On 20 June 2013 16:56, Jeff Roberson <jroberson_at_jroberson.net> wrote: > Just to add some more information; On my machine with 16GB of ram the > handful of recent UMA commits save about 20MB of kmem on boot. There are > 30% fewer buckets allocated. And all of the malloc zones have similar > amounts of cached space. Actually the page size malloc bucket is taking up > much less space. > > I don't know if the problem is unique to arm but I have tested x86 limited > to 512MB of ram without trouble. I will need the stats I mentioned before > to understand what has happened. Have you tried lower than 512MB? Like, 128MB? I have a 128MB -HEAD VM on i386 and it's working fine but I haven't done much digging to see how _well_ its working. I'm about to try a 64MB and 96MB VM. I'd like to go all the way down to 32MB (obviously with a cut down kernel, as GENERIC is pretty damned big!) and ensure that i386 isn't behaving poorly. There are still plenty of ARM/MIPS embedded boards that ship with 32MB (and less) RAM. I'm going to try stable/9 on 128MB of RAM soon. I know that 9.1-REL i386 + 128MB RAM results in a crash. Hopefully this stuff is better on stable/9. Thanks, AdrianReceived on Thu Jun 20 2013 - 22:56:32 UTC
This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:40:38 UTC