Details
-
Bug
-
Resolution: Cannot Reproduce
-
Critical
-
None
-
Lustre 2.12.2
-
None
-
2
-
9223372036854775807
Description
We have been setting ko2iblnd timeout = 150 (default of 50) for our cluster. From reading the code this is no longer being used and instead lnet_lnd_timeout is used.
For example in kiblnd_queue_tx_locked
timeout_ns = lnet_get_lnd_timeout() * NSEC_PER_SEC;
tx->tx_queued = 1;
tx->tx_deadline = ktime_add_ns(ktime_get(), timeout_ns);
and
lnet_get_lnd_timeout() returns the new default of 5. Does this mean we went from 150 to 5!
In the documentation it says that lnet_lnd_timeout derived from lnet_transaction_timeout and retry_count. But that is not getting set for tx->tx_deadline.
Am I reading the code correctly?
Attachments
Issue Links
- is related to
-
-
- Resolved
-
Activity
| Resolution | New: Cannot Reproduce [ 5 ] | |
| Status | Original: Open [ 1 ] | New: Resolved [ 5 ] |
| Link | Original: This issue is related to JFC-10 [ JFC-10 ] |
| Link | Original: This issue is related to JFC-21 [ JFC-21 ] |
| Link | Original: This issue is related to JFC-27 [ JFC-27 ] |
| Link | New: This issue is related to JFC-27 [ JFC-27 ] |
| Link | New: This issue is related to JFC-10 [ JFC-10 ] |
| Link | New: This issue is related to JFC-21 [ JFC-21 ] |
| Assignee | Original: WC Triage [ wc-triage ] | New: Amir Shehata [ ashehata ] |
| Description |
Original:
We have been setting ko2iblnd timeout = 150 (default of 50) for our cluster. From reading the code this is no longer being used and instead lnet_lnd_timeout is used.
For example in kiblnd_queue_tx_locked {code:java} timeout_ns = lnet_get_lnd_timeout() * NSEC_PER_SEC; tx->tx_queued = 1; tx->tx_deadline = ktime_add_ns(ktime_get(), timeout_ns); {code} and lnet_get_lnd_timeout() returns the new default of 5. Does this mean we went from 150 to 5! In the documentation it says that lnet_lnd_timeout derived from lnet_transaction_timeout and retry_count. But that is not getting set for tx->tx_deadline. Am I reading the code correctly. |
New:
We have been setting ko2iblnd timeout = 150 (default of 50) for our cluster. From reading the code this is no longer being used and instead lnet_lnd_timeout is used.
For example in kiblnd_queue_tx_locked {code:java} timeout_ns = lnet_get_lnd_timeout() * NSEC_PER_SEC; tx->tx_queued = 1; tx->tx_deadline = ktime_add_ns(ktime_get(), timeout_ns); {code} and lnet_get_lnd_timeout() returns the new default of 5. Does this mean we went from 150 to 5! In the documentation it says that lnet_lnd_timeout derived from lnet_transaction_timeout and retry_count. But that is not getting set for tx->tx_deadline. Am I reading the code correctly? |