DOS SMB Client Performance

Recently I had the need to use several different DOS VMs that all used a SMB network client. Although I did not use networking heavily, I noticed that there are massive differences in performance between the VMs. Copying a circa 42 MB file would take anywhere between about 5 seconds and 49 minutes (not a typo). What’s more, some VMs were fast in both directions, while others were very slow sending and yet others were very slow receiving.

Since in all cases the VMs communicated with the same server (Synology NAS running Samba) from the same host (AMD Ryzen 3800X running Windows 10 and VirtualBox), there really should not be that much performance variation, and yet there it was.

In all cases, NetBIOS over TCP/IP was used as the protocol underlying SMB, and it should be said that TCP/IP greatly complicates the picture. I used three different software stacks, mostly to get some sanity checking:

  • Microsoft Network Client 3.11 with included TCP/IP
  • IBM DOS LAN Services (DLS) version 4.0 with IBM TCP/IP
  • IBM DOS LAN Services 5.0 with Network TeleSystems TCP/IP

The SMB clients are in all cases very similar and in fact nearly identical. But the TCP/IP stacks are obviously different, and it matters.

It should be underscored that although the Microsoft Network Client and IBM DLS may make the impression of an integrated product, they are not. There are three separate layers:

  • The SMB client and DOS redirector
  • NetBIOS, either direct, over IPX, or over TCP/IP
  • NDIS network driver

The layers communicate through well defined interfaces and are interchangeable. From the very beginning (1984-85), the Microsoft and IBM SMB clients ran on top of NetBIOS and didn’t much care about the underlying machinery. It could be the NETBIOS in the actual ROM of the IBM PC Network Adapter, it could be the Token Ring NetBIOS emulator, it could be NetWare’s NetBIOS emulator, it could be be any of the numerous NetBIOS over TCP/IP implementations.

Similarly the NDIS interface is well abstracted and does not require an actual NDIS driver. There could be a packet driver or a Novell ODI driver actually controlling the network hardware and exposing an NDIS interface through a shim. The upper layers don’t care.

Same or Different?

The Microsoft Networks Client version 3.11 was the final DOS-based network client from Microsoft. It was freely available, had TCP/IP support with DHCP, and it worked pretty well. The TCP/IP stack was developed by Hewlett-Packard going back to the mid-1980s, and was once available as Hewlett-Packard ARPA Services for DOS. Microsoft first shipped the HP TCP/IP stack with the LAN Manager 2.1 client in 1991, and the final version from 1995 is not very different.

IBM was a little late to the TCP/IP game but in 1994, IBM LAN Server 4.0 shipped DOS LAN Services that could work with a separately installed IBM TCP/IP package (also provided with LAN Server 4.0). IBM offered TCP/IP version 2.1.1 for DOS, and much like the OS/2 offering, the product was chopped up into several separately orderable packages. Apart from the required base kit, there was a NFS kit, NetBIOS over TCP/IP kit, and a programming kit. LAN Sever 4.0 shipped with just the base (which included NDIS and ODI drivers) and NetBIOS over TCP/IP.

In 1995, IBM’s Warp Server 4.0 (which somewhat confusingly included LAN Server 5.0) shipped with an updated DLS 5.0. The new DOS LAN Services included a completely different TCP/IP stack from Network TeleSystems (NTS). The NTS TCP/IP stack for DOS survived for a good while as part of Norton Ghost boot disks, well into the early 2000s.

Starting Numbers

Now let’s see some numbers. The first table shows how long it takes to copy a 42 MB compressed archive from and to a file server using the default configuration of the three DOS-based SMB clients. Again, the actual SMB clients are very very similar, but the underlying TCP/IP stacks are three completely unrelated implementations.

Server to DOS client DOS client to server
MS Net 3.11 + MS TCP/IP 1.0a 4.2s 48m 43s
IBM DLS 4.0 + IBM TCP/IP 2.1.1 3m 22s 3m 5s
IBM DLS 5.0 + NTS TCP/IP 3.18 19s 4.6s
Copy performance in default configuration

Note that the copy performance in one direction is in no way predictive of copy performance in the other direction. The MS client has the fastest server to client times but incredibly awful performance copying from client to server. DLS 4.0 has uniformly poor performance in both directions. DLS 5.0 takes several times longer than the MS client when copying from the server, but it’s quick copying to the server.

So what is going on? Wireshark to the rescue…

TCP/IP and SMB Tunables

Anyone who has had the pleasure of analyzing poor TCP/IP performance knows that there are lots of variables and a good deal of complexity. It gets even more complicated when SMB is thrown into the mix.

SMB Read/Write RAW

For a long time, SMB has had the capability to use “raw” read and write requests. Raw SMB requests are large block transfers that actually somewhat bypass the SMB protocol. Raw SMB transfers can be close to 64K in size and are notable for not including the SMB header in most packets (that’s why they’re called raw).

Note that raw SMB is a concept orthogonal to the underlying protocol (TCP/IP, NetBEUI, etc.). When a raw request is initiated, the sending side produces a stream of data packets with no SMB headers until the entire raw request is completed. Raw SMB requests obviously cannot be mixed.

DLS 4.0 with IBM TCP/IP 2.1.1

After staring at the packet traces for a while and attempting various tweaks to both the DOS LAN Requester and the TCP/IP stack (the \TCPDOS\ETC\TCPDOS.INI has quite a lot of poorly documented tunables), I was not able to make any headway.

There was no obvious problem visible in the packet traces, notably no packet loss or retransmits. The DOS client was using SMB raw reads and writes, but somehow the transfers were just… slow. That is to say, the DOS client simply took relatively long (several milliseconds) to respond to network traffic. That very quickly adds up.

I know that the IBM DOS TCP/IP stack is not inherently slow and it performs reasonably well with NFS.

Given that this version of DLS was superseded and the DLS 4.0 + TCP/IP combination was surprisingly painful to install and configure, I gave up on it.

Note: After installing IBM’s TCP/IP 2.1.1 on top of PC DOS 2000, I was initially unable to get anywhere at all because every attempt to configure the default route failed with the following message:

Error: The route you are attempting to add already exists

even though the route most definitely did not exist. The answer was unexpectedly found in this document—the core DOSTCP.SYS driver needs to be updated to work with PC DOS 7 (there is no such problem with PC DOS 5.0). Updating the entire TCP/IP base and NetBIOS kits made no impact on the poor performance.

DLS 5.0 with NTS TCP/IP

Recall that DLS 5.0 turned out to have quite good send performance, but noticeably slower receive. Examining a Wireshark trace shows that sends are fast because they’re done efficiently using raw SMB requests. The DOS client sends 1,514-byte Ethernet frames with 1,460 bytes of payload in each TCP packet. Since the receiving side (file server) has a 65,535 byte TCP receive window which is larger than the raw SMB write size (65,024 bytes), the DOS client is able to blast out the entire block of data as fast as it can.

But on the receiving side, DLS 5.0 is not using raw SMB read. It’s instead using normal SMB read requests, which results in a lot of ping-pong traffic:

SMB Read Request →
TCP ACK ←
SMB Read Response ←
TCP ACK →
SMB Read Request →
TCP ACK ←
…

Each SMB Read Response only contains 1,024 bytes of payload. This is clearly not terribly efficient, and certainly nowhere near efficient as a SMB raw read.

The problem should be unrelated to the underlying TCP/IP transport, since it is the SMB client and not NetBIOS deciding whether raw reads will be used.

There’s a good number of tunables in DLS’s NETWORK.INI file. And since this was an IBM product, it’s quite well documented, in fact vastly better than Microsoft’s client.

This 1994 document (Understanding Performance Tuning Theory for IBM OS/2 LAN Server) explains in reasonable detail how “work buffers” and “big buffers” are used in SMB clients and servers.

This 1996 document (Inside OS/2 Warp Server, Volume 1: Exploring the Core Components) provided updated information for OS/2 Warp Server.

And finally this 1997 document (Network Clients for OS/2 Warp Server: OS/2 Warp 4, DOS/Windows, Windows 95/NT, and Apple Macintosh) covers among other things DLS 5.0 and the included NTS TCP/IP stack.

There I learned about the autocache, numbigbuf, sizbigbuf, numworkbuf, and sizworkbuf parameters. But changing those in NETWORK.INI made no impression on the DOS client, except some combinations made it crash.

More or less by accident I discovered something that all the IBM documents do not mention: I was using the protected-mode redirector (predir) which is meant to be equivalent to the full redirector but use less conventional memory. But somehow it’s not quite equivalent.

As soon as I switched to the full redirector, two things happened: Conventional memory usage went up by a couple dozen kilobytes, and suddenly the DOS client started issuing SMB raw read requests. This sped up large reads quite noticeably.

I also tried increasing the TCP window size for the NTS TCP/IP stack, but that did not bring any noticeable improvement.

At this point I did not try tweaking the redirector tunables further, in part because the performance seemed quite good, and in part because I could find no way to show what settings the DOS redirector is currently using. Besides (maybe) changes in performance, the only way to check if changing the settings made any difference is to see whether memory usage went up or down.

Microsoft Network Client 3.11

Looking at packet traces of Microsoft’s network client showed that, rather unsurprisingly, reads work quite well with using SMB raw reads, large packets, and no packet loss, but writes show clear problems.

Wireshark was showing frequent “TCP previous segment not captured” warnings on the outgoing (DOS client) side, followed by duplicate ACKs and retransmissions. Since this was using the built-in VirtualBox packet tracing, it’s not plausible the packets would fail to be captured. Moreover the receiving side (file server) certainly behaved like it never saw them.

After much head scratching, I was unable to determine what the problem was. In fact I saw the same behavior (incredibly slow writes) on physical DOS machines. That excludes the possibility of a virtualization/emulation bug.

In desperation, I tried the universal TCP/IP network boot disk, only to be shocked to discover that in the exact same VM, it’s not slow at all. It did not take me long to determine that the difference is the full vs. basic redirector. The full redirector is meant to have better performance, but something is going badly wrong in certain configurations.

That makes the problem even more mysterious, if anything: The environment is the same, the emulation is the same, the DOS network driver is the same, the TCP/IP stack is the same, but one redirector somehow fails to send packets every now and then and the other does not.

The issue also illustrates just how sensitive TCP/IP is to packet loss. Losing just one out of every 1,000 packets cuts the theoretical maximum TCP throughput by a factor of ten. In this scenario, the packet loss was much worse and the bandwidth was cut by a factor of several hundred.

Final Numbers

To summarize what I did or didn’t do with the three different DOS clients:

  • IBM DLS 4.0: gave up
  • IBM DLS 5.0: sped up reads by switching from protected-mode to full redirector
  • MS Client 3.11: vastly sped up writes by switching from full to basic redirector

Omitting the DLS 4.0 client, here are the updated numbers for the same 42 MB file copy:

Server to DOS client DOS client to server
MS Net 3.11 + MS TCP/IP 1.0a 3.9s 3.8s
IBM DLS 5.0 + NTS TCP/IP 3.18 3.5s 3.9s
Copy performance in modified configuration

The DLS 5.0 performance went up at the cost of higher conventional memory usage. To be fair, for normal use even the protected-mode redirector is very usable, but for moving a lot of data to the DOS client side, the full redirector is roughly 5 times faster.

The Microsoft Network Client 3.11 had trouble with the opposite direction and the performance with the full redirector when moving data from the DOS client to a file server was just atrocious. The basic redirector has fewer features, but most users are unlikely to notice, and the performance differential is huge.

After switching the redirector types, the IBM and Microsoft redirectors with very different underlying TCP/IP stacks perform almost identically.

Yes, networking is complicated.

This entry was posted in DOS, IBM, Microsoft, Networking. Bookmark the permalink.

15 Responses to DOS SMB Client Performance

  1. Tobis87 says:

    You could also try to use the FTP Software PC/TCP stack which can provide Netbios and works with the Lan Manager (available for DOS, Win 3.x and OS/2).

  2. Michal Necasek says:

    I’m somewhat tempted. I’m pretty sure there were even more NetBIOS over TCP/IP implementations, and they should all work with the MS/IBM SMB clients.

  3. MiaM says:

    Interesting!

    Two additional clients that you might want to have a go at, and was super common at the time, would be the older Microsoft client (named something with LAN Manager), and (a bit out of this scope, but still) the built in client in Windows for Workgroups 3.11.

    A difference between the two Microsoft clients for DOS is that one of them can run TCP/IP on an 8088 while the other requires at least a 286 for the TCP/IP part (while both happily runs NetBEUI on an 8088). That could be an indicator of differences in the actual TCP/IP code performance.

    While Windows for Workgroups 3.11 is kind of out of scope for your comparison, if you need to transfer large files it might be faster to install it and use it for the transfers than using the DOS clients. It will be really fast especially if your hardware is compatible with the 32 bit implementations of the disk and filesystem drivers (32-bit disk access, 32-bit file access) (in practice have a hard disk that fits under the 528MB limit or possibly have a larger hard disk with a controller that has drivers for Windows for Workgroups 3.11).

    Something that would probably be hard to test in a VM but shows up on real hardware, at least on really old machines, is CPU usage. Using the MS LAN Manager DOS client with TCP/IP on an 8088, with a WD/SMC 8003 (perhaps the best 8-bit ISA ethernet card) the performance scales linearly to the CPU speed on a computer with selectable 4.77 and 7.15MHz. IIRC it’s as slow as 37kbyte/sek to copy to the dos machine at 4.77MHz, but this is recalled from 20+ year old memory so I might misremember. From what I recall NetBEUI was unsurprisingly faster. The MS Client was also faster than the LAN Manager client when using NetBEUI.

    (The reason that I did these performance tests a bit over 20 years ago was that at the time I were using my Amiga 4000 as kind of my main computer, and for internet access I used a (fast -ish) RS232 connection but for copying local files I had an 8088 based PC emulator card (which could copy files between the PC emulation and the file systems on the Amiga side), so I had a practical every day use case for using a SMB client on an 8088. Later on someone wrote a small DOS program to run on the PC emulator card, accompanied by a driver on the Amiga side, to make a PC ISA network card with a packet driver act as a full network card for the Amiga side. With FTP the transfer rate was about 100kbyte/s, which I would assume partially were due to the packet driver being optimized for faster CPUs. The source code contained a lot of delays to make it work on faster CPUs but as I had about zero experience in actually programming in assembler on an 8088 I wasn’t able to assemble the source code. Coming from 68k and a bit of 6502 assember it was a bit frustrating being perfectly able to understand the code but not the dev tools).

  4. Shadow Lord says:

    Interesting. I was not aware MS-LANMAN worked with any other TCP/IP stacks. Is the FTP Software stack the only compatible stack? Or does LANMAN work with all TCP/IP stacks?

  5. Michal Necasek says:

    I didn’t even try FTP Software. The LANMan client should work with any stack that provides NetBIOS over TCP/IP, because LANMan generally works with anything that provides a NetBIOS interface. Microsoft shipped a variant of HP ARPA Services with their LM clients. IBM used their own DOS TCP/IP stack. There was that Network TeleSystems stack IBM shipped later. Way back when, there was an Excelan NetBIOS over TCP/IP kit. Sun’s PC-NFS supported NetBIOS. I’m sure there were several other implementations as well. I am not an expert but my impression is that if you already have a TCP/IP stack, implementing the NetBIOS RFCs on top of it is not a huge effort.

  6. Shadow Lord says:

    My interest is mostly in getting a less memory hungry stack. TBH the MS (HP) stack has been very stable in my experience but it is a memory hog…

  7. Shadow Lord says:

    Looks like I have to correct myself. Apparently I was aware of being able to use the stack from FTP Software. I found an old KB from MS that actually describes it in detail. It is article ID 100699 “Using FTP PC-TCP with LAN Manager 2.2”

  8. Michal Necasek says:

    I can’t find that but found something else instead: https://www.scosales.com/ta/kb/101655.html

    It matches my recollection that LM is actually reasonably flexible, but configuring it with other transports is far, far from obvious. I can’t quite put a finger on why, but the Protocol Manager (a 3Com invention I believe) always seemed like a horribly overengineered piece of junk to me, difficult to configure and easy to break. And when it broke, good luck finding out why. Everyone else (Novell, FTP Software, …) did it better and simpler.

  9. MiaM says:

    Side track: Interesting that SCO were sold with a NetBEUI compatible LAN manager server.

    I wounder what it would take to get that going on modern Linux?

  10. Shadow Lord says:

    Michael,

    I couldn’t find a link to it anywhere either. So here is the text pasted in for you. The process is a bit convoluted but not any more so then most of LAN Man setup. LOL.

    Using FTP PC-TCP with LAN Manager 2.2
    ===============================================================================
    Article ID: 100699

    This article was previously published under Q100699

    SUMMARY

    FTP Software’s PC/TCP can be used several ways with LAN Manager on an MS-DOS enhanced workstation.

    •the “Generic Kernel” protocol driver can be used as a transport for just PC/TCP applications in conjunction with a LAN Manager Transport providing services for the LAN Manager redirector and software
    •it can also be used as a LAN Manager transport through FTP’s NetBIOS driver
    To do this, you need the NDIS driver version of PC/TCP and FTP’s NetBIOS driver. The tests on which this article is based were conducted using version 2.2 of PC/TCP, which includes both drivers.
    Back to the top

    MORE INFORMATION

    First install the LAN Manager Enhanced Workstation software and use NetBEUI as the transport protocol. If you intend to use PC/TCP as the LAN Manager transport, you can remove the LOAD NETBEUI command from AUTOEXEC.BAT.

    Then install the PC/TCP software as instructed in its “Installation and Configuration Guide” under the section describing using an NDIS driver with the generic kernel. If you want to use the PC/TCP kernel as the LAN Manager transport, you need a copy of NETBIND.COM–you can use the version provided with PC/TCP on the “Unsupported Network Software” diskette. You can ignore the section on modifying PROTOCOL.INI.

    A sample of the configuration files are given here for using the PC/TCP as a LAN Manager transport. Several important notes are listed at the end of the article.

    CONFIG.SYS

    device = c:\dos\himem.sys
    device = c:\dos\emm386.exe noems x=d800-dfff
    dos=high,umb
    files=30
    buffers=20
    rem *****
    LASTDRIVE=Z
    DEVICEHIGH=C:\LANMAN.DOS\DRIVERS\PROTMAN\PROTMAN.DOS /i:C:\LANMAN.DOS
    DEVICEHIGH=C:\LANMAN.DOS\DRIVERS\ETHERNET\ELNKII\ELNKII.DOS
    rem ******* PC/TCP INSTALL ADDED LINE(S) – BEGIN ******
    rem ** If you do not have protman and ndis driver already loaded **
    rem ** before this, please do so. **
    DEVICEHIGH=C:\PCTCP\DIS_PKT.gup (*1)
    rem ******* PC/TCP INSTALL ADDED LINE(S) – END ******

    AUTOEXEC.BAT

    rem ******* PC/TCP INSTALL ADDED LINE(S) – BEGIN ******
    rem ****
    @REM ==== LANMAN 2.2 === DO NOT MODIFY BETWEEN THESE LINES === LANMAN
    2.2 ====
    SET PATH=C:\LANMAN.DOS\NETPROG;%PATH%
    @REM ==== LANMAN 2.2 === DO NOT MODIFY BETWEEN THESE LINES === LANMAN
    2.2 ====
    rem ******* PC/TCP INSTALL ADDED LINE(S) – BEGIN ******
    LOADHIGH C:\WINDOWS\SMARTDRIVE.EXE
    LOADHIGH C:\DOS\SHARE.EXE
    LOADHIGH C:\DOS\DOSKEY.COM
    SET PATH=C:\PCTCP;%PATH%
    SET PCTCP=C:\PCTCP\PCTCP.INI (*2)
    C:\PCTCP\NETBIND.COM (*3)
    C:\PCTCP\ETHDRV.EXE (*4)
    c:\pctcp\netbios -S “” (*5)
    rem ******* PC/TCP INSTALL ADDED LINE(S) – END ******
    NET START WORKSTATION

    PROTOCOL.INI

    [PROTMAN]
    DRIVERNAME = PROTMAN$
    DYNAMIC = YES
    PRIORITY = NETBEUI

    [NETBEUI_XIF]
    Drivername = netbeui$
    SESSIONS = 6
    NCBS = 12
    BINDINGS = “ELNKII_NIF”
    LANABASE = 0

    [ELNKII_NIF]
    ;
    ; 3c503 3Com EtherLink II adapter
    ;
    DRIVERNAME = ELNKII$
    INTERRUPT = 3
    IOADDRESS = 0x300
    DMACHANNEL = 1

    [PKTDRV]
    CHAINVEC = 0x62
    INTVEC = 0x60
    DRIVERNAME = PKTDRV$
    BINDINGS = “ELNKII_NIF”

    NOTES:
    (*1) This is the packet driver to NDIS converter module and must be loaded.

    (*2) This is the configuration module for the PC/TCP Kernel. The interface= parameter in the [pctcp kernel] section of this file must be set to the kernel driver loaded (see below) for proper operation.

    (*3) Netbind is used to bind the NDIS driver to the PC/TCP coversion module.

    (*4) This is the PC-210 Generic Kernel for DIX Ethernet. IEEEDRV.EXE is used for 802.3 Ethernet and TOKDRV.EXE is used for 802.5 Token Ring.

    (*5) This is the PC/TCP NetBIOS driver which must be loaded for RFC 1001 and 1002 compliance to provide a session layer to allow LAN Manager to communicate with the PC/TCP Kernel.
    Back to the top

    Article ID: 100699 – Last Review: February 28, 2014 – Revision: 1.0

    Keywords: kbnosurvey kbarchive KB100699

  11. Michal Necasek says:

    Wow, this is scary. So this was out there in 2014, and now the information is completely gone?!

    And yes, the whole setup with drivers in CONFIG.SYS and complicated PROTOCOL.INI and all that junk was just stupidly complicated.

  12. Shadow Lord says:

    This along with many other things. Welcome to the new internet. We used to say once it is online its out there forever but that is blatantly false now. There are so many informative sites that are gone (“The Printer Works”). Companies where bought up and the information and resources in their sites were destroyed (3Com, USR) or put behind paywalls (I am looking at you HP). Worst offenders are companies that have cleared content/info on their old products (Microsoft you sneaky bastard)….

    Of course there are still bastions of hope out there. Adaptec site still has info and drivers for all the products they used to produce. No idea how long that will last though. Unfortunately, there is no easy way to archive the information or data (lots of stupid click to agree buttons)

  13. Michal Necasek says:

    Microsoft is particularly bad, because not only they remove old information, they pretend that older versions never existed. Thus when their documentation says e.g. that a particular API is supported “since Windows XP”, it might be supported since XP, or XP might just be the oldest Windows version they admit to existing at that point in time.

    IBM OTOH has a treasure trove of information, like their announcement letter archives, and on their FTP they also offer fixes going decades back.

    But yeah, the future looks scary. A lot of information available today will be simply gone in 5-10 years, with no way to get it back.

  14. Melbourne says:

    Support for file sharing was stripped out of PC DOS 7 and moved into OS/2 and Windows, so incidental changes to the network API aren’t surprising.

    I was looking for a DOS version that supports both large partitions and file sharing, so I noticed the changes made to PC DOS 7 networking

  15. Michal Necasek says:

    Can you please provide some detail? I think you just made it up, or perhaps misunderstood something. There are no significant functional differences in PC DOS 7 compared to PC DOS 6.x. Most networking products, like Microsoft’s file and print client or IBM’s DLS, work just fine with PC DOS 2000. IBM’s TCP/IP is the rare exception.

Leave a Reply

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

This site uses Akismet to reduce spam. Learn how your comment data is processed.