79 lines · plain
1===========================================2Automatically bind swap device to numa node3===========================================4 5If the system has more than one swap device and swap device has the node6information, we can make use of this information to decide which swap7device to use in get_swap_pages() to get better performance.8 9 10How to use this feature11=======================12 13Swap device has priority and that decides the order of it to be used. To make14use of automatically binding, there is no need to manipulate priority settings15for swap devices. e.g. on a 2 node machine, assume 2 swap devices swapA and16swapB, with swapA attached to node 0 and swapB attached to node 1, are going17to be swapped on. Simply swapping them on by doing::18 19 # swapon /dev/swapA20 # swapon /dev/swapB21 22Then node 0 will use the two swap devices in the order of swapA then swapB and23node 1 will use the two swap devices in the order of swapB then swapA. Note24that the order of them being swapped on doesn't matter.25 26A more complex example on a 4 node machine. Assume 6 swap devices are going to27be swapped on: swapA and swapB are attached to node 0, swapC is attached to28node 1, swapD and swapE are attached to node 2 and swapF is attached to node3.29The way to swap them on is the same as above::30 31 # swapon /dev/swapA32 # swapon /dev/swapB33 # swapon /dev/swapC34 # swapon /dev/swapD35 # swapon /dev/swapE36 # swapon /dev/swapF37 38Then node 0 will use them in the order of::39 40 swapA/swapB -> swapC -> swapD -> swapE -> swapF41 42swapA and swapB will be used in a round robin mode before any other swap device.43 44node 1 will use them in the order of::45 46 swapC -> swapA -> swapB -> swapD -> swapE -> swapF47 48node 2 will use them in the order of::49 50 swapD/swapE -> swapA -> swapB -> swapC -> swapF51 52Similaly, swapD and swapE will be used in a round robin mode before any53other swap devices.54 55node 3 will use them in the order of::56 57 swapF -> swapA -> swapB -> swapC -> swapD -> swapE58 59 60Implementation details61======================62 63The current code uses a priority based list, swap_avail_list, to decide64which swap device to use and if multiple swap devices share the same65priority, they are used round robin. This change here replaces the single66global swap_avail_list with a per-numa-node list, i.e. for each numa node,67it sees its own priority based list of available swap devices. Swap68device's priority can be promoted on its matching node's swap_avail_list.69 70The current swap device's priority is set as: user can set a >=0 value,71or the system will pick one starting from -1 then downwards. The priority72value in the swap_avail_list is the negated value of the swap device's73due to plist being sorted from low to high. The new policy doesn't change74the semantics for priority >=0 cases, the previous starting from -1 then75downwards now becomes starting from -2 then downwards and -1 is reserved76as the promoted value. So if multiple swap devices are attached to the same77node, they will all be promoted to priority -1 on that node's plist and will78be used round robin before any other swap devices.79