Server can't use two CPU, the performance is very poor

[#1]

Hi all,

I have a problem with hardware in server, I appreciate if someone can help me.

My problem is when use two CPU in a dedicated qlikview server, when the server works with 2 CPU the performance is very very poor.

We have the following hardware in the server:

• CPU: 2 x Intel® Xeon® E5-2697 v2 (2.7GHz/12-core/30MB/8.0GT-s QPI/130W, DDR3-1866, HT, Turbo2- 3/3/3/3/3/3/3/4/5/6/7/8)
• RAM: 128Gb RAM PC3-12800R (DDR3-1600)
• Hard Disk: 2 x HP 300GB 6G SAS 10K 2.5in SC ENT HDD
• The servers have 2 cpu sockets, numa capability and hyper-threading capability
• Each CPU is 12 real cores and 12 virtual cores if HT is enabled
  

When the server works with a single CPU, its work fine. In this scenario the performance with HT enabled is better than HT disabled.

The problem appears when we add the additional CPU, both CPU are exactly the same model, both were purchased at same time with the server. In this moment the performance of server is very very poor and is impossible that the users uses the application.

What we tried?

TEST 1:

• 2 CPU
• NUMA (In BIOS appears as Node Interleaving) - Disabled
• Hyperthreading - Enabled

TEST 2:

• 2 CPU
• NUMA (In BIOS appears as Node Interleaving) - Enabled
• Hyperthreading - Enabled

TEST 3:

• 2 CPU
• NUMA (In BIOS appears as Node Interleaving) - Disabled
• Hyperthreading - Disabled

TEST 4 (Actual State):

• 1CPU
• NUMA (In BIOS appears as Node Interleaving) - Disabled
• Hyperthreading - Enabled

In the TEST 1, 2 and 3, the performance is poor. But in the TEST 4 (Now) the performance is better, but we need to use two cpu.

In all test the QlikView Soft-Switch is disabled (If I try to enabled the Soft-Switch the Qlikview Server Service cant start).

Environment:

• We dont use shared folders outside the server. All the files of the qlikview solutions are local in the server.
• This is not a virtual environment and the server is dedicated for Qlikview.
• Server version installed is: 11.0.11440.0
• We tried installing the QV Server 11.20 SR6 but we have errors in the log, and we came back to the same preovious version (11.0.11440.0) that work fine.

Upcoming Test:

We will try to test the actual state but with the other cpu to discard a physical hardware issue related with this cpu or the second socket.

Please can someone help me?

Thank you very much in advance.

Regards,

Guzmán.

[Troy1]

Hi Guzman

Were you able to resolve this issue. what's the outcome. Can you share your findings.

Thanks

[Anonymous]

Hi Guzman.

I have the same question as mgdpuro1‌, any updates?

We also are suffering performance issues. But we haven't tested using only one CPU.

We have 2 Xeon E5 2560 v2. And we get errors, and also get the feel that it should be faster.

Regards.

[#4]

Hi Roberto and mgdpuro1,

I could not resolve the issues with the use of two processors. I contacted to Qlik support but I can't arrive a solution.

If can you try with only one processor, you should see an improvement of performance, the problem is when you are using two processor and the communication between both cpu and the distributed RAM memory.

For any reason, this produces a very poor performance and some errors while users use qv applications.

I continue with this issue yet and now my client buy another server with only one processor but with 32 cores. This is better but using only one processor, more than one in a unique server produce poor performance.

What is the size of your QVW file? You have reviewed the qv application? (data model, relations of the tables, normalization, use of linked tables, amount of records, etc, etc? Can you split the file in 2 documents for example, one for an aggregation information (with less size) and another with the detail? Or split the history in a file and in another file the last X years/month to use with more frequency?

Theses changes can be help you to improvement the performance and usability of application.

I hope can help you.

Let me know if you have any question.

Regards,

Guzmán.

[Anonymous]

Hi. Thanks for your response.

We haven't been able to test with one cpu, it's not that easy in our case.

Size is near 300MB, there's a link table.

We have proposed architecturing the app in two as you mention (aggregated info and detail in another one) or segmenting, but they haven't adopted the idea yet.

We'll continue to work as they'll let us.

Thanks again.

[#6]

Hi Roberto,

Can you post here the hardware specifications of the QlikView Server?
The application is not too big, perhaps you have an opportunity for review some development best practices in script and data model or increment RAM memory.

Perhaps this topic in my blog can help you (Sorry it is in spanish):

gganalytics.blogspot.com/2014/03/qlikview-aspectos-considerar-para-velar.html

Also you can check my post in this discussion:

performance big app huge data set 500 million records

Let me know if you have any question.

Regards,

Guzmán.