2019-07-24 08:40:50

by Zhangshaokun

Subject: [RFC] performance regression with commit-id<adb03115f459> ("net: get rid of an signed integer overflow in ip_idents_reserve()")

Hi,

I've observed an significant performance regression with the following commit-id <adb03115f459>
("net: get rid of an signed integer overflow in ip_idents_reserve()").

Here are my test scenes:
----Server----
Cmd: iperf3 -s xxx.xxx.xxxx.xxx -p 10000 -i 0 -A 0
Kenel: 4.19.34
Server number: 32
Port: 10000 – 10032
CPU affinity: 0 – 32
CPU architecture: aarch64
NUMA node0 CPU(s): 0-23
NUMA node1 CPU(s): 24-47

----Client----
Cmd: iperf3 -u -c xxx.xxx.xxxx.xxx -p 10000 -l 16 -b 0 -t 0 -i 0 -A 8
Kenel: 4.19.34
Client number: 32
Port: 10000 – 10032
CPU affinity: 0 – 32
CPU architecture: aarch64
NUMA node0 CPU(s): 0-23
NUMA node1 CPU(s): 24-47

Firstly, With patch <adb03115f459> ("net: get rid of an signed integer overflow in ip_idents_reserve()") ,
client’s cpu is 100%, and function ip_idents_reserve() cpu usage is very high, but the result is not good.
03:08:32 AM IFACE rxpck/s txpck/s rxkB/s txkB/s rxcmp/s txcmp/s rxmcst/s %ifutil
03:08:33 AM eth0 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
03:08:33 AM eth1 0.00 3461296.00 0.00 196049.97 0.00 0.00 0.00 0.00
03:08:33 AM lo 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00

Secondly, revert that patch, use atomic_add_return() instead, the result is better, as below:
03:23:24 AM IFACE rxpck/s txpck/s rxkB/s txkB/s rxcmp/s txcmp/s rxmcst/s %ifutil
03:23:25 AM lo 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
03:23:25 AM eth1 0.00 12834590.00 0.00 726959.20 0.00 0.00 0.00 0.00
03:23:25 AM eth0 7.00 11.00 0.40 2.95 0.00 0.00 0.00 0.00

Thirdly, atomic is not used in ip_idents_reserve() completely ,while each cpu core allocates its own ID segment,
Such as: cpu core0 allocate ID 0 – 1023, cpu core1 allocate 1024 – 2047, …,etc
the result is the best:
03:27:06 AM IFACE rxpck/s txpck/s rxkB/s txkB/s rxcmp/s txcmp/s rxmcst/s %ifutil
03:27:07 AM lo 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
03:27:07 AM eth1 0.00 14275505.00 0.00 808573.53 0.00 0.00 0.00 0.00
03:27:07 AM eth0 0.00 2.00 0.00 0.18 0.00 0.00 0.00 0.00

Because atomic operation performance is bottleneck when cpu core number increase, Can we revert the patch or
use ID segment for each cpu core instead?

Thanks in advance,
Shaokun

2019-07-24 08:57:53

by Eric Dumazet

Subject: Re: [RFC] performance regression with commit-id<adb03115f459> ("net: get rid of an signed integer overflow in ip_idents_reserve()")

On 7/24/19 10:38 AM, Zhangshaokun wrote:
> Hi,
>
> I've observed an significant performance regression with the following commit-id <adb03115f459>
> ("net: get rid of an signed integer overflow in ip_idents_reserve()").

Yes this UBSAN false positive has been painful



>
> Here are my test scenes:
> ----Server----
> Cmd: iperf3 -s xxx.xxx.xxxx.xxx -p 10000 -i 0 -A 0
> Kenel: 4.19.34
> Server number: 32
> Port: 10000 – 10032
> CPU affinity: 0 – 32
> CPU architecture: aarch64
> NUMA node0 CPU(s): 0-23
> NUMA node1 CPU(s): 24-47
>
> ----Client----
> Cmd: iperf3 -u -c xxx.xxx.xxxx.xxx -p 10000 -l 16 -b 0 -t 0 -i 0 -A 8
> Kenel: 4.19.34
> Client number: 32
> Port: 10000 – 10032
> CPU affinity: 0 – 32
> CPU architecture: aarch64
> NUMA node0 CPU(s): 0-23
> NUMA node1 CPU(s): 24-47
>
> Firstly, With patch <adb03115f459> ("net: get rid of an signed integer overflow in ip_idents_reserve()") ,
> client’s cpu is 100%, and function ip_idents_reserve() cpu usage is very high, but the result is not good.
> 03:08:32 AM IFACE rxpck/s txpck/s rxkB/s txkB/s rxcmp/s txcmp/s rxmcst/s %ifutil
> 03:08:33 AM eth0 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
> 03:08:33 AM eth1 0.00 3461296.00 0.00 196049.97 0.00 0.00 0.00 0.00
> 03:08:33 AM lo 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
>
> Secondly, revert that patch, use atomic_add_return() instead, the result is better, as below:
> 03:23:24 AM IFACE rxpck/s txpck/s rxkB/s txkB/s rxcmp/s txcmp/s rxmcst/s %ifutil
> 03:23:25 AM lo 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
> 03:23:25 AM eth1 0.00 12834590.00 0.00 726959.20 0.00 0.00 0.00 0.00
> 03:23:25 AM eth0 7.00 11.00 0.40 2.95 0.00 0.00 0.00 0.00
>
> Thirdly, atomic is not used in ip_idents_reserve() completely ,while each cpu core allocates its own ID segment,
> Such as: cpu core0 allocate ID 0 – 1023, cpu core1 allocate 1024 – 2047, …,etc
> the result is the best:

Not sure what you mean.

Less entropy in IPv4 ID is not going to help when fragments _are_ needed.

Send 40,000 datagrams of 2000 bytes each, add delays, reorders, and boom, most of the packets will be lost.

This is not because your use case does not need proper IP ID that we can mess with them.

If you need to send packets very fast, maybe use AF_PACKET ?

> 03:27:06 AM IFACE rxpck/s txpck/s rxkB/s txkB/s rxcmp/s txcmp/s rxmcst/s %ifutil
> 03:27:07 AM lo 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
> 03:27:07 AM eth1 0.00 14275505.00 0.00 808573.53 0.00 0.00 0.00 0.00
> 03:27:07 AM eth0 0.00 2.00 0.00 0.18 0.00 0.00 0.00 0.00
>
> Because atomic operation performance is bottleneck when cpu core number increase, Can we revert the patch or
> use ID segment for each cpu core instead?


This has been discussed in the past.

https://lore.kernel.org/lkml/[email protected]/

We can revert now UBSAN has been fixed.

Or even use Peter patch : https://lore.kernel.org/lkml/[email protected]/

However, you will still hit badly a shared cache line, not matter what.

Some arches are known to have terrible LL/SC implementation :/

2019-07-25 12:51:34

by Zhangshaokun

Subject: Re: [RFC] performance regression with commit-id<adb03115f459> ("net: get rid of an signed integer overflow in ip_idents_reserve()")

Hi Eric,

Thanks your quick reply.

On 2019/7/24 16:56, Eric Dumazet wrote:
>
>
> On 7/24/19 10:38 AM, Zhangshaokun wrote:
>> Hi,
>>
>> I've observed an significant performance regression with the following commit-id <adb03115f459>
>> ("net: get rid of an signed integer overflow in ip_idents_reserve()").
>
> Yes this UBSAN false positive has been painful
>
>
>
>>
>> Here are my test scenes:
>> ----Server----
>> Cmd: iperf3 -s xxx.xxx.xxxx.xxx -p 10000 -i 0 -A 0
>> Kenel: 4.19.34
>> Server number: 32
>> Port: 10000 – 10032
>> CPU affinity: 0 – 32
>> CPU architecture: aarch64
>> NUMA node0 CPU(s): 0-23
>> NUMA node1 CPU(s): 24-47
>>
>> ----Client----
>> Cmd: iperf3 -u -c xxx.xxx.xxxx.xxx -p 10000 -l 16 -b 0 -t 0 -i 0 -A 8
>> Kenel: 4.19.34
>> Client number: 32
>> Port: 10000 – 10032
>> CPU affinity: 0 – 32
>> CPU architecture: aarch64
>> NUMA node0 CPU(s): 0-23
>> NUMA node1 CPU(s): 24-47
>>
>> Firstly, With patch <adb03115f459> ("net: get rid of an signed integer overflow in ip_idents_reserve()") ,
>> client’s cpu is 100%, and function ip_idents_reserve() cpu usage is very high, but the result is not good.
>> 03:08:32 AM IFACE rxpck/s txpck/s rxkB/s txkB/s rxcmp/s txcmp/s rxmcst/s %ifutil
>> 03:08:33 AM eth0 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
>> 03:08:33 AM eth1 0.00 3461296.00 0.00 196049.97 0.00 0.00 0.00 0.00
>> 03:08:33 AM lo 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
>>
>> Secondly, revert that patch, use atomic_add_return() instead, the result is better, as below:
>> 03:23:24 AM IFACE rxpck/s txpck/s rxkB/s txkB/s rxcmp/s txcmp/s rxmcst/s %ifutil
>> 03:23:25 AM lo 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
>> 03:23:25 AM eth1 0.00 12834590.00 0.00 726959.20 0.00 0.00 0.00 0.00
>> 03:23:25 AM eth0 7.00 11.00 0.40 2.95 0.00 0.00 0.00 0.00
>>
>> Thirdly, atomic is not used in ip_idents_reserve() completely ,while each cpu core allocates its own ID segment,
>> Such as: cpu core0 allocate ID 0 – 1023, cpu core1 allocate 1024 – 2047, …,etc
>> the result is the best:
>
> Not sure what you mean.
>
> Less entropy in IPv4 ID is not going to help when fragments _are_ needed.
>
> Send 40,000 datagrams of 2000 bytes each, add delays, reorders, and boom, most of the packets will be lost.
>
> This is not because your use case does not need proper IP ID that we can mess with them.
>

Got it, thanks your more explanation.

> If you need to send packets very fast, maybe use AF_PACKET ?
>

Ok, I will try it later.

>> 03:27:06 AM IFACE rxpck/s txpck/s rxkB/s txkB/s rxcmp/s txcmp/s rxmcst/s %ifutil
>> 03:27:07 AM lo 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
>> 03:27:07 AM eth1 0.00 14275505.00 0.00 808573.53 0.00 0.00 0.00 0.00
>> 03:27:07 AM eth0 0.00 2.00 0.00 0.18 0.00 0.00 0.00 0.00
>>
>> Because atomic operation performance is bottleneck when cpu core number increase, Can we revert the patch or
>> use ID segment for each cpu core instead?
>
>
> This has been discussed in the past.
>
> https://lore.kernel.org/lkml/[email protected]/
>
> We can revert now UBSAN has been fixed.
>
> Or even use Peter patch : https://lore.kernel.org/lkml/[email protected]/
>

I have tried this patch under the condition that I remove try_cmpxchg because there is no this API in arm64 :
09:21:16 PM IFACE rxpck/s txpck/s rxkB/s txkB/s rxcmp/s txcmp/s rxmcst/s %ifutil
09:21:17 PM lo 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
09:21:17 PM eth1 0.00 10434613.00 0.00 591023.00 0.00 0.00 0.00 0.00
09:21:17 PM eth0 1.00 0.00 0.12 0.00 0.00 0.00 0.00 0.00

The result is 10434613.00 pps and it is less than the atomic_add_return(12834590.00 pps).
Any thoughts?

Thanks,
Shaokun

> However, you will still hit badly a shared cache line, not matter what.
>
> Some arches are known to have terrible LL/SC implementation :/
>
>
> .
>