How well do Network Redirectors Perform?
by Stuart Baker
Because my last article, "What are Network Redirectors?", generated several phone calls and BBS email, I can only assume there is a lot of interest in the subject. This article addresses the performance one can expect when using network redirectors to access an OS/32 system running MTM and Reliance.
Before performance figures have meaning, one must define the hardware and software involved. I performed the tests using two PCs and an OS/32 system. The following describes the pertinent hardware and software.
PC System #1: (INT14)
PC System #2: (SERVER)
References to a direct connection refer to PC-Passport running on PC#1 using the Dell's serial port connected directly to the 3212. The direct connection tests were performed with the network software up and running in order to have the same system loading.
The network connection uses all three computers. The two PCs are linked together using LANtastic Ethernet. The LANtastic software provides a NETBIOS interface. The InstantCom//CS software uses the NETBIOS interface and creates EBIOS support on PC#1 through its INT14 TSR program. On PC#2 the InstantCom//CS software establishes a server to control the PC serial port that is connected to the OS/32 system. All connections to the OS/32 system used a speed of 19,200 bits per second (bps). During the testing there was no other activity on any of the systems.
Before getting down to actual numbers, I will discuss the general impressions received when running directly connected verses the network connection. To be honest, I was not able to determine the method used to access the system by visually observing the performance. I ran a variety of applications on MTM as well as Reliance, and could not see or feel any difference between the network and the direct connection. In Reliance, all of the screens snapped up very quickly. By all appearances, both methods of access were much quicker than the real 6312 terminal. I was able to send a break to stop a display files, I even had control over DTR to allow disconnecting a modem. I was not able to detect any delay in response at the keyboard. All in all, I was very impressed.
Now lets measure what the eye can't see. To determine the throughput of a 6312 terminal, I use a program called SCRNTEST. This program starts a timer and then outputs a continuous stream a data consisting of 10 full screens, ending with a "send status when ready" escape sequence. When the status is returned, the timer is read to calculate the actual bps rate achieved by the terminal. As long as there are no other users on the OS/32 system, the timing results are very consistent and accurate. Repeated tests on directly connected lines usually do not vary by more than two bps.
In the following discussion, I will use the directly connected PC-Passport as the basis of comparison. All connections are at 19,200 bps. To define the baseline, I ran SCRNTEST against PC-Passport first. The measured throughput was 19,160 bps. Next, I ran SCRNTEST on a real 6312 terminal. The measured throughput was 14,670 bps. The real 6312 is 23% slower, that explains why the Reliance screens seemed a little snappier on PC-Passport.
Now for the real test, PC-Passport connected through the network redirector. The performance was quite impressive, achieving an average throughput of 17,936 bps. In this test, the network only slowed things down by about 6%. I did notice that the throughput results varied more than expected from one run to the next. To better determine the throughput, I ran the program 10 times. The minimum throughput was 17,849 and the maximum was 18,134, for a total delta of 285 bps. For those of you that are mathematically inclined, the standard deviation of the sample was 94 bps. Apparently, the variation is introduced by the interaction of the data flow and the Ethernet packets. Since I did not write the networking software, I will not attempt to explain the variation. Even at the minimum throughput, the performance is very impressive.
For the next test, let's perform a Xmodem file transfer. I chose a 405 KB ZIP file for this test. The throughput, when sending from the OS/32 system to the PC, was 16,450 bps over the network, compared with 17,280 bps on the direct line. This is close to what one might expect from the previous test. When sending the same file from the PC to the OS/32 system, the throughput was 13,640 bps compared with 16,702 bps. That difference was greater that expected, the performance dropped by 18%. Again, I will not attempt to explain this variation.
As you can see from the above figures, network redirectors are capable of delivering impressive performance. Bear in mind, these tests were conducted under ideal conditions, no other users were on the test system. In real life, and with larger networks, I am sure you will experience more of an impact on performance using a network redirector.
With the exception of InstantCom//CS, I have worked with all of the software used in this test for over a year. The network has performed flawlessly, regardless of how heavily loaded it was. I highly recommend any of these products. I have only recently installed the InstantCom//CS software and am not sure if I may have overlooked something in the configuration. The system ran throughout all of the testing with no problems. In fact, I even let a continuous display files run for three hours with no problems. It even performed well while I did editing and compiles on the server (PC#2). But, when I tried to use some of the system monitoring utilities on the server, everything came to a screeching halt! Presently, I am assuming that I have overlooked something in the installation, considering how impressive the actual data throughput was. Until I have time for more extensive testing, I will refrain from making a recommendation on this software package.
Well that about does it for this issue. I am looking forward to meeting new people at Interchange 92. Start making your plans early so we have a good turnout.
The software products mentioned in this article are available from the following companies:
MS-DOS V 5.0
LANtastic Network Operating System V 4.00
InstantCom//CS Communications Server V 2.0
This SBSW.COM page has been optimized for printing.