Kafka Consumer consuming rate suddenly dropped

[Mu Kong <ko...@gmail.com>]

Hi, community

I have a flink application consuming from a kafka topic with 60 partitions.
The parallelism of the source is set to 60, same with the topic partition
number.
The *cluster.evenly-spread-out-slots *config is set to true in flink
cluster.
However, several hours later, the consuming rate of some subtasks of the
source suddenly dropped and caused delay.
There is no back pressure in the application as shown in the flink UI.
The consuming rate is like follows:
[image: image.png]

Is anyone also encountering the same problem?
Is there any way to further pinpoint the issue?


Thanks in advance!
Mu

Re: Kafka Consumer consuming rate suddenly dropped

[Mu Kong <ko...@gmail.com>]

Hi Akshay,

Thank you for helping out.
I checked the resource metrics, the CPU usage is pretty low, lower than 25%.
[image: image.png]
And the cluster (stand alone) is only running this job.

Thanks all the same.

Best regards,
Mu


On Mon, Jul 20, 2020 at 7:22 PM Jake <ft...@qq.com> wrote:

>
> Need some flink kafka consumer log and kafka server log!
>
>
> On Jul 20, 2020, at 5:45 PM, Mu Kong <ko...@gmail.com> wrote:
>
> Hi, community
>
> I have a flink application consuming from a kafka topic with 60 partitions.
> The parallelism of the source is set to 60, same with the topic partition
> number.
> The *cluster.evenly-spread-out-slots *config is set to true in flink
> cluster.
> However, several hours later, the consuming rate of some subtasks of the
> source suddenly dropped and caused delay.
> There is no back pressure in the application as shown in the flink UI.
> The consuming rate is like follows:
> <image.png>
>
> Is anyone also encountering the same problem?
> Is there any way to further pinpoint the issue?
>
>
> Thanks in advance!
> Mu
>
>
On Mon, Jul 20, 2020 at 7:19 PM Akshay Aggarwal <
akshay.aggarwal@flipkart.com> wrote:

> Hi Mu, Did you check the resource utilization metrics for your cluster? I
> once faced a similar issue, and figured it was because the overall CPU Load
> of the cluster spiked to 1+. This may happen if the cluster is shared, and
> some new job was deployed.
>
> ~Akshay
>
> On Mon, Jul 20, 2020 at 3:23 PM Mu Kong <ko...@gmail.com> wrote:
>
>> Hi, community
>>
>> I have a flink application consuming from a kafka topic with 60
>> partitions.
>> The parallelism of the source is set to 60, same with the topic partition
>> number.
>> The *cluster.evenly-spread-out-slots *config is set to true in flink
>> cluster.
>> However, several hours later, the consuming rate of some subtasks of the
>> source suddenly dropped and caused delay.
>> There is no back pressure in the application as shown in the flink UI.
>> The consuming rate is like follows:
>> [image: image.png]
>>
>> Is anyone also encountering the same problem?
>> Is there any way to further pinpoint the issue?
>>
>>
>> Thanks in advance!
>> Mu
>>
>
>
> *-----------------------------------------------------------------------------------------*
>
> *This email and any files transmitted with it are confidential and
> intended solely for the use of the individual or entity to whom they are
> addressed. If you have received this email in error, please notify the
> system manager. This message contains confidential information and is
> intended only for the individual named. If you are not the named addressee,
> you should not disseminate, distribute or copy this email. Please notify
> the sender immediately by email if you have received this email by mistake
> and delete this email from your system. If you are not the intended
> recipient, you are notified that disclosing, copying, distributing or
> taking any action in reliance on the contents of this information is
> strictly prohibited.*
>
>
>
> *Any views or opinions presented in this email are solely those of the
> author and do not necessarily represent those of the organization. Any
> information on shares, debentures or similar instruments, recommended
> product pricing, valuations and the like are for information purposes only.
> It is not meant to be an instruction or recommendation, as the case may be,
> to buy or to sell securities, products, services nor an offer to buy or
> sell securities, products or services unless specifically stated to be so
> on behalf of the Flipkart group. Employees of the Flipkart group of
> companies are expressly required not to make defamatory statements and not
> to infringe or authorise any infringement of copyright or any other legal
> right by email communications. Any such communication is contrary to
> organizational policy and outside the scope of the employment of the
> individual concerned. The organization will not accept any liability in
> respect of such communication, and the employee responsible will be
> personally liable for any damages or other liability arising.*
>
>
>
> *Our organization accepts no liability for the content of this email, or
> for the consequences of any actions taken on the basis of the information *
> provided,* unless that information is subsequently confirmed in writing.
> If you are not the intended recipient, you are notified that disclosing,
> copying, distributing or taking any action in reliance on the contents of
> this information is strictly prohibited.*
>
>
> *-----------------------------------------------------------------------------------------*
>
>

Re: Kafka Consumer consuming rate suddenly dropped

[Akshay Aggarwal <ak...@flipkart.com>]

Hi Mu, Did you check the resource utilization metrics for your cluster? I
once faced a similar issue, and figured it was because the overall CPU Load
of the cluster spiked to 1+. This may happen if the cluster is shared, and
some new job was deployed.

~Akshay

On Mon, Jul 20, 2020 at 3:23 PM Mu Kong <ko...@gmail.com> wrote:

> Hi, community
>
> I have a flink application consuming from a kafka topic with 60 partitions.
> The parallelism of the source is set to 60, same with the topic partition
> number.
> The *cluster.evenly-spread-out-slots *config is set to true in flink
> cluster.
> However, several hours later, the consuming rate of some subtasks of the
> source suddenly dropped and caused delay.
> There is no back pressure in the application as shown in the flink UI.
> The consuming rate is like follows:
> [image: image.png]
>
> Is anyone also encountering the same problem?
> Is there any way to further pinpoint the issue?
>
>
> Thanks in advance!
> Mu
>

-- 



*-----------------------------------------------------------------------------------------*


*This email and any files transmitted with it are confidential and 
intended solely for the use of the individual or entity to whom they are 
addressed. If you have received this email in error, please notify the 
system manager. This message contains confidential information and is 
intended only for the individual named. If you are not the named addressee, 
you should not disseminate, distribute or copy this email. Please notify 
the sender immediately by email if you have received this email by mistake 
and delete this email from your system. If you are not the intended 
recipient, you are notified that disclosing, copying, distributing or 
taking any action in reliance on the contents of this information is 
strictly prohibited.*****

 ****

*Any views or opinions presented in this 
email are solely those of the author and do not necessarily represent those 
of the organization. Any information on shares, debentures or similar 
instruments, recommended product pricing, valuations and the like are for 
information purposes only. It is not meant to be an instruction or 
recommendation, as the case may be, to buy or to sell securities, products, 
services nor an offer to buy or sell securities, products or services 
unless specifically stated to be so on behalf of the Flipkart group. 
Employees of the Flipkart group of companies are expressly required not to 
make defamatory statements and not to infringe or authorise any 
infringement of copyright or any other legal right by email communications. 
Any such communication is contrary to organizational policy and outside the 
scope of the employment of the individual concerned. The organization will 
not accept any liability in respect of such communication, and the employee 
responsible will be personally liable for any damages or other liability 
arising.*****

 ****

*Our organization accepts no liability for the 
content of this email, or for the consequences of any actions taken on the 
basis of the information *provided,* unless that information is 
subsequently confirmed in writing. If you are not the intended recipient, 
you are notified that disclosing, copying, distributing or taking any 
action in reliance on the contents of this information is strictly 
prohibited.*


_-----------------------------------------------------------------------------------------_

Re: Kafka Consumer consuming rate suddenly dropped

[Jake <ft...@qq.com>]

Hi Mu Kong

Yes, you need check your kafka cluser server log, network traffic, disk latency, cpu load.

Jake


> On Jul 22, 2020, at 7:34 PM, Till Rohrmann <tr...@apache.org> wrote:
> 
> Hi Mu Kong,
> 
> I think Jake was asking for the logs of your Kafka cluster and not the Flink TM logs.
> 
> Cheers,
> Till
> 
> On Wed, Jul 22, 2020 at 12:47 PM Mu Kong <kong.mu.biz@gmail.com <ma...@gmail.com>> wrote:
> Hi, Jake,
> 
> Thanks for offering help.
> I didn't find anything related to kafka in my tm log.
> Is there a way to enable the logging, or am I just looking into the wrong place?
> 
> Thanks in advance.
> 
> Best regards,
> Mu

Re: Kafka Consumer consuming rate suddenly dropped

[Till Rohrmann <tr...@apache.org>]

Hi Mu Kong,

I think Jake was asking for the logs of your Kafka cluster and not the
Flink TM logs.

Cheers,
Till

On Wed, Jul 22, 2020 at 12:47 PM Mu Kong <ko...@gmail.com> wrote:

> Hi, Jake,
>
> Thanks for offering help.
> I didn't find anything related to kafka in my tm log.
> Is there a way to enable the logging, or am I just looking into the wrong
> place?
>
> Thanks in advance.
>
> Best regards,
> Mu
>

Re: Kafka Consumer consuming rate suddenly dropped

[Mu Kong <ko...@gmail.com>]

Hi, Jake,

Thanks for offering help.
I didn't find anything related to kafka in my tm log.
Is there a way to enable the logging, or am I just looking into the wrong
place?

Thanks in advance.

Best regards,
Mu

Re: Kafka Consumer consuming rate suddenly dropped

[Jake <ft...@qq.com>]

Need some flink kafka consumer log and kafka server log!


> On Jul 20, 2020, at 5:45 PM, Mu Kong <ko...@gmail.com> wrote:
> 
> Hi, community
> 
> I have a flink application consuming from a kafka topic with 60 partitions.
> The parallelism of the source is set to 60, same with the topic partition number.
> The cluster.evenly-spread-out-slots config is set to true in flink cluster.
> However, several hours later, the consuming rate of some subtasks of the source suddenly dropped and caused delay.
> There is no back pressure in the application as shown in the flink UI.
> The consuming rate is like follows:
> <image.png>
> 
> Is anyone also encountering the same problem?
> Is there any way to further pinpoint the issue?
> 
> 
> Thanks in advance!
> Mu