El futuro de los miniPCs: iKoolCore R1-Pro potenciado por Proxmox - Página 6 de 13

Contenido

Ubuntu

Como era de esperar no hemos tenido problema alguno en la instalación de la última versión de Ubuntu 23.04

pharizna@r1-pro:~$ cat /etc/lsb-release
DISTRIB_ID=Ubuntu
DISTRIB_RELEASE=23.04
DISTRIB_CODENAME=lunar
DISTRIB_DESCRIPTION="Ubuntu 23.04"
pharizna@r1-pro:~$ uname -a
Linux r1-pro 6.2.0-31-generic #31-Ubuntu SMP PREEMPT_DYNAMIC Mon Aug 14 13:42:26 UTC 2023 x86_64 x86_64 x86_64 GNU/Linux
pharizna@r1-pro:~$ free -mh
               total       usado       libre  compartido   búf/caché   disponible
Mem:            15Gi       2,6Gi        10Gi       658Mi       3,1Gi        12Gi
Inter:         4,0Gi          0B       4,0Gi
pharizna@r1-pro:~$ df -mh
S.ficheros     Tamaño Usados  Disp Uso% Montado en
tmpfs            1,6G   2,0M  1,6G   1% /run
/dev/nvme0n1p2   116G    13G   98G  12% /
tmpfs            7,7G    55M  7,7G   1% /dev/shm
tmpfs            5,0M   8,0K  5,0M   1% /run/lock
/dev/nvme0n1p1   1,1G   6,1M  1,1G   1% /boot/efi
tmpfs            1,6G   128K  1,6G   1% /run/user/1000

pharizna@r1-pro:~$ cat /etc/lsb-release

DISTRIB_ID=Ubuntu

DISTRIB_RELEASE=23.04

DISTRIB_CODENAME=lunar

DISTRIB_DESCRIPTION="Ubuntu 23.04"

pharizna@r1-pro:~$ uname -a

Linux r1-pro 6.2.0-31-generic #31-Ubuntu SMP PREEMPT_DYNAMIC Mon Aug 14 13:42:26 UTC 2023 x86_64 x86_64 x86_64 GNU/Linux

pharizna@r1-pro:~$ free -mh

total usado libre compartido búf/caché disponible

Mem: 15Gi 2,6Gi 10Gi 658Mi 3,1Gi 12Gi

Inter: 4,0Gi 0B 4,0Gi

pharizna@r1-pro:~$ df -mh

S.ficheros Tamaño Usados Disp Uso% Montado en

tmpfs 1,6G 2,0M 1,6G 1% /run

/dev/nvme0n1p2 116G 13G 98G 12% /

tmpfs 7,7G 55M 7,7G 1% /dev/shm

tmpfs 5,0M 8,0K 5,0M 1% /run/lock

/dev/nvme0n1p1 1,1G 6,1M 1,1G 1% /boot/efi

tmpfs 1,6G 128K 1,6G 1% /run/user/1000

También, como no podía ser menos, hemos utilizado el típico SBC-BENCH (versión Review, claro)

pharizna@r1-pro:~$ sudo /bin/bash ./sbc-bench.sh -r
[sudo] contraseña para pharizna:
Starting to examine hardware/software for review purposes...

Average load and/or CPU utilization too high (too much background activity). Waiting...

Too busy for benchmarking: 14:12:45 up 30 min,  3 users,  load average: 0.91, 1.01, 0.79,  cpu: 11%
Too busy for benchmarking: 14:13:05 up 30 min,  3 users,  load average: 0.65, 0.94, 0.77,  cpu: 0%
Too busy for benchmarking: 14:13:10 up 31 min,  3 users,  load average: 0.60, 0.93, 0.77,  cpu: 0%
Too busy for benchmarking: 14:13:15 up 31 min,  3 users,  load average: 0.55, 0.91, 0.76,  cpu: 0%

sbc-bench v0.9.45

Installing needed tools: apt -f -qq -y install gcc make build-essential lm-sensors curl git sysstat powercap-utils binutils mmc-utils smartmontools stress-ng p7zip, tinymembench, ramlat, mhz, cpuminer. Done.
Checking cpufreq OPP. Done.
Executing tinymembench. Done.
Executing RAM latency tester. Done.
Executing OpenSSL benchmark. Done.
Executing 7-zip benchmark. Done.
Throttling test: heating up the device, 5 more minutes to wait. Done.
Checking cpufreq OPP again. Done (11 minutes elapsed).

Results validation:

  * Measured clockspeed not lower than advertised max CPU clockspeed
  * No swapping
  * Background activity (%system) OK
  * Powercap detected. Details: "sudo powercap-info -p intel-rapl"
  * Throttling occured

Full results uploaded to http://ix.io/4FgU

#    / Pentium Silver N6005 @ 2.00GHz

Tested with sbc-bench v0.9.45 on Sun, 03 Sep 2023 14:25:38 +0200. Full info: [http://ix.io/4FgU](http://ix.io/4FgU)

### General information:

    Pentium Silver N6005 @ 2.00GHz, Kernel: x86_64, Userland: amd64
   
    CPU sysfs topology (clusters, cpufreq members, clockspeeds)
                     cpufreq   min    max
     CPU    cluster  policy   speed  speed   core type
      0        0        0      800    3300   Pentium Silver N6005 @ 2.00GHz
      1        0        1      800    3300   Pentium Silver N6005 @ 2.00GHz
      2        0        2      800    3300   Pentium Silver N6005 @ 2.00GHz
      3        0        3      800    3300   Pentium Silver N6005 @ 2.00GHz

15763 KB available RAM

### Governors/policies (performance vs. idle consumption):

Original governor settings:

    cpufreq-policy0: powersave / 3300 MHz (performance powersave)
    cpufreq-policy1: powersave / 3300 MHz (performance powersave)
    cpufreq-policy2: powersave / 3300 MHz (performance powersave)
    cpufreq-policy3: powersave / 3300 MHz (performance powersave)

Tuned governor settings:

    cpufreq-policy0: performance / 3300 MHz
    cpufreq-policy1: performance / 3300 MHz
    cpufreq-policy2: performance / 3300 MHz
    cpufreq-policy3: performance / 3300 MHz

Status of performance related policies found below /sys:

    /sys/module/pcie_aspm/parameters/policy: [default] performance powersave powersupersave

### Clockspeeds (idle vs. heated up):

Before at 50.0°C:

    cpu0: OPP: 3300, Measured: 3290

After at 68.0°C:

    cpu0: OPP: 3300, Measured: 3290

### Performance baseline

  * memcpy: 9549.7 MB/s, memchr: 11200.3 MB/s, memset: 10222.6 MB/s
  * 16M latency: 126.0 125.3 126.3 125.6 126.0 122.7 119.4 120.6
  * 128M latency: 147.7 148.0 147.8 148.2 147.7 142.8 146.0 147.6
  * 7-zip MIPS (3 consecutive runs): 13069, 12679, 13079 (12940 avg), single-threaded: 3339
  * `aes-256-cbc     548728.70k   864608.17k   908079.79k   919478.61k   922927.10k   923019.95k`
  * `aes-256-cbc     548456.74k   865028.27k   908333.82k   919907.33k   923243.86k   922140.67k`

### PCIe and storage devices:

  * Intel Ethernet I226-V: Speed 5GT/s, Width x1, driver in use: igc
  * Intel Ethernet I226-V: Speed 5GT/s, Width x1, driver in use: igc
  * Intel Ethernet I226-V: Speed 5GT/s, Width x1, driver in use: igc
  * Intel Ethernet I226-V: Speed 5GT/s, Width x1, driver in use: igc
  * 119.2GB "UMIS RPJTJ128MED1MWX" SSD as /dev/nvme0: Speed 8GT/s, Width x2, 0% worn out, drive temp: 45°C
  * "Genesys Logic SD Card Reader and Writer" as /dev/sda: USB, Driver=usb-storage, 5Gbps (capable of 12Mbps, 480Mbps, 5Gbps)
  * "Genesys Logic SD Card Reader and Writer" as /dev/sdb: USB, Driver=usb-storage, 5Gbps (capable of 12Mbps, 480Mbps, 5Gbps)
  * "Genesys Logic SD Card Reader and Writer" as /dev/sdc: USB, Driver=usb-storage, 480Mbps (capable of 12Mbps, 480Mbps, 5Gbps)
  * "Genesys Logic SD Card Reader and Writer" as /dev/sdd: USB, Driver=usb-storage, 480Mbps (capable of 12Mbps, 480Mbps, 5Gbps)
  * Winbond W25Q256 16MB SPI NOR flash, drivers in use: spi-nor/intel-spi

### Swap configuration:

  * /swap.img on /dev/nvme0n1p2: 4.0G (0K used)

### Software versions:

  * Ubuntu 23.04
  * Compiler: /usr/bin/gcc (Ubuntu 12.3.0-1ubuntu1~23.04) 12.3.0 / x86_64-linux-gnu
  * OpenSSL 3.0.8, built on 7 Feb 2023 (Library: OpenSSL 3.0.8 7 Feb 2023)    

### Kernel info:

  * `/proc/cmdline: BOOT_IMAGE=/boot/vmlinuz-6.2.0-31-generic root=UUID=70ec93ad-1107-4655-a865-6be50f4f0fc7 ro quiet splash vt.handoff=7`
  * Vulnerability Mmio stale data:      Mitigation; Clear CPU buffers; SMT disabled
  * Vulnerability Spec store bypass:    Mitigation; Speculative Store Bypass disabled via prctl
  * Vulnerability Spectre v1:           Mitigation; usercopy/swapgs barriers and __user pointer sanitization
  * Vulnerability Srbds:                Vulnerable: No microcode
  * Kernel 6.2.0-31-generic / CONFIG_HZ=250

Waiting for the device to cool down................................................. 52.0°C

All known settings adjusted for performance. Device now ready for benchmarking.
Once finished stop with [ctrl]-[c] to get info about throttling, frequency cap
and too high background activity all potentially invalidating benchmark scores.
All changes with storage and PCIe devices as well as suspicious dmesg contents
will be reported too.

Time        CPU    load %cpu %sys %usr %nice %io %irq   Temp
14:27:51: 3300MHz  0.25  24%   1%  22%   0%   0%   0%  52.0°C
14:28:51: 3300MHz  0.09   0%   0%   0%   0%   0%   0%  51.0°C
14:29:51: 3300MHz  0.11   0%   0%   0%   0%   0%   0%  51.0°C
14:30:51: 3300MHz  0.04   0%   0%   0%   0%   0%   0%  50.0°C
14:31:51: 3300MHz  0.01   0%   0%   0%   0%   0%   0%  50.0°C
14:32:52: 3300MHz  0.00   0%   0%   0%   0%   0%   0%  49.0°C
14:33:52: 3300MHz  0.00   0%   0%   0%   0%   0%   0%  48.0°C
14:34:52: 3300MHz  0.00   0%   0%   0%   0%   0%   0%  48.0°C
14:35:52: 3300MHz  0.00   0%   0%   0%   0%   0%   0%  48.0°C
14:36:52: 3300MHz  0.00   0%   0%   0%   0%   0%   0%  47.0°C
14:37:52: 3294MHz  0.00   0%   0%   0%   0%   0%   0%  47.0°C
14:38:52: 3300MHz  0.00   0%   0%   0%   0%   0%   0%  45.0°C
14:39:52: 3300MHz  0.00   0%   0%   0%   0%   0%   0%  46.0°C
14:40:52: 3300MHz  0.00   0%   0%   0%   0%   0%   0%  46.0°C

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

pharizna@r1-pro:~$ sudo /bin/bash ./sbc-bench.sh -r

[sudo] contraseña para pharizna:

Starting to examine hardware/software for review purposes...

Average load and/or CPU utilization too high (too much background activity). Waiting...

Too busy for benchmarking: 14:12:45 up 30 min, 3 users, load average: 0.91, 1.01, 0.79, cpu: 11%

Too busy for benchmarking: 14:13:05 up 30 min, 3 users, load average: 0.65, 0.94, 0.77, cpu: 0%

Too busy for benchmarking: 14:13:10 up 31 min, 3 users, load average: 0.60, 0.93, 0.77, cpu: 0%

Too busy for benchmarking: 14:13:15 up 31 min, 3 users, load average: 0.55, 0.91, 0.76, cpu: 0%

sbc-bench v0.9.45

Installing needed tools: apt -f -qq -y install gcc make build-essential lm-sensors curl git sysstat powercap-utils binutils mmc-utils smartmontools stress-ng p7zip, tinymembench, ramlat, mhz, cpuminer. Done.

Checking cpufreq OPP. Done.

Executing tinymembench. Done.

Executing RAM latency tester. Done.

Executing OpenSSL benchmark. Done.

Executing 7-zip benchmark. Done.

Throttling test: heating up the device, 5 more minutes to wait. Done.

Checking cpufreq OPP again. Done (11 minutes elapsed).

Results validation:

* Measured clockspeed not lower than advertised max CPU clockspeed

* No swapping

* Background activity (%system) OK

* Powercap detected. Details: "sudo powercap-info -p intel-rapl"

* Throttling occured

Full results uploaded to http://ix.io/4FgU

# / Pentium Silver N6005 @ 2.00GHz

Tested with sbc-bench v0.9.45 on Sun, 03 Sep 2023 14:25:38 +0200. Full info: [http://ix.io/4FgU](http://ix.io/4FgU)

### General information:

Pentium Silver N6005 @ 2.00GHz, Kernel: x86_64, Userland: amd64

CPU sysfs topology (clusters, cpufreq members, clockspeeds)

cpufreq min max

CPU cluster policy speed speed core type

0 0 0 800 3300 Pentium Silver N6005 @ 2.00GHz

1 0 1 800 3300 Pentium Silver N6005 @ 2.00GHz

2 0 2 800 3300 Pentium Silver N6005 @ 2.00GHz

3 0 3 800 3300 Pentium Silver N6005 @ 2.00GHz

15763 KB available RAM

### Governors/policies (performance vs. idle consumption):

Original governor settings:

cpufreq-policy0: powersave / 3300 MHz (performance powersave)

cpufreq-policy1: powersave / 3300 MHz (performance powersave)

cpufreq-policy2: powersave / 3300 MHz (performance powersave)

cpufreq-policy3: powersave / 3300 MHz (performance powersave)

Tuned governor settings:

cpufreq-policy0: performance / 3300 MHz

cpufreq-policy1: performance / 3300 MHz

cpufreq-policy2: performance / 3300 MHz

cpufreq-policy3: performance / 3300 MHz

Status of performance related policies found below /sys:

/sys/module/pcie_aspm/parameters/policy: [default] performance powersave powersupersave

### Clockspeeds (idle vs. heated up):

Before at 50.0°C:

cpu0: OPP: 3300, Measured: 3290

After at 68.0°C:

cpu0: OPP: 3300, Measured: 3290

### Performance baseline

* memcpy: 9549.7 MB/s, memchr: 11200.3 MB/s, memset: 10222.6 MB/s

* 16M latency: 126.0 125.3 126.3 125.6 126.0 122.7 119.4 120.6

* 128M latency: 147.7 148.0 147.8 148.2 147.7 142.8 146.0 147.6

* 7-zip MIPS (3 consecutive runs): 13069, 12679, 13079 (12940 avg), single-threaded: 3339

* `aes-256-cbc 548728.70k 864608.17k 908079.79k 919478.61k 922927.10k 923019.95k`

* `aes-256-cbc 548456.74k 865028.27k 908333.82k 919907.33k 923243.86k 922140.67k`

### PCIe and storage devices:

* Intel Ethernet I226-V: Speed 5GT/s, Width x1, driver in use: igc

* 119.2GB "UMIS RPJTJ128MED1MWX" SSD as /dev/nvme0: Speed 8GT/s, Width x2, 0% worn out, drive temp: 45°C

* "Genesys Logic SD Card Reader and Writer" as /dev/sda: USB, Driver=usb-storage, 5Gbps (capable of 12Mbps, 480Mbps, 5Gbps)

* "Genesys Logic SD Card Reader and Writer" as /dev/sdb: USB, Driver=usb-storage, 5Gbps (capable of 12Mbps, 480Mbps, 5Gbps)

* "Genesys Logic SD Card Reader and Writer" as /dev/sdc: USB, Driver=usb-storage, 480Mbps (capable of 12Mbps, 480Mbps, 5Gbps)

* "Genesys Logic SD Card Reader and Writer" as /dev/sdd: USB, Driver=usb-storage, 480Mbps (capable of 12Mbps, 480Mbps, 5Gbps)

* Winbond W25Q256 16MB SPI NOR flash, drivers in use: spi-nor/intel-spi

### Swap configuration:

* /swap.img on /dev/nvme0n1p2: 4.0G (0K used)

### Software versions:

* Ubuntu 23.04

* Compiler: /usr/bin/gcc (Ubuntu 12.3.0-1ubuntu1~23.04) 12.3.0 / x86_64-linux-gnu

* OpenSSL 3.0.8, built on 7 Feb 2023 (Library: OpenSSL 3.0.8 7 Feb 2023)

### Kernel info:

* `/proc/cmdline: BOOT_IMAGE=/boot/vmlinuz-6.2.0-31-generic root=UUID=70ec93ad-1107-4655-a865-6be50f4f0fc7 ro quiet splash vt.handoff=7`

* Vulnerability Mmio stale data: Mitigation; Clear CPU buffers; SMT disabled

* Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl

* Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization

* Vulnerability Srbds: Vulnerable: No microcode

* Kernel 6.2.0-31-generic / CONFIG_HZ=250

Waiting for the device to cool down................................................. 52.0°C

All known settings adjusted for performance. Device now ready for benchmarking.

Once finished stop with [ctrl]-[c] to get info about throttling, frequency cap

and too high background activity all potentially invalidating benchmark scores.

All changes with storage and PCIe devices as well as suspicious dmesg contents

will be reported too.

Time CPU load %cpu %sys %usr %nice %io %irq Temp

14:27:51: 3300MHz 0.25 24% 1% 22% 0% 0% 0% 52.0°C

14:28:51: 3300MHz 0.09 0% 0% 0% 0% 0% 0% 51.0°C

14:29:51: 3300MHz 0.11 0% 0% 0% 0% 0% 0% 51.0°C

14:30:51: 3300MHz 0.04 0% 0% 0% 0% 0% 0% 50.0°C

14:31:51: 3300MHz 0.01 0% 0% 0% 0% 0% 0% 50.0°C

14:32:52: 3300MHz 0.00 0% 0% 0% 0% 0% 0% 49.0°C

14:33:52: 3300MHz 0.00 0% 0% 0% 0% 0% 0% 48.0°C

14:34:52: 3300MHz 0.00 0% 0% 0% 0% 0% 0% 48.0°C

14:35:52: 3300MHz 0.00 0% 0% 0% 0% 0% 0% 48.0°C

14:36:52: 3300MHz 0.00 0% 0% 0% 0% 0% 0% 47.0°C

14:37:52: 3294MHz 0.00 0% 0% 0% 0% 0% 0% 47.0°C

14:38:52: 3300MHz 0.00 0% 0% 0% 0% 0% 0% 45.0°C

14:39:52: 3300MHz 0.00 0% 0% 0% 0% 0% 0% 46.0°C

14:40:52: 3300MHz 0.00 0% 0% 0% 0% 0% 0% 46.0°C

Comparando los resultados con los obtenidos en la misma prueba con el R86S, en aquella ocasión la CPU se «sobrecalentó» hasta los 63ºC mientras que en este R1-Pro se han alcanzado los 68ºC lo que confirma que incluso con el nuevo diseño del disipador de cobre la refrigeración del R1-Pro sigue siendo peor que la del R86S

12108

11 Comments

Inline Feedbacks

Ver todos los comentarios

Admin

Pharizna

1 año antes

Al utilizar el backup del HA de mi casa madrileña pensaba que no iba a poder aprovechar casi nada. Sin embargo como la mayoría de los «servicios» funcionan a través de servidores en la nube puedo incluso controlar el AC de mi casa madrileña desde el pueblo manchego o ver como está el pH o el cloro de la piscina del pueblo indistintamente desde donde me encuentre. Claro!

Solo me falla la integración con la AEMET pero supongo es debido a la nueva versión que estoy usando en el pueblo.

Acabamos de hablar con Jackeroo y nos ha confirmado un nuevo R2 con mejoras. Con el mismo diseño tendrá sitio para una wifi M.2 y procesadores Intel de la siguiente generación y por tanto más fresquitos y más potentes.

En uno o dos meses lo estaremos revisando en PcDeMaNo. 😜

Lantzi

Interesado en el tema de PROXMOX. La Raspi me da muchos problemas ultimamente y no logro descubrir por qué (se queda horas como dormida¿?) Había mirado la posibilidad de montar PROXMOX en un Beelink Gemini M con un J4125 y 8GB pero no sé si será suficiente para moverlo con HA y poca cosa más

En respuesta a Lantzi

Seguro que sí. Venga ánimate y si tienes alguna duda ya sabes donde preguntar 😉

Dejando 2GB de RAM para el HA es suficiente y tampoco necesita de un procesador potente para que funcione.

En respuesta a Pharizna

Todo funcionando (creo)

Seguro que sí. Has pasado también el MQTT, etc? Con los scripts del fulano ese es super sencillo instalar cualquier cosa en Proxmox.

Yo estoy esperando que Rubén nos consiga un NAS con procesador Intel para instalar en él Proxmox y luego el resto incluyendo HA, Plex, Jellyfin, etc, etc 😏

Mosquitto lo tengo en el NAS. He montado Mariadb bajo Proxmox que parece que es lo que mas recomiendan y me falta instalar de alguna manera el RTL_433 pero esto no me corre prisa

Nuestro amigo Rubén (antes conocido como Rubik2k) especialista en NAS nos ha conseguido un potente ASUSTOR NIMBUSTOR 2 Gen2 (AS5402T) con procesador Intel Celeron N5105, 4 ranuras M.2 y dos bahías para SSD/HD, etc, etc.

Nuestra idea inicial es, después de haber hecho la revisión, «reconvertirlo» en un servidor con PROXMOX para HomeAssistant, Jellyfin, etc, etc… y para terminar… instalar el «firmware» de Synology (o QNAP) para recuperar su funcionamiento como NAS pero con la apariencia de uno de estos. Ya os iremos contando nuestros avances

Vaya pepino!!!.

Aunque la idea del proyecto la vamos teniendo clara ya solo nos faltan algunas cosillas de hardware:

– El NAS NIMBUSTOR 2
– Acabamos de pedir un SSD NVMe de 128 GB donde instalar el PROXMOX que nos llegará para primeros de octubre
– También hemos comprado un banco de memoria adicional de 8GB a los 4 que trae de serie el NAS para que no tengamos problemas de memoria para instalar muchas máquinas virtuales… según se nos vaya ocurriendo.

Ya se puede “preordenar” el nuevo R2 que se enviará a partir del 10 de octubre,