 |
 |
I don't think it's spurious wake-ups because of how the Semaphore class is implemented in either case. See: https://github.com/xrootd/xrootd/blob/master/src/XrdSys/XrdSysPthread.hh#L345 and https://github.com/xrootd/xrootd/blob/master/src/XrdSys/XrdSysLinuxSemaphore.hh#L169 Personally, I would bet on cache coherency or optimization issues. I would recommend inserting a memory fence before the call to `pSem->Post()`. GCC has a builtin for this. Look for ` __sync_synchronize`. -- You are receiving this because you are subscribed to this thread. Reply to this email directly or view it on GitHub: https://github.com/xrootd/xrootd/issues/404#issuecomment-240899117 ######################################################################## Use REPLY-ALL to reply to list To unsubscribe from the XROOTD-DEV list, click the following link: https://listserv.slac.stanford.edu/cgi-bin/wa?SUBED1=XROOTD-DEV&A=1