Oh, and I forgot the details. The mdb command used: mdb -k <<EOF ::walk thread myvar|::print kthread_t t_schedflag|::grep .==0|::eval <myvar=K|:: print kthread_t t_procp->p_user.u_comm EOF
What I found was that the threads where swapped out due to a memory shortfall and they where sleeping. Once swapped out they will not "un-swap" unless they go to running. The number displayed by the mdb output matched the 'w' column from vmstat. -- This message posted from opensolaris.org _______________________________________________ dtrace-discuss mailing list [email protected]
