October 23, 20241 yr Hello, I just updated my server hardware and found that it becomes unreachable after a certain amount of time. I read that some intel Nics can cause similar issue but I m not sure if thats the case here. This is what I found in the logs. Thanks' Oct 23 09:49:07 SKYdrive webGUI: Successful login user root from 192.168.1.113 Oct 23 09:49:14 SKYdrive kernel: igc 0000:01:00.0 eth0: PCIe link lost, device now detached Oct 23 09:49:14 SKYdrive kernel: ------------[ cut here ]------------ Oct 23 09:49:14 SKYdrive kernel: igc: Failed to read reg 0xc030! Oct 23 09:49:14 SKYdrive kernel: WARNING: CPU: 1 PID: 64 at drivers/net/ethernet/intel/igc/igc_main.c:6481 igc_rd32+0x76/0x8b [igc] Oct 23 09:49:14 SKYdrive kernel: Modules linked in: xt_CHECKSUM ipt_REJECT nf_reject_ipv4 xt_tcpudp ip6table_mangle ip6table_nat iptable_mangle vhost_net tun vhost vhost_iotlb tap xt_conntrack xt_MASQUERADE nf_conntrack_netlink nfnetlink xfrm_user xfrm_algo iptable_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 xt_addrtype br_netfilter xfs md_mod zfs(PO) zunicode(PO) zzstd(O) zlua(O) zavl(PO) icp(PO) zcommon(PO) znvpair(PO) spl(O) ip6table_filter ip6_tables iptable_filter ip_tables x_tables efivarfs af_packet 8021q garp mrp bridge stp llc bonding tls i915 intel_rapl_msr intel_rapl_common x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel kvm iosf_mbi drm_buddy i2c_algo_bit ttm btusb btrtl btbcm drm_display_helper btintel bluetooth drm_kms_helper crct10dif_pclmul crc32_pclmul crc32c_intel ghash_clmulni_intel sha512_ssse3 sha256_ssse3 drm sha1_ssse3 ecdh_generic aesni_intel ecc crypto_simd cryptd mei_hdcp mei_pxp gigabyte_wmi wmi_bmof rapl intel_cstate intel_uncore intel_gtt i2c_i801 mei_me Oct 23 09:49:14 SKYdrive kernel: i2c_smbus agpgart ahci igc libahci i2c_core mei syscopyarea sysfillrect sysimgblt thermal fan fb_sys_fops tpm_crb video tpm_tis tpm_tis_core wmi tpm backlight intel_pmc_core acpi_tad acpi_pad button unix Oct 23 09:49:14 SKYdrive kernel: CPU: 1 PID: 64 Comm: kworker/1:1 Tainted: P O 6.1.106-Unraid #1 Oct 23 09:49:14 SKYdrive kernel: Hardware name: Gigabyte Technology Co., Ltd. B760I AORUS PRO DDR4/B760I AORUS PRO DDR4, BIOS F12 09/27/2024 Oct 23 09:49:14 SKYdrive kernel: Workqueue: events igc_watchdog_task [igc] Oct 23 09:49:14 SKYdrive kernel: RIP: 0010:igc_rd32+0x76/0x8b [igc] Oct 23 09:49:14 SKYdrive kernel: Code: 8b bb 28 ff ff ff e8 9e 2a 11 e1 84 c0 75 0d 83 c8 ff eb 1a 8b 02 ff c0 75 f5 eb bf 89 ee 48 c7 c7 73 00 3a a0 e8 51 eb cd e0 <0f> 0b eb e1 5b 5d 41 5c c3 cc cc cc cc 83 c8 ff c3 cc cc cc cc 0f Oct 23 09:49:14 SKYdrive kernel: RSP: 0018:ffffc9000035be00 EFLAGS: 00010286 Oct 23 09:49:14 SKYdrive kernel: RAX: 0000000000000000 RBX: ffff8881054d0ba8 RCX: 0000000000000027 Oct 23 09:49:14 SKYdrive kernel: RDX: 0000000000000003 RSI: ffffffff820d99e1 RDI: 00000000ffffffff Oct 23 09:49:14 SKYdrive kernel: RBP: 000000000000c030 R08: 0000000000000000 R09: ffffffff82245fb0 Oct 23 09:49:14 SKYdrive kernel: R10: 00007fffffffffff R11: ffffffff829656fe R12: ffff8881054d0000 Oct 23 09:49:14 SKYdrive kernel: R13: 000000000000c030 R14: ffff888105bd5c80 R15: 0000000000000000 Oct 23 09:49:14 SKYdrive kernel: FS: 0000000000000000(0000) GS:ffff8884afa40000(0000) knlGS:0000000000000000 Oct 23 09:49:14 SKYdrive kernel: CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 Oct 23 09:49:14 SKYdrive kernel: CR2: 000019c5d243a958 CR3: 000000000420a005 CR4: 0000000000770ee0 Oct 23 09:49:14 SKYdrive kernel: PKRU: 55555554 Oct 23 09:49:14 SKYdrive kernel: Call Trace: Oct 23 09:49:14 SKYdrive kernel: <TASK> Oct 23 09:49:14 SKYdrive kernel: ? __warn+0xab/0x122 Oct 23 09:49:14 SKYdrive kernel: ? report_bug+0x109/0x17e Oct 23 09:49:14 SKYdrive kernel: ? igc_rd32+0x76/0x8b [igc] Oct 23 09:49:14 SKYdrive kernel: ? handle_bug+0x41/0x6f Oct 23 09:49:14 SKYdrive kernel: ? exc_invalid_op+0x13/0x60 Oct 23 09:49:14 SKYdrive kernel: ? asm_exc_invalid_op+0x16/0x20 Oct 23 09:49:14 SKYdrive kernel: ? igc_rd32+0x76/0x8b [igc] Oct 23 09:49:14 SKYdrive kernel: igc_update_stats+0x70/0x6ae [igc] Oct 23 09:49:14 SKYdrive kernel: igc_watchdog_task+0x308/0x435 [igc] Oct 23 09:49:14 SKYdrive kernel: process_one_work+0x1a8/0x295 Oct 23 09:49:14 SKYdrive kernel: worker_thread+0x18b/0x244 Oct 23 09:49:14 SKYdrive kernel: ? rescuer_thread+0x281/0x281 Oct 23 09:49:14 SKYdrive kernel: kthread+0xe4/0xef Oct 23 09:49:14 SKYdrive kernel: ? kthread_complete_and_exit+0x1b/0x1b Oct 23 09:49:14 SKYdrive kernel: ret_from_fork+0x1f/0x30 Oct 23 09:49:14 SKYdrive kernel: </TASK> Oct 23 09:49:14 SKYdrive kernel: ---[ end trace 0000000000000000 ]--- Oct 23 09:50:11 SKYdrive elogind-daemon[1162]: Power key pressed.
October 23, 20241 yr Community Expert 30 minutes ago, skycptn said: igc 0000:01:00.0 eth0: PCIe link lost, device now detached This means the NIC is dropping offline, assuming it's onboard, try disabling ASPM, or use an add-on NIC.
October 23, 20241 yr @skycptn There are several users here working with the Gigabyte B760I and some are facing the same problem (me included, see my postings in other related threads). I am gathering informations of what exactly is causing this behavior. ASPM could be one reason. But there are also user with the B760I running fine for months without a crash at all. At the moment, I assume it could be one of these things: ASPM enabled in BIOS (and using powertop within Unraid) WoL activated C-States enabled in BIOS (and using powertop within Unraid) EEE (Energy efficient Ethernet) enabled for the NIC I have used my system with the following things activated/deactivated for the last 20 days with no crash: ASPM enabled in BIOS (but no Powertop) C-States deactivated WoL active EEE not active So this seems to be a stable environment. But this is not max. power saving, so I want to go further... I am now testing with: ASPM enabled in BIOS (but no Powertop) C-States enabled in BIOS (with C8 highest, no Powertop) WoL deactivated (one user suggested to deactivate this if not needed) EEE not active If this is running stable for the next 20 days or so, I will try with powertop.
October 23, 20241 yr Author 1 hour ago, JayDee73 said: @skycptn There are several users here working with the Gigabyte B760I and some are facing the same problem (me included, see my postings in other related threads). I am gathering informations of what exactly is causing this behavior. ASPM could be one reason. But there are also user with the B760I running fine for months without a crash at all. At the moment, I assume it could be one of these things: ASPM enabled in BIOS (and using powertop within Unraid) WoL activated C-States enabled in BIOS (and using powertop within Unraid) EEE (Energy efficient Ethernet) enabled for the NIC I have used my system with the following things activated/deactivated for the last 20 days with no crash: ASPM enabled in BIOS (but no Powertop) C-States deactivated WoL active EEE not active So this seems to be a stable environment. But this is not max. power saving, so I want to go further... I am now testing with: ASPM enabled in BIOS (but no Powertop) C-States enabled in BIOS (with C8 highest, no Powertop) WoL deactivated (one user suggested to deactivate this if not needed) EEE not active If this is running stable for the next 20 days or so, I will try with powertop. Thanks for the reply. I will start testing then... Not happy with the situation
October 27, 20241 yr I had another NIC-detach-crash with the above mentioned settings. So with further research, de-activating ASPM at all will solve the issue. You can add pcie_port_pm=off pcie_aspm.policy=performance to the boot settings to achieve this. But with this option ALL PCI devices will have ASPM de-activated, which isn't really necessary, because we only have one problematic device (the NIC). So atm I am trying to enable ASPM in general (also running powertop) and only de-activate ASPM for the Intel NIC. Will monitor this setup during the coming days...
January 13, 20251 yr Where do you put pcie_port_pm=off pcie_aspm.policy=performance? Is it just in syslinux.cfg?
January 14, 20251 yr Community Expert 9 hours ago, TMRiddle said: Is it just in syslinux.cfg? Yes, after /bzroot for the default boot option.
July 20, 2025Jul 20 On 10/27/2024 at 5:24 PM, JayDee73 said:But with this option ALL PCI devices will have ASPM de-activated, which isn't really necessary, because we only have one problematic device (the NIC). So atm I am trying to enable ASPM in general (also running powertop) and only de-activate ASPM for the Intel NIC. Will monitor this setup during the coming days...Hi @JayDee73 ,What are your experiences so far?Do you have a tip on how to disable ASPM only for the INTEL NIC?to all other:Gigabyte released a new BIOS Version (v. F14c), does this version fix/improve the behaviour?Has anyone already used BIOS F14c and can share their experiences here?Link to Gigabyte (B760I AORUS PRO DDR4 (rev. 1.x)):https://www.gigabyte.com/eu/Motherboard/B760I-AORUS-PRO-DDR4-rev-1x/SupportBest regards
July 20, 2025Jul 20 20 minutes ago, Xenforce87 said:Hi @JayDee73 ,What are your experiences so far?Do you have a tip on how to disable ASPM only for the INTEL NIC?to all other:Gigabyte released a new BIOS Version (v. F14c), does this version fix/improve the behaviour?Has anyone already used BIOS F14c and can share their experiences here?Link to Gigabyte (B760I AORUS PRO DDR4 (rev. 1.x)):https://www.gigabyte.com/eu/Motherboard/B760I-AORUS-PRO-DDR4-rev-1x/SupportBest regardsTo be honest, I couldn't get it to go and finally switched over to another mobo. Also from Gigabyte, but with RTL8125 chipset.
Join the conversation
You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.