DPDK patches and discussions
 help / color / mirror / Atom feed
* [dpdk-dev] 【BUG REPORT】l3fwd-power can not exit by ctrl+c
@ 2020-05-20  3:18 oulijun
  2020-05-20  7:22 ` David Marchand
  2020-05-20  9:45 ` Burakov, Anatoly
  0 siblings, 2 replies; 19+ messages in thread
From: oulijun @ 2020-05-20  3:18 UTC (permalink / raw)
  To: david.marchand, harry.van.haaren; +Cc: dev

Hi, David Marchand && guys

    I am using 20.05-rc2 version to test based on HNS3 NIC hardware, and 
found that after starting l3fwd-power,

using ctrl+c cannot force quit. But I revert the patch(33666b4 service: 
fix crash on exit) and it is ok.

the log as follows:

Initializing rx queues on lcore 26 ...
Initializing rx queues on lcore 27 ... rxq=0,0,0 Port 0: softly parse 
packet type info


Checking link status...............0000:7d:00.1 
hns3_update_link_status(): Link status change to up!
done
Port 0 Link Up - speed 25000 Mbps - full-duplex
L3FWD_POWER: entering main loop on lcore 27
L3FWD_POWER:  -- lcoreid=27 portid=0 rxqueueid=0
L3FWD_POWER: lcore 26 has nothing to do
L3FWD_POWER: lcore 27 sleeps until interrupt triggers
L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
L3FWD_POWER: lcore 27 sleeps until interrupt triggers
L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
L3FWD_POWER: lcore 27 sleeps until interrupt triggers
L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
L3FWD_POWER: lcore 27 sleeps until interrupt triggers
L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
L3FWD_POWER: lcore 27 sleeps until interrupt triggers
L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
L3FWD_POWER: lcore 27 sleeps until interrupt triggers
L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
L3FWD_POWER: lcore 27 sleeps until interrupt triggers
L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
L3FWD_POWER: lcore 27 sleeps until interrupt triggers
L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
L3FWD_POWER: lcore 27 sleeps until interrupt triggers
L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
L3FWD_POWER: lcore 27 sleeps until interrupt triggers
L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
L3FWD_POWER: lcore 27 sleeps until interrupt triggers
L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
L3FWD_POWER: lcore 27 sleeps until interrupt triggers
^CPOWER: Power management governor of lcore 26 has been set back to  
successfully
POWER: Power management of lcore 26 has exited from 'userspace' mode and 
been set back to the original
POWER: Power management governor of lcore 27 has been set back to 
successfully
POWER: Power management of lcore 27 has exited from 'userspace' mode and 
been set back to the original
0000:7d:00.1 hns3_dev_close(): Close port 0 finished
User forced exit
[root@centos-C3 build]#

Thanks

Lijun Ou







^ permalink raw reply	[flat|nested] 19+ messages in thread

* Re: [dpdk-dev] 【BUG REPORT】l3fwd-power can not exit by ctrl+c
  2020-05-20  3:18 [dpdk-dev] 【BUG REPORT】l3fwd-power can not exit by ctrl+c oulijun
@ 2020-05-20  7:22 ` David Marchand
  2020-05-20  8:41   ` oulijun
  2020-05-22  8:17   ` oulijun
  2020-05-20  9:45 ` Burakov, Anatoly
  1 sibling, 2 replies; 19+ messages in thread
From: David Marchand @ 2020-05-20  7:22 UTC (permalink / raw)
  To: oulijun
  Cc: Van Haaren Harry, dev, Burakov, Anatoly, David Hunt, Pattan, Reshma

Hello,

On Wed, May 20, 2020 at 5:18 AM oulijun <oulijun@huawei.com> wrote:
>     I am using 20.05-rc2 version to test based on HNS3 NIC hardware, and
> found that after starting l3fwd-power,
>
> using ctrl+c cannot force quit. But I revert the patch(33666b4 service:
> fix crash on exit) and it is ok.

We had a fix in rc1 that is supposed to fix this.
https://git.dpdk.org/dpdk/commit?id=613ce6691c0d5ac0f99d7995f1e8e4ac86643882

Copying Anatoly and David H. too.


>
> the log as follows:
>
> Initializing rx queues on lcore 26 ...
> Initializing rx queues on lcore 27 ... rxq=0,0,0 Port 0: softly parse
> packet type info
>
>
> Checking link status...............0000:7d:00.1
> hns3_update_link_status(): Link status change to up!
> done
> Port 0 Link Up - speed 25000 Mbps - full-duplex
> L3FWD_POWER: entering main loop on lcore 27
> L3FWD_POWER:  -- lcoreid=27 portid=0 rxqueueid=0
> L3FWD_POWER: lcore 26 has nothing to do
> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
> ^CPOWER: Power management governor of lcore 26 has been set back to
> successfully
> POWER: Power management of lcore 26 has exited from 'userspace' mode and
> been set back to the original
> POWER: Power management governor of lcore 27 has been set back to
> successfully
> POWER: Power management of lcore 27 has exited from 'userspace' mode and
> been set back to the original
> 0000:7d:00.1 hns3_dev_close(): Close port 0 finished
> User forced exit
> [root@centos-C3 build]#

So I understand those traces are for when it works.

What about the traces when it does not work?
Can you get a backtrace to know where the process is stuck?


Thanks for reporting.

-- 
David Marchand


^ permalink raw reply	[flat|nested] 19+ messages in thread

* Re: [dpdk-dev] 【BUG REPORT】l3fwd-power can not exit by ctrl+c
  2020-05-20  7:22 ` David Marchand
@ 2020-05-20  8:41   ` oulijun
  2020-05-20  8:49     ` David Marchand
  2020-05-20 11:37     ` Burakov, Anatoly
  2020-05-22  8:17   ` oulijun
  1 sibling, 2 replies; 19+ messages in thread
From: oulijun @ 2020-05-20  8:41 UTC (permalink / raw)
  To: David Marchand
  Cc: Van Haaren Harry, dev, Burakov, Anatoly, David Hunt, Pattan, Reshma



在 2020/5/20 15:22, David Marchand 写道:
> Hello,
> 
> On Wed, May 20, 2020 at 5:18 AM oulijun <oulijun@huawei.com> wrote:
>>      I am using 20.05-rc2 version to test based on HNS3 NIC hardware, and
>> found that after starting l3fwd-power,
>>
>> using ctrl+c cannot force quit. But I revert the patch(33666b4 service:
>> fix crash on exit) and it is ok.
> 
> We had a fix in rc1 that is supposed to fix this.
> https://git.dpdk.org/dpdk/commit?id=613ce6691c0d5ac0f99d7995f1e8e4ac86643882
> 
> Copying Anatoly and David H. too.
> 
> 
>>
>> the log as follows:
>>
>> Initializing rx queues on lcore 26 ...
>> Initializing rx queues on lcore 27 ... rxq=0,0,0 Port 0: softly parse
>> packet type info
>>
>>
>> Checking link status...............0000:7d:00.1
>> hns3_update_link_status(): Link status change to up!
>> done
>> Port 0 Link Up - speed 25000 Mbps - full-duplex
>> L3FWD_POWER: entering main loop on lcore 27
>> L3FWD_POWER:  -- lcoreid=27 portid=0 rxqueueid=0
>> L3FWD_POWER: lcore 26 has nothing to do
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> ^CPOWER: Power management governor of lcore 26 has been set back to
>> successfully
>> POWER: Power management of lcore 26 has exited from 'userspace' mode and
>> been set back to the original
>> POWER: Power management governor of lcore 27 has been set back to
>> successfully
>> POWER: Power management of lcore 27 has exited from 'userspace' mode and
>> been set back to the original
>> 0000:7d:00.1 hns3_dev_close(): Close port 0 finished
>> User forced exit
>> [root@centos-C3 build]#
> 
> So I understand those traces are for when it works.
> 
> What about the traces when it does not work?
> Can you get a backtrace to know where the process is stuck?
I think that it is entered the rte_exit and can not eixt
> 
> 
> Thanks for reporting.
> 
the log as follows when it not works:
L3FWD_POWER: lcore 27 sleeps until interrupt triggers
^CPOWER: Power management governor of lcore 26 has been set back to 
successfully
POWER: Power management of lcore 26 has exited from 'userspace' mode and 
been set back to the original
POWER: Power management governor of lcore 27 has been set back to 
successfully
POWER: Power management of lcore 27 has exited from 'userspace' mode and 
been set back to the original
0000:7d:00.1 hns3_dev_close(): Close port 0 finished
User forced exit




it can not exit and enter the shell window.

Thanks


^ permalink raw reply	[flat|nested] 19+ messages in thread

* Re: [dpdk-dev] 【BUG REPORT】l3fwd-power can not exit by ctrl+c
  2020-05-20  8:41   ` oulijun
@ 2020-05-20  8:49     ` David Marchand
  2020-05-20 11:37     ` Burakov, Anatoly
  1 sibling, 0 replies; 19+ messages in thread
From: David Marchand @ 2020-05-20  8:49 UTC (permalink / raw)
  To: oulijun
  Cc: Van Haaren Harry, dev, Burakov, Anatoly, David Hunt, Pattan, Reshma

On Wed, May 20, 2020 at 10:41 AM oulijun <oulijun@huawei.com> wrote:
> the log as follows when it not works:
> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
> ^CPOWER: Power management governor of lcore 26 has been set back to
> successfully
> POWER: Power management of lcore 26 has exited from 'userspace' mode and
> been set back to the original
> POWER: Power management governor of lcore 27 has been set back to
> successfully
> POWER: Power management of lcore 27 has exited from 'userspace' mode and
> been set back to the original
> 0000:7d:00.1 hns3_dev_close(): Close port 0 finished
> User forced exit
>
>
>
>
> it can not exit and enter the shell window.

Please attach a gdb, list the threads running and get a backtrace on each.
Thanks.


-- 
David Marchand


^ permalink raw reply	[flat|nested] 19+ messages in thread

* Re: [dpdk-dev] 【BUG REPORT】l3fwd-power can not exit by ctrl+c
  2020-05-20  3:18 [dpdk-dev] 【BUG REPORT】l3fwd-power can not exit by ctrl+c oulijun
  2020-05-20  7:22 ` David Marchand
@ 2020-05-20  9:45 ` Burakov, Anatoly
  2020-05-21  1:26   ` oulijun
  1 sibling, 1 reply; 19+ messages in thread
From: Burakov, Anatoly @ 2020-05-20  9:45 UTC (permalink / raw)
  To: oulijun, david.marchand, harry.van.haaren; +Cc: dev

On 20-May-20 4:18 AM, oulijun wrote:
> Hi, David Marchand && guys
> 
>     I am using 20.05-rc2 version to test based on HNS3 NIC hardware, and 
> found that after starting l3fwd-power,
> 
> using ctrl+c cannot force quit. But I revert the patch(33666b4 service: 
> fix crash on exit) and it is ok.
> 
> the log as follows:
> 
> Initializing rx queues on lcore 26 ...
> Initializing rx queues on lcore 27 ... rxq=0,0,0 Port 0: softly parse 
> packet type info
> 
> 
> Checking link status...............0000:7d:00.1 
> hns3_update_link_status(): Link status change to up!
> done
> Port 0 Link Up - speed 25000 Mbps - full-duplex
> L3FWD_POWER: entering main loop on lcore 27
> L3FWD_POWER:  -- lcoreid=27 portid=0 rxqueueid=0
> L3FWD_POWER: lcore 26 has nothing to do
> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
> ^CPOWER: Power management governor of lcore 26 has been set back to 
> successfully
> POWER: Power management of lcore 26 has exited from 'userspace' mode and 
> been set back to the original
> POWER: Power management governor of lcore 27 has been set back to 
> successfully
> POWER: Power management of lcore 27 has exited from 'userspace' mode and 
> been set back to the original
> 0000:7d:00.1 hns3_dev_close(): Close port 0 finished
> User forced exit

The "user forced exit" string is from before the patches were applied. 
You are obviously not using the rc2 version. Please pull down the latest 
l3fwd-power code and retest.

> [root@centos-C3 build]#
> 
> Thanks
> 
> Lijun Ou
> 
> 
> 
> 
> 
> 


-- 
Thanks,
Anatoly

^ permalink raw reply	[flat|nested] 19+ messages in thread

* Re: [dpdk-dev] 【BUG REPORT】l3fwd-power can not exit by ctrl+c
  2020-05-20  8:41   ` oulijun
  2020-05-20  8:49     ` David Marchand
@ 2020-05-20 11:37     ` Burakov, Anatoly
  1 sibling, 0 replies; 19+ messages in thread
From: Burakov, Anatoly @ 2020-05-20 11:37 UTC (permalink / raw)
  To: oulijun, David Marchand; +Cc: Van Haaren Harry, dev, David Hunt, Pattan, Reshma

On 20-May-20 9:41 AM, oulijun wrote:
> 
> 
> 在 2020/5/20 15:22, David Marchand 写道:
>> Hello,
>>
>> On Wed, May 20, 2020 at 5:18 AM oulijun <oulijun@huawei.com> wrote:
>>>      I am using 20.05-rc2 version to test based on HNS3 NIC hardware, 
>>> and
>>> found that after starting l3fwd-power,
>>>
>>> using ctrl+c cannot force quit. But I revert the patch(33666b4 service:
>>> fix crash on exit) and it is ok.
>>
>> We had a fix in rc1 that is supposed to fix this.
>> https://git.dpdk.org/dpdk/commit?id=613ce6691c0d5ac0f99d7995f1e8e4ac86643882 
>>
>>
>> Copying Anatoly and David H. too.

Yes, and also this fix:

https://git.dpdk.org/dpdk/commit/?id=f4d1e19c293dc95073614f630ea729cf0bfb57b7

It's part of rc2 as well. With the above two fixes, all problems with 
quitting the app should have been fixed (and were fixed, according to 
our testing).

>>
>>
>>>
>>> the log as follows:
>>>
>>> Initializing rx queues on lcore 26 ...
>>> Initializing rx queues on lcore 27 ... rxq=0,0,0 Port 0: softly parse
>>> packet type info
>>>
>>>
>>> Checking link status...............0000:7d:00.1
>>> hns3_update_link_status(): Link status change to up!
>>> done
>>> Port 0 Link Up - speed 25000 Mbps - full-duplex
>>> L3FWD_POWER: entering main loop on lcore 27
>>> L3FWD_POWER:  -- lcoreid=27 portid=0 rxqueueid=0
>>> L3FWD_POWER: lcore 26 has nothing to do
>>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>>> ^CPOWER: Power management governor of lcore 26 has been set back to
>>> successfully
>>> POWER: Power management of lcore 26 has exited from 'userspace' mode and
>>> been set back to the original
>>> POWER: Power management governor of lcore 27 has been set back to
>>> successfully
>>> POWER: Power management of lcore 27 has exited from 'userspace' mode and
>>> been set back to the original
>>> 0000:7d:00.1 hns3_dev_close(): Close port 0 finished
>>> User forced exit
>>> [root@centos-C3 build]#
>>
>> So I understand those traces are for when it works.
>>
>> What about the traces when it does not work?

Yes, supplying log "when it worked" is not helpful if the goal is to 
figure out what went wrong :)

>> Can you get a backtrace to know where the process is stuck?
> I think that it is entered the rte_exit and can not eixt
>>
>>
>> Thanks for reporting.
>>
> the log as follows when it not works:
> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
> ^CPOWER: Power management governor of lcore 26 has been set back to 
> successfully
> POWER: Power management of lcore 26 has exited from 'userspace' mode and 
> been set back to the original
> POWER: Power management governor of lcore 27 has been set back to 
> successfully
> POWER: Power management of lcore 27 has exited from 'userspace' mode and 
> been set back to the original
> 0000:7d:00.1 hns3_dev_close(): Close port 0 finished
> User forced exit

Again, this looks like a pre-rc1 log. Please retest with latest rc2 code.

> 
> 
> 
> 
> it can not exit and enter the shell window.
> 
> Thanks
> 


-- 
Thanks,
Anatoly

^ permalink raw reply	[flat|nested] 19+ messages in thread

* Re: [dpdk-dev] 【BUG REPORT】l3fwd-power can not exit by ctrl+c
  2020-05-20  9:45 ` Burakov, Anatoly
@ 2020-05-21  1:26   ` oulijun
  2020-05-21 10:46     ` Burakov, Anatoly
  0 siblings, 1 reply; 19+ messages in thread
From: oulijun @ 2020-05-21  1:26 UTC (permalink / raw)
  To: Burakov, Anatoly, david.marchand, harry.van.haaren; +Cc: dev



在 2020/5/20 17:45, Burakov, Anatoly 写道:
> On 20-May-20 4:18 AM, oulijun wrote:
>> Hi, David Marchand && guys
>>
>>     I am using 20.05-rc2 version to test based on HNS3 NIC hardware, 
>> and found that after starting l3fwd-power,
>>
>> using ctrl+c cannot force quit. But I revert the patch(33666b4 
>> service: fix crash on exit) and it is ok.
>>
>> the log as follows:
>>
>> Initializing rx queues on lcore 26 ...
>> Initializing rx queues on lcore 27 ... rxq=0,0,0 Port 0: softly parse 
>> packet type info
>>
>>
>> Checking link status...............0000:7d:00.1 
>> hns3_update_link_status(): Link status change to up!
>> done
>> Port 0 Link Up - speed 25000 Mbps - full-duplex
>> L3FWD_POWER: entering main loop on lcore 27
>> L3FWD_POWER:  -- lcoreid=27 portid=0 rxqueueid=0
>> L3FWD_POWER: lcore 26 has nothing to do
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> ^CPOWER: Power management governor of lcore 26 has been set back to 
>> successfully
>> POWER: Power management of lcore 26 has exited from 'userspace' mode 
>> and been set back to the original
>> POWER: Power management governor of lcore 27 has been set back to 
>> successfully
>> POWER: Power management of lcore 27 has exited from 'userspace' mode 
>> and been set back to the original
>> 0000:7d:00.1 hns3_dev_close(): Close port 0 finished
>> User forced exit
> 
> The "user forced exit" string is from before the patches were applied. 
> You are obviously not using the rc2 version. Please pull down the latest 
> l3fwd-power code and retest.
> 
sorry, our version is 20.05-rc0
>> [root@centos-C3 build]#
>>
>> Thanks
>>
>> Lijun Ou
>>
>>
>>
>>
>>
>>
> 
> 


^ permalink raw reply	[flat|nested] 19+ messages in thread

* Re: [dpdk-dev] 【BUG REPORT】l3fwd-power can not exit by ctrl+c
  2020-05-21  1:26   ` oulijun
@ 2020-05-21 10:46     ` Burakov, Anatoly
  0 siblings, 0 replies; 19+ messages in thread
From: Burakov, Anatoly @ 2020-05-21 10:46 UTC (permalink / raw)
  To: oulijun, david.marchand, harry.van.haaren; +Cc: dev

On 21-May-20 2:26 AM, oulijun wrote:
> 
> 
> 在 2020/5/20 17:45, Burakov, Anatoly 写道:
>> On 20-May-20 4:18 AM, oulijun wrote:
>>> Hi, David Marchand && guys
>>>
>>>     I am using 20.05-rc2 version to test based on HNS3 NIC hardware, 
>>> and found that after starting l3fwd-power,
>>>
>>> using ctrl+c cannot force quit. But I revert the patch(33666b4 
>>> service: fix crash on exit) and it is ok.
>>>
>>> the log as follows:
>>>
>>> Initializing rx queues on lcore 26 ...
>>> Initializing rx queues on lcore 27 ... rxq=0,0,0 Port 0: softly parse 
>>> packet type info
>>>
>>>
>>> Checking link status...............0000:7d:00.1 
>>> hns3_update_link_status(): Link status change to up!
>>> done
>>> Port 0 Link Up - speed 25000 Mbps - full-duplex
>>> L3FWD_POWER: entering main loop on lcore 27
>>> L3FWD_POWER:  -- lcoreid=27 portid=0 rxqueueid=0
>>> L3FWD_POWER: lcore 26 has nothing to do
>>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>>> ^CPOWER: Power management governor of lcore 26 has been set back to 
>>> successfully
>>> POWER: Power management of lcore 26 has exited from 'userspace' mode 
>>> and been set back to the original
>>> POWER: Power management governor of lcore 27 has been set back to 
>>> successfully
>>> POWER: Power management of lcore 27 has exited from 'userspace' mode 
>>> and been set back to the original
>>> 0000:7d:00.1 hns3_dev_close(): Close port 0 finished
>>> User forced exit
>>
>> The "user forced exit" string is from before the patches were applied. 
>> You are obviously not using the rc2 version. Please pull down the 
>> latest l3fwd-power code and retest.
>>
> sorry, our version is 20.05-rc0

Yep. The bug you are reporting has been partially fixed in rc1, and 
fully fixed in rc2. So, please test rc2.

>>> [root@centos-C3 build]#
>>>
>>> Thanks
>>>
>>> Lijun Ou
>>>
>>>
>>>
>>>
>>>
>>>
>>
>>
> 


-- 
Thanks,
Anatoly

^ permalink raw reply	[flat|nested] 19+ messages in thread

* Re: [dpdk-dev] 【BUG REPORT】l3fwd-power can not exit by ctrl+c
  2020-05-20  7:22 ` David Marchand
  2020-05-20  8:41   ` oulijun
@ 2020-05-22  8:17   ` oulijun
  2020-05-22  9:00     ` Burakov, Anatoly
  2020-05-22  9:02     ` Hunt, David
  1 sibling, 2 replies; 19+ messages in thread
From: oulijun @ 2020-05-22  8:17 UTC (permalink / raw)
  To: David Marchand
  Cc: Van Haaren Harry, dev, Burakov, Anatoly, David Hunt, Pattan, Reshma



在 2020/5/20 15:22, David Marchand 写道:
> Hello,
> 
> On Wed, May 20, 2020 at 5:18 AM oulijun <oulijun@huawei.com> wrote:
>>      I am using 20.05-rc2 version to test based on HNS3 NIC hardware, and
>> found that after starting l3fwd-power,
>>
>> using ctrl+c cannot force quit. But I revert the patch(33666b4 service:
>> fix crash on exit) and it is ok.
> 
> We had a fix in rc1 that is supposed to fix this.
> https://git.dpdk.org/dpdk/commit?id=613ce6691c0d5ac0f99d7995f1e8e4ac86643882
> 
> Copying Anatoly and David H. too.
> 
Hi, David Marchand
    I am only merged the patch(examples/l3fwd-power: implement proper 
shutdown) based on 20.05-rc0 and test. the bug is not resolved.
Can you provide me with complete solution?  I want to understand the 
cause of the whole problem

The gdb print as follows:
[root@centos-C3 build]# ./l3fwd-power -w 0000:7d:00.1  -c 0xc000000 -n 4 
-- -P -p 0x01 --config '(0,0,27)' --parse-ptype
EAL: Detected 128 lcore(s)
EAL: Detected 4 NUMA nodes
EAL: Multi-process socket /var/run/dpdk/rte/mp_socket
EAL: Selected IOVA mode 'VA'
EAL: No available hugepages reported in hugepages-2048kB
EAL: No available hugepages reported in hugepages-32768kB
EAL: No available hugepages reported in hugepages-64kB
EAL: Probing VFIO support...
EAL: VFIO support initialized
EAL: PCI device 0000:7d:00.1 on NUMA socket 0
EAL:   probe driver: 19e5:a221 net_hns3
Promiscuous mode selected
soft parse-ptype is enabled
POWER: Env isn't set yet!
POWER: Attempting to initialise ACPI cpufreq power management...
POWER: Power management governor of lcore 26 has been set to user space 
successfully
POWER: Initialized successfully for lcore 26 power management
POWER: Initialized successfully for lcore 27 power management
port 0 is not present on the board
EAL: Error - exiting with code: 1
   Cause: check_port_config failed
[root@centos-C3 build]# ./l3fwd-power -w 0000:7d:00.1  -c 0xc000000 -n 4 
-- -P -p 0x01 --config '(0,0,27)' --parse-ptype
EAL: Detected 128 lcore(s)
EAL: Detected 4 NUMA nodes
EAL: Multi-process socket /var/run/dpdk/rte/mp_socket
EAL: Selected IOVA mode 'PA'
EAL: No available hugepages reported in hugepages-2048kB
EAL: No available hugepages reported in hugepages-32768kB
EAL: No available hugepages reported in hugepages-64kB
EAL: Probing VFIO support...
EAL: VFIO support initialized
EAL: PCI device 0000:7d:00.1 on NUMA socket 0
EAL:   probe driver: 19e5:a221 net_hns3
EAL:   using IOMMU type 1 (Type 1)
EAL: Ignore mapping IO port bar(1)
EAL: Ignore mapping IO port bar(3)
Promiscuous mode selected
soft parse-ptype is enabled
POWER: Env isn't set yet!
POWER: Attempting to initialise ACPI cpufreq power management...
POWER: Initialized successfully for lcore 26 power management
POWER: Initialized successfully for lcore 27 power management
Initializing port 0 ... Creating queues: nb_rxq=1 nb_txq=2... Port 0 
modified RSS hash function based on hardware support,requested:0x20820 
configured:0x820
  Address:00:18:2D:01:00:9E, Allocated mbuf pool on socket 0
LPM: Adding route 0x01010100 / 24 (0)
LPM: Adding route 0x02010100 / 24 (1)
LPM: Adding route 0x03010100 / 24 (2)
LPM: Adding route 0x04010100 / 24 (3)
LPM: Adding route 0x05010100 / 24 (4)
LPM: Adding route 0x06010100 / 24 (5)
LPM: Adding route 0x07010100 / 24 (6)
LPM: Adding route 0x08010100 / 24 (7)
txq=26,0,0 txq=27,1,0

Initializing rx queues on lcore 26 ...
Initializing rx queues on lcore 27 ... rxq=0,0,0 Port 0: softly parse 
packet type info


Checking link status...............0000:7d:00.1 
hns3_update_link_status(): Link status change to up!
done
Port 0 Link Up - speed 25000 Mbps - full-duplex
L3FWD_POWER: entering main loop on lcore 27
L3FWD_POWER:  -- lcoreid=27 portid=0 rxqueueid=0
L3FWD_POWER: lcore 26 has nothing to do
L3FWD_POWER: lcore 27 sleeps until interrupt triggers
L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
L3FWD_POWER: lcore 27 sleeps until interrupt triggers
L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
L3FWD_POWER: lcore 27 sleeps until interrupt triggers
L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
L3FWD_POWER: lcore 27 sleeps until interrupt triggers
L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
L3FWD_POWER: lcore 27 sleeps until interrupt triggers
^C^C^C^C^C


Killed
[root@centos-C3 build]#
[root@centos-C3 build]#
[root@centos-C3 build]#
[root@centos-C3 build]# gdb
GNU gdb (GDB) Red Hat Enterprise Linux 7.6.1-114.el7
Copyright (C) 2013 Free Software Foundation, Inc.
License GPLv3+: GNU GPL version 3 or later 
<http://gnu.org/licenses/gpl.html>
This is free software: you are free to change and redistribute it.
There is NO WARRANTY, to the extent permitted by law.  Type "show copying"
and "show warranty" for details.
This GDB was configured as "aarch64-redhat-linux-gnu".
For bug reporting instructions, please see:
<http://www.gnu.org/software/gdb/bugs/>.
(gdb) set args
(gdb)
(gdb)
(gdb) ./l3fwd-power -w 0000:7d:00.1  -c 0xc000000 -n 4 -- -P -p 0x01 
--config '(0,0,27)' --parse-ptype
Undefined command: "".  Try "help".
(gdb) quit
[root@centos-C3 build]# gdb ./l3fwd-power
GNU gdb (GDB) Red Hat Enterprise Linux 7.6.1-114.el7
Copyright (C) 2013 Free Software Foundation, Inc.
License GPLv3+: GNU GPL version 3 or later 
<http://gnu.org/licenses/gpl.html>
This is free software: you are free to change and redistribute it.
There is NO WARRANTY, to the extent permitted by law.  Type "show copying"
and "show warranty" for details.
This GDB was configured as "aarch64-redhat-linux-gnu".
For bug reporting instructions, please see:
<http://www.gnu.org/software/gdb/bugs/>...
Reading symbols from 
/root/dpdk/examples/l3fwd-power/build/l3fwd-power...done.
(gdb) set args
(gdb) -w 0000:7d:00.1  -c 0xc000000 -n 4 -- -P -p 0x01 --config 
'(0,0,27)' --parse-ptype
Undefined command: "-w".  Try "help".
(gdb) -w 0000:7d:00.1  -c 0xc000000 -n 4 -- -P -p 0x01 --config 
'(0,0,27)' --parse-ptype
Undefined command: "-w".  Try "help".
(gdb) -w 0000:7d:00.1  -c 0xc000000 -n 4 -- -P -p 0x01 --config 
'(0,0,27)' --parse-ptype
Undefined command: "-w".  Try "help".
(gdb) set args -w 0000:7d:00.1  -c 0xc000000 -n 4 -- -P -p 0x01 --config 
'(0,0,27)' --parse-ptype
(gdb) r
Starting program: /root/dpdk/examples/l3fwd-power/build/./l3fwd-power -w 
0000:7d:00.1  -c 0xc000000 -n 4 -- -P -p 0x01 --config '(0,0,27)' 
--parse-ptype
Missing separate debuginfo for /root/lib/libnuma.so.1
Try: yum --enablerepo='*debug*' install 
/usr/lib/debug/.build-id/ce/4eea0b0f2150f70a080bbd8835e43e78373096.debug
[Thread debugging using libthread_db enabled]
Using host libthread_db library "/lib64/libthread_db.so.1".
EAL: Detected 128 lcore(s)
EAL: Detected 4 NUMA nodes
[New Thread 0xfffff7ca8510 (LWP 87238)]
EAL: Multi-process socket /var/run/dpdk/rte/mp_socket
[New Thread 0xfffff74a7510 (LWP 87239)]
EAL: Selected IOVA mode 'PA'
EAL: No available hugepages reported in hugepages-2048kB
EAL: No available hugepages reported in hugepages-32768kB
EAL: No available hugepages reported in hugepages-64kB
EAL: Probing VFIO support...
EAL: VFIO support initialized
[New Thread 0xfffff6c86510 (LWP 87240)]
EAL: PCI device 0000:7d:00.1 on NUMA socket 0
EAL:   probe driver: 19e5:a221 net_hns3
EAL:   using IOMMU type 1 (Type 1)
EAL: Ignore mapping IO port bar(1)
EAL: Ignore mapping IO port bar(3)
Promiscuous mode selected
soft parse-ptype is enabled
POWER: Env isn't set yet!
POWER: Attempting to initialise ACPI cpufreq power management...
POWER: Initialized successfully for lcore 26 power management
POWER: Initialized successfully for lcore 27 power management
Initializing port 0 ... Creating queues: nb_rxq=1 nb_txq=2... Port 0 
modified RSS hash function based on hardware support,requested:0x20820 
configured:0x820
  Address:00:18:2D:01:00:9E, Allocated mbuf pool on socket 0
LPM: Adding route 0x01010100 / 24 (0)
LPM: Adding route 0x02010100 / 24 (1)
LPM: Adding route 0x03010100 / 24 (2)
LPM: Adding route 0x04010100 / 24 (3)
LPM: Adding route 0x05010100 / 24 (4)
LPM: Adding route 0x06010100 / 24 (5)
LPM: Adding route 0x07010100 / 24 (6)
LPM: Adding route 0x08010100 / 24 (7)
txq=26,0,0 txq=27,1,0

Initializing rx queues on lcore 26 ...
Initializing rx queues on lcore 27 ... rxq=0,0,0 Port 0: softly parse 
packet type info

0000:7d:00.1 hns3_update_link_status(): Link status change to up!

Checking link statusdone
Port 0 Link Up - speed 25000 Mbps - full-duplex
L3FWD_POWER: entering main loop on lcore 27
L3FWD_POWER:  -- lcoreid=27 portid=0 rxqueueid=0
L3FWD_POWER: lcore 26 has nothing to do
L3FWD_POWER: lcore 27 sleeps until interrupt triggers
^C
Program received signal SIGINT, Interrupt.
0x0000000000832bd0 in rte_eal_wait_lcore ()
Missing separate debuginfos, use: debuginfo-install 
glibc-2.17-260.el7.aarch64
(gdb) list
1       ../sysdeps/aarch64/crti.S: No such file or directory.
(gdb) l
1       in ../sysdeps/aarch64/crti.S
(gdb) ls
Undefined command: "ls".  Try "help".
(gdb) info threads
   Id   Target Id         Frame
   4    Thread 0xfffff6c86510 (LWP 87240) "lcore-slave-27" 
0x0000fffff7dc47d4 in epoll_pwait () from /lib64/libc.so.6
   3    Thread 0xfffff74a7510 (LWP 87239) "rte_mp_handle" 
0x0000fffff7e7a918 in recvmsg () from /lib64/libpthread.so.0
   2    Thread 0xfffff7ca8510 (LWP 87238) "eal-intr-thread" 
0x0000fffff7dc47d4 in epoll_pwait () from /lib64/libc.so.6
* 1    Thread 0xfffff7ce2110 (LWP 87235) "l3fwd-power" 
0x0000000000832bd0 in rte_eal_wait_lcore ()
(gdb)

Thanks
Lijun Ou
> 
>>
>> the log as follows:
>>
>> Initializing rx queues on lcore 26 ...
>> Initializing rx queues on lcore 27 ... rxq=0,0,0 Port 0: softly parse
>> packet type info
>>
>>
>> Checking link status...............0000:7d:00.1
>> hns3_update_link_status(): Link status change to up!
>> done
>> Port 0 Link Up - speed 25000 Mbps - full-duplex
>> L3FWD_POWER: entering main loop on lcore 27
>> L3FWD_POWER:  -- lcoreid=27 portid=0 rxqueueid=0
>> L3FWD_POWER: lcore 26 has nothing to do
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> L3FWD_POWER: lcore 27 is waked up from rx interrupt on port 0 queue 0
>> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
>> ^CPOWER: Power management governor of lcore 26 has been set back to
>> successfully
>> POWER: Power management of lcore 26 has exited from 'userspace' mode and
>> been set back to the original
>> POWER: Power management governor of lcore 27 has been set back to
>> successfully
>> POWER: Power management of lcore 27 has exited from 'userspace' mode and
>> been set back to the original
>> 0000:7d:00.1 hns3_dev_close(): Close port 0 finished
>> User forced exit
>> [root@centos-C3 build]#
> 
> So I understand those traces are for when it works.
> 
> What about the traces when it does not work?
> Can you get a backtrace to know where the process is stuck?
> 
> 
> Thanks for reporting.
> 


^ permalink raw reply	[flat|nested] 19+ messages in thread

* Re: [dpdk-dev] 【BUG REPORT】l3fwd-power can not exit by ctrl+c
  2020-05-22  8:17   ` oulijun
@ 2020-05-22  9:00     ` Burakov, Anatoly
  2020-05-22  9:02     ` Hunt, David
  1 sibling, 0 replies; 19+ messages in thread
From: Burakov, Anatoly @ 2020-05-22  9:00 UTC (permalink / raw)
  To: oulijun, David Marchand; +Cc: Van Haaren Harry, dev, David Hunt, Pattan, Reshma

On 22-May-20 9:17 AM, oulijun wrote:
> 
> 
> 在 2020/5/20 15:22, David Marchand 写道:
>> Hello,
>>
>> On Wed, May 20, 2020 at 5:18 AM oulijun <oulijun@huawei.com> wrote:
>>>      I am using 20.05-rc2 version to test based on HNS3 NIC hardware, 
>>> and
>>> found that after starting l3fwd-power,
>>>
>>> using ctrl+c cannot force quit. But I revert the patch(33666b4 service:
>>> fix crash on exit) and it is ok.
>>
>> We had a fix in rc1 that is supposed to fix this.
>> https://git.dpdk.org/dpdk/commit?id=613ce6691c0d5ac0f99d7995f1e8e4ac86643882 
>>
>>
>> Copying Anatoly and David H. too.
>>
> Hi, David Marchand
>     I am only merged the patch(examples/l3fwd-power: implement proper 
> shutdown) based on 20.05-rc0 and test.

Why are you testing 20.05-rc0 when there is a later version that already 
has all of this fixed? What's the point of creating additional 
difficulties for yourself, and, more importantly, reporting bugs to the 
community that are already fixed while also not testing the version that 
has those fixes? What are you trying to do that requires you to use rc0 
instead of rc2 or later?

We know rc0 was buggy. We had one patch (linked to by David above) in 
rc1 that fixed it. We had another one in rc2 (linked by myself in 
another email: 
https://git.dpdk.org/dpdk/commit/?id=f4d1e19c293dc95073614f630ea729cf0bfb57b7) 
which completed the fix. Both of these patches are present in rc2 and 
later. So why not try and test rc2 or laster, instead of cherry-picking 
patches on top of rc0?

  the bug is not resolved.
> Can you provide me with complete solution?  I want to understand the 
> cause of the whole problem
> 

The cause of the problem is described in the commit messages for the 
patches. The one David linked to was because l3fwd was exiting 
incorrectly and was relying on particulars of implementation of 
rte_exit() which exited the application straight away, without waiting 
for threads to finish. The one i linked to fixed an additional issue 
related to waiting for interrupts - there was no timeout, so the thread 
never woke up if there was no traffic, and thus rte_exit() couldn't 
finish as well.

All of the above was fixed by rc2, and later versions have these fixes 
as well. So, why are you insisting on using an outdated version for testing?

-- 
Thanks,
Anatoly

^ permalink raw reply	[flat|nested] 19+ messages in thread

* Re: [dpdk-dev] 【BUG REPORT】l3fwd-power can not exit by ctrl+c
  2020-05-22  8:17   ` oulijun
  2020-05-22  9:00     ` Burakov, Anatoly
@ 2020-05-22  9:02     ` Hunt, David
  2020-05-26  3:50       ` oulijun
  1 sibling, 1 reply; 19+ messages in thread
From: Hunt, David @ 2020-05-22  9:02 UTC (permalink / raw)
  To: oulijun, David Marchand
  Cc: Van Haaren Harry, dev, Burakov, Anatoly, Pattan, Reshma


On 22/5/2020 9:17 AM, oulijun wrote:
>
>
> 在 2020/5/20 15:22, David Marchand 写道:
>> Hello,
>>
>> On Wed, May 20, 2020 at 5:18 AM oulijun <oulijun@huawei.com> wrote:
>>>      I am using 20.05-rc2 version to test based on HNS3 NIC 
>>> hardware, and
>>> found that after starting l3fwd-power,
>>>
>>> using ctrl+c cannot force quit. But I revert the patch(33666b4 service:
>>> fix crash on exit) and it is ok.
>>
>> We had a fix in rc1 that is supposed to fix this.
>> https://git.dpdk.org/dpdk/commit?id=613ce6691c0d5ac0f99d7995f1e8e4ac86643882 
>>
>>
>> Copying Anatoly and David H. too.
>>
> Hi, David Marchand
>    I am only merged the patch(examples/l3fwd-power: implement proper 
> shutdown) based on 20.05-rc0 and test. the bug is not resolved.
> Can you provide me with complete solution?  I want to understand the 
> cause of the whole problem
>

Hi Lijun,

     The complete solution is to use a version with all of the fixes, as 
Anatoly suggested previously. I have just checked out the latest tip of 
the master branch, and l3fwd-power exits gracefully with a single CTRL-C:


...
Checking link statusdone
Port 0 Link Up - speed 100000 Mbps - full-duplex
L3FWD_POWER: entering main loop on lcore 27
L3FWD_POWER:  -- lcoreid=27 portid=0 rxqueueid=0
L3FWD_POWER: lcore 26 has nothing to do
L3FWD_POWER: lcore 27 sleeps until interrupt triggers
*^C*POWER: Power management governor of lcore 26 has been set back to  
successfully
POWER: Power management of lcore 26 has exited from 'performance' mode 
and been set back to the original
POWER: Power management governor of lcore 27 has been set back to 
successfully
POWER: Power management of lcore 27 has exited from 'performance' mode 
and been set back to the original
#


Rgds,
Dave.




^ permalink raw reply	[flat|nested] 19+ messages in thread

* Re: [dpdk-dev] 【BUG REPORT】l3fwd-power can not exit by ctrl+c
  2020-05-22  9:02     ` Hunt, David
@ 2020-05-26  3:50       ` oulijun
  2020-05-26  8:36         ` Hunt, David
  2020-05-26  9:24         ` Burakov, Anatoly
  0 siblings, 2 replies; 19+ messages in thread
From: oulijun @ 2020-05-26  3:50 UTC (permalink / raw)
  To: Hunt, David, David Marchand
  Cc: Van Haaren Harry, dev, Burakov, Anatoly, Pattan, Reshma

Hi,
    I have update the code into 20.05-rc2. However, the l3fwd-power 
startup fail.

[root@centos-C3 build]# l3fwd-power -w 0000:7d:00.1  -c 0xc000000 -n 4 
-- -P -p 0x01 --config '(0,0,27)' --parse-ptype
EAL: Detected 128 lcore(s)
EAL: Detected 4 NUMA nodes
EAL: Multi-process socket /var/run/dpdk/rte/mp_socket
EAL: Selected IOVA mode 'PA'
EAL: No available hugepages reported in hugepages-2048kB
EAL: No available hugepages reported in hugepages-32768kB
EAL: No available hugepages reported in hugepages-64kB
EAL: Probing VFIO support...
EAL: VFIO support initialized
EAL:   using IOMMU type 1 (Type 1)
EAL: Ignore mapping IO port bar(1)
EAL: Ignore mapping IO port bar(3)
EAL: Probe PCI driver: net_hns3 (19e5:a221) device: 0000:7d:00.1 (socket 0)
No telemetry legacy support - No legacy callbacks, legacy socket not created
Promiscuous mode selected
soft parse-ptype is enabled
POWER: Env isn't set yet!
POWER: Attempting to initialise ACPI cpufreq power management...
POWER: Power management governor of lcore 26 has been set to user space 
successfully
POWER: File not opened
POWER: Cannot get available frequencies of lcore 26
POWER: Attempting to initialise PSTAT power management...
POWER: Power management governor of lcore 26 has been set to performance 
successfully
POWER: Error opening '/dev/cpu/26/msr': No such file or directory
POWER: Cannot init for setting frequency for lcore 26
POWER: Attempting to initialise VM power management...
GUEST_CHANNEL: Opening channel 
'/dev/virtio-ports/virtio.serial.port.poweragent.26' for lcore 26
GUEST_CHANNEL: Unable to to connect to 
'/dev/virtio-ports/virtio.serial.port.poweragent.26' with error No such 
file or directory
POWER: Unable to set Power Management Environment for lcore 26
POWER: Library initialization failed on core 26
EAL: Error - exiting with code: 1
   Cause: init_power_library failed

Thanks
Lijun Ou

在 2020/5/22 17:02, Hunt, David 写道:
> 
> On 22/5/2020 9:17 AM, oulijun wrote:
>>
>>
>> 在 2020/5/20 15:22, David Marchand 写道:
>>> Hello,
>>>
>>> On Wed, May 20, 2020 at 5:18 AM oulijun <oulijun@huawei.com> wrote:
>>>>      I am using 20.05-rc2 version to test based on HNS3 NIC 
>>>> hardware, and
>>>> found that after starting l3fwd-power,
>>>>
>>>> using ctrl+c cannot force quit. But I revert the patch(33666b4 service:
>>>> fix crash on exit) and it is ok.
>>>
>>> We had a fix in rc1 that is supposed to fix this.
>>> https://git.dpdk.org/dpdk/commit?id=613ce6691c0d5ac0f99d7995f1e8e4ac86643882 
>>>
>>>
>>> Copying Anatoly and David H. too.
>>>
>> Hi, David Marchand
>>    I am only merged the patch(examples/l3fwd-power: implement proper 
>> shutdown) based on 20.05-rc0 and test. the bug is not resolved.
>> Can you provide me with complete solution?  I want to understand the 
>> cause of the whole problem
>>
> 
> Hi Lijun,
> 
>      The complete solution is to use a version with all of the fixes, as 
> Anatoly suggested previously. I have just checked out the latest tip of 
> the master branch, and l3fwd-power exits gracefully with a single CTRL-C:
> 
> 
> ...
> Checking link statusdone
> Port 0 Link Up - speed 100000 Mbps - full-duplex
> L3FWD_POWER: entering main loop on lcore 27
> L3FWD_POWER:  -- lcoreid=27 portid=0 rxqueueid=0
> L3FWD_POWER: lcore 26 has nothing to do
> L3FWD_POWER: lcore 27 sleeps until interrupt triggers
> *^C*POWER: Power management governor of lcore 26 has been set back to  
> successfully
> POWER: Power management of lcore 26 has exited from 'performance' mode 
> and been set back to the original
> POWER: Power management governor of lcore 27 has been set back to 
> successfully
> POWER: Power management of lcore 27 has exited from 'performance' mode 
> and been set back to the original
> #
> 
> 
> Rgds,
> Dave.
> 
> 
> 


^ permalink raw reply	[flat|nested] 19+ messages in thread

* Re: [dpdk-dev] 【BUG REPORT】l3fwd-power can not exit by ctrl+c
  2020-05-26  3:50       ` oulijun
@ 2020-05-26  8:36         ` Hunt, David
  2020-05-26  9:11           ` oulijun
  2020-05-27  6:10           ` oulijun
  2020-05-26  9:24         ` Burakov, Anatoly
  1 sibling, 2 replies; 19+ messages in thread
From: Hunt, David @ 2020-05-26  8:36 UTC (permalink / raw)
  To: oulijun, David Marchand
  Cc: Van Haaren Harry, dev, Burakov, Anatoly, Pattan, Reshma

Hi Lijun,

On 26/5/2020 4:50 AM, oulijun wrote:
> Hi,
>    I have update the code into 20.05-rc2. However, the l3fwd-power 
> startup fail.
>
> [root@centos-C3 build]# l3fwd-power -w 0000:7d:00.1  -c 0xc000000 -n 4 
> -- -P -p 0x01 --config '(0,0,27)' --parse-ptype
>

--snip--

> POWER: Attempting to initialise ACPI cpufreq power management...
> POWER: Power management governor of lcore 26 has been set to user 
> space successfully
> POWER: File not opened
> POWER: Cannot get available frequencies of lcore 26
> POWER: Attempting to initialise PSTAT power management...
> POWER: Power management governor of lcore 26 has been set to 
> performance successfully
> POWER: Error opening '/dev/cpu/26/msr': No such file or directory
> POWER: Cannot init for setting frequency for lcore 26


This was not happening in your previous logs, have you got the 'msr' 
kernel module loaded?

> POWER: Attempting to initialise VM power management...
> GUEST_CHANNEL: Opening channel 
> '/dev/virtio-ports/virtio.serial.port.poweragent.26' for lcore 26
> GUEST_CHANNEL: Unable to to connect to 
> '/dev/virtio-ports/virtio.serial.port.poweragent.26' with error No 
> such file or directory


I did not see any GUEST_CHANNEL notifications in the previous logs you 
provided,  has your setup changed in any way?

By the way, I can run the command you provided above (without the 
whitelist) without any errors on my system, and a single CTRL-C exits 
gracefully. I am not running in a VM.

Rgds,
Dave.


^ permalink raw reply	[flat|nested] 19+ messages in thread

* Re: [dpdk-dev] 【BUG REPORT】l3fwd-power can not exit by ctrl+c
  2020-05-26  8:36         ` Hunt, David
@ 2020-05-26  9:11           ` oulijun
  2020-05-27  6:10           ` oulijun
  1 sibling, 0 replies; 19+ messages in thread
From: oulijun @ 2020-05-26  9:11 UTC (permalink / raw)
  To: Hunt, David, David Marchand
  Cc: Van Haaren Harry, dev, Burakov, Anatoly, Pattan, Reshma



在 2020/5/26 16:36, Hunt, David 写道:
> Hi Lijun,
> 
> On 26/5/2020 4:50 AM, oulijun wrote:
>> Hi,
>>    I have update the code into 20.05-rc2. However, the l3fwd-power 
>> startup fail.
>>
>> [root@centos-C3 build]# l3fwd-power -w 0000:7d:00.1  -c 0xc000000 -n 4 
>> -- -P -p 0x01 --config '(0,0,27)' --parse-ptype
>>
> 
> --snip--
> 
>> POWER: Attempting to initialise ACPI cpufreq power management...
>> POWER: Power management governor of lcore 26 has been set to user 
>> space successfully
>> POWER: File not opened
>> POWER: Cannot get available frequencies of lcore 26
>> POWER: Attempting to initialise PSTAT power management...
>> POWER: Power management governor of lcore 26 has been set to 
>> performance successfully
>> POWER: Error opening '/dev/cpu/26/msr': No such file or directory
>> POWER: Cannot init for setting frequency for lcore 26
> 
> 
> This was not happening in your previous logs, have you got the 'msr' 
> kernel module loaded?
> 
Yes. But what I don't understand is that the dpdk version I use is 
different, and the kernel module is the same. the 20.05-rc0 is ok when 
startup and the 20.05-rc2 is not. I don't notice the msr module.
>> POWER: Attempting to initialise VM power management...
>> GUEST_CHANNEL: Opening channel 
>> '/dev/virtio-ports/virtio.serial.port.poweragent.26' for lcore 26
>> GUEST_CHANNEL: Unable to to connect to 
>> '/dev/virtio-ports/virtio.serial.port.poweragent.26' with error No 
>> such file or directory
> 
> 
> I did not see any GUEST_CHANNEL notifications in the previous logs you 
> provided,  has your setup changed in any way?
> 
> By the way, I can run the command you provided above (without the 
> whitelist) without any errors on my system, and a single CTRL-C exits 
> gracefully. I am not running in a VM.
> 
I don't running vm. I want to test the 20.05-rc2 according to your 
advice. the kernel is the same.
> Rgds,
> Dave.
> 
> 
> .
> 


^ permalink raw reply	[flat|nested] 19+ messages in thread

* Re: [dpdk-dev] 【BUG REPORT】l3fwd-power can not exit by ctrl+c
  2020-05-26  3:50       ` oulijun
  2020-05-26  8:36         ` Hunt, David
@ 2020-05-26  9:24         ` Burakov, Anatoly
  2020-05-27  6:04           ` oulijun
  1 sibling, 1 reply; 19+ messages in thread
From: Burakov, Anatoly @ 2020-05-26  9:24 UTC (permalink / raw)
  To: oulijun, Hunt, David, David Marchand
  Cc: Van Haaren Harry, dev, Pattan, Reshma

On 26-May-20 4:50 AM, oulijun wrote:
> Hi,
>     I have update the code into 20.05-rc2. However, the l3fwd-power 
> startup fail.
> 
> [root@centos-C3 build]# l3fwd-power -w 0000:7d:00.1  -c 0xc000000 -n 4 
> -- -P -p 0x01 --config '(0,0,27)' --parse-ptype
> EAL: Detected 128 lcore(s)
> EAL: Detected 4 NUMA nodes
> EAL: Multi-process socket /var/run/dpdk/rte/mp_socket
> EAL: Selected IOVA mode 'PA'
> EAL: No available hugepages reported in hugepages-2048kB
> EAL: No available hugepages reported in hugepages-32768kB
> EAL: No available hugepages reported in hugepages-64kB
> EAL: Probing VFIO support...
> EAL: VFIO support initialized
> EAL:   using IOMMU type 1 (Type 1)
> EAL: Ignore mapping IO port bar(1)
> EAL: Ignore mapping IO port bar(3)
> EAL: Probe PCI driver: net_hns3 (19e5:a221) device: 0000:7d:00.1 (socket 0)
> No telemetry legacy support - No legacy callbacks, legacy socket not 
> created
> Promiscuous mode selected
> soft parse-ptype is enabled
> POWER: Env isn't set yet!
> POWER: Attempting to initialise ACPI cpufreq power management...
> POWER: Power management governor of lcore 26 has been set to user space 
> successfully
> POWER: File not opened
> POWER: Cannot get available frequencies of lcore 26
> POWER: Attempting to initialise PSTAT power management...
> POWER: Power management governor of lcore 26 has been set to performance 
> successfully
> POWER: Error opening '/dev/cpu/26/msr': No such file or directory
> POWER: Cannot init for setting frequency for lcore 26
> POWER: Attempting to initialise VM power management...
> GUEST_CHANNEL: Opening channel 
> '/dev/virtio-ports/virtio.serial.port.poweragent.26' for lcore 26
> GUEST_CHANNEL: Unable to to connect to 
> '/dev/virtio-ports/virtio.serial.port.poweragent.26' with error No such 
> file or directory
> POWER: Unable to set Power Management Environment for lcore 26
> POWER: Library initialization failed on core 26
> EAL: Error - exiting with code: 1
>    Cause: init_power_library failed
> 
> Thanks
> Lijun Ou
> 

Hi,

Previously, l3fwd-power was very lax in what it was allowing. Now, if it 
can't enable power management, it will not run, because it is more 
strict in what it allows.

As is shown in the log, it tries to initialize ACPI power management, 
but fails. Then, it tries to initialize pstate mode, and it appears that 
MSR driver is not loaded, so it doesn't work either. It also tries to 
check if a KVM channel exists, which doesn't, and that fails as well. 
So, no power management environment can be enabled, and the application 
fails to start.

In order to make it work, you should either boot in ACPI mode (kernel 
parameter: "intel_pstate=disable"), or load the MSR driver (root 
command: modprobe msr).

This more strict power library initialization was added because we saw 
people misusing l3fwd-power to attempt to run without power management 
environment being initialized (such as inside a VM while not having 
telemetry mode enabled), which it was not designed to do and which would 
be an invalid test.

-- 
Thanks,
Anatoly

^ permalink raw reply	[flat|nested] 19+ messages in thread

* Re: [dpdk-dev] 【BUG REPORT】l3fwd-power can not exit by ctrl+c
  2020-05-26  9:24         ` Burakov, Anatoly
@ 2020-05-27  6:04           ` oulijun
  2020-05-27  8:57             ` Burakov, Anatoly
  0 siblings, 1 reply; 19+ messages in thread
From: oulijun @ 2020-05-27  6:04 UTC (permalink / raw)
  To: Burakov, Anatoly, Hunt, David, David Marchand
  Cc: Van Haaren Harry, dev, Pattan, Reshma



在 2020/5/26 17:24, Burakov, Anatoly 写道:
> On 26-May-20 4:50 AM, oulijun wrote:
>> Hi,
>>     I have update the code into 20.05-rc2. However, the l3fwd-power 
>> startup fail.
>>
>> [root@centos-C3 build]# l3fwd-power -w 0000:7d:00.1  -c 0xc000000 -n 4 
>> -- -P -p 0x01 --config '(0,0,27)' --parse-ptype
>> EAL: Detected 128 lcore(s)
>> EAL: Detected 4 NUMA nodes
>> EAL: Multi-process socket /var/run/dpdk/rte/mp_socket
>> EAL: Selected IOVA mode 'PA'
>> EAL: No available hugepages reported in hugepages-2048kB
>> EAL: No available hugepages reported in hugepages-32768kB
>> EAL: No available hugepages reported in hugepages-64kB
>> EAL: Probing VFIO support...
>> EAL: VFIO support initialized
>> EAL:   using IOMMU type 1 (Type 1)
>> EAL: Ignore mapping IO port bar(1)
>> EAL: Ignore mapping IO port bar(3)
>> EAL: Probe PCI driver: net_hns3 (19e5:a221) device: 0000:7d:00.1 
>> (socket 0)
>> No telemetry legacy support - No legacy callbacks, legacy socket not 
>> created
>> Promiscuous mode selected
>> soft parse-ptype is enabled
>> POWER: Env isn't set yet!
>> POWER: Attempting to initialise ACPI cpufreq power management...
>> POWER: Power management governor of lcore 26 has been set to user 
>> space successfully
>> POWER: File not opened
>> POWER: Cannot get available frequencies of lcore 26
>> POWER: Attempting to initialise PSTAT power management...
>> POWER: Power management governor of lcore 26 has been set to 
>> performance successfully
>> POWER: Error opening '/dev/cpu/26/msr': No such file or directory
>> POWER: Cannot init for setting frequency for lcore 26
>> POWER: Attempting to initialise VM power management...
>> GUEST_CHANNEL: Opening channel 
>> '/dev/virtio-ports/virtio.serial.port.poweragent.26' for lcore 26
>> GUEST_CHANNEL: Unable to to connect to 
>> '/dev/virtio-ports/virtio.serial.port.poweragent.26' with error No 
>> such file or directory
>> POWER: Unable to set Power Management Environment for lcore 26
>> POWER: Library initialization failed on core 26
>> EAL: Error - exiting with code: 1
>>    Cause: init_power_library failed
>>
>> Thanks
>> Lijun Ou
>>
> 
> Hi,
> 
> Previously, l3fwd-power was very lax in what it was allowing. Now, if it 
> can't enable power management, it will not run, because it is more 
> strict in what it allows.
> 
> As is shown in the log, it tries to initialize ACPI power management, 
> but fails. Then, it tries to initialize pstate mode, and it appears that 
> MSR driver is not loaded, so it doesn't work either. It also tries to 
> check if a KVM channel exists, which doesn't, and that fails as well. 
> So, no power management environment can be enabled, and the application 
> fails to start.
> 
> In order to make it work, you should either boot in ACPI mode (kernel 
> parameter: "intel_pstate=disable"), or load the MSR driver (root 
> command: modprobe msr).
> 
> This more strict power library initialization was added because we saw 
> people misusing l3fwd-power to attempt to run without power management 
> environment being initialized (such as inside a VM while not having 
> telemetry mode enabled), which it was not designed to do and which would 
> be an invalid test.
> 
thanks. I will try it


^ permalink raw reply	[flat|nested] 19+ messages in thread

* Re: [dpdk-dev] 【BUG REPORT】l3fwd-power can not exit by ctrl+c
  2020-05-26  8:36         ` Hunt, David
  2020-05-26  9:11           ` oulijun
@ 2020-05-27  6:10           ` oulijun
  2020-05-27  8:21             ` Hunt, David
  1 sibling, 1 reply; 19+ messages in thread
From: oulijun @ 2020-05-27  6:10 UTC (permalink / raw)
  To: Hunt, David, David Marchand
  Cc: Van Haaren Harry, dev, Burakov, Anatoly, Pattan, Reshma



在 2020/5/26 16:36, Hunt, David 写道:
> Hi Lijun,
> 
> On 26/5/2020 4:50 AM, oulijun wrote:
>> Hi,
>>    I have update the code into 20.05-rc2. However, the l3fwd-power 
>> startup fail.
>>
>> [root@centos-C3 build]# l3fwd-power -w 0000:7d:00.1  -c 0xc000000 -n 4 
>> -- -P -p 0x01 --config '(0,0,27)' --parse-ptype
>>
> 
> --snip--
> 
>> POWER: Attempting to initialise ACPI cpufreq power management...
>> POWER: Power management governor of lcore 26 has been set to user 
>> space successfully
>> POWER: File not opened
>> POWER: Cannot get available frequencies of lcore 26
>> POWER: Attempting to initialise PSTAT power management...
>> POWER: Power management governor of lcore 26 has been set to 
>> performance successfully
>> POWER: Error opening '/dev/cpu/26/msr': No such file or directory
>> POWER: Cannot init for setting frequency for lcore 26
> 
> 
> This was not happening in your previous logs, have you got the 'msr' 
> kernel module loaded?
> 
>> POWER: Attempting to initialise VM power management...
>> GUEST_CHANNEL: Opening channel 
>> '/dev/virtio-ports/virtio.serial.port.poweragent.26' for lcore 26
>> GUEST_CHANNEL: Unable to to connect to 
>> '/dev/virtio-ports/virtio.serial.port.poweragent.26' with error No 
>> such file or directory
> 
> 
> I did not see any GUEST_CHANNEL notifications in the previous logs you 
> provided,  has your setup changed in any way?
> 
> By the way, I can run the command you provided above (without the 
> whitelist) without any errors on my system, and a single CTRL-C exits 
> gracefully. I am not running in a VM.
> 
> Rgds,
> Dave.
>
Is your hardware system x86? My system is arm64
> 
> .
> 


^ permalink raw reply	[flat|nested] 19+ messages in thread

* Re: [dpdk-dev] 【BUG REPORT】l3fwd-power can not exit by ctrl+c
  2020-05-27  6:10           ` oulijun
@ 2020-05-27  8:21             ` Hunt, David
  0 siblings, 0 replies; 19+ messages in thread
From: Hunt, David @ 2020-05-27  8:21 UTC (permalink / raw)
  To: oulijun, David Marchand
  Cc: Van Haaren Harry, dev, Burakov, Anatoly, Pattan, Reshma


On 27/5/2020 7:10 AM, oulijun wrote:
>
>
> 在 2020/5/26 16:36, Hunt, David 写道:
>> Hi Lijun,
>>
>> On 26/5/2020 4:50 AM, oulijun wrote:
>>> Hi,
>>>    I have update the code into 20.05-rc2. However, the l3fwd-power 
>>> startup fail.
>>>
>>> [root@centos-C3 build]# l3fwd-power -w 0000:7d:00.1  -c 0xc000000 -n 
>>> 4 -- -P -p 0x01 --config '(0,0,27)' --parse-ptype
>>>
>>
>> --snip--
>>
>>> POWER: Attempting to initialise ACPI cpufreq power management...
>>> POWER: Power management governor of lcore 26 has been set to user 
>>> space successfully
>>> POWER: File not opened
>>> POWER: Cannot get available frequencies of lcore 26
>>> POWER: Attempting to initialise PSTAT power management...
>>> POWER: Power management governor of lcore 26 has been set to 
>>> performance successfully
>>> POWER: Error opening '/dev/cpu/26/msr': No such file or directory
>>> POWER: Cannot init for setting frequency for lcore 26
>>
>>
>> This was not happening in your previous logs, have you got the 'msr' 
>> kernel module loaded?
>>
>>> POWER: Attempting to initialise VM power management...
>>> GUEST_CHANNEL: Opening channel 
>>> '/dev/virtio-ports/virtio.serial.port.poweragent.26' for lcore 26
>>> GUEST_CHANNEL: Unable to to connect to 
>>> '/dev/virtio-ports/virtio.serial.port.poweragent.26' with error No 
>>> such file or directory
>>
>>
>> I did not see any GUEST_CHANNEL notifications in the previous logs 
>> you provided,  has your setup changed in any way?
>>
>> By the way, I can run the command you provided above (without the 
>> whitelist) without any errors on my system, and a single CTRL-C exits 
>> gracefully. I am not running in a VM.
>>
>> Rgds,
>> Dave.
>>
> Is your hardware system x86? My system is arm64
>>
>> .
>>
>

I'm on an x86 system.

Rgds,
Dave.


^ permalink raw reply	[flat|nested] 19+ messages in thread

* Re: [dpdk-dev] 【BUG REPORT】l3fwd-power can not exit by ctrl+c
  2020-05-27  6:04           ` oulijun
@ 2020-05-27  8:57             ` Burakov, Anatoly
  0 siblings, 0 replies; 19+ messages in thread
From: Burakov, Anatoly @ 2020-05-27  8:57 UTC (permalink / raw)
  To: oulijun, Hunt, David, David Marchand
  Cc: Van Haaren Harry, dev, Pattan, Reshma

On 27-May-20 7:04 AM, oulijun wrote:
> 
> 
> 在 2020/5/26 17:24, Burakov, Anatoly 写道:
>> On 26-May-20 4:50 AM, oulijun wrote:
>>> Hi,
>>>     I have update the code into 20.05-rc2. However, the l3fwd-power 
>>> startup fail.
>>>
>>> [root@centos-C3 build]# l3fwd-power -w 0000:7d:00.1  -c 0xc000000 -n 
>>> 4 -- -P -p 0x01 --config '(0,0,27)' --parse-ptype
>>> EAL: Detected 128 lcore(s)
>>> EAL: Detected 4 NUMA nodes
>>> EAL: Multi-process socket /var/run/dpdk/rte/mp_socket
>>> EAL: Selected IOVA mode 'PA'
>>> EAL: No available hugepages reported in hugepages-2048kB
>>> EAL: No available hugepages reported in hugepages-32768kB
>>> EAL: No available hugepages reported in hugepages-64kB
>>> EAL: Probing VFIO support...
>>> EAL: VFIO support initialized
>>> EAL:   using IOMMU type 1 (Type 1)
>>> EAL: Ignore mapping IO port bar(1)
>>> EAL: Ignore mapping IO port bar(3)
>>> EAL: Probe PCI driver: net_hns3 (19e5:a221) device: 0000:7d:00.1 
>>> (socket 0)
>>> No telemetry legacy support - No legacy callbacks, legacy socket not 
>>> created
>>> Promiscuous mode selected
>>> soft parse-ptype is enabled
>>> POWER: Env isn't set yet!
>>> POWER: Attempting to initialise ACPI cpufreq power management...
>>> POWER: Power management governor of lcore 26 has been set to user 
>>> space successfully
>>> POWER: File not opened
>>> POWER: Cannot get available frequencies of lcore 26
>>> POWER: Attempting to initialise PSTAT power management...
>>> POWER: Power management governor of lcore 26 has been set to 
>>> performance successfully
>>> POWER: Error opening '/dev/cpu/26/msr': No such file or directory
>>> POWER: Cannot init for setting frequency for lcore 26
>>> POWER: Attempting to initialise VM power management...
>>> GUEST_CHANNEL: Opening channel 
>>> '/dev/virtio-ports/virtio.serial.port.poweragent.26' for lcore 26
>>> GUEST_CHANNEL: Unable to to connect to 
>>> '/dev/virtio-ports/virtio.serial.port.poweragent.26' with error No 
>>> such file or directory
>>> POWER: Unable to set Power Management Environment for lcore 26
>>> POWER: Library initialization failed on core 26
>>> EAL: Error - exiting with code: 1
>>>    Cause: init_power_library failed
>>>
>>> Thanks
>>> Lijun Ou
>>>
>>
>> Hi,
>>
>> Previously, l3fwd-power was very lax in what it was allowing. Now, if 
>> it can't enable power management, it will not run, because it is more 
>> strict in what it allows.
>>
>> As is shown in the log, it tries to initialize ACPI power management, 
>> but fails. Then, it tries to initialize pstate mode, and it appears 
>> that MSR driver is not loaded, so it doesn't work either. It also 
>> tries to check if a KVM channel exists, which doesn't, and that fails 
>> as well. So, no power management environment can be enabled, and the 
>> application fails to start.
>>
>> In order to make it work, you should either boot in ACPI mode (kernel 
>> parameter: "intel_pstate=disable"), or load the MSR driver (root 
>> command: modprobe msr).
>>
>> This more strict power library initialization was added because we saw 
>> people misusing l3fwd-power to attempt to run without power management 
>> environment being initialized (such as inside a VM while not having 
>> telemetry mode enabled), which it was not designed to do and which 
>> would be an invalid test.
>>
> thanks. I will try it
> 

In another email, you said that your system is arm64. The pstate mode 
won't work on that (it's an Intel-specific driver, after all), and i'm 
not sure if ACPI would work either, we never tested it on arm64 and i'm 
not even sure it's _supposed to_ work. The librte_power library has 
always been IA-specific.

I have a sneaking suspicion that you too are attempting to use 
l3fwd-power to test interrupts, rather than the librte_power library. Is 
that the case?

-- 
Thanks,
Anatoly

^ permalink raw reply	[flat|nested] 19+ messages in thread

end of thread, other threads:[~2020-05-27  8:57 UTC | newest]

Thread overview: 19+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-05-20  3:18 [dpdk-dev] 【BUG REPORT】l3fwd-power can not exit by ctrl+c oulijun
2020-05-20  7:22 ` David Marchand
2020-05-20  8:41   ` oulijun
2020-05-20  8:49     ` David Marchand
2020-05-20 11:37     ` Burakov, Anatoly
2020-05-22  8:17   ` oulijun
2020-05-22  9:00     ` Burakov, Anatoly
2020-05-22  9:02     ` Hunt, David
2020-05-26  3:50       ` oulijun
2020-05-26  8:36         ` Hunt, David
2020-05-26  9:11           ` oulijun
2020-05-27  6:10           ` oulijun
2020-05-27  8:21             ` Hunt, David
2020-05-26  9:24         ` Burakov, Anatoly
2020-05-27  6:04           ` oulijun
2020-05-27  8:57             ` Burakov, Anatoly
2020-05-20  9:45 ` Burakov, Anatoly
2020-05-21  1:26   ` oulijun
2020-05-21 10:46     ` Burakov, Anatoly

DPDK patches and discussions

This inbox may be cloned and mirrored by anyone:

	git clone --mirror http://inbox.dpdk.org/dev/0 dev/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 dev dev/ http://inbox.dpdk.org/dev \
		dev@dpdk.org
	public-inbox-index dev

Example config snippet for mirrors.
Newsgroup available over NNTP:
	nntp://inbox.dpdk.org/inbox.dpdk.dev


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git