weirdr.net is a Fediverse instance that uses the ActivityPub protocol. In other words, users at this host can communicate with people that use software like Mastodon, Pleroma, Friendica, etc. all around the world.

This server runs the snac software and there is no automatic sign-up process.

Site description
This is a dual Pentium Pro running NetBSD.
Check out the floppy museum for hints on how to get in touch. Or, you know, ping me on the fediverse. :)
Admin account
@ltning@weirdr.net

Search results for tag #mtcp

8 ★ 4 ↺

[?]Ltning »
@ltning@weirdr.net

Despite all the things IBM did right with OS/2, there were some absolutely mind-boggling decisions made. Today's example: Using Java (version 1.11 or better, mind you) and a Netscape browser plug-in to install TCP/IP. Other than the chicken-and-egg-problem (which is solved by installing the transport services - NIC and protocol drivers - first), there's the fact that they had a perfectly good software installation framework which ran fine on like 6-8MB of RAM (total!). This variant swaps until my CF card starts sweating with 16MB, and is s-l-o-w!

I mean yeah, great, I get a proper BSD-4.4, 32-bit TCP/IP stack and tools. But it's taken me half a day. Getting the installation files over involved loading packet drivers and using in a DOS session. Which works .. surprisingly well. But still .. FixPak43, reboot. MPTS, reboot. Netscape 2.02, reboot. Java 1.18, reboot. Feature Installer plug-in (no reboot). Then, finally, TCP/IP.

All this to have a machine to play with at .


    [?]ltning »
    @ltning@pleroma.anduin.net

    For any #MTCP, #DOS and #Retrocomputing nerds out there who are also running httpserv and want pretty graphs, poke me for a recipe for a hideosly bloated #logstash configuration to ingest the UDP logs.

    I feed it to #Graylog which stores the data in #Opensearch - a pipeline that combined (and this is accurate) needs, conservatively, 4096 times as much RAM as the floppy museum itself (8MB).

    And while looking at this when making this screenshot: I wonder why someone would hit http//floppy.museum with a Referer-header indicating they come from a salesforce-dot-com address? http-colon-slashslash-136.146.46.127 (about halfway down the list).

    #msdos #bloatware #theremustbeabetterway

    Screenshot of a Graylog dashboard showing number of hits in the last 24h, a world map with geographic distribution of the source IPs, a doughnut showing the distribution of pages visited (mostly the root path), a bar graph showing request counts per URI over time, and finally a list of all the recent requests. This list contains timestamp, which museum server handled the request, the remote IP, the country code of the remote IP, the path requested, and the Referer, if any.

    Alt...Screenshot of a Graylog dashboard showing number of hits in the last 24h, a world map with geographic distribution of the source IPs, a doughnut showing the distribution of pages visited (mostly the root path), a bar graph showing request counts per URI over time, and finally a list of all the recent requests. This list contains timestamp, which museum server handled the request, the remote IP, the country code of the remote IP, the path requested, and the Referer, if any.

      [?]mbbrutman »
      @mbbrutman@mastodon.sdf.org

      mTCP NetDrive users ... the read-ahead version is ready for testing. I'm looking for your feedback on how well it works in your environment. See the announcement here for download links: groups.google.com/g/mtcp/c/ktD (no sign-in required)

      Next up ... I know how I'm going to make writes faster too. With just a little more code in the driver.

        [?]mbbrutman »
        @mbbrutman@mastodon.sdf.org

        NetDrive with read-ahead caching, running on a VM to a local server and to a server 50ms away. A 4KB read-ahead cache results in a 3x speedup locally and nearly a 5x speedup on the remote server.

        Real hardware results depend on the speed of the hardware. Slow machines don't benefit much when connected to local servers, but they still get the full benefit on remote connections.

        mTCP Netdrive read-ahead caching benchmark results.  A local server sees a 3x speedup using a 4KB cache, while a remote server sees nearly a 5x speedup.

        Alt...mTCP Netdrive read-ahead caching benchmark results. A local server sees a 3x speedup using a 4KB cache, while a remote server sees nearly a 5x speedup.

          [?]mbbrutman »
          @mbbrutman@mastodon.sdf.org

          And this is where real hardware asserts itself ...

          Using a 4KB read-ahead cache on the DOS side in a VM gave a 5x speedup, which was great and expected; you ask for 1KB and you get 4KB more without having to wait a full round trip.

          But the PCjr said no. After a week of cleaning up the code and gathering stats I understand the problem better; it's just processing packets as fast as it can. The best speed-up on that specific test is 30%, which isn't bad, but not 5x.

            ltning boosted

            [?]mbbrutman »
            @mbbrutman@mastodon.sdf.org

            The latest mTCP for DOS is available!

            This version includes some changes to improve TCP reliability on long running (but idle) connections, black & white Sixel graphics in Telnet, a Telnet emulation bug fix, and other small fixes sprinkled around.

            The source code to NetDrive (network attached storage) is also published now - enjoy reading an unholy mix of x86 assembly code talking to Golang over UDP!

            Spread the word! Friends don't let friends run old code ...