Whamcloud - gitweb
LU-17258 socklnd: stop connecting on too many retries 55/53955/3
authorSerguei Smirnov <ssmirnov@whamcloud.com>
Wed, 7 Feb 2024 18:48:08 +0000 (10:48 -0800)
committerOleg Drokin <green@whamcloud.com>
Fri, 23 Feb 2024 07:17:06 +0000 (07:17 +0000)
commit02caf7170762d97dac4f367651addc7d90b6eb32
treefe6c3862eda5cc12d8992b6624d444885284f891
parenta6886dba0ed8a622c9831cd33d310d933492c72d
LU-17258 socklnd: stop connecting on too many retries

If peer repeatedly rejects connection requests with EALREADY,
assume that it doesn't support as many connections as we're trying
to create. Make sure to stop connecting to the peer altogether and
either continue with already created connections if there's at least
one of each type, or fail.

This helps avoid the assertion:

"ASSERTION( (wanted & ((((1UL))) << (3))) != 0 ) failed"

Test-Parameters: trivial testlist=sanity-lnet
Fixes: 5afe3b053 ("LU-17258 socklnd: ensure connection type established upon race")
Signed-off-by: Serguei Smirnov <ssmirnov@whamcloud.com>
Change-Id: I6072e91cc36544fc2f56c91cd78f6637cf82ecbc
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53955
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Frank Sehr <fsehr@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Cyril Bordage <cbordage@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
lnet/klnds/socklnd/socklnd.c
lnet/klnds/socklnd/socklnd_cb.c