You are not logged in.

#1 2018-02-07 21:41:35

Maniaxx
Member
From: .de
Registered: 2014-05-14
Posts: 172

[SOLVED][Bug]Kernel 4.15 - Default TCP Congestion BBR - Slow network

Hallo,
with kernel 4.15.1-2 my Samba connection is capped to ~300kB/s. The only fix so far is to downgrade to 4.14. The connection is SMBv1/CIFS to an Android device. Other connections are normal (5MB/s) on both devices. It looks like a hardcap/steady output like it would be QOS or something. Its not fluctuating at all. I have no traffic control installed at all though.

Anyone noticed this as well or know a fix for this?

Last edited by Maniaxx (2018-02-18 17:40:13)


sys2064

Offline

#2 2018-02-08 13:39:25

Buddlespit
Member
From: Chesapeake, Va.
Registered: 2014-02-07
Posts: 429

Re: [SOLVED][Bug]Kernel 4.15 - Default TCP Congestion BBR - Slow network

Maniaxx wrote:

Anyone noticed this as well or know a fix for this?

Stop using SMBv1? My network is running SMBv3 (v1 and v2 disabled) with a wired transfer rate of approx 43MB/s. Wifi transfer rates are at about 2-3MB/s.

Offline

#3 2018-02-09 09:18:48

Maniaxx
Member
From: .de
Registered: 2014-05-14
Posts: 172

Re: [SOLVED][Bug]Kernel 4.15 - Default TCP Congestion BBR - Slow network

What throughout do you have when you disable v2 and v3?


sys2064

Offline

#4 2018-02-09 11:37:16

Buddlespit
Member
From: Chesapeake, Va.
Registered: 2014-02-07
Posts: 429

Re: [SOLVED][Bug]Kernel 4.15 - Default TCP Congestion BBR - Slow network

I don't use v1. It's a huge security risk. Google SMBv1.

Offline

#5 2018-02-09 12:30:21

Maniaxx
Member
From: .de
Registered: 2014-05-14
Posts: 172

Re: [SOLVED][Bug]Kernel 4.15 - Default TCP Congestion BBR - Slow network

It doesn't matter on internal LAN. It's a 3.4 kernel. There is no SMBv2.
Please test v1 if you want to help.


sys2064

Offline

#6 2018-02-09 15:25:22

seth
Member
Registered: 2012-09-03
Posts: 7,558

Re: [SOLVED][Bug]Kernel 4.15 - Default TCP Congestion BBR - Slow network

Maniaxx wrote:

It doesn't matter on internal LAN.

Errr..... major misconception.
Wannacry exploited an idiot that was stupid enough to click a penis enlargment promise (or a free military parade...) and then used the flaws in the original SMB protocol to infiltrate the entire network.
Using SMB (*any* version) over the internet would be even worse.

On topic: since you're blaming the kernel, are you using a cifs mount or some client-side implementation (kio_smb, smbclient, ...) and in case of the former, does the latter still perform fine?

Offline

#7 2018-02-09 22:11:58

jonno2002
Member
Registered: 2016-11-21
Posts: 42

Re: [SOLVED][Bug]Kernel 4.15 - Default TCP Congestion BBR - Slow network

one of my machines is having similar issues with samba and the 4.15 kernel too, with the 4.15 kernel i cant get more than 6 megabytes/sec over the gigabit lan , and after a down grade to 4.14.15 its back to full speed again... well only tested to my laptop over wifi but 6mbs to 35mbs is a BIG difference. (the machine is connected to the router via gigabit ethernet just in case that didnt make sense, and my laptop is on wireless AC)

the machine in question is a core2 duo laptop p7450, but whats really strange is i have another machine with a core2 duo e7600 (on gigabit eth to router, but is a desktop not a laptop) and its fine on the 4.15 kernel with samba, getting the full 35mb/s to my laptop.

all the machines are running arch obviously with the same samba config on all of them.

no idea what it could be, just thought id add to the thread, i would provide logs but i dont really know what would help.

Offline

#8 2018-02-09 22:24:19

seth
Member
Registered: 2012-09-03
Posts: 7,558

Re: [SOLVED][Bug]Kernel 4.15 - Default TCP Congestion BBR - Slow network

In case that wasn't clear from my last post: we need to isolate whether this is in the cifs module or the network stack.
Post #7 would suggest the latter so recording the network devices in question (lspci/lsusb) would probably help to spot pot. patterns and also jonno2002 should certainly try using the wired ethernet on his laptop (best w/ wifi deactivated altogether)

Offline

#9 2018-02-10 04:40:10

jonno2002
Member
Registered: 2016-11-21
Posts: 42

Re: [SOLVED][Bug]Kernel 4.15 - Default TCP Congestion BBR - Slow network

lspci:

00:00.0 Host bridge: Intel Corporation Mobile 4 Series Chipset Memory Controller Hub (rev 07)
00:01.0 PCI bridge: Intel Corporation Mobile 4 Series Chipset PCI Express Graphics Port (rev 07)
00:1a.0 USB controller: Intel Corporation 82801I (ICH9 Family) USB UHCI Controller #4 (rev 03)
00:1a.1 USB controller: Intel Corporation 82801I (ICH9 Family) USB UHCI Controller #5 (rev 03)
00:1a.7 USB controller: Intel Corporation 82801I (ICH9 Family) USB2 EHCI Controller #2 (rev 03)
00:1b.0 Audio device: Intel Corporation 82801I (ICH9 Family) HD Audio Controller (rev 03)
00:1c.0 PCI bridge: Intel Corporation 82801I (ICH9 Family) PCI Express Port 1 (rev 03)
00:1c.1 PCI bridge: Intel Corporation 82801I (ICH9 Family) PCI Express Port 2 (rev 03)
00:1c.4 PCI bridge: Intel Corporation 82801I (ICH9 Family) PCI Express Port 5 (rev 03)
00:1d.0 USB controller: Intel Corporation 82801I (ICH9 Family) USB UHCI Controller #1 (rev 03)
00:1d.1 USB controller: Intel Corporation 82801I (ICH9 Family) USB UHCI Controller #2 (rev 03)
00:1d.2 USB controller: Intel Corporation 82801I (ICH9 Family) USB UHCI Controller #3 (rev 03)
00:1d.3 USB controller: Intel Corporation 82801I (ICH9 Family) USB UHCI Controller #6 (rev 03)
00:1d.7 USB controller: Intel Corporation 82801I (ICH9 Family) USB2 EHCI Controller #1 (rev 03)
00:1e.0 PCI bridge: Intel Corporation 82801 Mobile PCI Bridge (rev 93)
00:1f.0 ISA bridge: Intel Corporation ICH9M LPC Interface Controller (rev 03)
00:1f.2 SATA controller: Intel Corporation 82801IBM/IEM (ICH9M/ICH9M-E) 4 port SATA Controller [AHCI mode] (rev 03)
00:1f.3 SMBus: Intel Corporation 82801I (ICH9 Family) SMBus Controller (rev 03)
01:00.0 VGA compatible controller: Advanced Micro Devices, Inc. [AMD/ATI] RV620/M82 [Mobility Radeon HD 3450/3470]
01:00.1 Audio device: Advanced Micro Devices, Inc. [AMD/ATI] RV620 HDMI Audio [Radeon HD 3450/3470/3550/3570]
02:00.0 Ethernet controller: Realtek Semiconductor Co., Ltd. RTL8111/8168/8411 PCI Express Gigabit Ethernet Controller (rev 02)
03:00.0 Network controller: Intel Corporation WiFi Link 5100
04:06.0 FireWire (IEEE 1394): Ricoh Co Ltd R5C832 IEEE 1394 Controller (rev 05)
04:06.1 SD Host controller: Ricoh Co Ltd R5C822 SD/SDIO/MMC/MS/MSPro Host Adapter (rev 22)
04:06.2 System peripheral: Ricoh Co Ltd R5C592 Memory Stick Bus Host Adapter (rev 12)
04:06.3 System peripheral: Ricoh Co Ltd xD-Picture Card Controller (rev 12)

lsusb

Bus 002 Device 002: ID 1058:1021 Western Digital Technologies, Inc. Elements Desktop (WDBAAU)
Bus 002 Device 001: ID 1d6b:0002 Linux Foundation 2.0 root hub
Bus 008 Device 001: ID 1d6b:0001 Linux Foundation 1.1 root hub
Bus 007 Device 001: ID 1d6b:0001 Linux Foundation 1.1 root hub
Bus 006 Device 002: ID 045e:0745 Microsoft Corp. Nano Transceiver v1.0 for Bluetooth
Bus 006 Device 001: ID 1d6b:0001 Linux Foundation 1.1 root hub
Bus 005 Device 001: ID 1d6b:0001 Linux Foundation 1.1 root hub
Bus 001 Device 002: ID 04f2:b008 Chicony Electronics Co., Ltd USB 2.0 Camera
Bus 001 Device 001: ID 1d6b:0002 Linux Foundation 2.0 root hub
Bus 004 Device 002: ID 08ff:1600 AuthenTec, Inc. AES1600
Bus 004 Device 001: ID 1d6b:0001 Linux Foundation 1.1 root hub
Bus 003 Device 001: ID 1d6b:0001 Linux Foundation 1.1 root hub

did a bit of a comparison of kernels and protocols too, this is transferring data from the offending machine to my laptop:

wireless with 4.15 kernel:
gvfs: 7 MB/s
cifs: 7 MB/s

ethernet with 4.15 kernel:
gvfs: 10 MB/s
cifs: 19 MB/s

wireless with 4.14 kernel:
gvfs: 35 MB/s
cifs: 51 MB/s

ethernet with 4.14 kernel:
gvfs: 68 MB/s
cifs: 99 MB/s

and also just for fun tried transferring data from the other core2 duo machine to my laptop, only using 4.15 kernel as i dont want to reboot this machine again.

wireless with 4.15 kernel:
gvfs: 35 MB/s
cifs: 35 MB/s

ethernet with 4.15 kernel:
gvfs: 92 MB/s
cifs: 110 MB/s

and lspci/lsusb to match:

00:00.0 Host bridge: Intel Corporation 4 Series Chipset DRAM Controller (rev 03)
00:01.0 PCI bridge: Intel Corporation 4 Series Chipset PCI Express Root Port (rev 03)
00:03.0 Communication controller: Intel Corporation 4 Series Chipset HECI Controller (rev 03)
00:03.2 IDE interface: Intel Corporation 4 Series Chipset PT IDER Controller (rev 03)
00:03.3 Serial controller: Intel Corporation 4 Series Chipset Serial KT Controller (rev 03)
00:19.0 Ethernet controller: Intel Corporation 82567LM-3 Gigabit Network Connection (rev 02)
00:1a.0 USB controller: Intel Corporation 82801JD/DO (ICH10 Family) USB UHCI Controller #4 (rev 02)
00:1a.1 USB controller: Intel Corporation 82801JD/DO (ICH10 Family) USB UHCI Controller #5 (rev 02)
00:1a.2 USB controller: Intel Corporation 82801JD/DO (ICH10 Family) USB UHCI Controller #6 (rev 02)
00:1a.7 USB controller: Intel Corporation 82801JD/DO (ICH10 Family) USB2 EHCI Controller #2 (rev 02)
00:1b.0 Audio device: Intel Corporation 82801JD/DO (ICH10 Family) HD Audio Controller (rev 02)
00:1c.0 PCI bridge: Intel Corporation 82801JD/DO (ICH10 Family) PCI Express Port 1 (rev 02)
00:1c.1 PCI bridge: Intel Corporation 82801JD/DO (ICH10 Family) PCI Express Port 2 (rev 02)
00:1d.0 USB controller: Intel Corporation 82801JD/DO (ICH10 Family) USB UHCI Controller #1 (rev 02)
00:1d.1 USB controller: Intel Corporation 82801JD/DO (ICH10 Family) USB UHCI Controller #2 (rev 02)
00:1d.2 USB controller: Intel Corporation 82801JD/DO (ICH10 Family) USB UHCI Controller #3 (rev 02)
00:1d.7 USB controller: Intel Corporation 82801JD/DO (ICH10 Family) USB2 EHCI Controller #1 (rev 02)
00:1e.0 PCI bridge: Intel Corporation 82801 PCI Bridge (rev a2)
00:1f.0 ISA bridge: Intel Corporation 82801JDO (ICH10DO) LPC Interface Controller (rev 02)
00:1f.2 SATA controller: Intel Corporation 82801JD/DO (ICH10 Family) SATA AHCI Controller (rev 02)
01:00.0 VGA compatible controller: NVIDIA Corporation GK208 [GeForce GT 710B] (rev a1)
01:00.1 Audio device: NVIDIA Corporation GK208 HDMI/DP Audio Controller (rev a1)
Bus 002 Device 001: ID 1d6b:0002 Linux Foundation 2.0 root hub
Bus 008 Device 001: ID 1d6b:0001 Linux Foundation 1.1 root hub
Bus 007 Device 001: ID 1d6b:0001 Linux Foundation 1.1 root hub
Bus 006 Device 001: ID 1d6b:0001 Linux Foundation 1.1 root hub
Bus 001 Device 001: ID 1d6b:0002 Linux Foundation 2.0 root hub
Bus 005 Device 001: ID 1d6b:0001 Linux Foundation 1.1 root hub
Bus 004 Device 001: ID 1d6b:0001 Linux Foundation 1.1 root hub
Bus 003 Device 001: ID 1d6b:0001 Linux Foundation 1.1 root hub

and just after writing all this up ive seen the reason these 2 machines act differently, 1 has a realtek ethernet device and the other has an intel. im guessing the newer kernel isnt liking the realtek device.

Offline

#10 2018-02-10 09:51:22

seth
Member
Registered: 2012-09-03
Posts: 7,558

Re: [SOLVED][Bug]Kernel 4.15 - Default TCP Congestion BBR - Slow network

You've a breakdown in wired and wireless connections, devices

02:00.0 Ethernet controller: Realtek Semiconductor Co., Ltd. RTL8111/8168/8411 PCI Express Gigabit Ethernet Controller (rev 02)
03:00.0 Network controller: Intel Corporation WiFi Link 5100

vs.

00:19.0 Ethernet controller: Intel Corporation 82567LM-3 Gigabit Network Connection (rev 02)

Could be some power saving mechanism. Is only smb affected or do you get this for eg. http up/downloads as well?
Do you have any power savong daemons running on the notebook? (tlp/laptop-mode-tools)

Also check dmesg for the devices.

Offline

#11 2018-02-10 22:27:49

Maniaxx
Member
From: .de
Registered: 2014-05-14
Posts: 172

Re: [SOLVED][Bug]Kernel 4.15 - Default TCP Congestion BBR - Slow network

I can add this:
- Not Samba-only. SSH affected as well.
- Only one direction is bad (Server/Arch->Client/Android). Other direction is ok.
- Yet another machine with SMBv2 is ok. Edit: Even SMBv1 (vers=1.0) is ok there.
- Affected system (Android) has kernel 3.4 with SMBv1-only and SSHd (OpenSSH_6.8p1, BoringSSL).
- Samba throughput gets better (~2.2MB/s) if i lower rsize to 8192 (mount initiated on client-side). Sometimes on rsize=16384 it transfers 3.8MB/s (expected speed) for some seconds and then drops down to 200kB/s.

$ lspci
00:00.0 Host bridge: Intel Corporation 2nd Generation Core Processor Family DRAM Controller (rev 09)
00:01.0 PCI bridge: Intel Corporation Xeon E3-1200/2nd Generation Core Processor Family PCI Express Root Port (rev 09)
00:16.0 Communication controller: Intel Corporation 6 Series/C200 Series Chipset Family MEI Controller #1 (rev 04)
00:1a.0 USB controller: Intel Corporation 6 Series/C200 Series Chipset Family USB Enhanced Host Controller #2 (rev 05)
00:1c.0 PCI bridge: Intel Corporation 6 Series/C200 Series Chipset Family PCI Express Root Port 1 (rev b5)
00:1c.4 PCI bridge: Intel Corporation 6 Series/C200 Series Chipset Family PCI Express Root Port 5 (rev b5)
00:1c.5 PCI bridge: Intel Corporation 6 Series/C200 Series Chipset Family PCI Express Root Port 6 (rev b5)
00:1c.7 PCI bridge: Intel Corporation 6 Series/C200 Series Chipset Family PCI Express Root Port 8 (rev b5)
00:1d.0 USB controller: Intel Corporation 6 Series/C200 Series Chipset Family USB Enhanced Host Controller #1 (rev 05)
00:1f.0 ISA bridge: Intel Corporation P67 Express Chipset Family LPC Controller (rev 05)
00:1f.2 SATA controller: Intel Corporation 6 Series/C200 Series Chipset Family 6 port Desktop SATA AHCI Controller (rev 05)
00:1f.3 SMBus: Intel Corporation 6 Series/C200 Series Chipset Family SMBus Controller (rev 05)
01:00.0 VGA compatible controller: NVIDIA Corporation GK104 [GeForce GTX 770] (rev a1)
01:00.1 Audio device: NVIDIA Corporation GK104 HDMI Audio Controller (rev a1)
03:00.0 Ethernet controller: Realtek Semiconductor Co., Ltd. RTL8111/8168/8411 PCI Express Gigabit Ethernet Controller (rev 06)
04:00.0 USB controller: Etron Technology, Inc. EJ168 USB 3.0 Host Controller (rev 01)
05:00.0 PCI bridge: ASMedia Technology Inc. ASM1083/1085 PCIe to PCI Bridge (rev 01)
06:01.0 Multimedia audio controller: Creative Labs EMU10k2/CA0100/CA0102/CA10200 [Sound Blaster Audigy Series] (rev 04)
06:01.1 Input device controller: Creative Labs SB Audigy Game Port (rev 04)
06:01.2 FireWire (IEEE 1394): Creative Labs SB Audigy FireWire Port (rev 04)

$ lsusb
Bus 004 Device 003: ID 046d:c024 Logitech, Inc. MX300 Optical Mouse
Bus 004 Device 002: ID 8087:0024 Intel Corp. Integrated Rate Matching Hub
Bus 004 Device 001: ID 1d6b:0002 Linux Foundation 2.0 root hub
Bus 003 Device 001: ID 1d6b:0003 Linux Foundation 3.0 root hub
Bus 002 Device 001: ID 1d6b:0002 Linux Foundation 2.0 root hub
Bus 001 Device 002: ID 8087:0024 Intel Corp. Integrated Rate Matching Hub
Bus 001 Device 001: ID 1d6b:0002 Linux Foundation 2.0 root hub

Last edited by Maniaxx (2018-02-10 22:49:52)


sys2064

Offline

#12 2018-02-10 22:52:28

jonno2002
Member
Registered: 2016-11-21
Posts: 42

Re: [SOLVED][Bug]Kernel 4.15 - Default TCP Congestion BBR - Slow network

03:00.0 Ethernet controller: Realtek Semiconductor Co., Ltd. RTL8111/8168/8411 PCI Express Gigabit Ethernet Controller (rev 06)
02:00.0 Ethernet controller: Realtek Semiconductor Co., Ltd. RTL8111/8168/8411 PCI Express Gigabit Ethernet Controller (rev 02)

both our problem systems have the same realtek ethernet device, different revisions but i bet they use the same kernel module "r8169" which im picking is the problem, i tried to compile the driver from the 4.14 kernel to work with the 4.15 but gave up, its above my skill level for now.

[edit] and yes i seem to recall x-forwarding over ssh was REALLY bad when using the 4.15 kernel, and back to normal after kernel downgrade to 4.14 [/edit]

Last edited by jonno2002 (2018-02-10 22:55:49)

Offline

#13 2018-02-10 23:20:55

seth
Member
Registered: 2012-09-03
Posts: 7,558

Re: [SOLVED][Bug]Kernel 4.15 - Default TCP Congestion BBR - Slow network

Seems the RT chip indeed...

lspci -vvs 03:00.0

respectively @jonno2002

lspci -vvs 02:00.0

(ie. for the ethernet slot)

Offline

#14 2018-02-10 23:43:35

Maniaxx
Member
From: .de
Registered: 2014-05-14
Posts: 172

Re: [SOLVED][Bug]Kernel 4.15 - Default TCP Congestion BBR - Slow network

seth wrote:
lspci -vvs 03:00.0
$ sudo lspci -vvs 03:00.0
03:00.0 Ethernet controller: Realtek Semiconductor Co., Ltd. RTL8111/8168/8411 PCI Express Gigabit Ethernet Controller (rev 06)
	Subsystem: ASRock Incorporation Motherboard (one of many)
	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: 0, Cache Line Size: 64 bytes
	Interrupt: pin A routed to IRQ 33
	Region 0: I/O ports at d000 [size=256]
	Region 2: Memory at f2104000 (64-bit, prefetchable) [size=4K]
	Region 4: Memory at f2100000 (64-bit, prefetchable) [size=16K]
	Capabilities: [40] Power Management version 3
		Flags: PMEClk- DSI- D1+ D2+ AuxCurrent=375mA PME(D0+,D1+,D2+,D3hot+,D3cold+)
		Status: D0 NoSoftRst+ PME-Enable- DSel=0 DScale=0 PME-
	Capabilities: [50] MSI: Enable+ Count=1/1 Maskable- 64bit+
		Address: 00000000fee02004  Data: 4025
	Capabilities: [70] Express (v2) Endpoint, MSI 01
		DevCap:	MaxPayload 256 bytes, PhantFunc 0, Latency L0s <512ns, L1 <64us
			ExtTag- AttnBtn- AttnInd- PwrInd- RBE+ FLReset- SlotPowerLimit 10.000W
		DevCtl:	Report errors: Correctable- Non-Fatal- Fatal- Unsupported-
			RlxdOrd- ExtTag- PhantFunc- AuxPwr- NoSnoop-
			MaxPayload 128 bytes, MaxReadReq 4096 bytes
		DevSta:	CorrErr- UncorrErr- FatalErr- UnsuppReq- AuxPwr+ TransPend-
		LnkCap:	Port #0, Speed 2.5GT/s, Width x1, ASPM L0s L1, Exit Latency L0s <512ns, L1 <64us
			ClockPM+ Surprise- LLActRep- BwNot- ASPMOptComp-
		LnkCtl:	ASPM Disabled; RCB 64 bytes Disabled- CommClk+
			ExtSynch- ClockPM- AutWidDis- BWInt- AutBWInt-
		LnkSta:	Speed 2.5GT/s, Width x1, TrErr- Train- SlotClk+ DLActive- BWMgmt- ABWMgmt-
		DevCap2: Completion Timeout: Not Supported, TimeoutDis+, LTR-, OBFF Not Supported
			 AtomicOpsCap: 32bit- 64bit- 128bitCAS-
		DevCtl2: Completion Timeout: 50us to 50ms, TimeoutDis-, LTR-, OBFF Disabled
			 AtomicOpsCtl: ReqEn-
		LnkCtl2: Target Link Speed: 2.5GT/s, EnterCompliance- SpeedDis-
			 Transmit Margin: Normal Operating Range, EnterModifiedCompliance- ComplianceSOS-
			 Compliance De-emphasis: -6dB
		LnkSta2: Current De-emphasis Level: -6dB, EqualizationComplete-, EqualizationPhase1-
			 EqualizationPhase2-, EqualizationPhase3-, LinkEqualizationRequest-
	Capabilities: [b0] MSI-X: Enable- Count=4 Masked-
		Vector table: BAR=4 offset=00000000
		PBA: BAR=4 offset=00000800
	Capabilities: [d0] Vital Product Data
pcilib: sysfs_read_vpd: read failed: Input/output error
		Not readable
	Capabilities: [100 v1] Advanced Error Reporting
		UESta:	DLP- SDES- TLP- FCP- CmpltTO- CmpltAbrt- UnxCmplt- RxOF- MalfTLP- ECRC- UnsupReq- ACSViol-
		UEMsk:	DLP- SDES- TLP- FCP- CmpltTO- CmpltAbrt- UnxCmplt- RxOF- MalfTLP- ECRC- UnsupReq- ACSViol-
		UESvrt:	DLP+ SDES+ TLP- FCP+ CmpltTO- CmpltAbrt- UnxCmplt- RxOF+ MalfTLP+ ECRC- UnsupReq- ACSViol-
		CESta:	RxErr- BadTLP- BadDLLP- Rollover- Timeout- NonFatalErr-
		CEMsk:	RxErr- BadTLP- BadDLLP- Rollover- Timeout- NonFatalErr+
		AERCap:	First Error Pointer: 00, ECRCGenCap+ ECRCGenEn- ECRCChkCap+ ECRCChkEn-
			MultHdrRecCap- MultHdrRecEn- TLPPfxPres- HdrLogCap-
		HeaderLog: 00000000 00000000 00000000 00000000
	Capabilities: [140 v1] Virtual Channel
		Caps:	LPEVC=0 RefClk=100ns PATEntryBits=1
		Arb:	Fixed- WRR32- WRR64- WRR128-
		Ctrl:	ArbSelect=Fixed
		Status:	InProgress-
		VC0:	Caps:	PATOffset=00 MaxTimeSlots=1 RejSnoopTrans-
			Arb:	Fixed- WRR32- WRR64- WRR128- TWRR128- WRR256-
			Ctrl:	Enable+ ID=0 ArbSelect=Fixed TC/VC=01
			Status:	NegoPending- InProgress-
	Capabilities: [160 v1] Device Serial Number 01-00-00-00-xx-xx-xx-xx
	Kernel driver in use: r8169
	Kernel modules: r8169

sys2064

Offline

#15 2018-02-11 01:11:24

jonno2002
Member
Registered: 2016-11-21
Posts: 42

Re: [SOLVED][Bug]Kernel 4.15 - Default TCP Congestion BBR - Slow network

02:00.0 Ethernet controller: Realtek Semiconductor Co., Ltd. RTL8111/8168/8411 PCI Express Gigabit Ethernet Controller (rev 02)
	Subsystem: Toshiba America Info Systems RTL8111/8168/8411 PCI Express Gigabit Ethernet Controller
	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: 0, Cache Line Size: 64 bytes
	Interrupt: pin A routed to IRQ 25
	Region 0: I/O ports at 3000 [size=256]
	Region 2: Memory at d5300000 (64-bit, non-prefetchable) [size=4K]
	Region 4: Memory at d0000000 (64-bit, prefetchable) [size=64K]
	Expansion ROM at d5320000 [disabled] [size=128K]
	Capabilities: [40] Power Management version 3
		Flags: PMEClk- DSI- D1+ D2+ AuxCurrent=375mA PME(D0+,D1+,D2+,D3hot+,D3cold+)
		Status: D0 NoSoftRst+ PME-Enable- DSel=0 DScale=0 PME-
	Capabilities: [50] MSI: Enable+ Count=1/1 Maskable- 64bit+
		Address: 00000000fee0300c  Data: 4163
	Capabilities: [70] Express (v1) Endpoint, MSI 01
		DevCap:	MaxPayload 256 bytes, PhantFunc 0, Latency L0s <512ns, L1 <8us
			ExtTag- AttnBtn- AttnInd- PwrInd- RBE+ FLReset- SlotPowerLimit 6.500W
		DevCtl:	Report errors: Correctable- Non-Fatal- Fatal- Unsupported-
			RlxdOrd+ ExtTag- PhantFunc- AuxPwr- NoSnoop-
			MaxPayload 128 bytes, MaxReadReq 4096 bytes
		DevSta:	CorrErr+ UncorrErr- FatalErr- UnsuppReq+ AuxPwr+ TransPend-
		LnkCap:	Port #0, Speed 2.5GT/s, Width x1, ASPM L0s L1, Exit Latency L0s <512ns, L1 <64us
			ClockPM+ Surprise- LLActRep- BwNot- ASPMOptComp-
		LnkCtl:	ASPM Disabled; RCB 64 bytes Disabled- CommClk+
			ExtSynch- ClockPM- AutWidDis- BWInt- AutBWInt-
		LnkSta:	Speed 2.5GT/s, Width x1, TrErr- Train- SlotClk+ DLActive- BWMgmt- ABWMgmt-
	Capabilities: [b0] MSI-X: Enable- Count=2 Masked-
		Vector table: BAR=4 offset=00000000
		PBA: BAR=4 offset=00000800
	Capabilities: [d0] Vital Product Data
pcilib: sysfs_read_vpd: read failed: Input/output error
		Not readable
	Capabilities: [100 v1] Advanced Error Reporting
		UESta:	DLP- SDES- TLP- FCP- CmpltTO- CmpltAbrt- UnxCmplt- RxOF- MalfTLP- ECRC- UnsupReq- ACSViol-
		UEMsk:	DLP- SDES- TLP- FCP- CmpltTO- CmpltAbrt- UnxCmplt- RxOF- MalfTLP- ECRC- UnsupReq- ACSViol-
		UESvrt:	DLP+ SDES+ TLP- FCP+ CmpltTO- CmpltAbrt- UnxCmplt- RxOF+ MalfTLP+ ECRC- UnsupReq- ACSViol-
		CESta:	RxErr+ BadTLP- BadDLLP- Rollover- Timeout- NonFatalErr-
		CEMsk:	RxErr- BadTLP- BadDLLP- Rollover- Timeout- NonFatalErr+
		AERCap:	First Error Pointer: 00, ECRCGenCap+ ECRCGenEn- ECRCChkCap+ ECRCChkEn-
			MultHdrRecCap- MultHdrRecEn- TLPPfxPres- HdrLogCap-
		HeaderLog: 00000000 00000000 00000000 00000000
	Capabilities: [140 v1] Virtual Channel
		Caps:	LPEVC=0 RefClk=100ns PATEntryBits=1
		Arb:	Fixed- WRR32- WRR64- WRR128-
		Ctrl:	ArbSelect=Fixed
		Status:	InProgress-
		VC0:	Caps:	PATOffset=00 MaxTimeSlots=1 RejSnoopTrans-
			Arb:	Fixed- WRR32- WRR64- WRR128- TWRR128- WRR256-
			Ctrl:	Enable+ ID=0 ArbSelect=Fixed TC/VC=ff
			Status:	NegoPending- InProgress-
	Capabilities: [160 v1] Device Serial Number 01-00-00-00-ff-ff-00-00
	Kernel driver in use: r8169
	Kernel modules: r8169

Offline

#16 2018-02-11 09:20:09

seth
Member
Registered: 2012-09-03
Posts: 7,558

Re: [SOLVED][Bug]Kernel 4.15 - Default TCP Congestion BBR - Slow network

https://git.kernel.org/pub/scm/linux/ke … .c?h=v4.15
1.14 was up to "2017-10-11    r8169: only enable PCI wakeups when WOL is active"

There're obviously suspicious patches, notably the two green settings ones (tested on *one* zotac nuc)
Ideally you could build the kernel and revert those patches (try reverting all of them first to ensure it's the driver, then the suspicious ones, last just by adding patch after patch until things break)

Offline

#17 2018-02-11 11:30:05

jonno2002
Member
Registered: 2016-11-21
Posts: 42

Re: [SOLVED][Bug]Kernel 4.15 - Default TCP Congestion BBR - Slow network

just tried compiling the 4.14 driver for 4.15 kernel and got this error:

make M=drivers/net/ethernet/realtek
  CC [M]  drivers/net/ethernet/realtek/r8169.o
drivers/net/ethernet/realtek/r8169.c: In function ‘rtl_init_one’:
drivers/net/ethernet/realtek/r8169.c:8457:2: error: implicit declaration of function ‘setup_timer’; did you mean ‘sk_stop_timer’? [-Werror=implicit-function-declaration]
  setup_timer(&tp->timer, rtl8169_phy_timer, (unsigned long)dev);
  ^~~~~~~~~~~
  sk_stop_timer
cc1: some warnings being treated as errors
make[1]: *** [scripts/Makefile.build:323: drivers/net/ethernet/realtek/r8169.o] Error 1
make: *** [Makefile:1508: _module_drivers/net/ethernet/realtek] Error 2

and to make sure i didnt do somthing wrong i compiled the 4.15 driver and that worked fine:

make M=drivers/net/ethernet/realtek
  CC [M]  drivers/net/ethernet/realtek/r8169.o
  Building modules, stage 2.
  MODPOST 1 modules
  CC      drivers/net/ethernet/realtek/r8169.mod.o
  LD [M]  drivers/net/ethernet/realtek/r8169.ko

i followed the arch wiki: https://wiki.archlinux.org/index.php/Co … nel_module


[EDIT] figured it out, just had to apply the "drivers/net: realtek: Convert timers to use timer_setup()" patch and it complied fine , will test later on and post back with results[/EDIT]

[EDIT] nope same thing, 6MB/s with only the convert timers patch added, so back on 4.14 kernel again [/EDIT]

Last edited by jonno2002 (2018-02-11 13:27:12)

Offline

#18 2018-02-11 19:55:26

Maniaxx
Member
From: .de
Registered: 2014-05-14
Posts: 172

Re: [SOLVED][Bug]Kernel 4.15 - Default TCP Congestion BBR - Slow network

Same here.
I will try tags/v4.15-rc1 and if that's still broken bisect to tags/v4.14.

Last edited by Maniaxx (2018-02-11 19:56:04)


sys2064

Offline

#19 2018-02-12 00:46:16

Maniaxx
Member
From: .de
Registered: 2014-05-14
Posts: 172

Re: [SOLVED][Bug]Kernel 4.15 - Default TCP Congestion BBR - Slow network

Looks like its not a driver/kernel bug. Rather kconfig.

I've compiled some stock linux-stable kernels (4.15.2, 4.14.18, 4.14.15). All have the bug. Even the formerly working 4.14.15.
I started on 4.15.2 and always created a derived kconfig (make localmodconfig) that gets created/adapted from /proc/config.gz filtered down to my current hardware. So the bug is on 4.14 as well if 4.15 kconfig is taken. The next compile was a full 4.14.15 build with stock Arch 4.14.15 .config and that worked properly again indeed.

Last edited by Maniaxx (2018-02-12 00:50:14)


sys2064

Offline

#20 2018-02-12 04:48:34

Maniaxx
Member
From: .de
Registered: 2014-05-14
Posts: 172

Re: [SOLVED][Bug]Kernel 4.15 - Default TCP Congestion BBR - Slow network

It's the default tcp congestion mode. Arch changed that in 4.15 from 'cubic' to 'bbr'.

It can be switched with:

sudo sysctl net.ipv4.tcp_congestion_control=cubic

@jonno2002:
Can you confirm?

Edit: I opened a bug report.
https://bugs.archlinux.org/task/57476

Last edited by Maniaxx (2018-02-12 05:23:52)


sys2064

Offline

#21 2018-02-12 11:34:45

jonno2002
Member
Registered: 2016-11-21
Posts: 42

Re: [SOLVED][Bug]Kernel 4.15 - Default TCP Congestion BBR - Slow network

i can confirm that

sudo sysctl net.ipv4.tcp_congestion_control=cubic

fixes the problem

Offline

#22 2018-02-13 18:54:51

munkoil
Member
From: Gothenburg, Sweden
Registered: 2010-05-03
Posts: 17

Re: [SOLVED][Bug]Kernel 4.15 - Default TCP Congestion BBR - Slow network

sudo sysctl net.ipv4.tcp_congestion_control=cubic

This fixes the problem for me as well.

I also have experienced slow network transfer from my server last couple of days, both ssh and nfs in my case.

Last edited by munkoil (2018-02-14 22:18:00)

Offline

#23 2018-02-13 22:27:55

Maniaxx
Member
From: .de
Registered: 2014-05-14
Posts: 172

Re: [SOLVED][Bug]Kernel 4.15 - Default TCP Congestion BBR - Slow network

Realtek NIC as well?


sys2064

Offline

#24 2018-02-14 05:17:17

munkoil
Member
From: Gothenburg, Sweden
Registered: 2010-05-03
Posts: 17

Re: [SOLVED][Bug]Kernel 4.15 - Default TCP Congestion BBR - Slow network

Maniaxx wrote:

Realtek NIC as well?

Yes

$ sudo lspci -vvs 03:00.0
03:00.0 Ethernet controller: Realtek Semiconductor Co., Ltd. RTL8111/8168/8411 PCI Express Gigabit Ethernet Controller (rev 06)
	Subsystem: ZOTAC International (MCO) Ltd. RTL8111/8168/8411 PCI Express Gigabit Ethernet Controller
	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: 0, Cache Line Size: 64 bytes
	Interrupt: pin A routed to IRQ 31
	Region 0: I/O ports at d000 [size=256]
	Region 2: Memory at d0004000 (64-bit, prefetchable) [size=4K]
	Region 4: Memory at d0000000 (64-bit, prefetchable) [size=16K]
	Capabilities: [40] Power Management version 3
		Flags: PMEClk- DSI- D1+ D2+ AuxCurrent=375mA PME(D0+,D1+,D2+,D3hot+,D3cold+)
		Status: D0 NoSoftRst+ PME-Enable- DSel=0 DScale=0 PME-
	Capabilities: [50] MSI: Enable+ Count=1/1 Maskable- 64bit+
		Address: 00000000fee08004  Data: 4024
	Capabilities: [70] Express (v2) Endpoint, MSI 01
		DevCap:	MaxPayload 256 bytes, PhantFunc 0, Latency L0s <512ns, L1 <64us
			ExtTag- AttnBtn- AttnInd- PwrInd- RBE+ FLReset- SlotPowerLimit 10.000W
		DevCtl:	Report errors: Correctable- Non-Fatal- Fatal- Unsupported-
			RlxdOrd- ExtTag- PhantFunc- AuxPwr- NoSnoop-
			MaxPayload 128 bytes, MaxReadReq 4096 bytes
		DevSta:	CorrErr+ UncorrErr- FatalErr- UnsuppReq+ AuxPwr+ TransPend-
		LnkCap:	Port #0, Speed 2.5GT/s, Width x1, ASPM L0s L1, Exit Latency L0s <512ns, L1 <64us
			ClockPM+ Surprise- LLActRep- BwNot- ASPMOptComp-
		LnkCtl:	ASPM Disabled; RCB 64 bytes Disabled- CommClk+
			ExtSynch- ClockPM- AutWidDis- BWInt- AutBWInt-
		LnkSta:	Speed 2.5GT/s, Width x1, TrErr- Train- SlotClk+ DLActive- BWMgmt- ABWMgmt-
		DevCap2: Completion Timeout: Not Supported, TimeoutDis+, LTR-, OBFF Not Supported
			 AtomicOpsCap: 32bit- 64bit- 128bitCAS-
		DevCtl2: Completion Timeout: 50us to 50ms, TimeoutDis-, LTR-, OBFF Disabled
			 AtomicOpsCtl: ReqEn-
		LnkCtl2: Target Link Speed: 2.5GT/s, EnterCompliance- SpeedDis-
			 Transmit Margin: Normal Operating Range, EnterModifiedCompliance- ComplianceSOS-
			 Compliance De-emphasis: -6dB
		LnkSta2: Current De-emphasis Level: -6dB, EqualizationComplete-, EqualizationPhase1-
			 EqualizationPhase2-, EqualizationPhase3-, LinkEqualizationRequest-
	Capabilities: [b0] MSI-X: Enable- Count=4 Masked-
		Vector table: BAR=4 offset=00000000
		PBA: BAR=4 offset=00000800
	Capabilities: [d0] Vital Product Data
pcilib: sysfs_read_vpd: read failed: Input/output error
		Not readable
	Capabilities: [100 v1] Advanced Error Reporting
		UESta:	DLP- SDES- TLP- FCP- CmpltTO- CmpltAbrt- UnxCmplt- RxOF- MalfTLP- ECRC- UnsupReq- ACSViol-
		UEMsk:	DLP- SDES- TLP- FCP- CmpltTO- CmpltAbrt- UnxCmplt- RxOF- MalfTLP- ECRC- UnsupReq- ACSViol-
		UESvrt:	DLP+ SDES+ TLP- FCP+ CmpltTO- CmpltAbrt- UnxCmplt- RxOF+ MalfTLP+ ECRC- UnsupReq- ACSViol-
		CESta:	RxErr- BadTLP- BadDLLP- Rollover- Timeout- NonFatalErr-
		CEMsk:	RxErr- BadTLP- BadDLLP- Rollover- Timeout- NonFatalErr+
		AERCap:	First Error Pointer: 00, ECRCGenCap+ ECRCGenEn- ECRCChkCap+ ECRCChkEn-
			MultHdrRecCap- MultHdrRecEn- TLPPfxPres- HdrLogCap-
		HeaderLog: 00000000 00000000 00000000 00000000
	Capabilities: [140 v1] Virtual Channel
		Caps:	LPEVC=0 RefClk=100ns PATEntryBits=1
		Arb:	Fixed- WRR32- WRR64- WRR128-
		Ctrl:	ArbSelect=Fixed
		Status:	InProgress-
		VC0:	Caps:	PATOffset=00 MaxTimeSlots=1 RejSnoopTrans-
			Arb:	Fixed- WRR32- WRR64- WRR128- TWRR128- WRR256-
			Ctrl:	Enable+ ID=0 ArbSelect=Fixed TC/VC=01
			Status:	NegoPending- InProgress-
	Capabilities: [160 v1] Device Serial Number 6c-00-00-00-68-4c-e0-00
	Kernel driver in use: r8169
	Kernel modules: r8169

Offline

#25 2018-02-15 04:38:21

Scale2boy
Member
Registered: 2018-02-15
Posts: 1

Re: [SOLVED][Bug]Kernel 4.15 - Default TCP Congestion BBR - Slow network

Well, I've met with this issue also a week ago, the samer r8169 NIC.
https://github.com/zen-kernel/zen-kerne … -364069269

And the cubic mode solves this issue.

Last edited by Scale2boy (2018-02-15 04:41:58)

Offline

Board footer

Powered by FluxBB