4 * imposed HINTs are terribly broken, resend the same data over and over again
5 * check ACK/HAVE redundancy
6 * small-progress update problem (aka peer nap)
7 guarantee size of updates < x% of data, on both ends
10 * move to the.zett's binmaps
11 * optimize redundant HASH messages
12 * move to rotated ACK queue
18 * file/hash-file re-open in read-only mode
19 * no cache recheck, failure-resistant
20 * unified events/callbacks
24 * all-swarm performance stats
25 * run chained setups (cmd line protocol subsetting)
26 * implement: multiple swift instances per server
27 * run thousand-daemon caching tests (use httpgw)
28 * use a dedicated tracker
29 * add NATs to the setup
30 * recover mfold.libswift.org