Hi all, Suppose, one for loop is going to be run 20 times. The 1st 10 loops are run on 1st cpu/core of a multi-cpu/multi-core system. Because of scheduling, the last 10 loops are executed on 2nd cpu/core. Now, if in each loop, one slave write on a PCI device are done. Now, what will be the ordering scenario of all 20 PCI slave writes. There will be ordering among first 10, as they are executed on same cpu/core. There will be ordering among next 10 also, as they are executed on same cpu/core. But what about ordering between first set & next set of 10 slave writes ? Whether first set & next set can get mixed ? Kindly give more info on this. If, i am missing somethings basic, kindly update me. TIA, Yogeshwar -- To unsubscribe from this list: send an email with "unsubscribe kernelnewbies" to ecartis@xxxxxxxxxxxx Please read the FAQ at http://kernelnewbies.org/FAQ
