All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Marek Marczykowski-Górecki" <marmarek@invisiblethingslab.com>
To: "Lifshits, Vitaly" <vitaly.lifshits@intel.com>
Cc: Jesse Brandeburg <jesse.brandeburg@intel.com>,
	Tony Nguyen <anthony.l.nguyen@intel.com>,
	netdev@vger.kernel.org, intel-wired-lan@lists.osuosl.org,
	regressions@lists.linux.dev, stable@vger.kernel.org,
	Sasha Levin <sashal@kernel.org>
Subject: Re: [Intel-wired-lan] [REGRESSION] e1000e heavy packet loss on Meteor Lake - 6.14.2
Date: Mon, 14 Apr 2025 14:58:09 +0200	[thread overview]
Message-ID: <Z_0GYR8jR-5NWZ9K@mail-itl> (raw)
In-Reply-To: <b1f5e997-033c-33ed-5e3b-6fe2632bf718@intel.com>

[-- Attachment #1: Type: text/plain, Size: 3603 bytes --]

On Mon, Apr 14, 2025 at 03:38:39PM +0300, Lifshits, Vitaly wrote:
> Do you see the high packet loss without the virtualization?

I can't check that easily right now, will try later.

> Can you please share the lspci output?

Sure:

00:07.0 Ethernet controller [0200]: Intel Corporation Device [8086:550a] (rev 20)
	Subsystem: CLEVO/KAPOK Computer Device [1558:a743]
	Physical Slot: 7
	Control: I/O- Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B- DisINTx+
	Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR- INTx-
	Latency: 64
	Interrupt: pin D routed to IRQ 69
	Region 0: Memory at f2000000 (32-bit, non-prefetchable) [size=128K]
	Capabilities: [c8] Power Management version 3
		Flags: PMEClk- DSI+ D1- D2- AuxCurrent=0mA PME(D0-,D1-,D2-,D3hot-,D3cold-)
		Status: D0 NoSoftRst+ PME-Enable- DSel=0 DScale=1 PME-
	Capabilities: [d0] MSI: Enable+ Count=1/1 Maskable- 64bit+
		Address: 00000000fee00000  Data: 0000
	Kernel driver in use: e1000e
	Kernel modules: e1000e



> Does your switch/link partner support flow control? if it is configurable
> can you try to enable it?

It does support it. Enabling it makes things much worse...

> Do you see any errors in dmesg related to the e1000e driver?

Not really.
dmesg | grep 'e1000e\|ens7':

[    3.088489] e1000e: Intel(R) PRO/1000 Network Driver
[    3.088512] e1000e: Copyright(c) 1999 - 2015 Intel Corporation.
[    3.093256] e1000e 0000:00:07.0: Interrupt Throttling Rate (ints/sec) set to dynamic conservative mode
[    3.343378] e1000e 0000:00:07.0 0000:00:07.0 (uninitialized): registered PHC clock
[    3.718946] e1000e 0000:00:07.0 eth0: (PCI Express:2.5GT/s:Width x1) d4:93:90:3e:0d:bb
[    3.718966] e1000e 0000:00:07.0 eth0: Intel(R) PRO/1000 Network Connection
[    3.719101] e1000e 0000:00:07.0 eth0: MAC: 16, PHY: 12, PBA No: FFFFFF-0FF
[    3.759444] e1000e 0000:00:07.0 ens7: renamed from eth0
[    8.632317] e1000e 0000:00:07.0 ens7: NIC Link is Up 1000 Mbps Full Duplex, Flow Control: None
[  239.458205] e1000e 0000:00:07.0 ens7: NIC Link is Down
[  242.485869] e1000e 0000:00:07.0 ens7: NIC Link is Up 1000 Mbps Full Duplex, Flow Control: Rx/Tx

(you can also see a test with flow control above)


And also ethtool output if useful:
Settings for ens7:
	Supported ports: [ TP ]
	Supported link modes:   10baseT/Half 10baseT/Full
	                        100baseT/Half 100baseT/Full
	                        1000baseT/Full
	Supported pause frame use: Symmetric Receive-only
	Supports auto-negotiation: Yes
	Supported FEC modes: Not reported
	Advertised link modes:  10baseT/Half 10baseT/Full
	                        100baseT/Half 100baseT/Full
	                        1000baseT/Full
	Advertised pause frame use: Symmetric Receive-only
	Advertised auto-negotiation: Yes
	Advertised FEC modes: Not reported
	Link partner advertised link modes:  10baseT/Half 10baseT/Full
	                                     100baseT/Half 100baseT/Full
	                                     1000baseT/Full
	Link partner advertised pause frame use: No
	Link partner advertised auto-negotiation: Yes
	Link partner advertised FEC modes: Not reported
	Speed: 1000Mb/s
	Duplex: Full
	Auto-negotiation: on
	Port: Twisted Pair
	PHYAD: 1
	Transceiver: internal
	MDI-X: on (auto)
	Supports Wake-on: d
	Wake-on: d
        Current message level: 0x00000007 (7)
                               drv probe link
	Link detected: yes


-- 
Best Regards,
Marek Marczykowski-Górecki
Invisible Things Lab

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]

WARNING: multiple messages have this Message-ID (diff)
From: "Marek Marczykowski-Górecki" <marmarek@invisiblethingslab.com>
To: "Lifshits, Vitaly" <vitaly.lifshits@intel.com>
Cc: Jesse Brandeburg <jesse.brandeburg@intel.com>,
	Tony Nguyen <anthony.l.nguyen@intel.com>,
	netdev@vger.kernel.org, intel-wired-lan@lists.osuosl.org,
	regressions@lists.linux.dev, stable@vger.kernel.org,
	Sasha Levin <sashal@kernel.org>
Subject: Re: [REGRESSION] e1000e heavy packet loss on Meteor Lake - 6.14.2
Date: Mon, 14 Apr 2025 14:58:09 +0200	[thread overview]
Message-ID: <Z_0GYR8jR-5NWZ9K@mail-itl> (raw)
In-Reply-To: <b1f5e997-033c-33ed-5e3b-6fe2632bf718@intel.com>

[-- Attachment #1: Type: text/plain, Size: 3603 bytes --]

On Mon, Apr 14, 2025 at 03:38:39PM +0300, Lifshits, Vitaly wrote:
> Do you see the high packet loss without the virtualization?

I can't check that easily right now, will try later.

> Can you please share the lspci output?

Sure:

00:07.0 Ethernet controller [0200]: Intel Corporation Device [8086:550a] (rev 20)
	Subsystem: CLEVO/KAPOK Computer Device [1558:a743]
	Physical Slot: 7
	Control: I/O- Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B- DisINTx+
	Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR- INTx-
	Latency: 64
	Interrupt: pin D routed to IRQ 69
	Region 0: Memory at f2000000 (32-bit, non-prefetchable) [size=128K]
	Capabilities: [c8] Power Management version 3
		Flags: PMEClk- DSI+ D1- D2- AuxCurrent=0mA PME(D0-,D1-,D2-,D3hot-,D3cold-)
		Status: D0 NoSoftRst+ PME-Enable- DSel=0 DScale=1 PME-
	Capabilities: [d0] MSI: Enable+ Count=1/1 Maskable- 64bit+
		Address: 00000000fee00000  Data: 0000
	Kernel driver in use: e1000e
	Kernel modules: e1000e



> Does your switch/link partner support flow control? if it is configurable
> can you try to enable it?

It does support it. Enabling it makes things much worse...

> Do you see any errors in dmesg related to the e1000e driver?

Not really.
dmesg | grep 'e1000e\|ens7':

[    3.088489] e1000e: Intel(R) PRO/1000 Network Driver
[    3.088512] e1000e: Copyright(c) 1999 - 2015 Intel Corporation.
[    3.093256] e1000e 0000:00:07.0: Interrupt Throttling Rate (ints/sec) set to dynamic conservative mode
[    3.343378] e1000e 0000:00:07.0 0000:00:07.0 (uninitialized): registered PHC clock
[    3.718946] e1000e 0000:00:07.0 eth0: (PCI Express:2.5GT/s:Width x1) d4:93:90:3e:0d:bb
[    3.718966] e1000e 0000:00:07.0 eth0: Intel(R) PRO/1000 Network Connection
[    3.719101] e1000e 0000:00:07.0 eth0: MAC: 16, PHY: 12, PBA No: FFFFFF-0FF
[    3.759444] e1000e 0000:00:07.0 ens7: renamed from eth0
[    8.632317] e1000e 0000:00:07.0 ens7: NIC Link is Up 1000 Mbps Full Duplex, Flow Control: None
[  239.458205] e1000e 0000:00:07.0 ens7: NIC Link is Down
[  242.485869] e1000e 0000:00:07.0 ens7: NIC Link is Up 1000 Mbps Full Duplex, Flow Control: Rx/Tx

(you can also see a test with flow control above)


And also ethtool output if useful:
Settings for ens7:
	Supported ports: [ TP ]
	Supported link modes:   10baseT/Half 10baseT/Full
	                        100baseT/Half 100baseT/Full
	                        1000baseT/Full
	Supported pause frame use: Symmetric Receive-only
	Supports auto-negotiation: Yes
	Supported FEC modes: Not reported
	Advertised link modes:  10baseT/Half 10baseT/Full
	                        100baseT/Half 100baseT/Full
	                        1000baseT/Full
	Advertised pause frame use: Symmetric Receive-only
	Advertised auto-negotiation: Yes
	Advertised FEC modes: Not reported
	Link partner advertised link modes:  10baseT/Half 10baseT/Full
	                                     100baseT/Half 100baseT/Full
	                                     1000baseT/Full
	Link partner advertised pause frame use: No
	Link partner advertised auto-negotiation: Yes
	Link partner advertised FEC modes: Not reported
	Speed: 1000Mb/s
	Duplex: Full
	Auto-negotiation: on
	Port: Twisted Pair
	PHYAD: 1
	Transceiver: internal
	MDI-X: on (auto)
	Supports Wake-on: d
	Wake-on: d
        Current message level: 0x00000007 (7)
                               drv probe link
	Link detected: yes


-- 
Best Regards,
Marek Marczykowski-Górecki
Invisible Things Lab

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]

  reply	other threads:[~2025-04-14 15:20 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-04-14 12:18 [Intel-wired-lan] [REGRESSION] e1000e heavy packet loss on Meteor Lake - 6.14.2 Marek Marczykowski-Górecki
2025-04-14 12:18 ` Marek Marczykowski-Górecki
2025-04-14 12:38 ` [Intel-wired-lan] " Lifshits, Vitaly
2025-04-14 12:38   ` Lifshits, Vitaly
2025-04-14 12:58   ` Marek Marczykowski-Górecki [this message]
2025-04-14 12:58     ` Marek Marczykowski-Górecki
2025-04-14 13:04     ` [Intel-wired-lan] " Lifshits, Vitaly
2025-04-14 13:04       ` Lifshits, Vitaly
2025-04-14 13:28       ` [Intel-wired-lan] " Marek Marczykowski-Górecki
2025-04-14 13:28         ` Marek Marczykowski-Górecki
2025-04-16 12:09       ` [Intel-wired-lan] " Lifshits, Vitaly
2025-04-16 12:43         ` Marek Marczykowski-Górecki
2025-04-21 12:44           ` Lifshits, Vitaly
2025-04-21 13:19             ` Marek Marczykowski-Górecki
2025-04-21 13:28               ` Marek Marczykowski-Górecki
2025-05-08  6:26                 ` Lifshits, Vitaly
2025-05-08 22:41                   ` Marek Marczykowski-Górecki
2025-05-08 23:13                     ` Paul Menzel
2025-05-08 23:28                       ` Marek Marczykowski-Górecki
2025-05-09  0:17                         ` Marek Marczykowski-Górecki
2025-06-18 13:28                           ` Marek Marczykowski-Górecki
2025-06-18 13:41                             ` Christian Heusel
2025-06-19 12:20                               ` Lifshits, Vitaly
2025-06-19 14:49                                 ` Marek Marczykowski-Górecki
2025-04-14 14:27     ` Marek Marczykowski-Górecki
2025-04-14 14:27       ` Marek Marczykowski-Górecki

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=Z_0GYR8jR-5NWZ9K@mail-itl \
    --to=marmarek@invisiblethingslab.com \
    --cc=anthony.l.nguyen@intel.com \
    --cc=intel-wired-lan@lists.osuosl.org \
    --cc=jesse.brandeburg@intel.com \
    --cc=netdev@vger.kernel.org \
    --cc=regressions@lists.linux.dev \
    --cc=sashal@kernel.org \
    --cc=stable@vger.kernel.org \
    --cc=vitaly.lifshits@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.