ID | Objective | Procedure | Expected Behaviour | Actual Results | Notes |
---|
IPv6_only.Config.SR.Client.1 | Configure Lustre Client using only IPv6. (SR, same subnet) | - Select an IPv6-enabled machine
- Install lustre client
- Configure the client to use a connected interface which has only IPv6 address configured
- Bring up lustre
- Execute "lnetctl net show"
- Execute "lnetctl ping" of own NID
| - "lnetctl net show" output should indicate an active NID featuring IPv6 address of the interface configured for use with LNet.
- "lnetctl ping" of own NID should be successful
|
|
|
IPv6_only.Config.SR.Client.2 | Configure second Lustre Client using only IPv6 and test connectivity between the two clients. (SR, same subnet) | - Select an IPv6-enabled machine
- Install lustre client
- Configure the client to use a connected interface which has only IPv6 address configured.
- Execute "ping" to the IPv6 of the other client
- Bring up lustre
- Execute "lnetctl net show"
- Execute "lnetctl ping" of own NID
- Execute "lnetctl ping" of the other client's NID
| - "ping" of the other client's IPv6 address should succeed
- "lnetctl net show" output should indicate an active NID featuring IPv6 address of the interface configured for use with LNet.
- "lnetctl ping" of own NID should be successful
- "lnetctl ping" of the other client's NID should be successful
|
| Assumes that Client.1 and Client.2 are on the same subnet and are able to reach each other over IPv6 network. |
IPv6_only.Config.SR.Server.1 | Configure Lustre Server using only IPv6 (SR, same subnet) | - Select an IPv6-enabled machine
- Install lustre server (ok to collocate MDS and OSS)
- Configure the server to use a connected interface which has only IPv6 address configured.
- Execute "ping" to the IPv6 of a client
- Bring up lustre
- Execute "lnetctl net show"
- Execute "lnetctl ping" of own NID
- Execute "lnetctl ping" of the client's NID
| - "ping" of the client's IPv6 address should succeed
- "lnetctl net show" output should indicate an active NID featuring IPv6 address of the interface configured for use with LNet.
- "lnetctl ping" of own NID should be successful
- "lnetctl ping" of the client NID should be successful
|
| Assumes that servers and clients are on the same subnet and are able to reach each other over IPv6 network. |
IPv6_only.Basic.LNet.SR.1 | Test basic connectivity between Lustre Server and Client on LNet level. (SR, same subnet) | Use the lustre server and clients setup in previous tests and - Load "lnet_selftest" on each node
- Configure and run "lnet_selftest" between the nodes
| - "lnet_selftest" should run without errors.
- Throughput reported by "lnet_selftest" should be adequate (verify against link speed).
|
|
|
IPv6_only.Basic.Lustre.SR.1 | Test Lustre FS performance with the Client and Server setup to use IPv6. (SR, same subnet) | Use the lustre server and clients setup in previous tests and - Mount lustre FS on the client(s)
- Run FIO
| - Lustre FS mount should succeed
- FIO should run without errors. Throughput reported by FIO should be adequate (verify against link speed and "lnet_selftest" results).
|
|
|
IPv6_only.Config.MultiSubnet.SR.1 | Configure Lustre Client and Lustre server to be on different IPv6 subnets (SR) | - Use IPv6_only.Config.SR.Client.1 to create a lustre client and IPv6_only.Config.SR.Server.1 to create a lustre server, but make sure they are using IPv6 addresses which are on different subnets.
- Execute "ping" from the client to IPv6 address of the server
- Bring up lustre
- Execute "lnetctl ping" between the client and the server NIDs
| - ping" of the server's IPv6 address from the client should succeed
- "lnetctl ping" of between the client and the server should be successful
|
|
|
IPv6_only.MultiSubnet.LNet.SR.1 | Test basic connectivity between Lustre Server and Client across IPv6 subnets on LNet level. (SR) | - Use IPv6_only.Config.MultiSubnet.SR.1 for setup
- Load "lnet_selftest" on each node
- Configure and run "lnet_selftest" between the nodes
| - "lnet_selftest" should run without errors.
- Throughput reported by "lnet_selftest" should be adequate (verify against link speed).
|
|
|
IPv6_only.MultiSubnet.Lustre.SR.1 | Test Lustre FS performance with the Client and Server setup to use IPv6 across subnets. (SR) | - Use IPv6_only.Config.MultiSubnet.SR.1 for setup
- Mount lustre FS on the client(s)
- Run FIO
| - Lustre FS mount should succeed
- FIO should run without errors. Throughput reported by FIO should be adequate (verify against link speed and "lnet_selftest" results).
|
|
|
IPv6_only.Config.MR.Client.1 | Configure Lustre Client using only IPv6. (MR, same subnet) | - Select an IPv6-enabled machine
- Install lustre client
- Configure the client to use 2 connected interfaces with only IPv6 address configured on each
- Bring up lustre
- Execute "lnetctl net show"
- Execute "lnetctl ping" of own NIDs
| - "lnetctl net show" output should indicate 2 active NIDs featuring IPv6 addresses of the interfaces configured for use with LNet.
- "lnetctl ping" of own NIDs should be successful
|
|
|
IPv6_only.Config.MR.Client.2 | Configure second Lustre Client using only IPv6 and test connectivity between the two clients. (MR, same subnet) | - Select an IPv6-enabled machine
- Install lustre client
- Configure the client to use 2 connected interfaces with only IPv6 address configured on each
- Execute "ping" to the IPv6 addresses of the other client
- Bring up lustre
- Execute "lnetctl net show"
- Execute "lnetctl ping" of own NIDs
- Execute "lnetctl ping" of the other client's NIDs
| - "ping" of the other client's IPv6 addresses should succeed
- "lnetctl net show" output should indicate 2 active NIDs featuring IPv6 addresses of the interfaces configured for use with LNet.
- "lnetctl ping" of own NIDs should be successful
- "lnetctl ping" of the other client's NIDs should be successful
|
| Assumes that Client.1 and Client.2 are on the same subnet and are able to reach each other over IPv6 network. |
IPv6_only.Config.MR.Server.1 | Configure Lustre Server using only IPv6 (MR, same subnet) | - Select an IPv6-enabled machine
- Install lustre server (ok to collocate MDS and OSS)
- Configure the LNet on the server to use 2 IPv6-only interfaces.
- Execute "ping" to the IPv6 addresses of the client
- Bring up lustre
- Execute "lnetctl net show"
- Execute "lnetctl ping" of own NIDs
- Execute "lnetctl ping" of the client's NIDs
| - "ping" of the client's IPv6 addresses should succeed
- "lnetctl net show" output should indicate 2 active NIDs featuring IPv6 address of the interface configured for use with LNet.
- "lnetctl ping" of own NIDs should be successful
- "lnetctl ping" of the client NIDs should be successful
|
| Assumes that servers and clients are on the same subnet and are able to reach each other over IPv6 network. |
IPv6_only.Basic.LNet.MR.1 | Test basic connectivity between Lustre Server and Client on LNet level. (MR, same subnet) | Use the lustre server and clients setup in previous tests and - Load "lnet_selftest" on each node
- Make sure that nodes have "discovered" each other
- Configure and run "lnet_selftest" between the nodes, make sure to use the "primary NIDs" of each node
- Capture "lnetctl net show -v 4" and "netstat -i" outputs before and after the "lnet_selftest"
| - "lnet_selftest" should run without errors.
- Throughput reported by "lnet_selftest" should be adequate (verify against link speed).
- Compare "lnetctl net show -v 4" outputs captured before and after the "lnet_selftest" run. Verify that test traffic is distributed evenly across NIDs.
- Compare "netstat -i" outputs captured before and after the "lnet_selftest"run. Verify that test traffic is evenly distributed across interfaces used by LNet.
|
|
|
IPv6_only.Basic.Lustre.MR.1 | Test Lustre FS performance with the Client and Server setup to use IPv6. (MR, same subnet) | Use the lustre server and clients setup in previous tests and - Mount lustre FS on the client(s)
- Run FIO
| - Lustre FS mount should succeed
- FIO should run without errors. Throughput reported by FIO should be adequate (verify against link speed and "lnet_selftest" results).
|
|
|
IPv6_IPv4_collocated.Config.MR.LNet.1 | Configure node to use one IPv6 and one IPv4 interface for LNet (MR, two different lnets) | - Select a machine which is able to use both IPv4 and IPv6 and has at least two interfaces configured such that one can be IPv6 and another IPv4.
- Configure lustre on the node such that both IPv4 and IPv6 are used each on its separate lnet
- Bring up lustre
- Execute "lnetctl net show"
- Execute "lnetctl ping" of own NID
| - "lnetctl net show" output should list both IPv4 and IPv6 NIDs as active.
- "lnetctl ping" of own NIDs should be successful
|
| This test is run at LNet level so it doesn't matter whether nodes are designated as servers or clients |
IPv6_IPv4_collocated.Basic.MR.LNet.1 | Test basic connectivity between nodes on LNet level. (MR, same subnet) | - Configuration is the same as IPv6_IPv4_collocated.Config.MR.LNet.1
- Make sure that nodes have "discovered" each other
- Load "lnet_selftest" on each node
- Configure and run "lnet_selftest" between the nodes
| - "lnet_selftest" should run without errors.
- Throughput reported by "lnet_selftest" should be adequate (verify against link speed).
- Compare "lnetctl net show -v 4" outputs captured before and after the "lnet_selftest" run. Verify that test traffic is distributed evenly across NIDs.
- Compare "netstat -i" outputs captured before and after the "lnet_selftest"run. Verify that test traffic is evenly distributed across interfaces used by LNet.
| ? | This test is run at LNet level so it doesn't matter whether nodes are designated as servers or clients |
IPv6_IPv4_routed.Config.SR.LNet.1 | Configure one node to use a single IPv6 NID and another to use IPv4 NID. Add lnet router between the two. (SR, lnet routing) | - Select 3 machines: A, B and R. A needs to have IPv6 interface configured. B needs to have IPv4 interface configured. R needs two interfaces, one IPv4 and another IPv6.
- Configure LNet on A to use tcp0 and on B to use tcp1
- Configure LNet on R to have IPv6 NID on tcp0 and IPv4 on tcp1. Enable lnet routing on R.
- Add route to tcp1 via R on A.
- Add route to tcp0 via R on B.
- Bring up A and B
- Bring up R
- Execute "lnetctl route show" on A and B
- Execute "lnetctl ping" from A to B
- Execute "lnetctl ping" from B to A
| - "lnetctl route show" should indicate that routes are "up"
- "lnetctl ping" between A and B should succeed
|
|
|
IPv6_IPv4_routed.Basic.SR.LNet.1 | Test basic connectivity between IPv4 and IPv6 nodes via LNet gateway. (SR, lnet routing) | - Use configuration from IPv6_IPv4_routed.Config.SR.LNet.1
- Load "lnet_selftest" on nodes A and B.
- Configure and run "lnet_selftest" between the nodes A and B
| - "lnet_selftest" should run without errors.
- Throughput reported by "lnet_selftest" should be adequate (verify against link speed).
|
|
|
IPv6_o2ib_routed.Config.SR.LNet.1 | Configure one node to use a single IPv6 NID and another to use an o2ib NID. Add lnet router between the two. (SR, lnet routing) | - Select 3 machines: A, B and R. A needs to have IPv6 interface configured. B needs to have o2ib interface configured. R needs two interfaces, one o2ib and another IPv6.
- Configure LNet on A to use tcp0 and on B to use o2ib0
- Configure LNet on R to have NIDs on o2ib and tcp0. Enable lnet routing on R.
- Add route to o2ib via R on A.
- Add route to tcp0 via R on B.
- Bring up A and B
- Bring up R
- Execute "lnetctl route show" on A and B
- Execute "lnetctl ping" from A to B
- Execute "lnetctl ping" from B to A
| - "lnetctl route show" should indicate that routes are "up"
- "lnetctl ping" between A and B should succeed
|
|
|
IPv6_o2ib_routed.Basic.SR.LNet.1 | Test basic connectivity between o2ib and IPv6 nodes via LNet gateway. (SR, lnet routing) | - Use configuration fromIPv6_o2ib_routed.Config.SR.LNet.1
- Load "lnet_selftest" on nodes A and B.
- Configure and run "lnet_selftest" between the nodes A and B
| - "lnet_selftest" should run without errors.
- Throughput reported by "lnet_selftest" should be adequate (verify against link speed).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|