2 ** ZCACHE PLAN FOR PROMOTION FROM STAGING **
4 Last updated: Feb 13, 2013
8 1. merge zcache and ramster to eliminate horrible code duplication
9 2. converge on a predictable, writeback-capable allocator
10 3. use debugfs instead of sysfs (per akpm feedback in 2011)
11 4. zcache side of cleancache/mm WasActive patch
12 5. zcache side of frontswap exclusive gets
13 6. zcache must be able to writeback to physical swap disk
14 (per Andrea Arcangeli feedback in 2011)
15 7. implement adequate policy for writeback
16 8. frontswap/cleancache work to allow zcache to be loaded
18 9. get core mm developer to review
19 10. incorporate feedback from review
20 11. get review/acks from 1-2 additional mm developers
21 12. incorporate any feedback from additional mm reviews
22 13. propose location/file-naming in mm tree
23 14. repeat 9-13 as necessary until akpm is happy and merges
27 1. DONE as part of "new" zcache; in staging/zcache for 3.9
28 2. DONE as part of "new" zcache (cf zbud.[ch]); in staging/zcache for 3.9
29 (this was the core of the zcache1 vs zcache2 flail)
30 3. DONE as part of "new" zcache; in staging/zcache for 3.9
31 4. DONE (w/caveats) as part of "new" zcache; per cleancache performance
32 feedback see https://lkml.org/lkml/2011/8/17/351, in
33 staging/zcache for 3.9; dependent on proposed mm patch, see
34 https://lkml.org/lkml/2012/1/25/300
35 5. DONE as part of "new" zcache; performance tuning only,
36 in staging/zcache for 3.9; dependent on frontswap patch
37 merged in 3.7 (33c2a174)
38 6. DONE (w/caveats), prototyped as part of "new" zcache, had
39 bad memory leak; reimplemented to use sjennings clever tricks
40 and proposed mm patches with new version in staging/zcache
41 for 3.9, see https://lkml.org/lkml/2013/2/6/437;
42 7. PROTOTYPED as part of "new" zcache; in staging/zcache for 3.9;
43 needs more review (plan to discuss at LSF/MM 2013)
44 8. IN PROGRESS; owned by Konrad Wilk; v2 recently posted
45 http://lkml.org/lkml/2013/2/1/542
46 9. IN PROGRESS; owned by Konrad Wilk; Mel Gorman provided
47 great feedback in August 2012 (unfortunately of "old"
49 10. Konrad posted series of fixes (that now need rebasing)
50 https://lkml.org/lkml/2013/2/1/566
51 11. NOT DONE; owned by Konrad Wilk
52 12. TBD (depends on quantity of feedback)
53 13. PROPOSED; one suggestion proposed by Dan; needs more ideas/feedback
54 14. TBD (depends on feedback)
58 Not sure. Seth Jennings is now pursuing a separate but semi-parallel
59 track. Akpm clearly has to approve for any mm merge to happen. Minchan
60 Kim has interest but may be happy if/when zram is merged into mm. Konrad
61 Wilk may be maintainer if akpm decides compression is maintainable
62 separately from the rest of mm. (More LSF/MM 2013 discussion.)
64 ZCACHE FUTURE NEW FUNCTIONALITY
66 A. Support zsmalloc as an alternative high-density allocator
67 (See https://lkml.org/lkml/2013/1/23/511)
68 B. Support zero-filled pages more efficiently
69 C. Possibly support three zbuds per pageframe when space allows