DAOS-17535 cart: not exclude self when create corpc for IV #16357
Conversation
|
Ticket title is 'DAOS checker cannot completed on Aurora after some engines excluded' |
Nasf-Fan
force-pushed
the
Nasf-Fan/DAOS-17535
branch
from
0a04e2b to
28d97ae
Compare
Nasf-Fan
force-pushed
the
Nasf-Fan/DAOS-17535
branch
from
28d97ae to
79a3909
Compare
|
Test stage Functional Hardware Medium Verbs Provider MD on SSD completed with status FAILURE. https://jenkins-3.daos.hpc.amslabs.hpecorp.net/job/daos-stack/job/daos/job/PR-16357/3/display/redirect |
Nasf-Fan
force-pushed
the
Nasf-Fan/DAOS-17535
branch
from
79a3909 to
63edfe2
Compare
|
Test stage Functional Hardware Medium MD on SSD completed with status UNSTABLE. https://jenkins-3.daos.hpc.amslabs.hpecorp.net/job/daos-stack/job/daos//view/change-requests/job/PR-16357/4/testReport/ |
|
Test stage Functional Hardware Medium Verbs Provider MD on SSD completed with status FAILURE. https://jenkins-3.daos.hpc.amslabs.hpecorp.net//job/daos-stack/job/daos/view/change-requests/job/PR-16357/4/execution/node/1468/log |
src/cart/crt_iv.c
Outdated
| excluded_list.rl_nr = 1; | ||
| excluded_list.rl_ranks = excluded_ranks; | ||
| excluded_ranks[0] = ivns_internal->cii_grp_priv->gp_self; | ||
| /* Perform refresh on local node */ |
There was a problem hiding this comment.
if you are including self now in sync corpc then perhaps the local update here should be removed?
There was a problem hiding this comment.
Not sure, let me test whether that works or not.
Nasf-Fan
force-pushed
the
Nasf-Fan/DAOS-17535
branch
3 times, most recently
from
009fec2 to
c28313a
Compare
|
Test stage NLT on EL 8.8 completed with status UNSTABLE. https://jenkins-3.daos.hpc.amslabs.hpecorp.net/job/daos-stack/job/daos//view/change-requests/job/PR-16357/7/testReport/ |
|
Test stage Functional Hardware Medium MD on SSD completed with status FAILURE. https://jenkins-3.daos.hpc.amslabs.hpecorp.net//job/daos-stack/job/daos/view/change-requests/job/PR-16357/7/execution/node/1470/log |
Nasf-Fan
force-pushed
the
Nasf-Fan/DAOS-17535
branch
from
c28313a to
4e72a38
Compare
|
Test stage Functional Hardware Large MD on SSD completed with status FAILURE. https://jenkins-3.daos.hpc.amslabs.hpecorp.net//job/daos-stack/job/daos/view/change-requests/job/PR-16357/8/execution/node/1637/log |
online_rebuild_mdtest failed for DAOS-17751, not related with the patch. |
|
Ping reviewers, thanks! |
Otherwise, it may misguide subsequent crt_get_filtered_grp_rank_list() and regard the IV root to be as non-exist in the ranks list, then fail related IV operation with -DER_NONEXIST. It maybe not a perfected solution for current cart IV logic. But to be some temporary option, it makes CR to be workable when some ranks dead. Add new test case to verify such corner case. Signed-off-by: Fan Yong <[email protected]>
Nasf-Fan
force-pushed
the
Nasf-Fan/DAOS-17535
branch
from
4e72a38 to
45b2b2a
Compare
|
Resolve merge conflict. |
|
Ping reviewers, thanks! |
|
@jgmoore-or , would you please to help review the patch? Thanks! |
|
@alexbarcelo is this PR sufficient for the problem, or it's just a workaround and requires more work? |
|
Are you pinging me? Wrong Alex? |
|
@frostedcmos is this PR sufficient for the problem, or it may require more work? |
from carts perspective either the current or this prs behavior is fine and is a matter of preference, but looks like this ticket DAOS-17535 is properly solved by a different daos-level PR #17329 |
yes, we do not need this pr any longer. |
Otherwise, it may misguide subsequent crt_get_filtered_grp_rank_list() and regard the IV root to be as non-exist in the ranks list, then fail related IV operation with -DER_NONEXIST.
It maybe not a perfected solution for current cart IV logic. But to be some temporary option, it makes CR to be workable when some ranks dead.
Add new test case to verify such corner case.
Steps for the author:
After all prior steps are complete: