I bought this board because it has 2 lanes. So I changed the number of lanes in the dtb from 1 to 2. I need confirmation of an expert but my quick speed test with 2 lanes looks promising : gt@yy3568:~$ sudo hdparm -tT --direct /dev/nvme0n1p1 /dev/nvme0n1p1: Timing O_DIRECT cached reads: 1062 MB in 2.00 seconds = 530.34 MB/sec Timing O_DIRECT disk reads: 928 MB in 3.00 seconds = 308.97 MB/sec gt@yy3568:~$ sudo dmesg | grep lane [ 4.183004] phy phy-fe8c0000.phy.6: lane number 0, val 1 [ 4.183679] phy phy-fe8c0000.phy.6: lane number 1, val 2 pcie@fe280000 { compatible = "rockchip,rk3568-pcie"; #address-cells = <0x03>; #size-cells = <0x02>; bus-range = <0x20 0x2f>; clocks = <0x0f 0x8f 0x0f 0x90 0x0f 0x91 0x0f 0x92 0x0f 0x93>; clock-names = "aclk_mst\0aclk_slv\0aclk_dbi\0pclk\0aux"; device_type = "pci"; interrupts = <0x00 0xa5 0x04 0x00 0xa4 0x04 0x00 0xa3 0x04 0x00 0xa2 0x04 0x00 0xa1 0x04>; interrupt-names = "sys\0pmc\0msg\0legacy\0err"; #interrupt-cells = <0x01>; interrupt-map-mask = <0x00 0x00 0x00 0x07>; interrupt-map = <0x00 0x00 0x00 0x01 0xcb 0x00 0x00 0x00 0x00 0x02 0xcb 0x01 0x00 0x00 0x00 0x03 0xcb 0x02 0x00 0x00 0x00 0x04 0xcb 0x03>; linux,pci-domain = <0x02>; num-ib-windows = <0x06>; num-ob-windows = <0x02>; max-link-speed = <0x03>; msi-map = <0x2000 0x66 0x2000 0x1000>; num-lanes = <0x02>; phys = <0xca>; phy-names = "pcie-phy"; power-domains = <0x11 0x0f>; reg = <0x03 0xc0800000 0x00 0x400000 0x00 0xfe280000 0x00 0x10000 0x00 0xf0000000 0x00 0x100000>; ranges = <0x1000000 0x00 0xf0100000 0x00 0xf0100000 0x00 0x100000 0x2000000 0x00 0xf0200000 0x00 0xf0200000 0x00 0x1e00000 0x3000000 0x03 0x80000000 0x03 0x80000000 0x00 0x40000000>; reg-names = "dbi\0apb\0config"; resets = <0x0f 0xc1>; reset-names = "pipe"; status = "okay"; pinctrl-names = "default"; pinctrl-0 = <0xcc>; reset-gpios = <0x58 0x1e 0x00>; vpcie3v3-supply = <0xcd>; phandle = <0x271>; legacy-interrupt-controller { interrupt-controller; #address-cells = <0x00>; #interrupt-cells = <0x01>; interrupt-parent = <0x01>; interrupts = <0x00 0xa2 0x01>; phandle = <0xcb>; }; };

After much trouble with my old build environment I cloned Hqnicolas build repo. Now I can confirm that it seems to work. I made a quick speed comparison between the ssd and my external USB drive: gt@yy3568:~$ sudo hdparm -tT --direct /dev/sda /dev/sda: Timing O_DIRECT cached reads: 178 MB in 2.00 seconds = 88.89 MB/sec Timing O_DIRECT disk reads: 322 MB in 3.01 seconds = 106.88 MB/sec gt@yy3568:~$ sudo hdparm -tT --direct /dev/nvme0n1p1 /dev/nvme0n1p1: Timing O_DIRECT cached reads: 1160 MB in 2.00 seconds = 579.44 MB/sec Timing O_DIRECT disk reads: 690 MB in 3.00 seconds = 229.89 MB/sec Thank you very much to both @Arthur Gu and @Hqnicolas

Here your debugging activity will need to start. There is an awful lot of things unknown, to others on this forum but more important, also to yourself. It could already be that your server (Armbian) has nothing to do with it, but that it is the info in your router (even caching stuff) that has refreshed, simply because you probably restarted, so something was not 'reset proof'. I have seen many of such things myself in my house/home networking and in conjunction with various ISP's (also mobile4G). Which made me use my own (open-source) router instance for example, so I can at least check all what is needed in such case as you have. But it might be simple, you can use wget (do 'man wget' first to see all options) to mimic browser behavior and that should already say something. If docker etc is involved, make sure you understand all (virtual) networking, it can get very complex. I haven't seen potentially disturbing things from Armbian 26.2.1, but I removed/blocked also several things, like no netplan.io, that at least works on Debian Trixie based installs. There have been lots of security related updates in Debian recently, so make sure you log and see changes to packages (edit listchanges.conf)

Hello, I’m facing yet another strange problem, and I am posting it here as well, because I think it could be OS related. Some details about my server: Armbian 26.2.1 trixie Nginx Nextcloud (latest) MariaDB Letsencrypt (updated 3 weeks ago) Until a few days ago, every browser on any of my devices could call the web gui of my server and Nextcloud presented its login page. Then, after the latest OS update, suddenly browsers tell my they can’t connect to the server, but every synching app on any of devices still work perfectly! And I can even access my files on the server by using FolderSync’s¹ internal file browser. It is just the browsers that can’t connect any more, no matter which browser, no matter which device! There is no error message in the appropriate log files, neither in the system log, nor in Nextcloud’s own log, and the message that the browsers present is simply some variation of “I can’t connect to server”. No specific reason, no error code. This is more than strange to me. I would get it if synching apps would have stopped working as well, but that is not the case. Does any one have an explanation for this mystery? If you need more information, just let my know! Many thanks in advance! (¹ Synching app on Android.)

Perfect! It seems to be working well. ### lsblk: NAME FSTYPE SIZE MOUNTPOINT UUID mmcblk0 29.1G └─mmcblk0p1 ext4 28.8G / 53bf3b54-4988-4318-bf78-9ff6f0b851e5 mmcblk0boot0 4M mmcblk0boot1 4M zram1 ext4 50M /var/log 921565d0-0680-469e-ac03-555369d9549f zram2 0B nvme0n1 238.5G ├─nvme0n1p1 ntfs 529M 80DE33D8DE33C566 ├─nvme0n1p2 vfat 100M 5A34-53D4 ├─nvme0n1p3 16M └─nvme0n1p4 ntfs 237.8G 220438F50438CD93