Am Dienstag, den 22.05.2018, 12:36 +0200 schrieb Michael Biebl: > Am 22.05.2018 um 12:27 schrieb Benjamin Drung: > > What do you suggest to do instead? > > For that I know too little how rdma works, so I can't really answer > that.
Mellanox ConnectX architecture is: mlx4_core is the lower level PCI driver which register on the PCI id, and protocol specific drivers are depended on it: mlx4_en - for Ethernet and mlx4_ib for Infiniband. NIC could have multiple ports which can change their type dynamically. We use the request_module() call to load the relevant protocol driver when needed: on loading time or at port type change event. The ib_ipoib kernel modules provides IP over Infiniband support. The order is as following: 1) The kernel loads mlx4_core on boot (due to device detection) 2) mlx4_core loads mlx4_ib 3) udev triggers rdma-load-modules@infiniband.service 4) rdma-load-modules@infiniband.service loads ib_ipoib (can be configured in /etc/rdma) 5) networking.service brings up the IPoIB devices > networking.service calls 'udevadm > > settle' in 'ExecStartPre'. > > It does, indeed. But not unconditionally. > > ifupdown is basically installed on every system, even if e.g. > NetworkManager is actually in charge and /e/n/i is empty. > > This would mean you unconditionally pull in systemd-udev- > settle.service > on basically every system out there, and we certainly don't want > that. > systemd-udev-settle.service is a hack. -- Benjamin Drung System Developer Debian & Ubuntu Developer ProfitBricks GmbH Greifswalder Str. 207 10405 Berlin Email: benjamin.dr...@profitbricks.com URL: https://www.profitbricks.de Sitz der Gesellschaft: Berlin Registergericht: Amtsgericht Charlottenburg, HRB 125506 B Geschäftsführer: Achim Weiss, Matthias Steinberg, Christoph Steffens
signature.asc
Description: This is a digitally signed message part
