Patrick Thomas wrote: > > > Uhh, Terry, neither form of SHM uses KVA. Either pageable or physically > > > backed. The memory is only mapped into processes and is NOT mapped into > > > KVA anywhere. (*) > > > > You and Alfred are right. > > > > It looks like this was corrected by John Dyson, shortly after he > > had checked it in to work that way. > > So the conclusion is that: > > sysctl kern.ipc.shm_use_phys=1 > > Is not even potentially a magic bullet for the issue I am seeing (since > either way, all those greatly increased SHM/SEM settings I added are not > using KVA) ??
It will save some KVA, especially after forks, as Peter pointed out. But it's unlikely at this point, given the off-list issues, that your problem is KVA space, particularly since it's happening at the same time very day. -- Terry To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
