On 13/12/2017, Sage Weil wrote: > Another thought that is somewhat trivial but probably necessary and > smallish is the log/ framework. This might be a good test case for > the legacy <-> seastar communications infrastructure. It's all > one-way, which simplifies things a bit, and the implementation > should be pretty straightforward? This might be a good opportunity to revisit how we do logging. What we have right now is pretty heavyweight and does a lot of string manipulation at runtime we might be better avoiding. > Another question is how the logger/perfcounters will need to change > in a seastar world. We'd basically shard the perfcounters, have one set per core, and handle queries by having one core send messages to the others asking for the values and just returning the sum. It sounds more heavy, but when we ditch the locks and atomics it ends up a lot less burdensome. -- Senior Software Engineer Red Hat Storage, Ann Arbor, MI, US IRC: Aemerson@OFTC, Actinic@Freenode 0x80F7544B90EDBFB9 E707 86BA 0C1B 62CC 152C 7C12 80F7 544B 90ED BFB9 -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
