Minisforum ms-01 i9-13900H 96GB with Proxmox

[GFHandel]

The unreleased BIOS in the internal version has been sent to you via private message

Hi, can you please send my the new BIOS as well? I'm on 1.22 (from the website) but still having these crashes at least twice a week now.

 

[reneil1337]

maximum was 4 days, mostly 1-2 days

 

[jsunjones]

It's been a record 7 days (fingers crossed)

 

[reneil1337]

thats sounds great! will be back at the server to install the bios and test lower ram frequency next week. is that everything you changed resulting in the 7 days run @jsunjones ?

 

[jsunjones]

I did that as well as get the latest microcode

 

[reneil1337]

amazing. which is the latest microcode? do you maybe have a link? prepping everything for next week

 

[jsunjones]

basically just use this documentation, it should give you the latest one (0x4121 I believe)

 

[jars1]

Hello @jsunjones, please provide v1.23 BIOS version. Same issue on (2) MS-01s:
Linux node4 6.5.13-5-pve #1 SMP PREEMPT_DYNAMIC PMX 6.5.13-5 (2024-04-05T11:03Z) x86_64 GNU/Linux

microcode : 0x410c

# dmidecode 3.4
Getting SMBIOS data from sysfs.
SMBIOS 3.5.0 present.

Handle 0x0028, DMI type 17, 92 bytes
Memory Device
Array Handle: 0x0027
Error Information Handle: Not Provided
Total Width: 64 bits
Data Width: 64 bits
Size: 48 GB
Form Factor: SODIMM
Set: None
Locator: Controller0-ChannelA-DIMM0
Bank Locator: BANK 0
Type: DDR5
Type Detail: Synchronous
Speed: 5600 MT/s
Manufacturer: Crucial Technology
Serial Number: E9ECF421
Asset Tag: 9876543210
Part Number: CT48G56C46S5.M16B1
Rank: 2
Configured Memory Speed: 5200 MT/s
Minimum Voltage: 1.1 V
Maximum Voltage: 1.1 V
Configured Voltage: 1.1 V
Memory Technology: DRAM
Memory Operating Mode Capability: Volatile memory
Firmware Version: Not Specified
Module Manufacturer ID: Bank 6, Hex 0x9B
Module Product ID: Unknown
Memory Subsystem Controller Manufacturer ID: Unknown
Memory Subsystem Controller Product ID: Unknown
Non-Volatile Size: None
Volatile Size: 48 GB
Cache Size: None
Logical Size: None

Handle 0x0029, DMI type 17, 92 bytes
Memory Device
Array Handle: 0x0027
Error Information Handle: Not Provided
Total Width: 64 bits
Data Width: 64 bits
Size: 48 GB
Form Factor: SODIMM
Set: None
Locator: Controller1-ChannelA-DIMM0
Bank Locator: BANK 0
Type: DDR5
Type Detail: Synchronous
Speed: 5600 MT/s
Manufacturer: Crucial Technology
Serial Number: E9ECF3D7
Asset Tag: 9876543210
Part Number: CT48G56C46S5.M16B1
Rank: 2
Configured Memory Speed: 5200 MT/s
Minimum Voltage: 1.1 V
Maximum Voltage: 1.1 V
Configured Voltage: 1.1 V
Memory Technology: DRAM
Memory Operating Mode Capability: Volatile memory
Firmware Version: Not Specified
Module Manufacturer ID: Bank 6, Hex 0x9B
Module Product ID: Unknown
Memory Subsystem Controller Manufacturer ID: Unknown
Memory Subsystem Controller Product ID: Unknown
Non-Volatile Size: None
Volatile Size: 48 GB
Cache Size: None
Logical Size: None



Jul 14 23:51:13 node4 kernel: general protection fault, probably for non-canonical address 0x91a5e04bf6350e32: 0000 [#1] PREEMPT SMP NOPTI
Jul 14 23:51:13 node4 kernel: CPU: 4 PID: 6148 Comm: pvestatd Tainted: P U W OE 6.5.13-5-pve #1
Jul 14 23:51:13 node4 kernel: Hardware name: Micro Computer (HK) Tech Limited Venus Series/AHWSA, BIOS AHWSA.1.22 03/12/2024
Jul 14 23:51:13 node4 kernel: RIP: 0010:kmem_cache_alloc+0x107/0x380
Jul 14 23:51:13 node4 kernel: Code: 0f 84 31 02 00 00 48 85 ff 0f 84 28 02 00 00 41 8b 44 24 28 49 8b 9c 24 b8 00 00 00 49 8d 88 00 20 00 00 4d 8b 0c 24 48 01 f8 <48> 33 18 48 89 c2 48 89 f8 48 0f ca 48 31
d3 4c 89 c2 65 49 0f c7
Jul 14 23:51:13 node4 kernel: RSP: 0018:ffffafec00c9fb30 EFLAGS: 00010282
Jul 14 23:51:13 node4 kernel: RAX: 91a5e04bf6350e32 RBX: 33751f7b33b83bcf RCX: 00000094f2992004
Jul 14 23:51:13 node4 kernel: RDX: 0000000000000000 RSI: 0000000000000000 RDI: 91a5e04bf6350e22
Jul 14 23:51:13 node4 kernel: RBP: ffffafec00c9fb78 R08: 00000094f2990004 R09: 0000000000039e10
Jul 14 23:51:13 node4 kernel: R10: 0000000000000000 R11: 0000000000000000 R12: ffff9f0fc0211e00
Jul 14 23:51:13 node4 kernel: R13: 0000000000000cc0 R14: ffff9f0feaeac640 R15: 0000000000000028
Jul 14 23:51:13 node4 kernel: FS: 00007cb0d3549740(0000) GS:ffff9f270f700000(0000) knlGS:0000000000000000
Jul 14 23:51:13 node4 kernel: CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
Jul 14 23:51:13 node4 kernel: CR2: 00005fd2750a96f8 CR3: 000000010153a000 CR4: 0000000000752ee0
Jul 14 23:51:13 node4 kernel: PKRU: 55555554
Jul 14 23:51:13 node4 kernel: Call Trace:
Jul 14 23:51:13 node4 kernel: <TASK>
Jul 14 23:51:13 node4 kernel: ? show_regs+0x6d/0x80
Jul 14 23:51:13 node4 kernel: ? die_addr+0x37/0xa0
Jul 14 23:51:13 node4 kernel: ? exc_general_protection+0x1c3/0x460
Jul 14 23:51:13 node4 kernel: ? asm_exc_general_protection+0x27/0x30
Jul 14 23:51:13 node4 kernel: ? kmem_cache_alloc+0x107/0x380
Jul 14 23:51:13 node4 kernel: ? vm_area_dup+0x4f/0x140
Jul 14 23:51:13 node4 kernel: vm_area_dup+0x4f/0x140
Jul 14 23:51:13 node4 kernel: ? mas_find+0x65/0x140
Jul 14 23:51:13 node4 kernel: dup_mmap+0x279/0x760
Jul 14 23:51:13 node4 kernel: copy_process+0x1c7f/0x1d50
Jul 14 23:51:13 node4 kernel: kernel_clone+0xbd/0x440
Jul 14 23:51:13 node4 kernel: ? hrtimer_try_to_cancel+0x1b/0x120
Jul 14 23:51:13 node4 kernel: __do_sys_clone+0x66/0xa0
Jul 14 23:51:13 node4 kernel: __x64_sys_clone+0x25/0x40
Jul 14 23:51:13 node4 kernel: do_syscall_64+0x58/0x90
Jul 14 23:51:13 node4 kernel: ? sigprocmask+0xb4/0xe0
Jul 14 23:51:13 node4 kernel: ? exit_to_user_mode_prepare+0x39/0x190
Jul 14 23:51:13 node4 kernel: ? syscall_exit_to_user_mode+0x37/0x60
Jul 14 23:51:13 node4 kernel: ? do_syscall_64+0x67/0x90
Jul 14 23:51:13 node4 kernel: ? irqentry_exit_to_user_mode+0x17/0x20
Jul 14 23:51:13 node4 kernel: ? irqentry_exit+0x43/0x50
Jul 14 23:51:13 node4 kernel: ? exc_page_fault+0x94/0x1b0
Jul 14 23:51:13 node4 kernel: entry_SYSCALL_64_after_hwframe+0x6e/0xd8
Jul 14 23:51:13 node4 kernel: RIP: 0033:0x7cb0d365c293
Jul 14 23:51:13 node4 kernel: Code: 00 00 00 00 00 66 90 64 48 8b 04 25 10 00 00 00 45 31 c0 31 d2 31 f6 bf 11 00 20 01 4c 8d 90 d0 02 00 00 b8 38 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 35 89 c2 85 c0 75 2c
64 48 8b 04 25 10 00 00
Jul 14 23:51:13 node4 kernel: RSP: 002b:00007ffebfc6c218 EFLAGS: 00000246 ORIG_RAX: 0000000000000038
Jul 14 23:51:13 node4 kernel: RAX: ffffffffffffffda RBX: 0000000000000002 RCX: 00007cb0d365c293
Jul 14 23:51:13 node4 kernel: RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000001200011
Jul 14 23:51:13 node4 kernel: RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
Jul 14 23:51:13 node4 kernel: R10: 00007cb0d3549a10 R11: 0000000000000246 R12: 0000000000000001
Jul 14 23:51:13 node4 kernel: R13: 00007ffebfc6c330 R14: 00007ffebfc6c3b0 R15: 00007cb0d3885020
Jul 14 23:51:13 node4 kernel: </TASK>
Jul 14 23:51:13 node4 kernel: Modules linked in: veth snumbd26(OE) snapapi26(OE) rpcsec_gss_krb5 auth_rpcgss nfsv4 nfs lockd grace fscache netfs ebtable_filter ebtables ip6table_raw ip6t_REJECT nf_reject_ip
v6 ip6table_filter ip6_tables iptable_raw xt_mac ipt_REJECT nf_reject_ipv4 xt_physdev xt_addrtype xt_multiport xt_conntrack nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 xt_tcpudp xt_set xt_comment xt_mark ipt
able_filter bpfilter ip_set_hash_net ip_set sctp ip6_udp_tunnel udp_tunnel nf_tables nvme_fabrics 8021q garp mrp bonding tls softdog sunrpc binfmt_misc nfnetlink_log nfnetlink intel_rapl_msr intel_rapl_comm
on intel_uncore_frequency intel_uncore_frequency_common snd_hda_codec_hdmi snd_hda_codec_realtek snd_hda_codec_generic ledtrig_audio nvidia_vgpu_vfio(OE) snd_sof_pci_intel_tgl snd_sof_intel_hda_common sound
wire_intel snd_sof_intel_hda_mlink soundwire_cadence snd_sof_intel_hda snd_sof_pci snd_sof_xtensa_dsp nvidia(POE) snd_sof snd_sof_utils snd_soc_hdac_hda snd_hda_ext_core snd_soc_acpi_intel_match i915(OE) sn
d_soc_acpi
Jul 14 23:51:13 node4 kernel: soundwire_generic_allocation soundwire_bus x86_pkg_temp_thermal intel_powerclamp snd_soc_core snd_compress coretemp ac97_bus snd_pcm_dmaengine kvm_intel crct10dif_pclmul snd_h
da_intel polyval_clmulni mt7921e polyval_generic snd_intel_dspcfg ghash_clmulni_intel mt7921_common btusb snd_intel_sdw_acpi sha256_ssse3 btrtl snd_hda_codec mt76_connac_lib sha1_ssse3 drm_buddy btbcm mt76
ttm snd_hda_core aesni_intel btintel drm_display_helper crypto_simd snd_hwdep btmtk mac80211 mei_hdcp mei_pxp cec snd_pcm cryptd bluetooth rc_core cfg80211 mdev snd_timer cmdlinepart mei_me drm_kms_helper e
cdh_generic spi_nor snd rapl kvm i2c_algo_bit soundcore libarc4 intel_cstate ecc mtd wmi_bmof pcspkr mei acpi_pad acpi_tad mac_hid zfs(PO) spl(O) vhost_net vhost vhost_iotlb tap vfio_pci vfio_pci_core irqby
pass vfio_iommu_type1 vfio iommufd drm efi_pstore dmi_sysfs ip_tables x_tables autofs4 btrfs blake2b_generic xor raid6_pq libcrc32c simplefb xhci_pci nvme xhci_pci_renesas i40e crc32_pclmul spi_intel_pci i2
c_i801 thunderbolt
Jul 14 23:51:13 node4 kernel: xhci_hcd nvme_core spi_intel igc i2c_smbus nvme_common video pinctrl_tigerlake wmi
Jul 14 23:51:13 node4 kernel: ---[ end trace 0000000000000000 ]---
Jul 14 23:51:13 node4 kernel: RIP: 0010:kmem_cache_alloc+0x107/0x380
Jul 14 23:51:13 node4 kernel: Code: 0f 84 31 02 00 00 48 85 ff 0f 84 28 02 00 00 41 8b 44 24 28 49 8b 9c 24 b8 00 00 00 49 8d 88 00 20 00 00 4d 8b 0c 24 48 01 f8 <48> 33 18 48 89 c2 48 89 f8 48 0f ca 48 31
d3 4c 89 c2 65 49 0f c7
Jul 14 23:51:13 node4 kernel: RSP: 0018:ffffafec00c9fb30 EFLAGS: 00010282
Jul 14 23:51:13 node4 kernel: RAX: 91a5e04bf6350e32 RBX: 33751f7b33b83bcf RCX: 00000094f2992004
Jul 14 23:51:13 node4 kernel: RDX: 0000000000000000 RSI: 0000000000000000 RDI: 91a5e04bf6350e22
Jul 14 23:51:13 node4 kernel: RBP: ffffafec00c9fb78 R08: 00000094f2990004 R09: 0000000000039e10
Jul 14 23:51:13 node4 kernel: R10: 0000000000000000 R11: 0000000000000000 R12: ffff9f0fc0211e00
Jul 14 23:51:13 node4 kernel: R13: 0000000000000cc0 R14: ffff9f0feaeac640 R15: 0000000000000028
Jul 14 23:51:13 node4 kernel: FS: 00007cb0d3549740(0000) GS:ffff9f270f700000(0000) knlGS:0000000000000000
Jul 14 23:51:13 node4 kernel: CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
--More--

 

[Toormser]

Can anyone confirm this, that the MS-01 works without any issues with the tweakes from here like

• microcode update
• BIOS update to latest version

I think about to buying the MS-01 for Proxmox but currently I'm not sure how stable it is. I'm planning to install 1 Windows 11 machine and some debian servers on it.

 

[jars1]

Hello @Toormser , I own (2) MS-01 13900h both exact same specs: Crucial Technology (2)x48GB - 5600MTs, microcode : 0x410c , 6.5.13-5-pve kernel. Both experience random/unexpected shutdowns. Both had BIOS AHWSA.1.22 03/12/2024 BIOS version. @jsunjones kindly shared with me beta BIOS v 1.24 which allows lowering DDR5 freq. which he suggests to lower to 4400 MTs. I choose to upgrade bios and lower mem to 4800MTs and retry. Will let you know if stay stable for more than 4 days. This might be related to this video. If anyone with more in-depth knowledge on this topic could provide some insight, it would be greatly appreciated.

 

[jsunjones]

I can’t take credit for the bios. That belongs to @JaxJiang

also i have not shared the bios. This should come directly from @JaxJiang

 

[jars1]

My bad, correct @JaxJiang shared it with me.

 

[Toormser]

Maybe @JaxJiang can share the BETA Bios with all of us?

 

[JaxJiang]

Maybe @JaxJiang can share the BETA Bios with all of us?

The BIOS is currently under internal testing. In order to count the number of problems, you can send me a private message directly.

 

[Toormser]

The BIOS is currently under internal testing. In order to count the number of problems, you can send me a private message directly.

Can you share it with me? Thanks.

 

[reneil1337]

Just flashed the BIOS 1.24 and lowered the RAM frequency to 4400. Now its time to go past 1 week uptime. Fingers crossed!

 

[jars1]

I require higher memory speeds, at least 4800MT/s, due to the tasks I run. The i9-13900H supports DDR5 up to 5200MT/s, with the base DDR5 transfer speed being around 4800MT/s. Could you explain why the RAM clock speed has been downgraded to 4400MT/s, aside from gaining stability? What is the technical reason for this downgrade? and is this a temporary workaround from Minisforum which BIOS version 1.24 allows underclocking the memory without applying any permanent fixes to the issue which allow for mem transfer speed to be set back to AUTO/5200 MT/s?


Thank you.

 

[Toormser]

and ... additional to the latest post: Will this fail behaivor finally fixed in a future bios-version to increase the MTS back to 5200?

 

[JaxJiang]

and ... additional to the latest post: Will this fail behaivor finally fixed in a future bios-version to increase the MTS back to 5200?

This problem is hard to traking. Currently we recommand using kingston RAM if you want to run 5200Mhz.
There is no any report of memory issue from kingston RAM.

 

[Toormser]

This problem is hard to traking. Currently we recommand using kingston RAM if you want to run 5200Mhz.
There is no any report of memory issue from kingston RAM.

Can you share the direct link to your supported kingston RAM like from Amazon, Bestbuy or Vendor directly.