-
Bug
-
Resolution: Unresolved
-
Normal
-
None
-
rhel-7.9, rhel-7.9.z
-
None
-
Normal
-
sst_pt_libraries
-
ssg_platform_tools
-
1
-
False
-
-
-
x86_64
What were you trying to do that didn't work?
When cu is running program, it happened that the multiple threads are caught in the pthread_rwlock_rdlock of the same lock object:
–
#0 0x00002b76c4b8954d in __lll_lock_wait () from traffic_server-libs/lib64/libpthread.so.0
#1 0x00002b76c4b861b2 in pthread_rwlock_rdlock () from traffic_server-libs/lib64/libpthread.so.0
–
It seems to be a bug in glibc/libpthread
Please provide the package NVR for which bug is seen:
How reproducible:
everytime
Steps to reproduce
We found a deadlock scenario in NPTL's rwlock implementation,
relating to additional scheduling dependencies which NPTL imposes on
concurrent readers.
It happens when facing sufficient congestion between both
read- and write-locking candidates queued.
Expected results
Deadlock should not occur
Actual results
Deadlock occurring causing system to get hung and need to be restarted