20mW	not passive
1TB SSD	1.65W	1.79W	2W	12mW	significant, probably higher when busy
MicroSD	1.6W	3W	6W	1.93W	highest power usage, possibly even higher when busy
Ethernet	1.69W	1.64W	1.76W	N/A	comparable to the SSD card

So it looks like all expansion cards but the USB-C ones are active, i.e. they draw power with idle. The USB-A cards are the least concern, sucking out 10mW, pretty much within the margin of error. But both the DisplayPort and HDMI do take a few hundred miliwatts. It looks like USB-A connectors have this fundamental flaw that they necessarily draw some powers because they lack the power negotiation features of USB-C. At least according to this post:

It seems the USB A must have power going to it all the time, that the old USB 2 and 3 protocols, the USB C only provides power when there is a connection. Old versus new.

Apparently, this is a problem specific to the USB-C to USB-A adapter that ships with the Framework. Some people have actually changed their orders to all USB-C because of this problem, but I'm not sure the problem is as serious as claimed in the forums. I couldn't reproduce the "one watt" power drains suggested elsewhere, at least not repeatedly. (A previous version of this post did show such a power drain, but it was in a less controlled test environment than the series of more rigorous tests above.) The worst offenders are the storage cards: the SSD drive takes at least one watt of power and the MicroSD card seems to want to take all the way up to 6 watts of power, both just sitting there doing nothing. This confirms claims of 1.4W for the SSD (but not 5W) power usage found elsewhere. The former post has instructions on how to disable the card in software. The MicroSD card has been reported as using 2 watts, but I've seen it as high as 6 watts, which is pretty damning. The Framework team has a beta update for the DisplayPort adapter but currently only for Windows (LVFS technically possible, "under investigation"). A USB-A firmware update is also under investigation. It is therefore likely at least some of those power management issues will eventually be fixed. Note that the upcoming Ethernet card has a reported 2-8W power usage, depending on traffic. I did my own power usage tests in powerstat-wayland and they seem lower than 2W. The upcoming 6.2 Linux kernel might also improve battery usage when idle, see this Phoronix article for details, likely in early 2023.

Idle power usage tests under Wayland Update: I redid those tests under Wayland, see powerstat-wayland for details. The TL;DR: is that power consumption is either smaller or similar.

Idle power usage tests, 3.06 beta BIOS I redid the idle tests after the 3.06 beta BIOS update and ended up with this results:

Device	Minimum	Average	Max	Stdev	Note
Baseline	1.96W	2.01W	2.11W	30mW	1 USB-C, screen off, backlight off, no radios
2 USB-C	1.95W	2.16W	3.69W	430mW	USB-C confirmed as mostly passive...
3 USB-C	1.95W	2.16W	3.69W	430mW	... although with extra stdev
1TB SSD	3.72W	3.85W	4.62W	200mW	unchanged from before upgrade
1 USB-A	1.97W	2.18W	4.02W	530mW	unchanged
2 USB-A	1.97W	2.00W	2.08W	30mW	unchanged
3 USB-A	1.94W	1.99W	2.03W	20mW	unchanged
MicroSD w/o card	3.54W	3.58W	3.71W	40mW	significant improvement! 2-3W power saving!
MicroSD w/ card	3.53W	3.72W	5.23W	370mW	new measurement! increased deviation
DisplayPort	2.28W	2.31W	2.37W	20mW	unchanged
1 HDMI	2.43W	2.69W	4.53W	460mW	unchanged
2 HDMI	2.53W	2.59W	2.67W	30mW	unchanged
External USB	3.85W	3.89W	3.94W	30mW	new result
Ethernet	3.60W	3.70W	4.91W	230mW	unchanged

Note that the table summary is different than the previous table: here we show the absolute numbers while the previous table was doing a confusing attempt at showing relative (to the baseline) numbers. Conclusion: the 3.06 BIOS update did not significantly change idle power usage stats except for the MicroSD card which has significantly improved. The new "external USB" test is also interesting: it shows how the provided 1TB SSD card performs (admirably) compared to existing devices. The other new result is the MicroSD card with a card which, interestingly, uses less power than the 1TB SSD drive.

Standby battery usage I wrote some quick hack to evaluate how much power is used during sleep. Apparently, this is one of the areas that should have improved since the first Framework model, let's find out. My baseline for comparison is the Purism laptop, which, in 10 minutes, went from this:

sep 28 11:19:45 angela systemd-sleep[209379]: /sys/class/power_supply/BAT/charge_now                      =   6045 [mAh]

... to this:

sep 28 11:29:47 angela systemd-sleep[209725]: /sys/class/power_supply/BAT/charge_now                      =   6037 [mAh]

That's 8mAh per 10 minutes (and 2 seconds), or 48mA, or, with this battery, about 127 hours or roughly 5 days of standby. Not bad! In comparison, here is my really old x220, before:

sep 29 22:13:54 emma systemd-sleep[176315]: /sys/class/power_supply/BAT0/energy_now                     =   5070 [mWh]

... after:

sep 29 22:23:54 emma systemd-sleep[176486]: /sys/class/power_supply/BAT0/energy_now                     =   4980 [mWh]

... which is 90 mwH in 10 minutes, or a whopping 540mA, which was possibly okay when this battery was new (62000 mAh, so about 100 hours, or about 5 days), but this battery is almost dead and has only 5210 mAh when full, so only 10 hours standby. And here is the Framework performing a similar test, before:

sep 29 22:27:04 angela systemd-sleep[4515]: /sys/class/power_supply/BAT1/charge_full                    =   3518 [mAh]
sep 29 22:27:04 angela systemd-sleep[4515]: /sys/class/power_supply/BAT1/charge_now                     =   2861 [mAh]

... after:

sep 29 22:37:08 angela systemd-sleep[4743]: /sys/class/power_supply/BAT1/charge_now                     =   2812 [mAh]

... which is 49mAh in a little over 10 minutes (and 4 seconds), or 292mA, much more than the Purism, but half of the X220. At this rate, the battery would last on standby only 12 hours!! That is pretty bad. Note that this was done with the following expansion cards:

• 2 USB-C
• 1 1TB SSD drive
• 1 USB-A with a hub connected to it, with keyboard and LAN

Preliminary tests without the hub (over one minute) show that it doesn't significantly affect this power consumption (300mA). This guide also suggests booting with nvme.noacpi=1 but this still gives me about 5mAh/min (or 300mA). Adding mem_sleep_default=deep to the kernel command line does make a difference. Before:

sep 29 23:03:11 angela systemd-sleep[3699]: /sys/class/power_supply/BAT1/charge_now                     =   2544 [mAh]

... after:

sep 29 23:04:25 angela systemd-sleep[4039]: /sys/class/power_supply/BAT1/charge_now                     =   2542 [mAh]

... which is 2mAh in 74 seconds, which is 97mA, brings us to a more reasonable 36 hours, or a day and a half. It's still above the x220 power usage, and more than an order of magnitude more than the Purism laptop. It's also far from the 0.4% promised by upstream, which would be 14mA for the 3500mAh battery. It should also be noted that this "deep" sleep mode is a little more disruptive than regular sleep. As you can see by the timing, it took more than 10 seconds for the laptop to resume, which feels a little alarming as your banging the keyboard to bring it back to life. You can confirm the current sleep mode with:

# cat /sys/power/mem_sleep
s2idle [deep]

In the above, deep is selected. You can change it on the fly with:

printf s2idle > /sys/power/mem_sleep

Here's another test:

sep 30 22:25:50 angela systemd-sleep[32207]: /sys/class/power_supply/BAT1/charge_now                     =   1619 [mAh]
sep 30 22:31:30 angela systemd-sleep[32516]: /sys/class/power_supply/BAT1/charge_now                     =   1613 [mAh]

... better! 6 mAh in about 6 minutes, works out to 63.5mA, so more than two days standby. A longer test:

oct 01 09:22:56 angela systemd-sleep[62978]: /sys/class/power_supply/BAT1/charge_now                     =   3327 [mAh]
oct 01 12:47:35 angela systemd-sleep[63219]: /sys/class/power_supply/BAT1/charge_now                     =   3147 [mAh]

That's 180mAh in about 3.5h, 52mA! Now at 66h, or almost 3 days. I wasn't sure why I was seeing such fluctuations in those tests, but as it turns out, expansion card power tests show that they do significantly affect power usage, especially the SSD drive, which can take up to two full watts of power even when idle. I didn't control for expansion cards in the above tests running them with whatever card I had plugged in without paying attention so it's likely the cause of the high power usage and fluctuations. It might be possible to work around this problem by disabling USB devices before suspend. TODO. See also this post. In the meantime, I have been able to get much better suspend performance by unplugging all modules. Then I get this result:

oct 04 11:15:38 angela systemd-sleep[257571]: /sys/class/power_supply/BAT1/charge_now                     =   3203 [mAh]
oct 04 15:09:32 angela systemd-sleep[257866]: /sys/class/power_supply/BAT1/charge_now                     =   3145 [mAh]

Which is 14.8mA! Almost exactly the number promised by Framework! With a full battery, that means a 10 days suspend time. This is actually pretty good, and far beyond what I was expecting when starting down this journey. So, once the expansion cards are unplugged, suspend power usage is actually quite reasonable. More detailed standby tests are available in the standby-tests page, with a summary below. There is also some hope that the Chromebook edition specifically designed with a specification of 14 days standby time could bring some firmware improvements back down to the normal line. Some of those issues were reported upstream in April 2022, but there doesn't seem to have been any progress there since. TODO: one final solution here is suspend-then-hibernate, which Windows uses for this TODO: consider implementing the S0ix sleep states , see also troubleshooting TODO: consider https://github.com/intel/pm-graph

Standby expansion cards test results This table is a summary of the more extensive standby-tests I have performed:

Device	Wattage	Amperage	Days	Note
baseline	0.25W	16mA	9	sleep=deep nvme.noacpi=1
s2idle	0.29W	18.9mA	~7	sleep=s2idle nvme.noacpi=1
normal nvme	0.31W	20mA	~7	sleep=s2idle without nvme.noacpi=1
1 USB-C	0.23W	15mA	~10
2 USB-C	0.23W	14.9mA		same as above
1 USB-A	0.75W	48.7mA	3	+500mW (!!) for the first USB-A card!
2 USB-A	1.11W	72mA	2	+360mW
3 USB-A	1.48W	96mA	<2	+370mW
1TB SSD	0.49W	32mA	<5	+260mW
MicroSD	0.52W	34mA	~4	+290mW
DisplayPort	0.85W	55mA	<3	+620mW (!!)
1 HDMI	0.58W	38mA	~4	+250mW
2 HDMI	0.65W	42mA	<4	+70mW

Conclusions:

• USB-C cards take no extra power on suspend, possibly less than empty slots, more testing required
• USB-A cards take a lot more power on suspend (300-500mW) than on regular idle (~10mW, almost negligible)
• 1TB SSD and MicroSD cards seem to take a reasonable amount of power (260-290mW), compared to their runtime equivalents (1-6W!)
• DisplayPort takes a surprising lot of power (620mW), almost double its average runtime usage (390mW)
• HDMI cards take, surprisingly, less power (250mW) in standby than the DP card (620mW)
• and oddly, a second card adds less power usage (70mW?!) than the first, maybe a circuit is used by both?

A discussion of those results is in this forum post.

Standby expansion cards test results, 3.06 beta BIOS Framework recently (2022-11-07) announced that they will publish a firmware upgrade to address some of the USB-C issues, including power management. This could positively affect the above result, improving both standby and runtime power usage. The update came out in December 2022 and I redid my analysis with the following results:

Device	Wattage	Amperage	Days	Note
baseline	0.25W	16mA	9	no cards, same as before upgrade
1 USB-C	0.25W	16mA	9	same as before
2 USB-C	0.25W	16mA	9	same
1 USB-A	0.80W	62mA	3	+550mW!! worse than before
2 USB-A	1.12W	73mA	<2	+320mW, on top of the above, bad!
Ethernet	0.62W	40mA	3-4	new result, decent
1TB SSD	0.52W	34mA	4	a bit worse than before (+2mA)
MicroSD	0.51W	22mA	4	same
DisplayPort	0.52W	34mA	4+	upgrade improved by 300mW
1 HDMI	?	38mA	?	same
2 HDMI	?	45mA	?	a bit worse than before (+3mA)
Normal	1.08W	70mA	~2	Ethernet, 2 USB-C, USB-A

Full results in standby-tests-306. The big takeaway for me is that the update did not improve power usage on the USB-A ports which is a big problem for my use case. There is a notable improvement on the DisplayPort power consumption which brings it more in line with the HDMI connector, but it still doesn't properly turn off on suspend either. Even worse, the USB-A ports now sometimes fails to resume after suspend, which is pretty annoying. This is a known problem that will hopefully get fixed in the final release.

Battery wear protection The BIOS has an option to limit charge to 80% to mitigate battery wear. There's a way to control the embedded controller from runtime with fw-ectool, partly documented here. The command would be:

sudo ectool fwchargelimit 80

I looked at building this myself but failed to run it. I opened a RFP in Debian so that we can ship this in Debian, and also documented my work there. Note that there is now a counter that tracks charge/discharge cycles. It's visible in tlp-stat -b, which is a nice improvement:

root@angela:/home/anarcat# tlp-stat -b
--- TLP 1.5.0 --------------------------------------------
+++ Battery Care
Plugin: generic
Supported features: none available
+++ Battery Status: BAT1
/sys/class/power_supply/BAT1/manufacturer                   = NVT
/sys/class/power_supply/BAT1/model_name                     = Framewo
/sys/class/power_supply/BAT1/cycle_count                    =      3
/sys/class/power_supply/BAT1/charge_full_design             =   3572 [mAh]
/sys/class/power_supply/BAT1/charge_full                    =   3541 [mAh]
/sys/class/power_supply/BAT1/charge_now                     =   1625 [mAh]
/sys/class/power_supply/BAT1/current_now                    =    178 [mA]
/sys/class/power_supply/BAT1/status                         = Discharging
/sys/class/power_supply/BAT1/charge_control_start_threshold = (not available)
/sys/class/power_supply/BAT1/charge_control_end_threshold   = (not available)
Charge                                                      =   45.9 [%]
Capacity                                                    =   99.1 [%]

One thing that is still missing is the charge threshold data (the (not available) above). There's been some work to make that accessible in August, stay tuned? This would also make it possible implement hysteresis support.

Ethernet expansion card The Framework ethernet expansion card is a fancy little doodle: "2.5Gbit/s and 10/100/1000Mbit/s Ethernet", the "clear housing lets you peek at the RTL8156 controller that powers it". Which is another way to say "we didn't completely finish prod on this one, so it kind of looks like we 3D-printed this in the shop".... The card is a little bulky, but I guess that's inevitable considering the RJ-45 form factor when compared to the thin Framework laptop. I have had a serious issue when trying it at first: the link LEDs just wouldn't come up. I made a full bug report in the forum and with upstream support, but eventually figured it out on my own. It's (of course) a power saving issue: if you reboot the machine, the links come up when the laptop is running the BIOS POST check and even when the Linux kernel boots. I first thought that the problem is likely related to the powertop service which I run at boot time to tweak some power saving settings. It seems like this:

echo 'on' > '/sys/bus/usb/devices/4-2/power/control'

... is a good workaround to bring the card back online. You can even return to power saving mode and the card will still work:

echo 'auto' > '/sys/bus/usb/devices/4-2/power/control'

Further research by Matt_Hartley from the Framework Team found this issue in the tlp tracker that shows how the USB_AUTOSUSPEND setting enables the power saving even if the driver doesn't support it, which, in retrospect, just sounds like a bad idea. To quote that issue:

By default, USB power saving is active in the kernel, but not force-enabled for incompatible drivers. That is, devices that support suspension will suspend, drivers that do not, will not.

So the fix is actually to uninstall tlp or disable that setting by adding this to /etc/tlp.conf:

USB_AUTOSUSPEND=0

... but that disables auto-suspend on all USB devices, which may hurt other power usage performance. I have found that a a combination of:

USB_AUTOSUSPEND=1
USB_DENYLIST="0bda:8156"

and this on the kernel commandline:

usbcore.quirks=0bda:8156:k

... actually does work correctly. I now have this in my /etc/default/grub.d/framework-tweaks.cfg file:

# net.ifnames=0: normal interface names ffs (e.g. eth0, wlan0, not wlp166
s0)
# nvme.noacpi=1: reduce SSD disk power usage (not working)
# mem_sleep_default=deep: reduce power usage during sleep (not working)
# usbcore.quirk is a workaround for the ethernet card suspend bug: https:
//guides.frame.work/Guide/Fedora+37+Installation+on+the+Framework+Laptop/
108?lang=en
GRUB_CMDLINE_LINUX="net.ifnames=0 nvme.noacpi=1 mem_sleep_default=deep usbcore.quirks=0bda:8156:k"
# fix the resolution in grub for fonts to not be tiny
GRUB_GFXMODE=1024x768

Other than that, I haven't been able to max out the card because I don't have other 2.5Gbit/s equipment at home, which is strangely satisfying. But running against my Turris Omnia router, I could pretty much max a gigabit fairly easily:

[ ID] Interval           Transfer     Bitrate         Retr
[  5]   0.00-10.00  sec  1.09 GBytes   937 Mbits/sec  238             sender
[  5]   0.00-10.00  sec  1.09 GBytes   934 Mbits/sec                  receiver

The card doesn't require any proprietary firmware blobs which is surprising. Other than the power saving issues, it just works. In my power tests (see powerstat-wayland), the Ethernet card seems to use about 1.6W of power idle, without link, in the above "quirky" configuration where the card is functional but without autosuspend.

Proprietary firmware blobs The framework does need proprietary firmware to operate. Specifically:

• the WiFi network card shipped with the DIY kit is a AX210 card that requires a 5.19 kernel or later, and the firmware-iwlwifi non-free firmware package
• the Bluetooth adapter also loads the firmware-iwlwifi package (untested)
• the graphics work out of the box without firmware, but certain power management features come only with special proprietary firmware, normally shipped in the firmware-misc-nonfree but currently missing from the package

Note that, at the time of writing, the latest i915 firmware from linux-firmware has a serious bug where loading all the accessible firmware results in noticeable I estimate 200-500ms lag between the keyboard (not the mouse!) and the display. Symptoms also include tearing and shearing of windows, it's pretty nasty. One workaround is to delete the two affected firmware files:

cd /lib/firmware && rm adlp_guc_70.1.1.bin adlp_guc_69.0.3.bin
update-initramfs -u

You will get the following warning during build, which is good as it means the problematic firmware is disabled:

W: Possible missing firmware /lib/firmware/i915/adlp_guc_69.0.3.bin for module i915
W: Possible missing firmware /lib/firmware/i915/adlp_guc_70.1.1.bin for module i915

But then it also means that critical firmware isn't loaded, which means, among other things, a higher battery drain. I was able to move from 8.5-10W down to the 7W range after making the firmware work properly. This is also after turning the backlight all the way down, as that takes a solid 2-3W in full blast. The proper fix is to use some compositing manager. I ended up using compton with the following systemd unit:

[Unit]
Description=start compositing manager
PartOf=graphical-session.target
ConditionHost=angela
[Service]
Type=exec
ExecStart=compton --show-all-xerrors --backend glx --vsync opengl-swc
Restart=on-failure
[Install]
RequiredBy=graphical-session.target

compton is orphaned however, so you might be tempted to use picom instead, but in my experience the latter uses much more power (1-2W extra, similar experience). I also tried compiz but it would just crash with:

anarcat@angela:~$ compiz --replace
compiz (core) - Warn: No XI2 extension
compiz (core) - Error: Another composite manager is already running on screen: 0
compiz (core) - Fatal: No manageable screens found on display :0

When running from the base session, I would get this instead:

compiz (core) - Warn: No XI2 extension
compiz (core) - Error: Couldn't load plugin 'ccp'
compiz (core) - Error: Couldn't load plugin 'ccp'

Thanks to EmanueleRocca for figuring all that out. See also this discussion about power management on the Framework forum. Note that Wayland environments do not require any special configuration here and actually work better, see my Wayland migration notes for details.

Also note that the iwlwifi firmware also looks incomplete. Even with the package installed, I get those errors in dmesg:

[   19.534429] Intel(R) Wireless WiFi driver for Linux
[   19.534691] iwlwifi 0000:a6:00.0: enabling device (0000 -> 0002)
[   19.541867] iwlwifi 0000:a6:00.0: firmware: failed to load iwlwifi-ty-a0-gf-a0-72.ucode (-2)
[   19.541881] iwlwifi 0000:a6:00.0: firmware: failed to load iwlwifi-ty-a0-gf-a0-72.ucode (-2)
[   19.541882] iwlwifi 0000:a6:00.0: Direct firmware load for iwlwifi-ty-a0-gf-a0-72.ucode failed with error -2
[   19.541890] iwlwifi 0000:a6:00.0: firmware: failed to load iwlwifi-ty-a0-gf-a0-71.ucode (-2)
[   19.541895] iwlwifi 0000:a6:00.0: firmware: failed to load iwlwifi-ty-a0-gf-a0-71.ucode (-2)
[   19.541896] iwlwifi 0000:a6:00.0: Direct firmware load for iwlwifi-ty-a0-gf-a0-71.ucode failed with error -2
[   19.541903] iwlwifi 0000:a6:00.0: firmware: failed to load iwlwifi-ty-a0-gf-a0-70.ucode (-2)
[   19.541907] iwlwifi 0000:a6:00.0: firmware: failed to load iwlwifi-ty-a0-gf-a0-70.ucode (-2)
[   19.541908] iwlwifi 0000:a6:00.0: Direct firmware load for iwlwifi-ty-a0-gf-a0-70.ucode failed with error -2
[   19.541913] iwlwifi 0000:a6:00.0: firmware: failed to load iwlwifi-ty-a0-gf-a0-69.ucode (-2)
[   19.541916] iwlwifi 0000:a6:00.0: firmware: failed to load iwlwifi-ty-a0-gf-a0-69.ucode (-2)
[   19.541917] iwlwifi 0000:a6:00.0: Direct firmware load for iwlwifi-ty-a0-gf-a0-69.ucode failed with error -2
[   19.541922] iwlwifi 0000:a6:00.0: firmware: failed to load iwlwifi-ty-a0-gf-a0-68.ucode (-2)
[   19.541926] iwlwifi 0000:a6:00.0: firmware: failed to load iwlwifi-ty-a0-gf-a0-68.ucode (-2)
[   19.541927] iwlwifi 0000:a6:00.0: Direct firmware load for iwlwifi-ty-a0-gf-a0-68.ucode failed with error -2
[   19.541933] iwlwifi 0000:a6:00.0: firmware: failed to load iwlwifi-ty-a0-gf-a0-67.ucode (-2)
[   19.541937] iwlwifi 0000:a6:00.0: firmware: failed to load iwlwifi-ty-a0-gf-a0-67.ucode (-2)
[   19.541937] iwlwifi 0000:a6:00.0: Direct firmware load for iwlwifi-ty-a0-gf-a0-67.ucode failed with error -2
[   19.544244] iwlwifi 0000:a6:00.0: firmware: direct-loading firmware iwlwifi-ty-a0-gf-a0-66.ucode
[   19.544257] iwlwifi 0000:a6:00.0: api flags index 2 larger than supported by driver
[   19.544270] iwlwifi 0000:a6:00.0: TLV_FW_FSEQ_VERSION: FSEQ Version: 0.63.2.1
[   19.544523] iwlwifi 0000:a6:00.0: firmware: failed to load iwl-debug-yoyo.bin (-2)
[   19.544528] iwlwifi 0000:a6:00.0: firmware: failed to load iwl-debug-yoyo.bin (-2)
[   19.544530] iwlwifi 0000:a6:00.0: loaded firmware version 66.55c64978.0 ty-a0-gf-a0-66.ucode op_mode iwlmvm

Some of those are available in the latest upstream firmware package (iwlwifi-ty-a0-gf-a0-71.ucode, -68, and -67), but not all (e.g. iwlwifi-ty-a0-gf-a0-72.ucode is missing) . It's unclear what those do or don't, as the WiFi seems to work well without them. I still copied them in from the latest linux-firmware package in the hope they would help with power management, but I did not notice a change after loading them. There are also multiple knobs on the iwlwifi and iwlmvm drivers. The latter has a power_schmeme setting which defaults to 2 (balanced), setting it to 3 (low power) could improve battery usage as well, in theory. The iwlwifi driver also has power_save (defaults to disabled) and power_level (1-5, defaults to 1) settings. See also the output of modinfo iwlwifi and modinfo iwlmvm for other driver options.

Graphics acceleration After loading the latest upstream firmware and setting up a compositing manager (compton, above), I tested the classic glxgears. Running in a window gives me odd results, as the gears basically grind to a halt:

Running synchronized to the vertical refresh.  The framerate should be
approximately the same as the monitor refresh rate.
137 frames in 5.1 seconds = 26.984 FPS
27 frames in 5.4 seconds =  5.022 FPS

Ouch. 5FPS! But interestingly, once the window is in full screen, it does hit the monitor refresh rate:

300 frames in 5.0 seconds = 60.000 FPS

I'm not really a gamer and I'm not normally using any of that fancy graphics acceleration stuff (except maybe my browser does?). I installed intel-gpu-tools for the intel_gpu_top command to confirm the GPU was engaged when doing those simulations. A nice find. Other useful diagnostic tools include glxgears and glxinfo (in mesa-utils) and (vainfo in vainfo). Following to this post, I also made sure to have those settings in my about:config in Firefox, or, in user.js:

user_pref("media.ffmpeg.vaapi.enabled", true);

Note that the guide suggests many other settings to tweak, but those might actually be overkill, see this comment and its parents. I did try forcing hardware acceleration by setting gfx.webrender.all to true, but everything became choppy and weird. The guide also mentions installing the intel-media-driver package, but I could not find that in Debian. The Arch wiki has, as usual, an excellent reference on hardware acceleration in Firefox.

Chromium / Signal desktop bugs It looks like both Chromium and Signal Desktop misbehave with my compositor setup (compton + i3). The fix is to add a persistent flag to Chromium. In Arch, it's conveniently in ~/.config/chromium-flags.conf but that doesn't actually work in Debian. I had to put the flag in /etc/chromium.d/disable-compositing, like this:

export CHROMIUM_FLAGS="$CHROMIUM_FLAGS --disable-gpu-compositing"

It's possible another one of the hundreds of flags might fix this issue better, but I don't really have time to go through this entire, incomplete, and unofficial list (!?!). Signal Desktop is a similar problem, and doesn't reuse those flags (because of course it doesn't). Instead I had to rewrite the wrapper script in /usr/local/bin/signal-desktop to use this instead:

exec /usr/bin/flatpak run --branch=stable --arch=x86_64 org.signal.Signal --disable-gpu-compositing "$@"

This was mostly done in this Puppet commit. I haven't figured out the root of this problem. I did try using picom and xcompmgr; they both suffer from the same issue. Another Debian testing user on Wayland told me they haven't seen this problem, so hopefully this can be fixed by switching to wayland.

Graphics card hangs I believe I might have this bug which results in a total graphical hang for 15-30 seconds. It's fairly rare so it's not too disruptive, but when it does happen, it's pretty alarming. The comments on that bug report are encouraging though: it seems this is a bug in either mesa or the Intel graphics driver, which means many people have this problem so it's likely to be fixed. There's actually a merge request on mesa already (2022-12-29). It could also be that bug because the error message I get is actually:

Jan 20 12:49:10 angela kernel: Asynchronous wait on fence 0000:00:02.0:sway[104431]:cb0ae timed out (hint:intel_atomic_commit_ready [i915]) 
Jan 20 12:49:15 angela kernel: i915 0000:00:02.0: [drm] GPU HANG: ecode 12:0:00000000 
Jan 20 12:49:15 angela kernel: i915 0000:00:02.0: [drm] Resetting chip for stopped heartbeat on rcs0 
Jan 20 12:49:15 angela kernel: i915 0000:00:02.0: [drm] GuC firmware i915/adlp_guc_70.1.1.bin version 70.1 
Jan 20 12:49:15 angela kernel: i915 0000:00:02.0: [drm] HuC firmware i915/tgl_huc_7.9.3.bin version 7.9 
Jan 20 12:49:15 angela kernel: i915 0000:00:02.0: [drm] HuC authenticated 
Jan 20 12:49:15 angela kernel: i915 0000:00:02.0: [drm] GuC submission enabled 
Jan 20 12:49:15 angela kernel: i915 0000:00:02.0: [drm] GuC SLPC enabled

It's a solid 30 seconds graphical hang. Maybe the keyboard and everything else keeps working. The latter bug report is quite long, with many comments, but this one from January 2023 seems to say that Sway 1.8 fixed the problem. There's also an earlier patch to add an extra kernel parameter that supposedly fixes that too. There's all sorts of other workarounds in there, for example this:

echo "options i915 enable_dc=1 enable_guc_loading=1 enable_guc_submission=1 edp_vswing=0 enable_guc=2 enable_fbc=1 enable_psr=1 disable_power_well=0"   sudo tee /etc/modprobe.d/i915.conf

from this comment... So that one is unsolved, as far as the upstream drivers are concerned, but maybe could be fixed through Sway.

Weird USB hangs / graphical glitches I have had weird connectivity glitches better described in this post, but basically: my USB keyboard and mice (connected over a USB hub) drop keys, lag a lot or hang, and I get visual glitches. The fix was to tighten the screws around the CPU on the motherboard (!), which is, thankfully, a rather simple repair.

USB docks are hell Note that the monitors are hooked up to angela through a USB-C / Thunderbolt dock from Cable Matters, with the lovely name of 201053-SIL. It has issues, see this blog post for an in-depth discussion.

Shipping details I ordered the Framework in August 2022 and received it about a month later, which is sooner than expected because the August batch was late. People (including me) expected this to have an impact on the September batch, but it seems Framework have been able to fix the delivery problems and keep up with the demand. As of early 2023, their website announces that laptops ship "within 5 days". I have myself ordered a few expansion cards in November 2022, and they shipped on the same day, arriving 3-4 days later.

The supply pipeline There are basically 6 steps in the Framework shipping pipeline, each (except the last) accompanied with an email notification:

1. pre-order
2. preparing batch
3. preparing order
4. payment complete
5. shipping
6. (received)

This comes from the crowdsourced spreadsheet, which should be updated when the status changes here. I was part of the "third batch" of the 12th generation laptop, which was supposed to ship in September. It ended up arriving on my door step on September 27th, about 33 days after ordering. It seems current orders are not processed in "batches", but in real time, see this blog post for details on shipping.

Shipping trivia I don't know about the others, but my laptop shipped through no less than four different airplane flights. Here are the hops it took:

• Taoyuan, Taiwan 2022-09-23
• Anchorage, Alaska, USA (?!) 2022-09-24
• Memphis, Tennessee, USA 2022-09-25
• Winnipeg, Manitoba, Canada (!! back the wrong way!) 2022-09-26
• Mirabel, Qu bec, Canada 2022-09-27
• Montr al, Qu bec, Canada

I can't quite figure out how to calculate exactly how much mileage that is, but it's huge. The ride through Alaska is surprising enough but the bounce back through Winnipeg is especially weird. I guess the route happens that way because of Fedex shipping hubs. There was a related oddity when I had my Purism laptop shipped: it left from the west coast and seemed to enter on an endless, two week long road trip across the continental US.

Other resources

• dock questions:
  • list of compatible USB-C docks but beware of the above compatibility problems on the 12th gen
  • see also this comprehensive post on USB/TB/DP/docks which has a section on the Framework specifically
  • anelki recommended the OWC docks which primarily target Macs but apparently "make really good ones"
  • someone else recommended buying "Thunderbolt" docks instead of "USB-C" as the latter don't necessarily include the former, recommending CalDigit docks
• mods:
  • desktop mod (from this discussion), also a normal desktop adapter to reuse an existing case (from this thread)
  • mainboard case (official!)
  • battery case (!), the verge has extra photos of the mainboard and battery cases
  • tablet mod (kind of clunky, but works!)
  • keyboard mod (i.e. turn the Framework keyboard, touch pad, fingerprint reader and power buttons into a "normal" USB keyboard and hub)
  • triple screen laptop mod (video)
  • Thinkpad 701C transplant
  • Braille laptop
• Debian installation report, has good tips on the firmware hacks necessary
• Excellent 12th gen review from an Arch Linux user
• cool expansion port mods:
  • empty drawer
  • dual USB-C (mockup only), expansion hub (just an idea, references other discussions), actually seriously considered by Framework, limited by existing chipsets for now
  • full-size SD card reader
  • magnetic charger
  • Yubikey 5 case and solokey case
  • screwdriver
  • Ethernet (official, back-order as of 2022-09-13, now shipping as of 2023)
  • votes seem to go towards Ethernet and full-sized SD card reader
  • 3D printed expansion card holder
  • LTE modem card (design stage)
  • check out this forum category for a cornucopia of those
• upstream resources:
  • community forum, lots of information, much support, wow!
  • knowledge base
  • repair guides
  • Linux-specific guides
  • blog (RSS)
  • chat is on Discord, but bridged with Matrix, there's talk of bridging it with IRC as well, for now there's a handful of us in #framework on https://libera.chat/
  • GitHub organization, interesting repositories include the Expansion Cards, Input Modules, Expansion Bay, mainboard, EmbeddedController

• Where Flathub is today as a strong ecosystem with 2,000 apps
• Our progress on evolving Flathub from a build service to an app store
• The economic barrier to growing the ecosystem, and its consequences
• What s next to overcome our challenges with focused initiatives