From mboxrd@z Thu Jan 1 00:00:00 1970 X-Spam-Checker-Version: SpamAssassin 3.4.4 (2020-01-24) on inbox.vuxu.org X-Spam-Level: X-Spam-Status: No, score=-0.8 required=5.0 tests=DKIM_INVALID,DKIM_SIGNED, HTML_FONT_LOW_CONTRAST,HTML_MESSAGE,MAILING_LIST_MULTI, T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.4 Received: (qmail 6186 invoked from network); 3 Aug 2023 22:54:50 -0000 Received: from minnie.tuhs.org (50.116.15.146) by inbox.vuxu.org with ESMTPUTF8; 3 Aug 2023 22:54:50 -0000 Received: from minnie.tuhs.org (localhost [IPv6:::1]) by minnie.tuhs.org (Postfix) with ESMTP id 3C7A1416E8; Fri, 4 Aug 2023 08:54:46 +1000 (AEST) Received: from mail-vs1-xe32.google.com (mail-vs1-xe32.google.com [IPv6:2607:f8b0:4864:20::e32]) by minnie.tuhs.org (Postfix) with ESMTPS id 6D20B416E5 for ; Fri, 4 Aug 2023 08:54:39 +1000 (AEST) Received: by mail-vs1-xe32.google.com with SMTP id ada2fe7eead31-447d394d1ebso108551137.1 for ; Thu, 03 Aug 2023 15:54:39 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=ccc.com; s=google; t=1691103278; x=1691708078; h=cc:to:subject:message-id:date:from:in-reply-to:references :mime-version:from:to:cc:subject:date:message-id:reply-to; bh=OrlRvLP4blVZ0+sImIViIrRcPGfmnrVIGzTavM8nASs=; b=Ib/aLXtGUtaAwPpqiCFLVd21Z9vWVaRgtciiIu17Q8tefYDf5y+FA2xhjuLV6604bv jrq3d2DjTrDabuJd4BWCqngrWUdg0Nd0EjL0VebiurYxDZWS+1M5GfmO3/UZ3yQXKDLB OHbt+K2WBt/82eDOkIWxan/u5jMOIkixxie4A= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20221208; t=1691103278; x=1691708078; h=cc:to:subject:message-id:date:from:in-reply-to:references :mime-version:x-gm-message-state:from:to:cc:subject:date:message-id :reply-to; bh=OrlRvLP4blVZ0+sImIViIrRcPGfmnrVIGzTavM8nASs=; b=DkwZt/WdhV7FlDhZ08vtqoQ/4hso9eQR37cWZTz3OCyy8FHGIVCxYn+o6WkIXLGsJj HHZI2U9bvL6rtz9JK2ojzyiWbUVf1XA60y4dU7p46sAxbdAyYl26cZpEZlQMeJ0E70GK 4uuqJlZjD8yJHUYYoyUqYchyA5fz0J1sO01F9BfBbXEeFCYCRvZp0EdToUz3HmEEMpLy nftzM05lIsdajiVwNAgtbzEM80uHNIr7chWXAsjR1MAPr/1j+uxEbmZLSFj4AoGB5o+g aYJNrdk5HdXSvhWP471pzr9xj0j91fc8uiRx1ap3j+irNgpG+7cfmt4kyMUIDjSz0NPP l4aQ== X-Gm-Message-State: AOJu0YyjjnyioMSIik7FojWkYvwoKYwh4cIGXdimXxblgx/E0XwXsvR3 kjFr0/JNhPyeVYheFH1K3poIg1PPXKd2bgIiZoJ3rt5C5KARVlhkyPc= X-Google-Smtp-Source: AGHT+IFIObZUx3Cbxmq5wQaUl8LXQQUl4+1NW7VRozgrQlCMpNHUZyZIf97MdAcCfdPJvgleA7hvNs02YlluUh5Pxzw= X-Received: by 2002:a67:f713:0:b0:43f:3426:9e35 with SMTP id m19-20020a67f713000000b0043f34269e35mr24899vso.12.1691103278098; Thu, 03 Aug 2023 15:54:38 -0700 (PDT) MIME-Version: 1.0 References: <8246.1690761540@cesium.clock.org> <29602.1690887524@cesium.clock.org> <20230803005106.GA12652@mcvoy.com> <202308031657.373GvVvW008640@ultimate.com> In-Reply-To: From: Clem Cole Date: Thu, 3 Aug 2023 18:54:02 -0400 Message-ID: To: Will Senn Content-Type: multipart/alternative; boundary="0000000000002b7d3e06020caa5b" Message-ID-Hash: DOQE3HIWIKHRLTKNNBRW3HLUOMY7IFJ7 X-Message-ID-Hash: DOQE3HIWIKHRLTKNNBRW3HLUOMY7IFJ7 X-MailFrom: clemc@ccc.com X-Mailman-Rule-Misses: dmarc-mitigation; no-senders; approved; emergency; loop; banned-address; member-moderation; nonmember-moderation; administrivia; implicit-dest; max-recipients; max-size; news-moderation; no-subject; digests; suspicious-header CC: tuhs@tuhs.org X-Mailman-Version: 3.3.6b1 Precedence: list Subject: [TUHS] Re: Split addressing (I/D) space (inspired by the death of the python... thread) List-Id: The Unix Heritage Society mailing list Archived-At: List-Archive: List-Help: List-Owner: List-Post: List-Subscribe: List-Unsubscribe: --0000000000002b7d3e06020caa5b Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable =E1=90=A7 below... [and I meant to answer the second =C2=BD of your question before] On Thu, Aug 3, 2023 at 6:09=E2=80=AFPM Will Senn wrot= e: > Clem, > > Oh, so... Without I/D, you're stuck with 64k max per process, with I/D, > you can use 64k for I and 64k for D. > Exactly but ... more in a minute. > Was that it, or were there other tricks to get even more allocated (didn'= t > the 11 max out at 256k)? > Different issues... the MMU on the 40 class and the 45/55 allows 256K [18 bits], the MMU for the 70 class is 4M [22 bits], Unibus I/O controllers had 18 bits of address and RH70 controllers could support 22 bits of extended addresses - see the processor and peripheral handbooks for details [or I can explain offline]. What the PDP-11 books calls 'pages' are 64-byte segments. So the MMU is set up to allow the processor to address 64K or 64KI/64KD at the time, depending on if you have the I/D hardware, and the MMU is set up as to which 'pages' are being addressed. But you could overlay things ... [0405 files] with 'thunks'. So to allow a process (or the kernel) to have more than 64K, overlays can be loaded into memory and since the total physical space memory space is either 18 or 22 bits, if the kernel supports overlays - processes could get bigger [which is part of your first question]. V7 was when 0405 [text only] overlays were added. With DEC's release of v7m - Fred Cantor rewrote the overlay code and they became more general [and that would go into 2.9BSD]. So the programmer needs to decide what you wanted to put into what overlay. For processes, the kernel can swap out segments and replace them as needed. The key is that link needs to generate near/far style calls and it can be a PITA. If you want to access a routine that is not currently mapped into memory, the 'thunk' needs to ask the OS to switch it. Great thought of what was going to be stored where. > > The kernel could be compiled either with, or without separate I/D. The > only reason not to is if you didn't have more then 64k or were there othe= r > reasons? > Well by V6, UNIX needed at least 64K of physical memory and it was really slow with anything less than 256K. For the kernel, using I/D allowed the kernel to grow more easily. By the time of trying to cram networking into it, running on anything less than an 11/44 was pretty hard. That said, Able made an alternate MMU called the ENABLE that allow 4M of memory on a Unibus system. It worked at a cache/bus repeater. So you set the internal MMU to point to it and then use its MMU. Very cool and a soft spot for me. I ran an 11/60 [which is 40 class] with 2M of memory in Teklabs with the first Enable board. For whatever its worth, even with 4M the kernel had started to become a problem for V7 on an 11/70. Data buffers eat a lot of memory. > > So, besides the kernel what apps tended to be split? If I remember > correctly, vi was one, pascal another? > Anything that started to get big ;-) Ppeople ran out of data space and text space from 64K fairly fast. With the 32-bit Vax, the UNIX Small is Beautiful thinking started to fall away. Rob has an excellent paper -> "cat -v considered harmful" BSD UNIX, and the Vaxen greatly fueled that. Adding features and thinking less about what functionality was really needed started to get lost [so now we have Gnu - but I digress]. Werner and the BSD 2.9 folks are to be commended for what they did with so few resources. They moved things back from the Vax by using the overlays, but if you were to have any semblance of performance, you need the overlays to stay resident so you need that full 4M of memory. As for this specific question first two subsystems for the 11 that ran out of text space were indeed vi and Pascal subsystems (Joy having had his hand in both, BTW). But they were hardly the only ones once the genie was out of the bottle. Data space quickly became the real issue. People really wanted larger heaps in particular. In fact, by the 1990s, I knew of few programs that run out of 32-bit worth of text space, but many that started to run out of 32-bits of data space -> hence Alpha. But BTW: DEC took a performance hit originally, and there was a huge discussion at the time if 64-bits was really needed. =E1=90=A7 --0000000000002b7d3e06020caa5b Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable

3D""=E1=90=A7
below... [and I meant to answer the sec= ond =C2=BD of your question before]

On Thu, Aug 3, 2023 at 6:09=E2=80= =AFPM Will Senn <will.senn@gmail.com> wrote:
=20 =20 =20
Clem,

Oh, so... Without I/D, you're stuck with 64k max per process, wit= h I/D, you can use 64k for I and 64k for D.
Exactly=C2=A0but ... more in a minute.=


=C2=A0
Was that it, or were there other tricks to get even more allocated (didn't the 11 max out at 256k)?
Different issues... the MMU on the 40 class and the 45/55 allows 256K = [18 bits], the MMU for the 70 class is 4M [22 bits],=C2=A0Unibus= I/O controllers had 18 bits of address and RH70 controllers could <= font color=3D"#0000ff">support 22 bits of extended addresses - see the proc= essor and peripheral=C2=A0handbooks for details [or I can explain offline].=

What the PDP-11 books calls = 'pages' are 64-byte segments.=C2=A0 So the MMU is set up to allow t= he processor to address 64K or 64KI/64KD at the time, depending on if you= =C2=A0have the=C2=A0I/D hardware, and the MMU is set up as to which 'pa= ges' are being addressed.

But you could overlay things ... [040= 5 files] with 'thunks'.

=
So to allow a process (or the kerne= l) to have more than 64K, overlays can be loaded into memory and since the = total physical space memory space is either 18 or 22 bits, if the kernel su= pports overlays=C2=A0- processes could get bigger [which is part of your fi= rst question].=C2=A0
V7 was when 040= 5 [text only] overlays were added.=C2=A0 =C2=A0With DEC's release of v7= m - Fred Cantor rewrote the overlay code and they became more general [and = that would go into 2.9BSD].

So the programmer needs to decide what= you wanted to put into what overlay.=C2=A0 =C2=A0For processes, the kernel= can swap out segments and replace them as needed.=C2=A0 =C2=A0The key is t= hat link needs to generate near/far style calls and it can be a PITA.=C2=A0= If you want to access a routine that is not currently mapped into memory, = the 'thunk' needs to ask the OS to switch it. Great thought of what= was going to be stored where.
=C2=A0

= =C2=A0

The kernel could be compiled either with, or without separate I/D. The only reason not to is if you didn't have more then 64k or wer= e there other reasons?
Well by V6, UNIX needed at least 64K of physical memory and it= was really slow with anything less than 256K.=C2=A0 =C2=A0For the kernel, = using I/D allowed the kernel to grow more easily.=C2=A0 By the time of tryi= ng to cram networking into it, running on anything less than an 11/44 was p= retty hard.

That said, Able made an alternate MMU called t= he ENABLE that allow 4M of memory on a Unibus system.=C2=A0 It worked at a = cache/bus repeater.=C2=A0 So you set the internal MMU to point to it and th= en use its MMU.=C2=A0 =C2=A0Very cool and a soft spot for me.=C2=A0<= span style=3D"color:rgb(0,0,255)">I ran an 11/60 [which is 40 class] with 2= M of memory in Teklabs with the first Enable board.

For whatever=C2=A0its worth, even with 4M the kernel had started to= become a problem for V7 on an 11/70.=C2=A0 Data buffers eat a lot of memor= y.

So, besides the kernel what apps tended to be split? If I remember correctly, vi was one, pascal another?
<= font color=3D"#0000ff">Anything that started to get big ;-)=C2= =A0

Ppeople ran out of data space and text space from 64K f= airly fast.=C2=A0 =C2=A0With the 32-bit Vax, the UNIX Small is Beautiful th= inking started to fall away.=C2=A0 =C2=A0Rob has an excellent paper -> &= quot;cat -v considered harmful"=C2=A0 =C2=A0BSD UNIX, and the Vaxen gr= eatly fueled that.=C2=A0 =C2=A0Adding features and thinking less about what= functionality was really needed started to get lost [so now we have Gnu - = but I digress].=C2=A0 Werner and the BSD 2.9 folks are to be commended for = what they did with so few resources.=C2=A0 =C2=A0They moved things back fro= m the Vax by using the overlays, but if you were to have any semblance of p= erformance, you need the overlays to stay resident so you need that full 4M= of memory.

=
As for this=C2=A0specific que= stion first two subsystems for the 11 that ran out of text space were indee= d vi and Pascal subsystems (Joy having had his hand in both, BTW).=C2=A0 Bu= t they were hardly the only ones once the genie was out of the bottle.=C2= =A0 =C2=A0Data space quickly became the real issue.=C2=A0 = People really wanted larger heaps in particular.=C2=A0=C2=A0<= span style=3D"font-family:arial,helvetica,sans-serif;color:rgb(0,0,255)">= =C2=A0In fact, by the 1990s, I knew of few programs that run out of 32-bit = worth of text space, but=C2=A0many tha= t=C2=A0started=C2=A0to=C2=A0run out of 32-bits of dat= a space -> hence Alpha.=C2=A0 =C2=A0But BTW:=C2=A0 DEC took a perfor= mance hit originally, and there was a huge discussion at the time if 64-bit= s was really needed.=C2=A0 =C2=A0
3D""==E1=90=A7
--0000000000002b7d3e06020caa5b--