[LU-16260] LNet: enforce a positive minimum for lnd_timeout Created: 21/Oct/22  Updated: 04/Apr/23  Resolved: 04/Apr/23

Status: Resolved
Project: Lustre
Component/s: None
Affects Version/s: None
Fix Version/s: Lustre 2.16.0

Type: Bug Priority: Minor
Reporter: Serguei Smirnov Assignee: Frank Sehr
Resolution: Fixed Votes: 0
Labels: None

Severity: 3
Rank (Obsolete): 9223372036854775807

 Description   

lnd_timeout is calculated using the following formula:

lnd_timeout = (lnet_transaction_timeout - 1) / (retry_count + 1) 

currently lnet_transaction_timeout is allowed to be as low as 1 which makes derived 0 lnd_transaction timeout value possible, for example:

# lnetctl set transaction_timeout 1
# lnetctl global show
global:
    numa_range: 0
    max_interfaces: 200
    discovery: 1
    drop_asym_route: 0
    retry_count: 0
    transaction_timeout: 1
    health_sensitivity: 100
    recovery_interval: 1
    router_sensitivity: 100
    lnd_timeout: 0
    response_tracking: 3
    recovery_limit: 0
    max_recovery_ping_interval: 900

There probably should be reasonable minimal positive thresholds defined for both lnd_timeout and lnet_transaction_timeout.



 Comments   
Comment by Gerrit Updater [ 09/Mar/23 ]

"Frank Sehr <fsehr@whamcloud.com>" uploaded a new patch: https://review.whamcloud.com/c/fs/lustre-release/+/50236
Subject: LU-16260 lnet: enforce a positive minimum for lnd_timeout
Project: fs/lustre-release
Branch: master
Current Patch Set: 1
Commit: f780c2863d1186bba5683a4002748b6f8af5a298

Comment by Gerrit Updater [ 04/Apr/23 ]

"Oleg Drokin <green@whamcloud.com>" merged in patch https://review.whamcloud.com/c/fs/lustre-release/+/50236/
Subject: LU-16260 lnet: enforce a positive minimum for lnd_timeout
Project: fs/lustre-release
Branch: master
Current Patch Set:
Commit: 3b4bd39beb95c8988dd95b26e22b2cfae6f99f7e

Comment by Peter Jones [ 04/Apr/23 ]

Landed for 2.16

Generated at Sat Feb 10 03:25:25 UTC 2024 using Jira 9.4.14#940014-sha1:734e6822bbf0d45eff9af51f82432957f73aa32c.