Skip to contentSkip to conversation

net: Kill link between CSUM and SG features.

Regression Joseph Salisbury 3 participants 7 messages Jul 16, 2013 – Jul 17, 2013

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

Hi Pravin,

A bug was opened against the Ubuntu kernel[0]. After a kernel bisect, it was found that reverting the following commit resolved this bug:

commit ec5f061564238892005257c83565a0b58ec79295

Author: Pravin B Shelar <[email protected]>
Date:   Thu Mar 7 09:28:01 2013 +0000

net: Kill link between CSUM and SG features.

The regression was introduced as of v3.10-rc1.

I see that you are the author of this patch, so I wanted to run this by you. I was thinking of requesting a revert for v3.11, but I wanted to get your feedback first.

Thanks,

Joe

[0] http://pad.lv/1200243

#1 lore raw
Quoted 9 lines · Joseph Salisbury

Hi Pravin,

A bug was opened against the Ubuntu kernel[0]. After a kernel bisect, it was found that reverting the following commit resolved this bug:

commit ec5f061564238892005257c83565a0b58ec79295

Author: Pravin B Shelar <[email protected]>
Date:   Thu Mar 7 09:28:01 2013 +0000
Quoted 10 lines

net: Kill link between CSUM and SG features.

The regression was introduced as of v3.10-rc1.

I see that you are the author of this patch, so I wanted to run this by you. I was thinking of requesting a revert for v3.11, but I wanted to get your feedback first.

This issue was reported before and turning off sg solves problem for HyperV driver. Drivers (intel and bnx2x) that I tested works fine with this patch. Have you seen the issue on any other NIC?

Quoted 10 lines

Thanks,

Joe

[0] http://pad.lv/1200243

--
To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html

#2 lore raw
Quoted 16 lines · Pravin Shelar
Quoted 14 lines · Joseph Salisbury

Hi Pravin,

A bug was opened against the Ubuntu kernel[0]. After a kernel bisect, it was found that reverting the following commit resolved this bug:

commit ec5f061564238892005257c83565a0b58ec79295

Author: Pravin B Shelar <[email protected]>
Date:   Thu Mar 7 09:28:01 2013 +0000

net: Kill link between CSUM and SG features.

The regression was introduced as of v3.10-rc1.

Quoted 8 lines
Quoted 5 lines

I see that you are the author of this patch, so I wanted to run this by you. I was thinking of requesting a revert for v3.11, but I wanted to get your feedback first.

This issue was reported before and turning off sg solves problem for HyperV driver. Drivers (intel and bnx2x) that I tested works fine with this patch. Have you seen the issue on any other NIC?

Thanks for the feedback. We have only seen it on Intel hardware. Can you send a pointer to the patch? If so, we can provide some additional testing. Do you plan on submitting the patch for inclusion in 3.11?

Quoted 12 lines
Quoted 12 lines

Thanks,

Joe

[0] http://pad.lv/1200243

--
To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html

#3 lore raw
Quoted 22 lines · Joseph Salisbury
Quoted 21 lines · Pravin Shelar
Quoted 19 lines · Joseph Salisbury

Hi Pravin,

A bug was opened against the Ubuntu kernel[0]. After a kernel bisect, it was found that reverting the following commit resolved this bug:

commit ec5f061564238892005257c83565a0b58ec79295

Author: Pravin B Shelar <[email protected]>
Date:   Thu Mar 7 09:28:01 2013 +0000

net: Kill link between CSUM and SG features.

The regression was introduced as of v3.10-rc1.

I see that you are the author of this patch, so I wanted to run this by you. I was thinking of requesting a revert for v3.11, but I wanted to get your feedback first.

Quoted 9 lines
Quoted 3 lines

This issue was reported before and turning off sg solves problem for HyperV driver. Drivers (intel and bnx2x) that I tested works fine with this patch. Have you seen the issue on any other NIC?

Thanks for the feedback. We have only seen it on Intel hardware. Can you send a pointer to the patch? If so, we can provide some additional testing. Do you plan on submitting the patch for inclusion in 3.11?

What I mean is I do not see any problem with the patch that you have pointed out on ixgbe and bnx2x platforms. HyperV problem went away with disabling sg by ethtool utility.

Can you also give me more information about regression you are seeing like driver name, features of the NIC set and features of device without this patch. Does any other NIC than HyperV having this issue?

Thanks.

Quoted 13 lines
Quoted 12 lines
Quoted 12 lines

Thanks,

Joe

[0] http://pad.lv/1200243

--
To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html

#4 lore raw
Quoted 27 lines · Pravin Shelar
Quoted 25 lines · Joseph Salisbury
Quoted 24 lines · Pravin Shelar
Quoted 9 lines · Joseph Salisbury

Hi Pravin,

A bug was opened against the Ubuntu kernel[0]. After a kernel bisect, it was found that reverting the following commit resolved this bug:

commit ec5f061564238892005257c83565a0b58ec79295

Author: Pravin B Shelar <[email protected]>
Date:   Thu Mar 7 09:28:01 2013 +0000
Quoted 10 lines

net: Kill link between CSUM and SG features.

The regression was introduced as of v3.10-rc1.

I see that you are the author of this patch, so I wanted to run this by you. I was thinking of requesting a revert for v3.11, but I wanted to get your feedback first.

This issue was reported before and turning off sg solves problem for HyperV driver. Drivers (intel and bnx2x) that I tested works fine with this patch. Have you seen the issue on any other NIC?

Quoted 8 lines
Quoted 5 lines

Thanks for the feedback. We have only seen it on Intel hardware. Can you send a pointer to the patch? If so, we can provide some additional testing. Do you plan on submitting the patch for inclusion in 3.11?

What I mean is I do not see any problem with the patch that you have pointed out on ixgbe and bnx2x platforms. HyperV problem went away with disabling sg by ethtool utility.

Yes, we also see that the problem goes away when disabling sg with ethtool. There was a significant improvement in throughput with sg enabled, so it's unfortunate it must be disabled.

Quoted 4 lines

Can you also give me more information about regression you are seeing like driver name, features of the NIC set and features of device without this patch. Does any other NIC than HyperV having this issue?

Some details info about the HyperV guest can be seen here:
http://paste.ubuntu.com/5884549/

In that output, you will see that scatter-gather is off, which was done manually.

Only a HyperV NIC is having this issue.

Quoted 19 lines

Thanks.

Quoted 11 lines
Quoted 11 lines
Quoted 11 lines

Thanks,

Joe

[0] http://pad.lv/1200243

--
To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

#5 lore raw
Quoted 60 lines

-----Original Message-----
From: Joseph Salisbury [mailto:[email protected]]
Sent: Wednesday, July 17, 2013 8:31 AM
To: Pravin Shelar
Cc: [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; LKML; KY Srinivasan; Haiyang Zhang
Subject: Re: [Regression][v3.10][v3.11] net: Kill link between CSUM and SG features.

Quoted 9 lines · Pravin Shelar
Quoted 7 lines · Joseph Salisbury
Quoted 6 lines · Pravin Shelar
Quoted 4 lines · Joseph Salisbury

Hi Pravin,

A bug was opened against the Ubuntu kernel[0]. After a kernel bisect, it was found that reverting the following commit resolved this

bug:

Quoted 15 lines
Quoted 15 lines
Quoted 15 lines
Quoted 15 lines

commit ec5f061564238892005257c83565a0b58ec79295

Author: Pravin B Shelar <[email protected]>
Date:   Thu Mar 7 09:28:01 2013 +0000

net: Kill link between CSUM and SG features.

The regression was introduced as of v3.10-rc1.

I see that you are the author of this patch, so I wanted to run this by you. I was thinking of requesting a revert for v3.11, but I wanted to get your feedback first.

Quoted 6 lines
Quoted 6 lines
Quoted 3 lines

This issue was reported before and turning off sg solves problem for HyperV driver. Drivers (intel and bnx2x) that I tested works fine with this patch. Have you seen the issue on any other NIC?

Thanks for the feedback. We have only seen it on Intel hardware. Can you send a pointer to the patch? If so, we can provide some additional testing. Do you plan on submitting the patch for inclusion in

3.11?

Quoted 5 lines
Quoted 2 lines

What I mean is I do not see any problem with the patch that you have pointed out on ixgbe and bnx2x platforms. HyperV problem went away with disabling sg by ethtool utility.

Yes, we also see that the problem goes away when disabling sg with ethtool. There was a significant improvement in throughput with sg enabled, so it's unfortunate it must be disabled.

Quoted 4 lines

Can you also give me more information about regression you are seeing like driver name, features of the NIC set and features of device without this patch. Does any other NIC than HyperV having this issue?

Quoted 7 lines

Some details info about the HyperV guest can be seen here:
http://paste.ubuntu.com/5884549/

In that output, you will see that scatter-gather is off, which was done manually.

Only a HyperV NIC is having this issue.

I have submitted a patch which has been accepted, and queued for -stable branch as well: http://patchwork.ozlabs.org/patch/259596/
It removes the NETIF_F_SG flag from the hv_netvsc driver, which doesn't currently support SG mode.

Thanks,
- Haiyang

#6 lore raw
Quoted 61 lines · Haiyang Zhang
Quoted 61 lines

-----Original Message-----
From: Joseph Salisbury [mailto:[email protected]]
Sent: Wednesday, July 17, 2013 8:31 AM
To: Pravin Shelar
Cc: [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; LKML; KY Srinivasan; Haiyang Zhang
Subject: Re: [Regression][v3.10][v3.11] net: Kill link between CSUM and SG features.

Quoted 9 lines · Pravin Shelar
Quoted 7 lines · Joseph Salisbury
Quoted 6 lines · Pravin Shelar
Quoted 4 lines · Joseph Salisbury

Hi Pravin,

A bug was opened against the Ubuntu kernel[0]. After a kernel bisect, it was found that reverting the following commit resolved this

bug:

Quoted 14 lines
Quoted 14 lines
Quoted 14 lines
Quoted 14 lines

commit ec5f061564238892005257c83565a0b58ec79295

Author: Pravin B Shelar <[email protected]>
Date:   Thu Mar 7 09:28:01 2013 +0000

net: Kill link between CSUM and SG features.

The regression was introduced as of v3.10-rc1.

I see that you are the author of this patch, so I wanted to run this by you. I was thinking of requesting a revert for v3.11, but I wanted to get your feedback first.

Quoted 6 lines
Quoted 6 lines
Quoted 3 lines

This issue was reported before and turning off sg solves problem for HyperV driver. Drivers (intel and bnx2x) that I tested works fine with this patch. Have you seen the issue on any other NIC?

Thanks for the feedback. We have only seen it on Intel hardware. Can you send a pointer to the patch? If so, we can provide some additional testing. Do you plan on submitting the patch for inclusion in

3.11?

Quoted 4 lines
Quoted 1 line

What I mean is I do not see any problem with the patch that you have pointed out on ixgbe and bnx2x platforms. HyperV problem went away with disabling sg by ethtool utility.

Yes, we also see that the problem goes away when disabling sg with ethtool. There was a significant improvement in throughput with sg enabled, so it's unfortunate it must be disabled.

Quoted 3 lines

Can you also give me more information about regression you are seeing like driver name, features of the NIC set and features of device without this patch. Does any other NIC than HyperV having this issue?

Some details info about the HyperV guest can be seen here:
http://paste.ubuntu.com/5884549/

In that output, you will see that scatter-gather is off, which was done manually.

Quoted 9 lines
Quoted 1 line

Only a HyperV NIC is having this issue.

I have submitted a patch which has been accepted, and queued for -stable branch as well: http://patchwork.ozlabs.org/patch/259596/
It removes the NETIF_F_SG flag from the hv_netvsc driver, which doesn't currently support SG mode.

Thanks,
- Haiyang

That's great. Thanks, Haiyang!