This section shows results achieved running the different use cases on the AIX platform.

Before using performance information, be sure to read the general information under Notices.

The results in this section were obtained by running sufficient copies of each message flow so that in most cases the system CPU utilisation was 80% or greater.

Information provided

The results provided in this section include the following performance data:

Message Size:
Records the approximate size of the message that is used as input to the test, not including the message header. This is the size of the XML or equivalent non-XML message payload.
Persistent State:
Indicates whether the messages used in the test is persistent or not.This state can have the following two values:

  • The value Full Persistent is used to indicate that the message tested is persistent.
    • This value is applicable only to WebSphere MQ messages.
    • If a message is persistent, WebSphere MQ ensures that the message is not lost when a failure occurs, by copying it to disk.
  • The value Non Persistent is used for other type of messages.
Message Rate:
Indicates the number of round trips or message flow invocations per second.
% CPU Busy:
Indicates the percentage of CPU usage on the server machine. This includes the total of CPU used by all processes: IBM Integration Bus, WebSphere MQ queue manager, database manager and others. The rate is expressed as a percentage of the CPU’s capacity that is used by all processors on the server machine.
CPU ms/msg:
Indicates the overall CPU cost per message, that is, the CPU milliseconds per message.

  • You can calculate the value of the CPU cost per message by using the following formula:
    • ((Number of cores * 1000) * (% of CPU / 100)) / Message Rate.
  • This cost includes IBM Integration Bus, WebSphere MQ, DB2, and any operating system costs.
  • Note: The results are specific to the system on from which they have been obtained. If you want to project (or predict) message processing capacity for other systems, you must make a suitable adjustment to allow for differences in the capacity of the two systems.

Performance Results

Typically, as the message size increases, the message rate decreases, and the cost of CPU per message increases.
Persistent MQ messages are written to the MQ log on disk. This causes an overhead in CPU and IO costs and a reduction in message rate. The speed of disk on which the MQ log is configured becomes a key factor. See Tuning for more information.
For details on the measurement environment, see Measurement environment.

When planning a system, it is important to understand the complexities of the processing required so that adequate resources can be provided to meet the requirements of the particular situation.



Aggregation

Non Persistent Full Persistence
Msg Size Msg Rate % CPU Busy CPU ms/msg Msg Rate % CPU Busy CPU ms/msg
256b 1716.8 100.0 2.3 1231.1 97.0 3.2
2kB 1514.1 98.7 2.6 1125.5 97.5 3.5
20kB 798.5 99.8 5.0 665.5 98.1 5.9
200kB 132.3 96.0 29.0 125.4 96.0 30.6
2000kB 13.5 99.0 294.2 13.1 95.8 291.5
20000kB 0.9 95.4 4387.6 0.8 96.8 4609.5

Coordinated Request/Reply

Non Persistent Full Persistence
Msg Size Msg Rate % CPU Busy CPU ms/msg Msg Rate % CPU Busy CPU ms/msg
256b 1398.3 96.5 2.8 1208.1 98.8 3.3
2kB 957.2 96.0 4.0  863.3 96.9 4.5
20kB 258.3 96.2 14.9 237.6 96.9 16.3
200kB 30.2 91.4 121.0 29.9 91.2 122.2
2000kB 3.1 92.2 1204.8 3.1  92.5 1198.7
20000kB 0.3 97.6 13466.2 0.3 93.0 11996.1

 

Large Messaging

Non Persistent Full Persistence
Msg Size Msg Rate % CPU Busy CPU ms/msg Msg Rate % CPU Busy CPU ms/msg
256b 8486.3 96.3 0.5 5485.6 96.0 0.7
2kB 5362.6 97.0 0.7 3711.5 96.0 1.0
20kB 942.4 96.4 4.1 672.7 95.0 5.6
200kB 101.0 97.0 38.4 75.6 95.0 50.3
2000kB 9.6 95.3 398.5 7.4 95.5 515.7
20000kB 1.0 88.4 3722.1 0.7 87.7 4803.8

Message Routing

Non Persistent Full Persistence
Msg Size Msg Rate % CPU Busy CPU ms/msg Msg Rate % CPU Busy CPU ms/msg
256b 18150.7 96.7 0.2 10277.4 98.0 0.4
2kB 17430.8 96.5 0.2 9324.3 96.5 0.4
20kB 12567.7 92.5 0.3 4662.4 58.7 0.5
200kB 1436.0 38.7 1.1 944.7 40.4  1.6
2000kB 141.4 35.1 9.9 102.8 33.2 12.9
20000kB 12.1 32.2 106.2 9.4 35.9 152.3

Transforming a message

Non Persistent Full Persistence
Msg Size Msg Rate % CPU Busy CPU ms/msg Msg Rate % CPU Busy CPU ms/msg
256b 14910.3 96.9 0.3 8831.9 95.0 0.4
2kB 7780.7 95.0 0.5 5732.1 96.3 0.7
20kB 1354.0 95.0 2.8 1247.8 97.0 4.1
200kB 139.2 95.0 27.3 137. 95.1 38.4
2000kB 13.3 96.6 290.0  13.5 96.5  398.5
20000kB 1.4 95.3 2761.4 1.3 94.1 3722.1

File out and file in

Non Persistent
Msg Size Msg Rate % CPU Busy CPU ms/msg
256b 1651.9 58.5 1.4
2kB 1670.1 59.9 1.4
20kB 1850.1 67.9 1.5
200kB 1267.8 93.3 2.9
2000kB 149.9 90.2 24.1
20000kB 13.1 89.8 273.3

SOAP Consumer

Non Persistent
Msg Size Msg Rate % CPU Busy CPU ms/msg
256b 3352.0 96.1 1.1
2kB 2597.5 95.5 1.5
20kB 899.8 96.6 4.3
200kB 112.7 96.4  34.2
2000kB 11.4 94.1 331.4
20000kB 1.1 87.2  3115.4

SOAP Provider

Non Persistent
Msg Size Msg Rate % CPU Busy CPU ms/msg
256b 6921.9 96.9 0.6
2kB 5324.4 96.2 0.7
20kB 1828.3 97.2 2.1
200kB 218.5 96.6 17.7
2000kB 23.4 96.0 164.2
20000kB 2.2 92.3 1663.6

ISO 8583 Transformation

Non Persistent
Msg Size Msg Rate % CPU Busy CPU ms/msg
120B 2829.5 96.1 1.4
134B 2121.5 97.2 1.8
1384B 1270.2 97.8 3.1

RESTful API – Post

Non Persistent
Msg Size Msg Rate % CPU Busy CPU ms/msg
256b 3569.4 99.0 1.1
2kB 1857.6 100.0 2.2
20kB 323.9 94.2 11.6

RESTful API – Get

Non Persistent
Msg Size Msg Rate % CPU Busy CPU ms/msg
256b 4109.7 98.2 1.0
2kB 2735.6 99.0 1.4
20kB 620.2 90.7 5.9

Measurement Environment

All throughput measurements where taken on a single server machine. The client type and machine on which they ran varied with the test. The details are given below.

Server Machine

The hardware consisted of:

  • IBM pSeries 780 with 1 x Quad-Core Power7 3.86GHz processors
  • SMT4 activated (4 hardware threads per core)
  • 143 GB SAS Hard Drive
  • SAN comprising
    • 8Gbps Brocade DCX director
    • IBM San Volume Controller (2145-8G4 nodes)
    • IBM DS8700
  • 32 GB RAM
  • 10 GB Ethernet Card

The software consisted of:

  • AIX 7.1 (Simultaneous Multi-Threading (SMT) was enabled)
  • WebSphere MQ V7.5.0.5
  • IBM Integration Bus V10
  • DB2 v10.5.0.5

Client Machine

The hardware consisted of:

  • IBM xSeries HS22 with 2 x Hex-Core Intel(R) Xeon(R) X5670
  • 2.93 GHz processors with HyperThreading turned on
  • One 135 GB SCSI hard drive formatted with NTFS
  • 32 GB RAM
  • 10 GB Ethernet card

The software consisted of:

  • Microsoft Windows Server 2008 R2
  • WebSphere MQ V7.5.0.1
  • IBM Java v1.7.0

Network Configuration

The client and server machines were connected using a full duplex 10 Gigabit Ethernet LAN with a single hub.

2 comments on"AIX Performance Report Results"

  1. Emile Kearns August 19, 2016

    Where can I get a performance comparison for IIB V10 from OS (Windows/AIX/ZLinux) perspective

    • Emile,
      We currently do not have a performance comparison between operating systems for IIB V10. We publish the report for each platform on a given set of hardware but we do not compare results between different operating systems.

Join The Discussion

Your email address will not be published. Required fields are marked *