Switch to QNAP QXG-10G2SF-CX4 network card

In the last year's review I mentioned about my plan to switch to QNAP QXG-10G2SF-CX4 dual port SFP+ PCIe Gen3 x8 network controller from the Dell 540-BBGS one. The QNAP card is based on Mellanox ConnectX-4 Lx controller, which NetBSD support was the primary reason for the replacement.

Since I have already tested this card on my main machine using Manjaro Linux and NetBSD (which even led to one NetBSD specific bugfix), I was expecting a simple drop-in replacement (I use Artix Linux in my NAS server currently). Unfortunately, it wasn't meant to be, I faced two worth to mention issues.

Dell 540-BBGS and QNAP QXG-10G2SF-CX4

The non-standard LED positions

The first issue is related to non standard LED indicators' positions. Instead of being placed on the side of the ports, they are positioned on the top of the card. Because of this, lights are completely blocked once the card is installed. It is due to the fact that the QNAP card is designed for their own NAS devices, not for normal PCs, where likely those indicators are visible. I am personally not using LED indicators often, but it may be an issue for others. I believe it may be resolvable by drilling holes in place of LED's positions, however I left it unresolved this time (there are 4 LED lights, activity and speed indicators for each port).

In addition to that, I got confused with the low profile brackets. Two of them are included in addition to full size bracket: one is standard PC style bracket, another seems to be either QNAP or some server specific. Since I replaced low profile bracket with full size one to attach it to my main PC, I got surprised by the one I found in the box upon the switch: 1) it is not bent on the "upper" side to fix it to the case 2) it has a small hole for the screw instead of the groove in a bit lower position in comparison. I forgot, that it was also a standard low profile bracket in the package (which I didn't put back to the box), instead I used QNAP specific one. Since my case uses a hinge to fix attached cards instead of screws, I drilled a small hole on this hinge aligned with bracket's hole and used a screw to fix the card. Once I realized that I have low profile bracket for a normal PC, my setup was already complete...

QNAP QXG-10G2SF-CX4 with the QNAP specific low profile bracket

Unsupported Mikrotik S+DA001 DAC cable

I do have two types of DAC cables, one is Mikrotik S+DA001 1 meter SFP+ cable, others are Ubiquiti UniFi UDC-3 3 meters cables. I used a mix of one Mikrotik and one Ubiquiti cables in my NAS , since the third one was attached to my main computer. This arrangement was required, because 1 meter was too short to reach my main computer from the switch device, however it could reach the closer placed NAS server. This cable worked well with all my previous network cards, even if Dell was showing warning regarding unsupported modules. Unfortunately, QNAP network card refused to work with it at all and showed an error instead: "port_module:249:(pid 0): Port module event[error]: module 0, Cable error, Unknown identifier". Thus, it is advisable to use either officially supported cables or make sure about their support in the community. Luckily, Ubiquiti cables are supported and work without any warnings. I needed to buy one more Ubiquiti cable to resolve the issue, which costs a bit over 20 euros for 1 meter cable with the price gradually increasing for the longer ones (up to 3 meters).

Summary

If blocked LED indicators are not an issue, the careful cable/module selection is the only important concern before buying this card. Otherwise, the card works well on all major operating systems out of the box without additional firmware packages needed. Software wise it didn't require any configuration changes, since interfaces are named by generic eth0/eth1 names in Linux, same as the Dell card. I only needed to update my MAC address in the router to make sure that the same IP address is assigned by DHCP server. This network controller also enables me for the potential transition to NetBSD in the future, and I do plan some initial testing later this year. Depending on the delayed NetBSD 10 release schedule, the final switch won't likely happen until the middle or even end of the next year though (in case of successful testing). Finally, I plan to add few iperf3 test results in next week or two, but I do expect similar results to the Dell card.

QNAP QXG-10G2SF-CX4

2021 (and beyond) in review

This article is incredibly late this year, thus it touches some events from the first half  of 2022 as well. The blog was quite dormant last year due to personal factors, however, they were few interesting developments in hardware/software side, including new purchases.

HP Color LaserJet Pro MFP M183fw

The need for the printer was getting more and more difficult to ignore, because of this I finally decided to buy one last year. Since, I got burned by the inkjet printers in the past, I have been looking for the laser one this time. Preferably, I wanted a multi-function device with a scanner, with options for network connection, including WiFi support. Colour support was a must too. Despite having pretty clear requirements, it proved to be pretty challenging to find one with all those features available. Laser printers tend to be business oriented, and they tend to be big, heavy, as well as expensive. In addition to previous expectations, I was also was trying to ensure that printer supplies will be readily available at least in the near future. There were some attractive options until I have checked availability of toners' cartridges. Eventually I ended up choosing HP Color LaserJet Pro MFP M183fw multi-functional printer/fax for around ~300 euros at the time of purchase. I definitely don't need fax, but other than that, it had all the points covered above. It even has Web UI interface for management. The biggest disadvantage is an old style physical printer management panel with the small screen. It is a bit cumbersome to use, but the dimensions are relatively compact, just slightly bigger than a typical ink-jet multi-functional devices. Windows and Linux were quite well supported, I could print and scan using network connection, however scanning quality on Linux was disappointing, forcing me to use Windows, if detailed scanning is needed. Printing is fine in both OSes though. I didn't manage to make it work in NetBSD (using network), however it was not essential for my case, thus I didn't try too hard. It's neat feature is it's ability to print from the Android phone, however it requires to create and use an HP account, which is honestly in my opinion, an unnecessary prerequisite. What is more, the HP app has issues with login operation, which redirects to the browser first, doesn't authenticate upon returning to the app. Eventually, I found out that only Opera mobile browser allows me to perform the operation. Multiple application updates didn't resolve the issue as of today. In conclusion, I am quite satisfied with the printer despite all the oddities, but some peculiarities can be a show-stopper for others, especially for Linux users. Finding cartridges may also be more difficult than I would like to, but supplies are available to buy the last time I have checked. The device is also affected by CVE-2022-3942 vulnerability without any patches available except recommendation to disable LLMNR feature, which I followed myself.

QNAP Dual-port SFP+ 10GbE network

Last year I bought one more 10Gbit network card. This time it was QNAP QXG-10G2SF-CX4 dual port SFP+ PCIe Gen3 x8 card for around 180 euros at the time of purchase. It is based on Mellanox ConnectX-4 Lx (now Nvidia) network controller, which attracted me to purchase it. This controller is supported by NetBSD and gives me an opportunity  to migrate my NAS server to this OS, as it was originally intended a decade ago :). Not sure if it will really happen soon, but the network card was the major missing piece in the puzzle. I may do some trials this year, but the final decision depends on various performance, stability and compatibility factors. On NetBSD I hit an issue that it wasn't working on current branch (future NetBSD 10 release), though it did on netbsd-9 one. After some investigation, it appeared to be due to my CPU core count, which was not a a power of 2  (6/12 cores/threads). RQ Table size was based on number of cores, though controller requires it to be a power of 2 by reference manual. Thus the patch was applied to ensure the correct number. Currently the network card is not actively used, but I am planning to swap it soon. Dell QLogic 57810 network card will go to a well deserved rest or will be sold/donated.

QNAP QXG-10G2SF-CX4 network controller

WD Blue SSD SN550 NVMe 1TB

The final significant purchase was made early this year in the form of WD Blue SN550 NVMe M.2 SSD.  I bought it for around ~100 euros. SSD doesn't have the most modern specs, nevertheless it is considerably faster than my SATA based SSD, at least on paper. I also preferred bigger capacity over more modern specifications. It is currently used as a major storage for my desktop NetBSD installation and I didn't have any visible issues with it so far. I haven't performed any speed tests though, thus I can't provide any numbers for comparison unfortunately.

WD SN550 NVMe SSD

ClockworkPi DevTerm

One of the most anticipated devices last year was a DevTerm computer. I bought the A04 model by the end of 2020, but this specific configuration appeared to be the last one to be ready for shipment. While RPi CM3 or A06 based models were shipped starting August/September of the last year, A04 shipments started around late 2021, even making some people anxious about that. I received mine in the beginning of this year. However, the whole process didn't turn out perfectly as I wanted it, starting from incorrect tracking info to a broken screen upon arrival. Moreover, I also damaged the WiFi antenna during assembly. Luckily, ClockworkPi team sent me replacements promptly without additional charge! Though I needed to wait again, I finally managed to fully assemble it as a complete working device by the end of January. A04 model is based on AllWinner H6 SoC and comes with pre-installed Clockwork OS (Armbian) Linux distribution. The device is really cute and nice, screen seems to be a bit small, but keyboard is surprisingly usable. I was hoping to use it pretty frequently, however it is not the case as of now. I did a one time attempt to boot NetBSD as well, however unsuccessfully. Likely it should be possible to run (considering that SoC is supported), but probably requires some work on boot configuration and properties, as it is the case for various specific ARM devices. Pre-installed Linux also had some peculiarities, for example, not all cores are enabled by default. It requires small script to enable them. I didn't manage to make HDMI work yet, but I believe this issue was discussed extensively in ClockworkPi forums and possibly solvable. Also I needed to install an app (or script) to change screen brightness with a simple shortcut, otherwise it was usually too low by default. Sound works OK. Battery life with moderate usage is quite short unfortunately, but it can be partially resolved by having at least two pairs of batteries, which can be easily replaced even on the fly. I hope to utilize it more in the future, but only time will tell.

ClockworkPi DevTerm

Biostar FX9830M NAS

At the end of 2020 I upgraded my NAS server to Biostar FX9830M motherboard and throughout the year it served me pretty well. I feel that it is bit too noisy, however, changing the CPU fan is a bit challenging because of an unusual pin connector. Nevertheless, I would like to find some solution to address the problem in the future. Few solutions are in my head, from a bigger computer case to improve airflow to even fan-less solutions. Some of those would need a few creative approach on how to install them. 

Software wise Artix Linux proves to be pretty stable with a major issue being abrupt Linux kernel changes at times. The network interfaces were renamed twice for an unknown reason over a year or so, which was rendering my network aggregation configuration to fail, since it was relying on those names. Another more mysterious issue is likely related to dhcpcd or OpenRC init system in the a way that IP address is not assigned at boot, which is only solved by rerunning dhcpcd service manually (even reboot doesn't help). After that it usually works OK on subsequent reboots (happened twice or three times over a year and half). Finally, once it stopped working because of missing firmware. The solution was to install a separate linux-firmware-bnx2x package, though it wasn't required before. I guess these issues can be partially attributed to rolling release distribution approach with the most up to date kernel and software.

Akasa Cyper SPX case

This year I acquired Akasa Cyper SPX case to accommodate my ICOP VEX2-6427-5C4NE board. This case has openings to install 4 serial ports, which seemed a pretty good choice for me (considering my board has exactly 4 serial headers), but it ended up to be a bit of a disappointment. The inside design has a piece of plastic sticking out, which prevented me from installing serial ports with rectangle shaped frames in the far left and right openings. Thus, I ended up utilizing only the two middle ones. Something more lean and rounded is needed for the edge openings, which I hope to either find them or modify the ones I own in the future. Unfortunately, the Akasa page does not provide a compatibility list or requirements and their customer support is unresponsive.

The board itself is not Mini-ITX, but a much smaller 3.5'' single-board design, because of this I tried to utilize board pads and some glue with limited success. Though I managed to position it successfully, the board is not very firm, making attachment of USB devices a bit challenging.

ICOP VEX2-6427 board placed inside Akasa Cyper SPX case

Other devices 

I did mention some devices on the last review like Pocketbook InkPad Color 7.8 and AsRock DeskMini X300, however I didn't have enough time to do any useful review about them. Pocketbook is quite a nice e-reader device, but little slow, especially with big PDF files which are usually available in colours, limiting its usage. It feels like such devices should have stronger hardware, however it likely brings challenge to keep long battery usage and increases the price. 

DeskMini X300 is definitely a good choice for the mini computer, if limited expansion options are not an issue. CPU support was extended to Ryzen 5000G series over the time, thus it can opt very performant models. In my case, Athlon 200GE CPU is installed and it is virtually silent. Probably major limitation was that initial configuration didn't have WiFi, side USBs and audio jack at back (only at the front). ASRock provides its own sets for all, but they are pretty expensive and hard to get. For side USB/WiFi though third party options can be adapted.

Other than that, I had some smaller purchases, but those were usually required to facilitate certain setup, like mini-PCIe SATA controller with the flat ports instead of 90 degrees ones or more silent Cherry G80-3000N mechanical keyboard.

ASRock X300M-STX board inside DeskMini X300

Work on NetBSD

Last year I was honoured to become an official NetBSD developer, which gave an ability to contribute to the project directly! At the time of writing this review, I already did over 200 commits, however those were mainly non functional changes like misspelling fixes. Nevertheless, I did some bug fixes too. Likely the main achievement was to finally identify why R6040 MAC was failing to work on Vortex86DX3 SoC. It took me countless hours in the span of around three years of debugging, including temporarily acquiring on more DX2 based system, but I managed to find out that it was related to certain speed control register (MDC) being restored to wrong value after reset action. This issue appeared to be the same not only across all BSDs but in Linux as well. Despite the fact, that interface was working up to 5.3 kernel version by luck, it was because Linux didn't check BMCR register on identifying the link state. That changed starting 5.3, thus R6040 MAC stopped working in Linux as well. Fortunately solution was just to restore MDC value back to original value leading to restored functionality. Just recently this change was applied to OpenBSD and FreeBSD as well, thus R6040 should should work properly on VortexDX3 SoC in all BSDs and Linux (I guess FreeBSD driver will be synced to Haiku OS code at some point). It was the first fix, which was actually reapplied to all major operating systems and motivates me to continue on such efforts. Other than that, I did few other fixes, mainly in drivers, I also did various testing/investigation work, wrote some missing documentation. Unfortunately, time constraints prevent me to work on some drivers more seriously, but I still have few projects in my mind, hopefully over the time I will manage to implement them. Nevertheless, I plan to stay an active member.

 

Future developments

I do not plan any major hardware purchases this year, however some upgrades and changes are possible. The main focus will likely to stay on the NetBSD project, which comes closer to branching netbsd-10. This may lead to more testing and debugging work and potentially some help in different areas. I am still trying to debug interrupt issue on Vortex86DX3 systems. On the other hand, I still dream to dig up and revive at least one of my Alpha machines. Hopefully, DevTerm will find more usage as well. Though I don't expect much articles in the next 6 months, I will make an effort not to be completely silent and share more interesting developments.

2020 in review

The beginning of 2021 was very difficult for me and my family. In January I unfortunately lost my father because of COVID-19. This deeply wounded me, but at the same time it was a special and unforgettable moment for us, because my second daughter was born just a few days later, four days to be exact. All of this diverted my focus from IT for a while. Despite that, few months later, I would like to keep tradition to write a yearly review, even if it is late. In 2020 I had some projects like new NAS setup and 10Gbit network hardware. In addition, I also bought ICOP VEX2-6427-5C4NE board which was one of the first DM&P Vortex EX2 SoC based solutions in the market.

ICOP VEX2-6427-5C4NE

VEX2-6427 was one of the first publicly announced boards based on the DM&P Vortex86 EX2 SoC, which intrigued me a bit due to its unusual main/secondary two-core design. In addition to that, I was expecting that it may help me to resolve R6040 Ethernet issue on BSD systems for my other VortexDX3 system. Finally, I was hoping to use it as small firewall system. Unfortunately, it was not meant to be. There were several reasons for that:

• the BIOS is based on SeaBIOS without ACPI support. Initial firmware didn't have any user interface. Though ICOP support provided me a BIOS update with UI configuration, I needed to buy miniPCIe graphics card in order to update and utilize it (I bought IEI IGCME-1300-R10, since it was much cheaper than DM&P VortexVGA solution, mainly due to shipping costs. Also Aspeed AST1300 is theoretically supported by NetBSD, though I haven't tested that yet Update: no, AST1300 does not seem to have DRM support in NetBSD).
  
• The secondary CPU core is not accessible in this board, thus defeating the purpose of the unique SoC design.
• Due to limited CPU performance, PCIe bandwidth is also limited. My original plan was to use 1 Gbit Ethernet on mini-PCIe card, but it failed to meet my performance expectations (usually transfer speed was way below 200MBit/s with Intel or Realtek controller). Similarly mini-PCIe SATA card was also under-performing compared to modern PCs (if I remember correctly, SSD was reaching up to 50MB/s reading performance, way below its capabilities on the modern platforms).
  
• Due to different R6040 PHY model and lack of ACPI support, I couldn't utilize it much to investigate DX3 SoC issue. On the other hand, it worked well on NetBSD without any modification. I submitted a patch to recognize new PHY model but even general PHY driver worked as well.
• NetBSD required manually to fix COM IRQs in the kernel configuration to boot into the system because of IRQ conflicts. Initially between USB and serial port, but later with some miniPCIe cards too. Only with the updated firmware, I was finally able to reassign IRQs to my own needs. Nevertheless, to utilize all COM ports, manual kernel is still needed (similarly, Linux also requires some bootloader configuration changes to properly support all serial ports, if needed). 

I also stumbled into stability issues, however it appeared to be caused by my own mistake. Apparently, PC sets serial port TX signal to 0V during PC boot and it triggers the peer to go to the debugger. In order to resolve that, hw.cnmagic=+++++ needs to be added to /etc/sysctl.conf as a workaround (cnmagic(9)). The signal does not trigger debugger in this case. Because of all these reasons, grand plan for the system ended up unfulfilled. Nevertheless, I am still planning to use it as a serial terminal between different systems and possibly as local pkgsrc packages storage to keep it busy.

During this time I submitted patches to identify new CPU ID and new devices, thus NetBSD should be more verbose about those and attach rdcpcib (PCI-ISA bridge) driver with more DM&P SoC models.

Despite the board failing to meet my expectations, I was pleasantly surprised with ICOP support. It was very prompt, professional and helpful. Would I need to do some professional embedded hardware business, I would be really happy to deal with this company.

Assembled VEX2-6427 board with SanDisk X110 SSD and Delock miniPCe Ethernet

Mikrotik 10 Gbit router

Last year I was slowly moving to 10 Gbit internal network, connecting my NAS, router and main PC, as well as some other devices from time to time. For that purpose I bought a Mikrotik CRS309-1G-8S+ switch. It has 8 SFP+ ports and one 1Gbit port, as well as one serial port. The size is pretty compact, it uses passive cooling with external radiator connected to CPU using heat pipes. The switch is based on dual-core Marvell 98DX8208 800MHz ARMv7 CPU. The device is relatively cheap, but the price has some trade offs: though it is packed with quite a bunch of features, CPU is not very powerful do handle something more than simple configuration. Thus, I also didn't spend much on setting it up beyond bonding interface for my NAS server. Of course, I followed the security advice from their own page to have at least basic protection for the switch itself, but I guess that's it. Also, I've read somewhere that it is not recommended to use RJ45 modules, since they tend to emit lots of heat and may cause SFP+ cage to overheat. It is a bit of a disadvantage with the increasing RJ45 10GBit solutions (myself I am using DAC and fiber cables only) but likely can be partially overcome by custom cooling solutions. The major issue was initial connection to the switch, since even 1Gbit port wasn't configured as DHCP client, making it really challenging to reach from the internal router network. Hopefully, I could access it using serial port, but it took me a while to understand how to configure 1Gbit port to get IP address from my router. Afterwards, it was pretty easy to setup, including enabling web interface. Network aggregation configuration wasn't very intuitive as well, but trial/error approach worked eventually. I good part that Mikrotik RouterOS is updated pretty frequently. There is a choice between stable/testing/development and event long term releases. Thus, updates are the only reason I am connecting to this device.

MikroTik CRS309-1G-8S+IN

Asus XG-C100F

Asus XG-C100F became my third 10GBit SFP+ network adapter. Previously acquired Edimax EN-9320SFP+ and Dell QLogic 57810S are not supported by NetBSD, because of this I couldn't use them in my desktop system. Only Dell card is supported by FreeBSD but the driver is huge and I gave up on trying to port it pretty soon and repurposed it to Linux based NAS system later. Tehuti 4010 based Edimax is not supported by any of BSDs, though PRs for FreeBSD were submitted by the company. I believe it would have been easier to port, would it be accepted, but time constraint forced me to choose easier path with Aquantia based controller. On the time of purchase, the driver was just recently introduced into current branch, eventually it was back-ported to netbsd-9 branch with 9.1 release. On arrival, the card wasn't supported out of the box, since adapter's specific AQC100 MAC controller wasn't yet included in the driver list. Adding device ID made it to be recognized by the driver, but every reboot required to reattach the cable to make it work, which obviously was quite inconvenient. Fortunately, the solution was found quickly by Ryo Shimizu. Thanks to him, adapter is working without any issues now, except that I need to work on some configuration to optimize performance. It is not on par with Linux, especially on uploading which seems to be capsized to 1Gbit for some reason. It is a future project which I will try to base on NetBSD documentation and/or help in the mailing lists and IRC. During that time Linux driver also had a small bug, which was reporting TP (twisted pair) as supported port instead of FIBRE. I submitted a bug, it was fixed pretty soon after (however, it was likely discovered independently from my bug report). Besides that, adapter works well both in NetBSD and Linux, but the latter shows much better performance by default. I am not sure about the current state of OpenBSD and FreeBSD support, it was lacking from default kernel in both the last time I checked. FreeBSD likely has a vendor provided driver, OpenBSD one is in development I believe. 

Asus XG-C100F

NAS project

Following upgrade to 10Gbit network and increasing issues with the Marvel based SATA controller on ADPE4S-PB daughterboard, I eventually decided to upgrade my NAS computer from Jetway JNF76 to much more modern Biostar FX9830M motherboard. I described the process pretty well in my blog towards the end of 2020, thus I won't be repeating them here. However, there are few negative notes which came up over the time. I had at least one overheating issue, once I tried to execute long running software building process. Also, I can't call the system very silent, maybe due to pretty confined environment it is currently placed, but it has a constant background noise. It's not annoying but it is consistently audible. Finally, my active hard drive (non backup one), which is placed at the bottom of the case, seems to operate on quite high temperatures. Because of that, I may need to work on better cooling soon, especially since summer is just around the corner. I believe, even putting the computer on some elevated support may help with that. Other than that, it serves me well, as the system itself is stable and solid. Hopefully, I will manage to improve cooling and noise issues over time to avoid potential hard drive failures.

Biostar FX9830M

Smaller purchases and projects

Most smaller purchases last year were related to failed ICOP project, thus some hardware is unused now. As mentioned previously, IGCME-1300-R10 miniPCIe graphics card was used only to update BIOS and readjusting its settings. For testing purposes I successfully booted MX Linux distribution with it. I also bought two miniPCIe Ethernet cards. One is Realtek 8111F based Delock 2x1Gbit low profile card and one more unbranded Intel i350 based card. Delock has a disadvantage in taller pin type connections, while Intel based one has flat cable between miniPCIe card and backplane card with Ethernet connectors. On another hand, Delock cables are more flexible compared to thick Intel one. Unfortunately, I can't comment much on their performance, since both were performing similarly because of limited board's PCIe bandwidth. If I would have connected ICOP support before buying second card, I wouldn't have bought it. Initially I believed that poor performance is a Realtek controller issue, but it wasn't the case.

IEI IGCME-1300-R10

I also bought a miniPCIe 2xSATA controller (ASmedia ASM1061 based) and SanDISK X110 32GB SSD as a main storage, since SD cards were seemingly limited to very poor I/O performance. I used 2xUSB to SATA 15 pin power cable to power up the SATA SSD itself. This solution worked pretty well but, similar to Ethernet card read/write performance was quite limited. Nevertheless, it still was a tangible improvement over SD cards. I was pleasantly surprised that VEX2-6427 board supported direct booting from this SATA controller, thus SD card was not needed after upgrade.

I also had a chance to buy 8xKMM53616000AK-6 FPM parity SIMM memory modules with the hope to revive Microway PC164 Screamer Alpha board. However, it appeared to be either board or CPU issue. Memory was recognized but nevertheless board was spitting lots of errors on boot. Due to time constraints I abandoned attempts to revive the system for now.

One more small project was triggered by the death of my old FORTRON EPSILON 600W PSU last year. Luckily, I had one more PSU available in my stockpile (non modular), previously used in AMD Opteron 3280 based system, thus I decided to switch to it instead of buying a new one. Unfortunately, its cables were not designed for bottom placement, and most of them were too short to reach their designated connectors on the motherboard. Conveniently, all required extensions were available for purchase in local stores. For 24-pin power and 6-pin GPU cable extensions I bought SilverStone PP07-MBR and PP07-IDE6R red cables. These are extremely nice with individually sleeved wires for protection. For 8-pin power extension cable I acquired simpler Delock 83342 extention cable. Besides solving the short cables issue it also helped me organize them better, since I could utilize case design by wiring them through the right part of the case.

Finally, by the end of the year I bought the Clockwork DevTerm A04 Kit. It will be my first ARM based computer, but its current proposed shipment date is on early June, which is a slight delay since initially it was supposedly to be shipped by the end of March 2021. Hopefully, no more delays will occur but with this current shortage of microelectronics everything is possible. Nevertheless, I feel excited about it and I hope it will become a very useful device.

NetBSD endeavors

Besides mentioned patches for DM&P SoC and related RDC devices, last year wasn't very fruitful for me. R6040 PHY issue on VortexDX3 didn't move forward and I don't expect to work on it this year as well. I have reported some typos, submitted a patch to properly identify VIA PHY with MIIVERBOSE option, fixed small dmesg issue for viadrmums driver (actually reported last year and fixed this year), submitted a bug report on auvia(4) audio device driver, which also was affecting some other audio devices, also had some discussions leading to one bugfix for VIA PadLock engine, updated CodeLite package in pkgsrc to 14 version (and this year to 15). Over the year I attempted to work on porting bxe(4) driver from FreeBSD, but abandoned it, since driver is way too big and my skills on such work are too limited. I've also started some work on improving unfinished unichromefb driver with hopes to progress more this year (but no promises). This year I don't expect to do much as well but the usual bug reporting, small fixes and typos, pkgsrc package updates/fixes are expected. Just recently I updated to NetBSD 9.2 release!

Besides NetBSD I also contributed to Kwort 4.3.5 release which I use irregularly on one of my testing machines. Mainly it contributed to installation process improvements. It is really nice and very minimal CRUX Linux based distribution. Give it a try! I also reviewed previous 4.3.4 version last year.

Summary and 2021

The highlight of 2020 was local network upgrade to 10GBit leading to various new hardware and upgraded NAS system. Interesting and unusual DM&P VortexEX2 based system mainly ended up as a playground last year with some expectations to utilize it more this year. Finally I made a first step to ARMv8 world with Clockwork DevTerm device, which will hopefully arrive pretty soon. In 2021 I already had quite a few purchases. I upgraded my main CPU from Zen to Zen 2. I also updated my mom's computer to ASRock DeskMini X300 with Athlon 200GE CPU. I gave my wife a Pocketbook InkPad Color 7.8'' e-reader as a birthday gift. Finally, I bought multifunction HP LaserJet Pro MFP M183fw printer. All of these devices a worth to be mentioned in the next year's review, but may also have dedicated articles if time permits.

ASRock DeskMini X300 and AMD Athlon 200GE

 

In meantime I wish you all to stay safe and healthy during this difficult period.

2019 in review

Starting last year I resumed writing yearly review after a long break. Since 2019 was no less active in various personal computer related projects, I believe it may start a tradition of such retrospective reviews for the years to come. So without further ado, I will move on the last year's activities.

Downgrade from Radeon RX 460 to Radeon R7 370

For almost two years, I used the AMD Radeon RX 460 GPU based Asus Dual RX460 OC edition graphics card. However, since 2019, I started using NetBSD much more regularly alongside with Manjaro Linux (which is still my primary OS) and, unfortunately, Radeon RX 460 GPU is unsupported by the former. Because of that, I decided to downgrade to an older generation hardware, so I can be comfortable in using them. After a broad research, I opted for the GIGABYTE GV-R737WF2OC-2GD which is a Radeon R7 370 based card. R7 370 uses Pitcairn Pro GPU core based on the 1st GCN architecture. The main motivation behind choosing this specific model was its similar performance to RX 460, its reasonable price and its availability in stock at local stores.

Despite some fears, the card didn't disappoint. NetBSD immediately recognized the GPU and applied proper drivers giving the expected hardware acceleration. Because of this, I started using NetBSD on my desktop quite regularly. To my surprise, it visually felt more responsive than RX 460 on Linux as well. Despite being an older model, its performance is actually at par with the replaced card in general usage, except possibly increased power usage.

Dell QLogic 57810 10G Ethernet card

Since my router supports one SFP+ 10Gbit Ethernet port, I was curious to try it out and bought the Edimax EN-9320SFP+ 10Gbit network card back in 2018. Though, being the cheapest 10Gbit solution at that time with the smallest card around, it had few annoying flaws. The card was based on Tehuti TN4010 NIC, which is poorly supported by the alternative operating systems except Windows. Any of the BSDs don't have a driver at all. Linux has one, but not in the mainline kernel. Thus, the Linux driver needs to be compiled and installed manually, and the process needs to be repeated almost after every kernel update (which happens relatively often). In the end, the Linux driver still had at least one issue - if computer goes to standby mode, NIC stops working after resume with only reboot bringing it back. Nevertheless, I was not planning to replace it, since alternatives were too expensive (especially Intel based solutions). Btw, Edimax also have never updated the driver in their page, I was using the one from github.

Unexpectedly though, one local shop offered Dell QLogic 57810 (Dell part 540-BBGS) dual port 10Gbit network card for a sizable discount. I checked that it was supported by at least FreeBSD, the Linux kernel had mainline kernel driver as well, so I took the bait and bought it. The card itself is much bigger than Edimax, having an active cooler and requires PCI-E 2.0 x8 slot instead of PCI-E 2.0 x4. On the other hand, it is a way more professional product having sophisticated firmware and two SFP+ ports. Once installed, it worked out of the box in Windows, Linux and FreeBSD, with no manual work required. Contrary to Tehuti NIC, it had no issues on resume in Linux as well. In general, I believe this purchase was pretty successful, except the fact that it is not supported by NetBSD.

I dream to port the FreeBSD driver to NetBSD, however, it may be too complicated task, since the driver is huge. Nevertheless, I am planning to make an attempt this year (sometime in 2020) and see what happens.

Dell QLogic 57810 dual SFP+ Ethernet controller

Toshiba MG04ACA600E and D-Link DGE-528T

Yet another hardware update was already extensively described in my blog. Though, the main goal was just to upgrade from 3TB hard drives to 6TB ones in my NAS server, it ended up with the bigger project from migration to Artix Linux to LVM RAID configuration on recycled 3TB drives.

The new hard drives were two identical Toshiba MG04ACA600E model drives which showed quite visible performance improvement in read operations but write speed seemingly was restricted by driver issues and showed only minimal improvement compared to older drives. Thanks to LVM RAID0 setup I also reused older 3TB drives as additional back-up storage.

Realtek RTL8169SC based D-Link DGE-528T network card was used to circumvent loss of the second Ethernet port. Together with integrated Realtek 8111C NIC it showed worse network speed over Intel based daughterboard card, but it was expected and acceptable downgrade.

Toshiba MG04ACA600E

Sanwa MA-TB41S trackball

For around ten years I was successfully using Kensington Optical Orbit trackball. It was bought in Sweden by my former colleague and friend. Initially I thought that it will stay only as an experiment, but proved to be one of the best devices I've ever used. Unfortunately, the right button started to fail so badly by the end of the last year, that I was finally forced to look for the possible alternative. Despite pretty limited trackball options, I must admit it was one of most challenging decisions on hardware selection process. The main reason for that was the lack of possibility to try them physically. I believe, there is a great risk of to buy uncomfortable trackball from the images only. It doesn't matter how much reviews you will read, there are too many factors which can affect the comfort, from your hand size to device quality and sensitivity. That is probably the reason why you can find so many contradicting opinions on the same product.

Theoretically I could even buy the same model, since Kensington is still selling it together with few other long-living models, but I wanted to find one with the scroll wheel. After long research I narrowed down the options to these three models:

• Elecom Deft Pro (M-DPT1MRBK)
• Kensington Orbit with Scroll Ring
• Sanwa Supply MA-TB41BK/S

Though, Sanwa trackball was my last choice, I ended up buying it because of difficulty to find Elecom model in Europe, and relatively bad reviews regarding the quality of Kensington trackball buttons. Unfortunately, I can't tell yet if I made a right choice... During, the first month I was really disappointed. The trackball appeared to be a bit too big for my hand, making it difficult to reach buttons comfortably. Quite often I was accidentally moving the ball before clicking mouse buttons, thus easily missing intended button or other UI element. Scroll wheel was too slow, too big and clunky. My hand was constantly getting tired. Nevertheless, I started to get used to it over the time, thus decreasing the strain of the hand and increasing precision. Though, the scroll wheel still stays as the biggest inconvenience, since it was the major feature I had been looking for. It works, but scrolling is very slow and reaction time after rotating the wheel visibly lags behind. Furthermore, my thumb gets painful and tired easily, even over the time I haven't really gotten used to it. Honestly, I am not sure, if I will keeping using it, I may switch to a regular mouse or try the Kensington Orbit trackball with the scroll ring. It is probably the most unsuccessful hardware purchase in 2019.

NetBSD

I was quite active in the NetBSD project community this year: I managed to port IC Plus IP1000/1001 PHY driver from OpenBSD (used by many VIA EPIA boards, also IC Plus own network cards), fixed support for VIA VX800 (and possibly VX855, VT8237S) SATA controller (previously partially working in IDE mode only), 4World USB to Serial adapter (already mentioned in 2018 review), found the fix for the Biostar X370GT5 SATA controller locking issue, requested to pull-up the fix for D-Link DUB1312 USB network card to NetBSD 8 release. In addition, I noticed and identified the applied fix for the long standing bug on Ryzen system, where the OS was failing to identify a second SATA hard drive. This bug was causing to stall even UEFI POST process on reboot. Fortunately, this fix made it into NetBSD 9.0 release. Also I noticed some typos and white-space issues in the code. Finally, I updated the seemingly abandoned Codelite IDE package in pkgsrc to build the latest stable version at that time (from 9.1 to 13.0). Despite these successes, I also had some let-downs. I couldn't fix the USB and Ethernet issues on eBox 3352DX3-AP computer. I found a workaround to make Ethernet controller work, in case SMP and ACPI is disabled, but the proper fix is still unclear. Besides that, once suddenly Fnatic Gear Rush keyboard stopped working, with the help of NetBSD developer I identified that it was caused by accidental switch to 6KRO mode. It appeared to be working in NKRO mode only (which was the opposite up to NetBSD 7.1 release). Hopefully, it can be fixed to work on both modes in the future. Seeing quite a successful last year, I hope that I will be able to solve some issues in 2020 as well.

eBox 3352DX3-AP 

The last chapter I will dedicate to some insights on how to run BSD system on eBox 3352DX3-AP VortexDX3 based system, since I promised that on the last review.

FreeBSD 12.0 works the best out of BSDs, which can perfectly boot on default BIOS configuration. The only issue is the integrated network controller (R6040) which fails to work. This issue is common to all BSDs, since drivers are based on FreeBSD one. Similarly to the described below workaround on NetBSD, it may be also applied for the FreeBSD. By removing all the vte_reset() calls in the driver and recompiling a custom kernel, it should make the network work. Unfortunately, the latest release at time of writing (12.1) introduced some regression which causes instant failure on boot. I submitted the bug report but I don't expect it to be resolved soon. So, in case FreeBSD is a preferred choice, I recommend to run 12.0 release. Alternatively to editing and compiling the custom kernel, USB based network controllers can be used to enable the network.

OpenBSD is probably on the worst situation. I identified only one way to boot into the system without kernel recompilation by disabling "ACPI aware OS" option in BIOS. However, neither USB nor Ethernet works, which renders the system usefulness limited to some local automatic jobs only. It can boot with ACPI enabled/IDE in legacy mode by recompiling kernel without DIAGNOSTIC option. SMP works in both cases. If you want to work with OpenBSD for any reason, I would recommend to look for the system with COM ports (or try to solder the one).

NetBSD support is somewhere in the middle among the three. In order to boot the system with "ACPI aware OS" option enabled in BIOS, IDE should be set to "legacy mode". Otherwise, various timeout exceptions will occur and system will fail to boot. Similarly to OpenBSD, neither USB nor network will work in this case but both CPU cores (SMP) will work without requirement to rebuild the kernel. Booting with ACPI and SMP disabled (boot -12) will give USB support. Furthermore, it is possible to make network work in this case as well, but removing vte_reset() calls in if_vte.c (R6040 driver) and rebuilding your custom kernel. In case loosing SMP and ACPI are acceptable options, it makes a fully working system. Unfortunately, a workaround for the network didn't work for OpenBSD (more specifically, it actually does work, but network still fails to connect due to some other issue).

Summary and 2020

2019 was a pretty good year in the hardware/software context. Most of my projects went smoothly, and newly acquired hardware met or even exceeded expectations (except the trackball). It was also the most active year in NetBSD for me. Besides starting using it as Desktop operating system quite regularly, I managed to provide several patches to improve hardware support and provided my first contribution to pkgsrc project. I hope to keep this pace in 2020 as well, though time-constraint is my main enemy. Hardware wise, I don't have specific plans for 2020. I may upgrade to a newer Ryzen CPU and upgrade some other parts but non of these are a high priority. Like last year, such decisions probably will depend on pricing and unexpected deals. I do plan to revive my Alpha CPU based Microway PC164 Screamer system and I already have bought "old new" 8x32MB modules of SIMM RAM (Samsung KMM53616000AK-6) for it. Considering all these future plans, I believe that I will write at least a few articles this year, which I hope will be an interesting read.

2013 and up

Happy new year everyone. I am not the most active blogger in the world but I still don't plan to be silent this year too. As usual this blog will be focused on activities with my own hardware and software. I hope some information will be useful for my blog readers too.

There are some plans this year which I can divide into several categories and probably the most of blog posts will be around these topics.

Hardware:

• I plan to change my NAS server which uses Jetway JNF76 mainboard into real NAS device. I think device will fall into the cheap NAS category (something like ZyXEL NSA325). The main point of the change is easier management. I don't have time and motivation to configure Linux to my all needs. NAS devices usually have simple web interface for most cases I need (power management, more versatile back-up, torrent, RAID). They use much less power too.
• My main desktop computer should be the same sandy bridge-ep platform I had bought last year. I have already upgraded memory to 16GB (4x4GB quad channel). I am not sure what I'll upgrade in it (maybe nothing) but the strongest candidates are GPU (to R4xxx series) and hard drive (to SSD).
• Microway Streamer PC164 has memory problems once again with new RAM sticks. Though I can install and boot NetBSD still. This system is almost unused. I just try to install the newer NetBSD version from time to time. Another DEC Alpha motherboard is unused too and I don't plan even to boot it in near future.
•  VIA VT-310DP is still good and healthy. And I use it often as my main testing platform. NetBSD support is greatly improved on it. 6 branch (probably will end up into 6.1 release) and current branch (7.0) doesn't have any problems at all. The fix for the freeze on second CPU detection was pulled up to 5, 6 branches (6.0 and 5.2 official releases has this fix). There are ACPI problems with SATA and USB devices on all official releases but current and 6 branches have already applied patches that addressed those problems too.
• VIA EPIA-M900 should remain the main desktop platform for my other family members. HDD was upgraded to Kingston V+200 120GB SSD last year. It greatly improved loading times of Windows and some applications (Starcraft II especially). CPU is the biggest bottleneck right now. I don't plan any big upgrades (I would like to have some small changes but there are difficult to implement). Maybe I'll write one more review on usage advantages and shortcomings some day.
• There is a possibility that I'll get some netbook (which are declared dead :D) or small laptop.

Software (operating systems):

• My main setup is Fedora Linux and NetBSD. Fedora plans to release 18 version soon. I'll upgrade as soon as possible of course. NetBSD released a major release (6.0) and some minors (6.0.1 and 5.2) last year. I expect that this year won't be major releases but 6.1 (with some new features and bug/security fixes) can be released. 6 release is ok for me so I probably won't need to switch to current branch I needed before 6 branch had appeared. I currently use 6.0.1 with patched kernel to support my integrated broadcom NIC (I applied patch from current branch into 6.0.1 source code). VT-310DP will use current branch.
• Haiku OS released Alpha 4.1. I still haven't tried it but I expect to do this (or newer build) sometime this year.
• Syllable development quite stalled right now (or very slow). It even was forked into Pyro OS because of this however no actual releases have been done yet by this forked project. I haven't used Syllable for years but I plan to look into it some time this year depending on situation.
• I hope to try DragonFly BSD just for curiosity at first.

Other activities:

• I will attend at FOSDEM'13. This is the first such conference for me but I hope to enjoy it.
• There are lots of great new CPUs in my CPU collection which I haven't placed to photo gallery yet. They will end up there eventually. I hope to spend some to provide more information on them but the result won't be noticeable this year I think. I am not sure how many new ones I'll buy this year but my focus switched to more rear ones so quantity won't be big.
• I dream to buy QNX based Blackberry 10 platform mobile phone (devices are planned to release on 31 January). 
•  I plan more actively to participate in NetBSD community.

Just update about my activities (NetBSD, CPU collection)

There are no new blog posts for some time now. This time however I actually don't have anything to write. There are no hardware changes recently. Though I plan to increase total RAM to 16GB (4x4GB) an make my system to use quad channel memory instead of dual channel one next week. NetBSD developers didn't find fast answer why integrated NIC doesn't work (on ASRock X79 Extreme4-M). I wasn't successful too despite the fact all other major BSDs (Free and Open) works ok with it. Because of this I also plan to insert some chip 1GBit PCI-E network card (most likely D-Link DGE-560T with marvell NIC). I hope that it will be a temporary solution until solution to enable correct operation of integrated one will be found. I also changed NVIDIA GeForce GTS450 graphics card to fanless ATI Radeon 2400XT. The main reason was a good NetBSD support but downside was higher power usage at idle (yes, GTS450 ate noticeably less energy on idle). Finally, there are problems with USB devices in NetBSD, I always need to reconnect mouse or keyboard after system is booted...

NetBSD reached 6.0 Beta 2 stage at current point and heading towards first release candidate. When we can expect release I still can't even predict. If I remember correctly  5.1 was released about 6 months after first RC release... Nevertheless you can download updated 5.1.2 version or use 6 daily branch. What is more, VT-310DP second CPU bug is finally  fixed on version 6 branch. It was VIA Eden CPU specific problem that it hid cmpxchg8b instruction support because of some Windows NT(!) bug. The worst thing that there was no BIOS entry to change that too (I saw such option on some Jetway VIA based motherboards). Fortunately, you can expose support for this instruction using software methods (some assembly). Despite this fix there are still some ACPI problems with VIA chipsets, because of this you still need to use -2 parameter (disable ACPI) at boot. There is a patch to this problem too and the system will boot correctly with ACPI enabled but you will see a constant interrupt storm in CPU activity. Because of this patch is not very suitable for production use. Maybe something will change in distant future :).

Finally, I updated my CPU collection photo album. It is difficult for me to list all new items as they came at different time but there are some new interesting ones. I bought new camera (Olympus SP-610UZ) so you can expect a little bit better photos in the future. Some of them I have already refreshed. The main new CPUs include Integraph Clipper C300 (new architecture and rare, hard to find item), HP PA-RISC 8800 (dual core, Itanium socket), HP Alpha 21364 1300 MHz (if wikipedia is not wrong it is the fastest Alpha), Zilog Z380 32-bit MPU, set of 6 Kendall Square Research supercomputer chips, Infineon MIPS CPU (new company in the list). So that is all for now.

Sandy Bridge-EP platform

While Intel's Ivy Bridge CPUs are on the horizon I happened to get Sandy Bridge-E sample on my hands. It is Sandy Bridge-EP 4S more precisely. This CPU will become a member of Xeon E5-4600 series when they will be released and they are primarily intended for 4-way servers. My sample is packed into 2011-land FC-LGA package and works on LGA 2011 socket.  Despite its intended purpose to be a server CPU it can be used on desktop perfectly too. My sample's s-spec is QAFF and its specifications are as follows:

•  3GHz frequency (30x multiplier), max 3.3 GHz on turbo boost
• 10 MB L3 cache
• 4 cores, 8 threads
• 32 nm 
• 130W TDP (not confirmed)
• support for AVX, SSE4.2 and other modern instructions and features like in most sandy bridge cpus.

So I would call it "low-end" or "mainstream" CPU on targeted platform and it is comparable to Core i7 3820 desktop CPU by specs but has much less frequency (3820 clocked at 3.6 GHz by default). CPU multiplier is locked. 

There is always a risk if you buy engineering sample CPU. Firstly, no motherboard will support it officially and you need to find at least some information on supported ones (mostly you need to know at least one supported motherboard from specific manufacturer and then compare their motherboard specifications, BIOS and CPU support to make decision if you are not satisfied this the one you found as compatible). In the worst case you probably will be able to sell incompatible motherboard for some little loss (of course, if you don't live in the small country like me). Secondly, you won't have any warranty. If CPU will die, nobody will replace it. Finally, you can't write a lot about it until official CPUs are released (Intel doesn't like leaked CPUs and can take actions on sellers and on even on bloggers). Nevertheless this CPU has more or less the same core as other Sandy Bridge-E(P) CPUs so you can always imagine performance by reading articles on similar items. When you consider all these factors and still decide to buy a CPU you should be ready to lost the money in the worst case. However, it is still aren't very risky decision in my experience. CPU is probably one of the most reliable parts compared to other computer parts. If you spend enough time to check motherboard compatibility and have enough sources to prove your decision this move becomes even less risky. On the bright side ES CPU can be purchased for less money than production chip (not applicable for first samples of new architecture or platform or very rare collectible old items).

Personally it is my second engineering sample CPU (used for actual computer, not for collection purposes). First one was Xeon E5540 ES Q1E2 Nehalem CPU. Unfortunately, X58 platform wasn't very satisfactory for my purposes and I replaced it with Athlon II X2 235E on AMD 780G platform. It was great platform until Jetway JNC81 motherboard died. Jetway replaced it with JNC84-E but it wasn't so friendly with NetBSD. What is more, I wanted more performance for compiling, folding and other tasks. Though, I still didn't plan to change computer initially in the near future but I bought Sandy Bridge-EP CPU at a reasonable price and decided build the platform on it.

I wanted to go as cheaply as possible because of this I bought relatively cheap ASRock Extreme4-M motherboard, Thermaltake Contac39 CPU cooler and reused some parts from retired mother's Phenom II X2 555 computer (like RAM and graphics card) and my computer (HDD). I plan to add two more RAM modules to make them work on 4 channel mode but currently system works on 2 channel mode. I also would like to get less powerful and more power efficient graphics card (GeForce GTS450 now) but it depends on how successfully I will sell my parts on second hand market. Nevertheless the platform still cost quite a lot as X79 motherboards are pricey and even the cheapest one cost about double of what I spent on one motherboard typically. Extreme-4M wasn't the cheapest one but Intel boards didn't have enough sources to prove compatibility (ironically) and Extreme-4M was more appealing for me than Extreme-3 which one was the cheapest solution from ASRock line.

So my current setup is:

• CPU: Intel QAFF Sandy Bridge-EP 4S 3GHz
• Moterboard: ASRock Extreme-4M
• RAM: 1xKingston KHX1600C9D3B1K2/8GX (2x is planned in the near future)
• HDD: Seagate Momentus 7200.4 250GB (ST9250410AS) (SATA2)
• CPU Cooler: Thermaltake Contac39
• DVD-RW: LG GH22NS40 (SATA)

System setup went without big problems. CPU was recognized as GenuineIntel 3GHz. It works on 1.2GHz on idle. Motherboard uses modern UEFI BIOS. I needed to set 1600 MHz for RAM manually as they worked as 1333MHz by default. No other big changes were needed. Fedora 16 booted without visible problems and worked perfectly. NetBSD wasn't so good. It booted better than on JNC84-E platform (it typically didn't load on first try and needed repeated boot command in the bootloader. This problem disappeared by surprise for me), but NIC (Broadcom BCM57781) didn't work correctly (as result no internet and network), GTS450 graphics card wasn't supported too (X.org failed to start). Keyboard needed reconnect on the first boot but problem didn't reoccur on other times.  So currently I need to solve these issues somehow. On the other hand I expected more worse situation as platform was relatively new. These two problems are quite small and solvable. Of course, USB3.0 is not supported on NetBSD but I don't have any devices anyway. The whole platform uses 86-92W on idle and ~160W on full CPU load (by folding@home). For comparison unlocked 4 core Phenom II X2 555 used around 200W and more with the same graphics card and RAM.

QAFF ES 3.0 GHz

I've chose EPIA-M900 for my VIA Nano X2 setup

While VIA prepares some new motherboards like EPIA-M910 and EPIA-920 (last one will be equipped with quad core CPU and VX11 (VT3456) chipset which has integrated DX11 compatible GPU) I've made a decision on my own configuration. It is quite unusual and consists of VIA embedded parts mainly.  So I've decided to take EPIA-M900 (EPIA-M900-16L) motherboard and eH1 graphics card. I've already received this hardware and started to test it.

In Win BM-639, VIA eH1, VIA EPIA-M900 boxes

EPIA-M900 is the most quality made motherboard from VIA embedded I've ever seen (especially compared to the most of VB series and old models). However, I admit that some recent models are similar by quality too. On the other hand this quality comes at substantially higher price than I would like to see. Unfortunately cooling system is made in VIA "fashion". It consists of the big aluminum heatsink over CPU and chipset and small, annoyingly loud fan. On the bright side the fan speed is controlled by CPU load using smart fan function in BIOS. However, it still emits unpleasant sound even at lower speed. GPU has a fan too but it seems less audible (no speed control). EPIA-M900 box is visually not appealing as it looks like simple corrugated cardboard box (I've never saw the one like that for motherboards earlier but as it is targeted for embedded market VIA probably decided to save money on box visual appearance). You will find a SATA cable, driver's CD and I/O shield besides the board itself. Yet again it is quite ordinary minimal set of accessories you'll find in most VIA products. There was two main reasons I chose this board. Firstly, it was the only VIA Nano X2 board which had a PCI-E x16 (effective speed up to x8) slot, secondly EPIA-M900 had two RAM slots and supported 8GB RAM while VB8004 (the other candidate) only one. Besides, it was easier to get than VB8004 with its graphics module.

EPIA-M900

VIA eH1 has more visual appealing and more standard box for such products. Accessories include DVI-VGA adapter and driver's CD. There is one caveat that you'll find a Linux tux image on the box indicating this graphics card "support" Linux but you won't find any drivers neither on cd nor in VIA Embedded web page. You can download some Linux drivers on s3graphics web site but you still won't be able to use them on modern Linux distributions as it has some code that won't compile on current kernel. I guess the card itself is supported by those proprietary drivers but I couldn't test them due to reason I mentioned above. There are no open source drivers for this GPU so the only way to use this card is VESA driver or try an older distributions (with 2.6.38 kernel or maybe even less). What is more, it doesn't use solid state capacitors as S3 graphics similar products.

VIA eH1 graphics card

The motherboard itself had some surprises that I hadn't notice or they hadn't been clearly defined in specifications. Firstly, most pin headers was smaller in size than standard ones. USB headers are surprisingly standard ones but front panel audio, fan, kbms and COM headers are mini variants. I saw smaller fan header (but forgot to check that they were only ones) and I knew about smaller COM headers but they were unneeded for me. Unfortunately I didn't know that front panel audio header and kbms header would be mini ones too. I actually don't know where to get adapters for them right now too. Second surprise was a missing RAID support in BIOS firmware (or I didn't found it). I though that such RAID support existed in all boards currently and you even had no need to check that. 

I tried some open source operating systems during this weekend. Linux (Fedora 16, openSUSE 12.1) and FreeBSD installed ok. NetBSD didn't boot (I guess because it doesn't support VX900 chipset still) but dual core CPU was recognized (UPDATE 2012-05-02: VX900 IDE support was added recently, so NetBSD 6_BETA currently boots on this board). Haiku boot sequence ended in kdebug with some stack trace. PC-BSD didn't boot too but it seems that it was a DVD boot loader problem because FreeBSD installed without any problems and surprisingly recognized all motherboard's integrated hardware (as you may or may not know PC-BSD is just desktop orientated FreeBSD variant). As I mentioned earlier eH1 graphics card and its HD audio is not supported on any open source OSes (except VESA driver).

I'll try to make some tests in open source OSes and/or Windows later on but I don't make any promises this time. I hope to test power usage too. To end this article on good note the board itself feels really good. It uses the most modern chips from VIA like VT2021 HD audio, VT6130 Gigabit Ethernet controller, VX900 integrated graphics with H.264 decoding acceleration on Windows, 8GB support (unfortunately USB 3.0 was not added for some unknown reason as the place for two connectors and VIA Labs chip was designed on the board). Smart fan control makes default fan bearable on idle. Finally dual core CPU has modern instructions support up to SSE4.1 and Intel compatible virtualization and it feels quite fast (I compiled quite a lot of source during this weekend, y-cruncher result is comparable to Merom 3M dual core pentium or celeron CPUs). Finally, the board quality gives hopes that VIA will continue to make more boards like this in the future and even improve them. BIOS could me more capable but it is embedded board so requirements are minimal for them I guess. Quite good FreeBSD support was a pleasant surprise too. I can't tell much about eH1 GPU right now as it will show its capabilities on Windows only.

P.S. I've updated my last  article on VIA Nano X2 solutions several times too. Probably I'll keep to do this for some time in the future.