Migration from VTAM to Telnet

This section explores the performance implications of migrating end-user 3270 connectivity from VTAM to TCP/IP Telnet. It should be used in conjunction with a similar 9121-480 comparison that is summarized in "Migration from VTAM to Telnet" in the VM/ESA 2.3.0 Performance Report. The measurements shown here were obtained on a larger processor that supports many more users.

Measurements were obtained by running the FS8F0R workload on a 9121-742 processor with the end users simulated by TPNS running on a separate system. VM/ESA 2.3.0 was used for all measurements. For the base measurement, connectivity was provided by VTAM 3.4.1 through a CTCA connection with the TPNS system. Table 1 compares this VTAM base measurement to a measurement using TCP/IP 310 Telnet through a 3172-3 Interconnect Controller and a 16Mbit IBM Token Ring.

Workload: FS8F0R:

Hardware Configuration:

Processor model: 9121-742
Processors used: 4
Storage:
 Real: 1024MB (default MDC)
 Expanded: 1024MB (MDC BIAS 0.1)
Tape: 3480 (Monitor)
 
DASD:

Note: RAMAC 2 refers to the RAMAC 2 Array Subsystem with 256MB cache and drawers in 3390-3 format.

 
Communications (CTCA):

 
Communications (Token Ring):
 
16 Mbit IBM Token Ring
3172-3 Interconnect Controller

Software Configuration:

Driver: TPNS
Think time distribution: Bactrian
CMS block size: 4KB
 
Virtual Machines:

Measurement Discussion:

The results demonstrate that TCP/IP VM Telnet connectivity can support large numbers of users (5100) with good response time (0.36 seconds).

VTAM supports the 3270 interface through the *CCS CP system service (accessed using IUCV requests), while Telnet provides this function through use of the Diagnose X'7C' logical device support facility. This difference is reflected in the results as a large decrease in PRIVOP/CMD and a large increase in DIAG/CMD. The fact that diagnose X'7C' has a longer pathlength than *CCS accounts for much of the CPU usage increase observed in the TCP/IP measurement relative to the VTAM base measurement. Another contributing factor is that TCP/IP does more communication I/Os than VTAM, as shown by the increase in DIAG 98/CMD.

The 3.9% increase in total processing requirements (PBT/CMD (H)) is much less than the 8.2% increase observed for the 9121-480 configuration (see "Migration from VTAM to Telnet" in the VM/ESA 2.3.0 Performance Report). This is because the larger 9121-742 configuration was configured with VSCS in 3 separate virtual machines, whereas the 9121-480 configuration was small enough that VSCS could be configured within the VTAM virtual machine. The external VSCS configuration is less efficient, raising the total VTAM processing requirements and reducing the difference between the VTAM and TCP/IP results.

Note the increase in master processor utilization (MASTER TOTAL (H)) that occurred when going from VTAM to TCP/IP. This is due to an increase in CP master processor utilization (MASTER CP (H)). This occured because most of the CP modules that implement Diagnose X'7C' obtain their MP serialization by running on the master processor. This increase in master processor contention caused the response time increase relative to the VTAM base case to be larger than it otherwise would have been.

Table 1. Migration from VTAM to TCP/IP