That will make sense to me. I think I need trace so deep enough for know it really means next time.
anyway, Thanks!!! 2014-09-17 13:16 GMT+08:00 Sage Weil <[email protected]>: > On Wed, 17 Sep 2014, Cheng Wei-Chung wrote: >> Dear all: >> >> I have seen this function few days. >> OSDMap::Incremental::get_net_marked_down >> >> There is something strange I don't know why. >> >> why we increase n when we got state and previous state is UP? >> if (p->second & CEPH_OSD_UP) { >> if (previous->is_up(p->first)) >> n++; // marked down >> else >> n--; // marked up >> } >> >> This function aims to help check whether the osd can be mark down or not, >> right? >> >> For counting the osd that state is down, the above function is >> counting the osd that state is up? >> >> I would like to know there is some minor error or something I don't >> really understand. > > For lame historical reasons the CEPH_OSD_UP flag in the incremental > *toggles* the up/down state ... it either means the OSD came up or that it > went down. > > sage > -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
