Contents | Previous | Next

2064-1C8, 2G/10G

Workload: CMS1 with Internal TPNS 

Hardware Configuration 

Processor model:            2064-1C8
Processors used:            8
Storage:
    Real:                   2GB (default MDC)
    Expanded:               10GB (MDC fixed at 512M)
 
DASD:


Type of
DASD


Control
Unit


Number
of Paths



PAGE



SPOOL


- Number of Volumes -
TDSK



User



Server



System

3390-3
RVA T82
8
15
8
4
150


2

Note: The DASD volumes are distributed across 13 RVA T82 subsystems. Each subsystem has 1536M of cache.

Software Configuration 

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


Virtual
Machine



Number



Type


Machine
Size



SHARE



RESERVED



Other Options

TP1
1
TPNS
256M
5000
14000
QUICKDSP ON
TCPIPn
4
TCPIP
512M
3000
14000
QUICKDSP ON
WRITER
1
CP monitor
2M
100


QUICKDSP ON
Unnnnn
10800
Users
3M
100




Measurement Discussion 

For this environment, real storage is sufficiently constrained that there is heavy paging to expanded storage. However, expanded storage is sufficiently large that DASD paging is essentially eliminated.

The measurement results are summarized in the following two tables. The first table contains the absolute results, while the second table show the results as ratios relative to the VM/ESA 2.4.0 base case. RTM and TPNS log data were not collected for these measurements. When available, corresponding VMPRF data has been substituted for the RTM data normally shown.

The results show that total processing requirements (PBT/CMD (H)) of z/VM 3.1.0 with 31-bit CP are equivalent to VM/ESA 2.4.0. Total processing requirements of z/VM 3.1.0 with 64-bit CP are about 1.5% higher than these as the result of a 5.7% increase in CP CPU time (CP/CMD (H)).

These results focus on migration of CP to z/VM 3.1.0. The CMS and GCS components were kept at the VM/ESA 2.4.0 level for all three measurements. This means that the z/VM 3.1.0 results do not include the effects of the Rexx runtime improvement (see Miscellaneous CMS Improvements), which reduces total CPU time per command command by about 0.2% for this workload.


Table 1. CMS-Intensive Migration from VM/ESA 2.4.0: 2064-1C8, 2G/10G


Release (CP)
CP
Run ID


2.4.0
31 bit
E240G823


3.1.0
31 bit
E1228822


3.1.0
64 bit
E1228824


Response Time
TRIV INT
NONTRIV INT
TOT INT



0.04
0.47
0.11



0.04
0.47
0.11



0.04
0.47
0.11


Throughput
ETR (T)
ITR (H)



1091.42
1241.22



1091.16
1236.27



1090.34
1223.03


Proc. Usage
PBT/CMD (H)
CP/CMD (H)
EMUL/CMD (H)



6.445
1.660
4.785



6.471
1.677
4.794



6.541
1.755
4.786


Processor Util.
TOTAL (H)
UTIL/PROC (H)
UTIL/PROC
TOTAL EMUL (H)
TOTAL EMUL
MASTER TOTAL
MASTER CP
MASTER EMUL
TVR(H)
TVR



703.45
87.93
87.80
522.29
535.20
88.70
46.40
42.30
1.35
1.23



706.10
88.26
88.20
523.06
536.00
89.10
46.70
42.40
1.35
1.23



713.21
89.15
89.00
521.84
534.40
90.10
48.30
41.80
1.37
1.24


Paging
READS/SEC
WRITES/SEC
PAGE/CMD
PAGE IO RATE
PAGE IO/CMD
XSTOR IN/SEC
XSTOR OUT/SEC
XSTOR/CMD



0
80
0.07
0.00
0.00
6194
6545
11.67



0
81
0.07
0.00
0.00
6224
6542
11.70



0
79
0.07
0.00
0.00
6275
6593
11.80


Queues
ELIGIBLE LIST



0.0



0.0



0.0


I/O
RIO RATE
RIO/CMD
NONPAGE RIO/CMD
DASD RESP TIME
MDC REAL SIZE (MB)
MDC XSTOR SIZE (MB)
MDC HIT RATIO



4602
4.22
4.22
5.8
191
512
96.5



4603
4.22
4.22
5.8
190
511
96.5



4586
4.21
4.21
5.8
179
511
96.6


PRIVOPs
PRIVOP/CMD
DIAG/CMD



58.77
77.75



58.69
77.76



58.50
77.66

Note: 2064-1C8; 8 processors; 2G central storage, 10G expanded storage; real MDC: default, xstor MDC: 512M; 11800 CMS1 users; internal TPNS; CMS and GCS are 2.4.0; T=TPNS, H=Hardware Monitor, Unmarked=VMPRF


Table 2. CMS-Intensive Migration from VM/ESA 2.4.0: 2064-1C8, 2G/10G - Ratios


Release (CP)
CP
Run ID


2.4.0
31 bit
E240G823


3.1.0
31 bit
E1228822


3.1.0
64 bit
E1228824


Response Time
TRIV INT
NONTRIV INT
TOT INT



1.000
1.000
1.000



1.000
1.002
1.001



1.000
0.994
0.996


Throughput
ETR (T)
ITR (H)



1.000
1.000



1.000
0.996



0.999
0.985


Proc. Usage
PBT/CMD (H)
CP/CMD (H)
EMUL/CMD (H)



1.000
1.000
1.000



1.004
1.011
1.002



1.015
1.057
1.000


Processor Util.
TOTAL (H)
UTIL/PROC (H)
UTIL/PROC
TOTAL EMUL (H)
TOTAL EMUL
MASTER TOTAL
MASTER CP
MASTER EMUL
TVR(H)
TVR



1.000
1.000
1.000
1.000
1.000
1.000
1.000
1.000
1.000
1.000



1.004
1.004
1.005
1.001
1.001
1.005
1.006
1.002
1.002
1.000



1.014
1.014
1.014
0.999
0.999
1.016
1.041
0.988
1.015
1.008


Paging
WRITES/SEC
PAGE/CMD
XSTOR IN/SEC
XSTOR OUT/SEC
XSTOR/CMD



1.000
1.000
1.000
1.000
1.000



1.013
1.013
1.005
1.000
1.002



0.988
0.988
1.013
1.007
1.011


I/O
RIO RATE
RIO/CMD
NONPAGE RIO/CMD
DASD RESP TIME
MDC REAL SIZE (MB)
MDC XSTOR SIZE (MB)
MDC HIT RATIO



1.000
1.000
1.000
1.000
1.000
1.000
1.000



1.000
1.000
1.000
1.000
0.994
1.000
1.000



0.997
0.998
0.998
1.000
0.939
1.000
1.001


PRIVOPs
PRIVOP/CMD
DIAG/CMD



1.000
1.000



0.999
1.000



0.995
0.999

Note: 2064-1C8; 8 processors; 2G central storage, 10G expanded storage; real MDC: default, xstor MDC: 512M; 11800 CMS1 users; internal TPNS; CMS and GCS are 2.4.0; T=TPNS, H=Hardware Monitor, Unmarked=VMPRF

Contents | Previous | Next