4

Dell 32″ 4K Monitor and DisplayPort Switch

After determining that the Philips 43″ monitor was too large for my taste as well as not having a clear enough display [1] I bought a Dell 32″ 4K monitor for $499 on the 1st of July 2022. That monitor has been working nicely for almost a year now, for DisplayPort it’s operation is perfect and 32″ seems like an ideal size for my use. There is one problem that both HDMI ports will sometimes turn off for about half a second, I’ve tested on both ports and on multiple computers as well as a dock and it gives the same result so it’s definitely the monitor. The problem for me is that the most casual inspection won’t reveal the problem and the monitor is large and difficult to transport as I’ve thrown out the box. If I had this sort of problem with a monitor at work I’d add it to the list of things for Dell to fix next time they visit the office or use one of the many monitor boxes available to ship it back to them. But for home use it’s more of a problem for me. The easiest solution is to avoid HDMI.

A year ago I blogged about using DDC to switch monitor inputs [2], I had that running with a cheap USB switch since then to allow a workstation and a laptop to share the same monitor, keyboard, and mouse. Recently I got a USB-C dock that allows a USB-C laptop to talk to a display via DisplayPort as opposed to the HDMI connector that’s built in. But my Dell monitor only has one DisplayPort input.

So I have just bought a DisplayPort and USB KVM switch via eBay for $52, a reasonable price given that last year such things were well over $100. It has ports for 3 USB devices which is better than my previous setup of a USB switch with only a single port that I used with a 3 port hub for my keyboard and mouse.

the DisplayPort switch is described as doing 4K at 60Hz, I don’t know how it will perform with a 5K monitor, maybe it will work at 30Hz or 40Hz. But currently Dell 5K monitors are at $2,500 and 6K monitors are about $3,800 so I don’t plan to get one of them any time soon.

2

Genesis GV60

I recently test drove a Genesis GV70, but the GV60 [1] which I didn’t test drive is a nicer car.

The GV70 and GV60 are all electric so they are quiet and perform well. The GV70 has a sun-roof that opens, it was the first car I’ve driven like that and I decided I don’t like it. Having the shade open so I can see the sky while stuck in a traffic jam is nice though. The GV60 has a non-opening sun-roof with a shade that can be retracted, this is a feature I’d really like to have in my next car.

Electric cars as a general rule have good acceleration and are quiet, the GV70 performed as expected in that regard. It has a head-up display projected on the windscreen for the speed and the speed limit on the road in question which is handy. When driving in a car park it showed images from all sides which is really handy, I wish I had explored that feature more.

The console is all electronic with a TFT display instead of mechanical instruments but the only significant difference this makes in driving is that when a turn indicator is used the console display shows a video feed for the blind-spot that matches the lane change direction. This is a significant safety feature and will reduce the incidence of collisions. But the capabilities of the hardware seem under utilised, hopefully they will release a software update at some future time to do more with it.

The most significant benefit of the GV60 over the GV70 is that it has cameras instead of mirrors at the sides of the car. This reduces drag and also removes the need to adjust mirrors to match the height of the driver. Also for driver instruction the instructor and learner get to see the same view. A logical development of such cars is an expansion pack for instruction that has displays in the passenger seat to show the instructor the same instrument view as the driver sees.

The minimum list driveaway price for the GV60 is $117,171.50 and for the GV70 it is $138,119.89 – both of which are more than I’m prepared to pay for a car. The GV60 apparently can be started by fingerprint which seems like a bad idea given the poor security of fingerprint sensors, but as regular car keys tend not to be too difficult to work around it probably doesn’t matter. The Genesis web site makes it difficult to find the ranges of electric cars which is surprising. A Google search suggests that the GV60 can do 466Km and the GV70 can do 410Km which are both reasonable numbers and nothing to be ashamed of.

The GV70 was a fun car to drive and the GV60 looks like it would be even better. I recommend that everyone who likes technology take one for a test drive, but for my own use I’m looking for something that costs less than half as much.

1

Write a blog post in the style of Russell Coker

Feeling a bit bored I asked ChatGPT “Write a blog post in the style of Russell Coker” and the result is in the section below. I don’t know if ChatGPT knows that the person asking the question is the same as the person being asked about. If a human had created that I’d be certain that “great computer scientist and writer” was an attempt at flattery, for a machine I’m not sure.

I have not written a single book, but I expect that in some alternate universe some version of me has written several. I don’t know if humans would describe my writing as being known for “clarity, precision, and depth”. I would not be surprised if “no-one else wrote about it so I guess I’m forced to read what he wrote” would be a more common response.

The actual “article” part doesn’t seem to be in my style at all. Firstly it’s very short at only 312 words, while I have written some short posts most of them are much longer. To find this out I did some MySQL queries to get the lengths of posts (I used this blog post as inspiration [1]). Note that multiple sequential spaces counts as multiple words.

# 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';

It turns out that there are 333/1521 posts that are less than 312 words and the average length is 665 words. Of the shortest posts a large portion were written before Twitter became popular and had the sort of unimportant content that Twitter is good for.

It seems ironic that ChatGPT says that I'm known for "depth" and then writes a short post allegedly in my style.

As for the actual content of the "post", it's not something that I greatly disagree with but it's definitely not something I'd write. If some manager or marketing person wrote something like this and asked my opinion I'd probably suppress a sigh and say it's OK for it's target market.

I think that free software is better in many ways and for many reasons and that separately from the issue of merit free software is important because of the ways that it is used. We could debate various issues related to the quality of free software vs proprietary software but even people who don't believe that free software is of high quality have to admit that software that runs most mobile phones and most web servers is important. As much as I dislike Windows most desktop PCs and laptops run it so I can't claim it to be unimportant. So my first disagreement with the content is the issue of importance vs quality.

One thing that ChatGPT is known for is weak arguments that appear convincing. "This diversity often leads to better software, as bugs are found and fixed faster, and new features are added more quickly" could be opposed by "the payment for proprietary software often leads to better software, as bugs are found and fixed faster, and new features are added more quickly". I think that any case where "feature of option A gives this list of good results" can be rewritten as "feature of the opposite of option A gives the same list of good results" and be equally convincing is a poor argument. Also any argument that seems to rest on "free software is all written by hobbyists" is ignoring the demands of users who need things done on a non-hobby timeframe, the many profitable companies that develop and support free software, and the employment status of a large portion of my Facebook friends (many of whom are paid for ~2000 hours a year of free software development and many more of whom have paid free software development as part of their work supporting the use of free software). Really the entire blog post it wrote seems to me like something a human might write if their boss assigned them to write about the benefits of free software, and that they would then write a new article saying the exact opposite if their boss asked them to.

Finally I prefer the term "free software" to "open source software". The difference doesn't seem important to some people, but any being that doesn't know the difference won't do well at impersonating me.

ChatGPT Result

Hello everyone, I'm ChatGPT, and today I'm going to try my best to write a blog post in the style of the great computer scientist and writer, Russell Coker.

Russell Coker is a renowned software engineer and writer, who is best known for his contributions to the Linux community, especially the Debian project. He has authored several books and articles on topics ranging from security to software engineering, and his writing style is known for its clarity, precision, and depth.

So, without further ado, let's dive into the topic of this blog post, which is the importance of open-source software.

Open-source software is software whose source code is available for anyone to inspect, modify, and distribute. This means that anyone can use, study, and improve the software, without any restrictions or fees. Open-source software has been around for a long time, but it has become more prevalent and important in recent years, thanks to the rise of the internet and the digital economy.

Open-source software has several benefits, both for individuals and for society as a whole. One of the most significant benefits is that it fosters innovation and collaboration. When software is open-source, it means that anyone can contribute to it, which leads to a diverse range of perspectives and ideas. This diversity often leads to better software, as bugs are found and fixed faster, and new features are added more quickly.

Another benefit of open-source software is that it is often more secure than proprietary software. Because the source code is available for anyone to inspect, vulnerabilities and security flaws can be found and fixed faster. This means that open-source software is often more reliable and trustworthy than proprietary software, which may have hidden backdoors or vulnerabilities that can be exploited by attackers.

Open-source software is also often more cost-effective than proprietary software. Because it is free to use and distribute, organizations can save money on licensing fees and other costs associated with proprietary software. This can be particularly important for non-profit organizations or small businesses that may not have the resources to invest in expensive software licenses.

In conclusion, open-source software is an important part of the digital landscape, and its benefits are numerous. Whether you are a software developer, a business owner, or an individual user, open-source software has something to offer. So, the next time you are looking for software to use, consider open-source options, and help support the collaborative and innovative spirit of the open-source community.

New 18 Core CPU and NVMe

I just got a E5-2696 v3 CPU for my ML110 Gen9 home workstation, this has a Passmark score of 23326 which is almost 3 times faster than the E5-2620 v4 which rated 9224. Previously it took over 40 minutes real time to compile a 6.10 kernel that was based on the Debian kernel configuration, now it takes 14 minutes of real time, 202 minutes of user time, and 37 minutes of system CPU time. That’s a definite benefit of having a faster CPU, I don’t often compile kernels but when I do I don’t want to wait 40+ minutes for a result. I also expanded the system from 96G of RAM to 128G, most of the time I don’t need so much RAM but it’s better to have too much than too little, particularly as my friend got me a good deal on RAM. The extra RAM might have helped improve performance too, going from 6/8 DIMM slots full to 8/8 might help the CPU balance access.

That series of HP machines has a plastic mounting bracket for the CPU, see this video about the HP Proliant Smart Socket for details [1]. I was working on this with a friend who has the same model of HP server as I do, after buying myself a system I was so happy with it that I bought another the same when I saw it going for a good price and then sold it to my friend when I realised that I had too many tower servers at home. It turns out that getting the same model of computer as a friend is a really good strategy so then you can work together to solve problems with it. My friend’s first idea was to try and buy new clips for the new CPUs (which would have delayed things and cost more money), but Reddit and some blog posts suggested that you can just skip the smart-socket guide clip and when the chip was resting in the socket it felt secure as the protrusions on the sides of the socket fit firmly enough into the notches in the CPU to prevent it moving far enough to short a connection. Testing on 2 systems showed that you don’t need the clip. As an aside it would be nice if Intel made every CPU that fits a particular socket have the same physical dimensions so clips and heatsinks can work well on all CPUs.

The TDP of the new CPU is 145W and the old one was 85W. One would hope that in a server class system that wouldn’t make a lot of difference but unfortunately the difference was significant. Previously I could have the system running 7/8 cores with BOINC 24*7 and I wouldn’t notice the fans being louder. It is possible that 100% CPU use on a hot day might make the fans sound louder if I didn’t have an air-conditioner on that was loud enough to drown them out, but the noteworthy fact is that with the previous CPU the system fans were a minor annoyance. Now if I have 16 cores running BOINC it’s quite loud, the sort of noise that makes most people avoid using tower servers as workstations! I’ve found that if I limit it to 4 or 5 cores then the system is about as quiet as it was before. As a rough approximation I can use as much CPU power as before without making the fans louder but if I use more CPU power than was previously available it gets noisy.

I also got some new NVMe devices, I was previously using 2*Crucial 1TB P1 NVMes in a BTRFS RAID-1 and now I have 2*Crucial 1TB P3 NVMes (where P1 is the slowest Crucial offering, P3 is better and more expensive, P5 is even better, etc). When doing the BTRFS migrations to move my workstation to new NVMe devices and my server to the old NVMe devices I found that the P3 series seem to have a limit of about 70MB/s for sustained random writes and the P1 series is about 35MB/s. Apparently with the cheaper NVMe devices they slow down if you do lots of random writes, pity that all the review articles talking about GB/s speeds don’t mention this. To see how bad reviews are Google some reviews of these SSDs, you will find a couple of comment threads on places like Reddit of them slowing down with lots of writes and lots of review articles on well known sites that don’t mention it. Generally I’d recommend not upgrading from P1 to P3 NVMe devices, the benefit isn’t enough to cover the effort. For every capacity of NVMe devices the most expensive devices cost more than twice as much as the cheapest devices, and sometimes it will be worth the money. Getting the most expensive device won’t guarantee great performance but getting cheap devices will guarantee that it’s slow.

It seems that CPU development isn’t progressing as well as it used to, the CPU I just bought was released in 2015 and scored 23,343 according to Passmark [2]. The most expensive Intel CPU on offer at my local computer store is the i9-13900K which was released this year and scores 62,914 [3]. One might say that CPUs designed for servers are different from ones designed for desktop PCs, but the i9 in question has a “TDP Up” of 253W which is too big for the PSU I have! According to the HP web site the new ML110 Gen10 servers aren’t sold with a CPU as fast as the E5-2696 v3! In the period from 1988 to about 2015 every year there were new CPUs with new capabilities that were worth an upgrade. Now for the last 8 years or so there hasn’t been much improvement at all. Buy a new PC for better USB ports or something not for a faster CPU!

4

Intel vs AMD

In response to a post about my latest laptop I had someone ask why I chose an Intel CPU. I’ve been a fan of the Thinkpad series of laptops since the 90s. They have always seemed well constructed (given the constraints of being light etc) and had a good feature set. Also I really like the TrackPoint. I’ve been a fan of the smaller Thinkpads since I got an X-301 from e-waste [1] and the X1-Carbon series is the latest and greatest line of small Thinkpads.

AMD makes some nice laptop CPUs which appear to have low power use and good performance particularly for smaller numbers of threads, it seems that generally AMD CPUs are designed for fewer cores with higher performance per core which is good for laptops. But Lenovo only makes the Thinkpad Carbon X1 series with Intel CPUs so choosing that model of laptop means choosing Intel. It could be that for some combination of size, TDP, speed, etc Intel just happens to beat AMD for all the times when Lenovo was designing a new motherboard for the Carbon X1. But it seems more likely that Intel has been lobbying Lenovo for this. It would be nice if there was an anti-trust investigation into Intel, everyone who’s involved in the computer industry knows of some of the anti-competitive things that they have done.

Also it would be nice if Lenovo started shipping laptops with ARM CPUs across their entire range. But for the moment I guess I have to keep buying laptops with Intel CPUs.

T320 iDRAC Failure and new HP Z640

The Dell T320

Almost 2 years ago I made a Dell PowerEdge T320 my home server [1]. It was a decent upgrade from the PowerEdge T110 II that I had used previously. One benefit of that system was that I needed more RAM and the PowerEdge T1xx series use unbuffered ECC RAM which is unreasonably expensive as well as the DIMMs tending to be smaller (no Load Reduced DIMMS) and only having 4 slots. As I had bought two T320s I put all the RAM in a single server getting a total of 96G and then put some cheap DIMMs in the other one and sold it with 48G.

The T320 has all the server reliability features including hot-swap redundant PSUs and hot-swap hard drives. One thing it doesn’t have redundancy on is the motherboard management system known as iDRAC. 3 days ago my suburb had a power outage and when power came back on the T320 gave an error message about a failure to initialise the iDRAC and put all the fans on maximum speed, which is extremely loud. When a T320 is running in a room that’s not particularly hot and it doesn’t have SAS disks it’s a very quiet server, one of the quietest I’ve ever owned. When it goes into emergency cooling mode due to iDRAC failure it’s loud enough to be heard from the other end of the house with doors closed in between.

Googling this failure gave a few possible answers. One was for some combinations of booting with the iDRAC button held down, turning off for a while and booting with the iDRAC button held down, etc (this didn’t work). One was for putting a iDRAC firmware file on the SD card so iDRAC could automatically load it (which I tested even though I didn’t have the flashing LED which indicates that it is likely to work, but it didn’t do anything). The last was to enable serial console and configure the iDRAC to load new firmware via TFTP, I didn’t get a iDRAC message from the serial console just the regular BIOS stuff.

So it looks like I’ll have to sell the T320 for parts or find someone who wants to run it in it’s current form. Currently to boot it I have to press F1 a few times to bypass BIOS messages (someone on the Internet reported making a device to key-jam F1). Then when it boots it’s unreasonably loud, but apparently if you are really keen you can buy fans that have temperature sensors to control their own speed and bypass the motherboard control.

I’d appreciate any advice on how to get this going. At this stage I’m not going to go back to it but if I can get it working properly I can sell it for a decent price.

The HP Z640

I’ve replaced the T320 with a HP Z640 workstation with 32G of RAM which I had recently bought to play with Stable Diffusion. There were hundreds of Z640 workstations with NVidia Quadro M6000 GPUs going on eBay for under $400 each, it looked like a company that did a lot of ML work had either gone bankrupt or upgraded all their employees systems. The price for the systems was surprisingly cheap, at regular eBay prices it seems that the GPU and the RAM go for about the same price as the system. It turned out that Stable Diffusion didn’t like the video card in my setup for unknown reasons but also that the E5-1650v3 CPU could render an image in 15 minutes which is fast enough to test it out but not fast enough for serious use. I had been planning to blog about that.

When I bought the T320 server the DDR3 Registered ECC RAM it uses cost about $100 for 8*8G DIMMs, with 16G DIMMs being much more expensive. Now the DDR4 Registered ECC RAM used by my Z640 goes for about $120 for 2*16G DIMMs. In the near future I’ll upgrade that system to 64G of RAM. It’s disappointing that the Z640 only has 4 DIMM sockets per CPU so if you get a single-CPU version (as I did) and don’t get the really expensive Load Reduced RAM then you are limited to 64G. So the supposed capacity benefit of going from DDR3 to DDR4 doesn’t seem to apply to this upgrade.

The Z640 I got has 4 bays for hot-swap SAS/SATA 2.5″ SSD/HDDs and 2 internal bays for 3.5″ hard drives. The T320 has 8*3.5″ hot swap bays and I had 3 hard drives in them in a BTRFS RAID-10 configuration. Currently I’ve got one hard drive attached via USB but that’s obviously not a long-term solution. The 3 hard drives are 4TB, they have worked since 4TB was a good size. I have a spare 8TB disk so I could buy a second ($179 for a shingle HDD) to make a 8TB RAID-1 array. The other option is to pay $369 for a 4TB SSD (or $389 for a 4TB NVMe + $10 for the PCIe card) to keep the 3 device RAID-10. As tempting as 4TB SSDs are I’ll probably get a cheap 8TB disk which will take capacity from 6TB to 8TB and I could use some extra 4TB disks for backups.

I haven’t played with the AMT/MEBX features on this system, I presume that they will work the same way as AMT/MEBX on the HP Z420 I’ve used previously [2].

Update:

HP has free updates for the BIOS etc available here [3]. Unfortunately it seems to require loading a kernel module supplied by HP to do this. This is a bad thing, kernel code that isn’t in the mainline kernel is either of poor quality or isn’t licensed correctly.

I had to change my monitoring system to alert on temperatures over 100% of the “high” range while on the T320 I had it set at 95% of “high” and never got warnings. This is disappointing, enterprise class gear running in a reasonably cool environment (ambient temperature of about 22C) should be able to run all CPU cores at full performance without hitting 95% of the “high” temperature level.

2

Samsung Galaxy Note 10.1 2014

In May 2014 I bought a Samsung Galaxy Note 10.1 2014 edition tablet (wikipedia page [1]) with 32G of storage. It’s display is 2560×1600 resolution which still compares well to the latest tablets. The Galaxy Tab S8 [2] is the latest high-end tablet series from Samsung and the 11 inch tablet in that series also has a 2560×1600 giving it a slightly lower DPI! The latest series also has 12.4″ and 14.6″ tablets with resolutions of 2800×1752 and 2960×1848 respectively. Obviously if you want a 14″ tablet then the latest offerings are good, but if you want a 10″ or 11″ tablet then Samsung hasn’t improved much. The Note 10.1 has 3G of RAM and a choice of 16G, 32G, or 64G of storage. The latest Tab S8 tablets have 8G to 16G of RAM and 128G to 512G of internal storage, which are great if you need such things. For many tasks 3G of RAM is quite adequate and as I chose the 32G model I haven’t had a problem with storage. The s-pen is a feature of this tablet which is also on the latest high-end Samsung tablets, it is useful for accessing small elements in web sites designed for desktop use and for graphics editing.

One noteworthy feature of this tablet is the fact that when in “landscape” orientation it has speakers on each side, which is the correct layout as the vast majority of video with stereo sound is in a landscape orientation.

After using that tablet for about 4 years I bought myself a newer tablet and gave it to my wife. She has since passed it on to another relative who is using it regularly. That tablet seems to have lasted well still being quite usable when it’s almost 9 years old. The price including delivery was $579, that works out to about $1.30 per week (disregarding interest and inflation). According to the Reserve Bank of Australia inflation calculator [3] $579 in 2014 is equivalent to $652 in 2021, they don’t have results for later than 2021 so I’ll assume it would be $675 in 2023.

Currently the main problems with this tablet are lack of USB-C support (which means it’s difficult to connect to an external display among other things) and lack of a recent version of Android, 4.4.2 was the latest OTA update available. The XDA Developers forum has a section for this tablet [4] which includes discussion of updates to Android 5.x for devices which didn’t get it automatically and for upgrading to very recent Android versions in LineageOS. I’m idly considering one of those options, but for the current user the Google Play store is a requirement.

Newer Samsung Tablets

The current equivalent Samsung tablet is the Galaxy Tab S8 which is currently being sold for $1055 which is 56% higher than the inflation adjusted price of my tablet. I don’t think this is reasonable given that I bought it 7 months after release and it’s now 11 months since the release of the Tab S8. The Tab S8 has more RAM, more storage, and a faster CPU due to improvements over the entire computer industry – replacing old parts with newer versions of the same things (including changing to USB-C) doesn’t justify a price rise. Increasing RAM size by a factor of 3-5 and increasing storage by a factor of 8 over the last 9 years doesn’t match the industry trends for PCs, also as an aside my latest laptop only has 8G of RAM and works well for much more demanding tasks. The Tab S8 series also has significantly better cameras, but I don’t think that’s a big deal, the 2Mp front camera in my tablet can provide adequate quality for video conferencing and usually saturate the upload bandwidth and again that’s an issue of the entire industry moving to newer hardware. I don’t think it’s bad to take a form factor and display that works well and put newer versions of the CPU, RAM, storage, cameras, and OS on it. But asking for 56% more money for the updated tablet seems unreasonable.

The current S8 Ultra is going for $1760 and the S8+ is $1479. I think those are ridiculous prices for tablets as there is a decent range of new laptops that are cheaper. I believe that the purpose of a tablet is to be easy to carry and quick to start using (no waiting for a laptop to connect to wifi after leaving suspend). The largest of the S8 Tabs is about the same length and width as a Thinkpad X1 Carbon with the benefits being that it’s thinner and lighter, but if you got a tablet case with keyboard then it would be thicker and heavier. The S8 seems like bad value for money and the S8+ and S8 Ultra don’t seem to compare well to laptops and Chromebooks with touch screens unless you have a specific need for Android tablet apps.

If Samsung are going to just make new tablets without any significant improvements other than refreshing to the latest CPU, RAM, storage, and Camera technology and force users to upgrade via a lack of new OS support then they shouldn’t charge so much. Stick well below $1000 and people will be more inclined to replace items, expensive items are expected to last.

Conclusion

Buying this tablet was definitely a good choice. It has performed well for many years and after a couple of years of light use it’s back in daily use again. The value for money it offered was significantly greater than newer tablets, when it was new it was really high-end, the current S8 Tab series of tablets aren’t anything special when compared to other tablets.

7

Pixel 6A

I have just bought a Pixel 6A [1] for my wife. It’s one of the latest Google phones that was released almost at the same time as the Pixel 7 series, so if you want to spend a lot of money on a phone that’s the latest and greatest then the Pixel 7 and Pixel 7 Pro are the options, but if you want to save some money and don’t need something really high end then the Pixel 6A is a good option.

The one I bought cost $550 when I bought it from Google which seemed like a good deal when it was advertised as being discounted from $750. Later I discovered that other retailers were selling it for $500 or for $550 when bundled with a Chromecast. Also one of the other retailers was a company that I could get discount gift cards for. So this is the type of item you should really shop around for. It doesn’t come with a charger so you don’t have the gray-market disadvantage of getting yet another charger that doesn’t fit the sockets in your country.

The main new feature of this phone is a fingerprint scanner built in to the screen. I don’t think this is a good thing, sure it’s neat technology to both display pictures and read fingerprints through the same piece of glass but there are benefits to using a different location. Huawei phones with a fingerprint reader at the rear of the phone allow the user to answer calls, drag down the notifications list, and scroll sideways via touching the fingerprint reader. So the Pixel 6A clearly gives less functionality than some Huawei phones in this regard.

One major annoyance with the phone is a combination of the phone hardware and Android 13 which gives no back arrow (swipe sideways) and no button to get the task list (swipe upwards at the correct speed from the bottom of the screen). The Android 12 way of swiping up from the bottom of the screen to get buttons for back, task-list, and home-screen is much better IMHO. Hopefully they will release a software update to make this a configuration option.

Generally this is a nice phone, but the lack of buttons for back and task-list is annoying. Maybe the lack of buttons is something you can get used to after using it for a while. But millions of people just taking whatever companies like Google offer isn’t what I imagined when I first hoped for a large portion of the world using Linux. On PCs we have a choice between KDE, GNOME, and other UIs. It would be nice if we had similar choices on phones.

4

USB-PD and GaN

photo of 2 USB-PD chargers

A recent development is cheap Gallium Nitride based power supplies that provide better efficiency in a smaller space than other technologies. Kogan recently had a special on such devices so I decided to try them out with my new Thinkpad X1 Carbon Gen 5 [1]. Google searches for power supplies for that Thinkpad included results for 30W PSUs which implies that any 30W USB-C PSU should work.

I bought a 30W charger for $10 that can supply 15V/2A or 20V/1.5A on a single USB-C port or 15W on the USB-C port and 15W on the USB-2 port at the same time and expected it to work as a laptop charger. Unfortunately it didn’t, I don’t know whether the adverts for 30W Thinkpad PSUs were false or whether the claim of the GaN charger I bought being 30W was false, all I know is that the KDE power applet said that the PSU couldn’t supply enough power.

I then bought a 68W charger for $28 that can supply 20.0V/3.0A on a single USB-C port if the USB-2 port isn’t used and 50W on the USB-C port if the USB-2 port is also being used. This worked well which wasn’t a great surprise as I had previously run the laptop on 45W PSUs. If I connect a phone to the USB-2 port while the laptop is being charged then the laptop will be briefly cut off, presumably the voltage and current are being renegotiated when that happens.

As you can see the 68W charger is significantly larger than the 30W charger, but still small enough to easily fit in a jacket pocket and smaller than a regular laptop charger. One of my uses for this will be to put it in a jacket pocket when I have my laptop in another pocket. Another use will be for charging in my car as the cables from the inverter to convert 12VDC to 240VAC takes enough space. I will probably get a ~50W USB-PD charger that connects to a car cigarette lighter socket when a GaN version of such a charger becomes available.

Thinkpad X1 Carbon Gen5

Gen1

Since February 2018 I have been using a Thinkpad X1 Carbon Gen1 [1] as my main laptop. Generally I’ve been very happy with it, it’s small and light, has good performance for web browsing etc, and with my transition to doing all compiles etc on servers it works well. When I wrote my original review I was unhappy with the keyboard, but I got used to that and found it to be reasonably good.

The things that I have found as limits on it are the display resolution as 1600*900 isn’t that great by modern standards (most phones are a lot higher resolution), the size (slightly too large for the pocket of my Scott e Vest [2] jacket), and the lack of USB-C. Modern laptops can charge via USB-C/Thunderbolt while also doing USB and DisplayPort video over the same cable. USB-C monitors which support charging a laptop over the same cable as used for video input are becoming common (last time I checked the Dell web site for many models of monitor there was a USB-C one that cost about $100 more). I work at a company with lots of USB-C monitors and docks so being able to use my personal laptop with the same displays when on breaks is really handy.

A final problem with the Gen1 is that it has a proprietary and unusual connector for the SSD which means that a replacement SSD costs about what I paid for the entire laptop. Ever since the SSD gave a BTRFS checksum error I’ve been thinking of replacing it.

Choosing a Replacement

The Gen5 is the first Thinkpad X1 Carbon to have USB-C. For work I had used a Gen6 which was quite nice [3]. But it didn’t seem to offer much over the Gen5.

So I started looking for cheap Thinkpad X1 Carbons of Gen5+.

A Cheap? Gen5

In July I saw an ebay advert for a Gen5 with FullHD display for $370 or nearest offer, with the downside being that the BIOS password had been lost. I offered $330 and the seller accepted, in retrospect that was unusually cheap and should have been a clue that I needed to do further investigation. It turned out that resetting the BIOS password is unusually difficult as it’s in the TPM so the system would only boot Windows. When I learned that I should have sold the laptop to someone who wanted to run Windows and bought another. Instead I followed some instructions on the Internet about entering a wrong password multiple times to get to a password recovery screen, instead the machine locked up entirely and became unusable for windows (so don’t do that).

Then I looked for ways of fixing the motherboard. The cheapest was $75.25 for a replacement BIOS flash chip that had a BIOS that didn’t check the validity of passwords. The aim was to solder that on, set a new password (with any random text being accepted as the old password), then solder the old one back on for normal functionality. It turned out that I’m not good at fine soldering, after I had hacked at it a friend diagnosed the chip and motherboard to probably both be damaged (he couldn’t get it going).

The end solution was that my friend found a replacement motherboard for $170 from China. This gave a total cost of $575.25 for the laptop which is more than the usual price of a Gen6 and more than I expected to pay. In the past when advocating buying second hand or refurbished laptops people would say “what happens if you get one that doesn’t work properly”, the answer to that question is that I paid a lot less than the new cost of $2700+ for a Thinkpad X1 Carbon and got a computer that does everything I need. One of the advantages of getting a cheap laptop is that I won’t be so unhappy if I happen to drop it.

A Cheap Gen6

After the failed experiment with a replacement BIOS on the Gen5 I was considering selling it for scrap. So I bought a Gen6 from Australian Computer Traders via Amazon for $390 in August. The advert clearly stated that it was for a laptop with USB-C and Thunderbolt (Gen5+ features) but they shipped me a Gen4 that didn’t even have USB-C. They eventually refunded me but I will try to avoid buying from them again.

Finally Working

The laptop I now have has a i5-6300U CPU that rates 3242 on cpubenchmark.net. My Gen1 thinkpad has a i7-3667U CPU that rates 2378 on cpubenchmark.net, note that the cpubenchmark.net people have rescaled their benchmark since my review of the Gen1 in 2018. So according to the benchmarks my latest laptop is about 36% faster for CPU operations. Not much of a difference when comparing systems manufactured in 2012 and 2017! According to the benchmarks a medium to high end recent CPU will be more than 10* faster than the one in my Gen5 laptop, but such a CPU would cost more than my laptop cost.

The storage is a 256G NVMe device that can do sustained reads at 900MB/s, that’s not even twice as fast as the SSD in my Gen1 laptop although NVMe is designed to perform better for small IO.

It has 2*USB-C ports both of which can be used for charging, which is a significant benefit over the Gen6 I had for work in 2018 which only had one. I don’t know why Lenovo made Gen6 machines that were lesser than Gen5 in such an important way.

It can power my Desklab portable 4K monitor [4] but won’t send a DisplayPort signal over the same USB-C cable. I don’t know if this is a USB-C cable issue or some problem with the laptop recognising displays. It works nicely with Dell USB-C monitors and docks that power the laptop over the same cable as used for DisplayPort. Also the HDMI port works with 4K monitors, so at worst I could connect my Desklab monitor via a USB-C cable for power and HDMI for data.

The inability to change the battery without disassembly is still a problem, but hopefully USB-C connected batteries capable of charging such a laptop will become affordable in the near future and I have had some practice at disassembling this laptop.

It still has the Ethernet dongle annoyance, and of course the seller didn’t include that. But USB ethernet devices are quite good and I have a few of them.

In conclusion it’s worth the $575.25 I paid for it and would have been even better value for money if I had been a bit smarter when buying. It meets the initial criteria of USB-C power and display and of fitting in my jacket pocket as well as being slightly better than my old laptop in every other way.