Jumbo allocation performance

[fengb]

ZeeAlloc does really poorly with variable-sized jumbo allocations. We should investigate a better way to reference these frames.

Detailed problem:

1. Jumbo frames are all stuck into a (singly) linked list
2. Only specific matches will fit jumbo frames (search size == frame size)

Potential solutions:

• Make search size <= frame size — this speeds up variable reuse at the cost of hurting exact size reuse and internal fragmentation
• Increase "page size" — this only punts the problem as well as causing more internal fragmentation
• Powers of 2 for jumbo — more internal fragmentation, still poor performance for lots of simultaneous allocations

[fengb]

wee_alloc has O(n) allocations, so maybe we should follow suit.

Interestingly, it also does "first fit", which matches our first "fix" strategy.

[fengb]

First fit has a hugely degenerate case where smaller frames tend to bubble into the back of the list and never match again because larger ones are in front and always match. Potential alternatives are:

• closest fit — slowest O(n) but should rarely degenerate
• reasonable fit (e.g. < 2*n)— still have early exits but less predictable

[fengb]

Default to closest fit, with options for exact or first.