- User Since
- May 16 2014, 7:29 PM (274 w, 2 d)
Fix 32-bit build.
Sat, Aug 17
It shouldn't be built for powerpc32, only powerpc64. However, it doesn't hurt anything, and is a good belt-and-suspenders change.
Fri, Aug 16
Thu, Aug 15
Address @kib's feedback. The man page will probably need more iterating, but I
think the code is correct. It may not be optimal, though.
Wed, Aug 14
Don't call getpid(), we can pass 0 now.
Incorporate mjg's changes.
Tue, Aug 13
Add a new sysctl, kern.proc.fdmap.<proc>, to provide the bitmap. Walk the bitmap instead of the file descriptor list.
Mon, Aug 12
Sun, Aug 11
Sat, Aug 10
Address @kib's feedback. Man page will probably require several iterations
to get right. It's still a little muddy.
Fri, Aug 9
Thu, Aug 8
Looks fine overall, just the one question. I just want to be sure this is thoroughly tested before it goes in, on the corner cases.
Looks good now.
Tue, Aug 6
Mon, Aug 5
Sun, Aug 4
Sat, Aug 3
Looks good. Can the same change apply to powerpc?
Fri, Aug 2
Address @hselasky's comments.
Thu, Aug 1
Wed, Jul 31
Thanks for checking. Looks good. I assume you tested on bare metal, too?
@hselasky yes, I'm working on it, but got sidetracked doing other things while working on it. I'll have an update either tonight or tomorrow.
Tue, Jul 30
Mon, Jul 29
Sun, Jul 28
Thu, Jul 25
Wed, Jul 24
Have you checked performance on this latest version?
Make MOEA64_STATS a compile option
Tue, Jul 23
Mon, Jul 22
Sun, Jul 21
I just tested with a *very* small page table (0x8000 entries on a 256GB machine), and hit the 'moea64_pte_insert: overflow' panic, which you had mentioned a few years back is indicative of the PTEGs being filled with wired entries. Checking the statistics, I do see 0x38 overflows, and other statistics look accurate, too. I don't see anything bad in this patch, because the only thing it does is optimistically try to insert the PVO, and go through the normal logic if it already exists.
Sat, Jul 20
Jul 20 2019
Jul 16 2019
Jul 15 2019
Jul 14 2019
Jul 13 2019
Jul 12 2019
It helps if I use an actual pointer.
Simplify the code. Revert to the first version tested.
Jul 11 2019
I still see merit in keeping statistics available, for assessing performance issues as you mentioned, but I don't see it necessary in the general case. If there are no objections, I'll take @luporl's request and add an option for MOEA64_STATS, possibly enabled in CURRENT, but disabled in STABLE.
What do the statistics give us in general for pmap? I don't see statistics on other archs, so I'm not sure what the benefit is. I understood for bringup and early stabilization, but we're in pretty solid territory now.
Jul 10 2019
Jul 9 2019
Jul 8 2019
This can now be abandoned, 8.0.1-rc3 was pulled in just the other day.
Jul 7 2019
Looks good overall. Just a couple nits..