Search results

it might be, but you will need to use some PLX riser to bifurcate the only slot (it will cost like cx3-/4 + fc card)

yes, i agree, since my question was about the pci-e slot, and cx-3 can boot via iscsi even (but im not sure the EMC AX4-5F supports it, i also could find the 4gb FCoE only)

To run NVMe over Fabrics (with a TCP backend), you generally just need a TCP/IP-capable NIC and an NVMe Target Server. As far as I know, the EMC AX4-5F might not support this feature, or FCoE. Its iSCSI support is a good sign, though I couldn't find clear confirmation of that online. Using your...

hello, is nvme-of-tcp not an option?

hello, 1) regarding eth - you are not obliged to bind/rebind driver just for vlan/link state update (vlan and link state attributes can be changed online) - you are not obliged to set mac address on VF and use random if it is acceptable for your software - you can assign required mac for VF via...

hello, i've taken a look to code and found two issues regarding to override functionality:: 1) at line 176 - it tries to resolve /sys/bus/pci/devices/0000:11:22:33.4/driver, but there is not particular attribute `driver` for mlx4_core driver (the attribute appears after driver bound) 2) at lines...

i just wanted to say: 1) vfio-pci (ids, new_id) and driver bind/unbind are not idempotent 2) use driver_override instead of vfio-pci ids/new_id and driver_probe instead of bind/unbind option `driver_override` is recommended to use since 3.16 for pci devices, and in 6.6 this mechanism is finally...

hello, @klui @naptastic on modern kernels (if im not mistaken - 6+) this way still works, but there is a little bit different (and recommended) approach; - do not directly bind VFs to driver, otherwise use `driver_override` to use particular driver (mlx4_core, vfio-pci, etc) echo mlx5_core >...

hello, 1) the module parameters triplet is important: you can use the third one only when both ports are in ETH mode 2) i guess the 2/4k MTU limitation is about of CX-3 VF using. on RDMA it has practically ~no impact, you can try to use CONNECTED mode if MTU matters (i.e. for non-RDMA...

hello, here is my conf, absolutely in-tree driver, no patches, the kernel is `6.19.12`, but the ~same with `7.0.12`-`7.1.5` dual port CX-3 card with None: in my case inbox opensm doesnt work with IB VF, i just installed nvidia's opensm and just drop single `opensm` binnary from `nvidia's...

hello, did you check guids for the cards?

hello, it looks like something wrong with infiniband libs/deps

hello, you need something like this: https://aliexpress.com/item/1005009798069379.html and https://aliexpress.com/item/1005007212456065.html

just plug cx4lx it looks like you have some kind of library/dependencies problem, did you try to boot your favorite (live) distro and check the cards?

are there any errors in dmesg (afrter reboot)? dmesg | grep 'mlx5\|DMAR' if you have virtualization enabled, like this intel_iommu=on iommu=pt pci=realloc intremap=no_x2apic_optout please check you also have "Enable 4G encoding' in BIOS

ok, you have both base guid&mac defined so the problem might be about loaded modules, like # lsmod | grep 'mlx5_ib\|uverb' mlx5_ib 487424 0 ib_uverbs 200704 2 mlx4_ib,mlx5_ib ib_core 516096 10...

hello, what does [mst]flint show? you also can restore guids by macs, i had the similar problem when was reflashing cx3 pro en to vpi fw

almost all of my cards (about 20) are from ali, and 4-5 from ebay, connectx-3/4/5/6 the same about transceivers and fibers, as well as switches

hello, yes that is please take into account: 1) connectx4-lx is more energy efficient i.e. - from offical docs Specifications - from user experience Connectx-4 Lx 2x 25GbE with ASPM support + idle power consumption measurements 2) connecting via chipset can utilize just 32 Gbps (theoretically)...

hello, 1) if you buy connecx4 (not lx version) it can be reflashed to vpi mode (ethernet+infiniband) 2) on any connectx (3/4/5 pro/lx/ex etc) you can use RDMA over ethernet (RoCE v1/v2) on iSCSI (iser) 3) as i remember correctly connectx does not support aspm