Hi, On 2018/10/17 5:00, Mindaugas Rasiukevicius wrote: > Hi, > > I recently implemented thmap [1] -- a concurrent trie-hash map, combining > the elements of hashing and radix trie. It is supports lock-free lookups > and concurrent inserts/deletes. It is designed to be optimal as a general > purpose *concurrent* associative array [2][3]. > > I am going to import it under src/sys/net/npf, so it could be used by NPF. > However, there are various other areas in the kernel where it could improve > the performance significantly, e.g. in the network stack, 5-tuple mapping > to socket (in_pcb.c). While I currently do not have plans to work in those > areas, if anybody would like to use it elsewhere, I can import thmap in the > src/sys/kern directory. Let me know.
If it is imported to src/sys/kern, I want use it to re-implement sys/netinet/ip_flow.c::ipflowtable. However, I don't have enough time to do it right now... > [1] https://github.com/rmind/thmap > [2] http://www.netbsd.org/~rmind/thmap_lookup_80_64bit_keys_intel_4980hq.svg > [3] http://www.netbsd.org/~rmind/thmap_insert_80_64bit_keys_intel_4980hq.svg Wow, excellent scaling! :) Thanks, -- ////////////////////////////////////////////////////////////////////// Internet Initiative Japan Inc. Device Engineering Section, IoT Platform Development Department, Network Division, Technology Unit Kengo NAKAHARA <k-nakah...@iij.ad.jp>
