home bbs files messages ]

Forums before death by AOL, social media and spammers... "We can't have nice things"

   comp.arch      Apparently more than just beeps & boops      131,241 messages   

[   << oldest   |   < older   |   list   |   newer >   |   newest >>   ]

   Message 129,443 of 131,241   
   Waldek Hebisch to John Levine   
   Re: VAX and other pages   
   20 Aug 25 01:49:41   
   
   From: antispam@fricas.org   
      
   John Levine  wrote:   
   > According to Anton Ertl :   
   >>John Levine  writes:   
   >>>SSDs often let you do 512 byte reads and writes for backward compatibility   
   even   
   >>>though the physical block size is much larger.   
   >>   
   >>Yes.  But if the argument had any merit that 512B is a good page size   
   >>because it avoids having to transfer 8, 16, or 32 sectors at a time,   
   >>it would still have merit, because the interface still shows 512B   
   >>sectors.   
   >   
   > I think we're agreeing that even in the early 1980s a 512 byte page was   
   > too small.  They certainly couldn't have made it any smaller, but they   
   > should have made it larger.   
   >   
   > S/370 was a decade before that and its pages were 2K or 4M.  The KI-10,   
   > the first PDP-10 with paging, had 2K pages in 1972.  Its pager was based   
   > on BBN's add-on pager for TENEX, built in 1970 also with 2K pages.   
      
   Several posts above I wrote:   
      
   : I think that in 1979 VAX 512 bytes page was close to optimal.   
   : Namely, IIUC smallest supported configuration was 128 KB RAM.   
   : That gives 256 pages, enough for sophisticated system with   
   : fine-grained access control.   
      
   Note that 360 has optional page protection used only for access   
   control.  In 370 era they had legacy of 2k or 4k pages, and   
   AFAICS IBM was mainly aiming at bigger machines, so they   
   were not so worried about fragmentation.  PDP-11 experience   
   possibly contributed to using smaller pages for VAX.   
      
   Microprocessors were designed with different constraints, which   
   led to bigger pages.  But VAX apparently could afford resonably   
   large TLB and due VMS structure gain was bigger than for other   
   OS-es.   
      
   And little correction: VAX architecture handbook is dated 1977,   
   so actually decision about page size had to be made at least   
   in 1977 and possibly earlier.   
      
   --   
                                 Waldek Hebisch   
      
   --- SoupGate-Win32 v1.05   
    * Origin: you cannot sedate... all the things you hate (1:229/2)   

[   << oldest   |   < older   |   list   |   newer >   |   newest >>   ]


(c) 1994,  bbs@darkrealms.ca