Add documentation for the newly introduced cpuset.actual_cpus file and describe the new semantics for updating cpusets upon CPU hotplug. Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@xxxxxxxxxxxxxxxxxx> Cc: stable@xxxxxxxxxxxxxxx --- Documentation/cgroups/cpusets.txt | 43 +++++++++++++++++++++++++------------ 1 files changed, 29 insertions(+), 14 deletions(-) diff --git a/Documentation/cgroups/cpusets.txt b/Documentation/cgroups/cpusets.txt index cefd3d8..374b9d2 100644 --- a/Documentation/cgroups/cpusets.txt +++ b/Documentation/cgroups/cpusets.txt @@ -168,7 +168,12 @@ Each cpuset is represented by a directory in the cgroup file system containing (on top of the standard cgroup files) the following files describing that cpuset: - - cpuset.cpus: list of CPUs in that cpuset + - cpuset.cpus: list of CPUs in that cpuset, as set by the user; + the kernel will not alter this upon CPU hotplug; + this file has read/write permissions + - cpuset.actual_cpus: list of CPUs actually available for the tasks in the + cpuset; the kernel can change this in the event of + CPU hotplug; this file is read-only - cpuset.mems: list of Memory Nodes in that cpuset - cpuset.memory_migrate flag: if set, move pages to cpusets nodes - cpuset.cpu_exclusive flag: is cpu placement exclusive? @@ -640,16 +645,25 @@ prior 'cpuset.mems' setting, will not be moved. There is an exception to the above. If hotplug functionality is used to remove all the CPUs that are currently assigned to a cpuset, -then all the tasks in that cpuset will be moved to the nearest ancestor -with non-empty cpus. But the moving of some (or all) tasks might fail if -cpuset is bound with another cgroup subsystem which has some restrictions -on task attaching. In this failing case, those tasks will stay -in the original cpuset, and the kernel will automatically update -their cpus_allowed to allow all online CPUs. When memory hotplug -functionality for removing Memory Nodes is available, a similar exception -is expected to apply there as well. In general, the kernel prefers to -violate cpuset placement, over starving a task that has had all -its allowed CPUs or Memory Nodes taken offline. +then the cpuset hierarchy is traversed, searching for the nearest +ancestor whose cpu mask has atleast one online cpu. Then the tasks in +the empty cpuset will be run on the cpus specified in that ancestor's cpu mask. +Note that during CPU hotplug operations, the tasks in a cpuset will not +be moved from one cpuset to another; only the the cpu mask of that cpuset +will be updated to ensure that there is atleast one online cpu, by trying +to closely resemble the cpu mask of the nearest non-empty ancestor containing +online cpus. + +When memory hotplug functionality for removing Memory Nodes is available, +if all the memory nodes currently assigned to a cpuset are removed via +hotplug, then all the tasks in that cpuset will be moved to the nearest +ancestor with non-empty memory nodes. But the moving of some (or all) +tasks might fail if cpuset is bound with another cgroup subsystem which +has some restrictions on task attaching. In this failing case, those +tasks will stay in the original cpuset, and the kernel will automatically +update their mems_allowed to allow all online nodes. +In general, the kernel prefers to violate cpuset placement, over starving +a task that has had all its allowed CPUs or Memory Nodes taken offline. There is a second exception to the above. GFP_ATOMIC requests are kernel internal allocations that must be satisfied, immediately. @@ -730,9 +744,10 @@ cgroup.event_control cpuset.memory_spread_page cgroup.procs cpuset.memory_spread_slab cpuset.cpu_exclusive cpuset.mems cpuset.cpus cpuset.sched_load_balance -cpuset.mem_exclusive cpuset.sched_relax_domain_level -cpuset.mem_hardwall notify_on_release -cpuset.memory_migrate tasks +cpuset.actual_cpus cpuset.sched_relax_domain_level +cpuset.mem_exclusive notify_on_release +cpuset.mem_hardwall tasks +cpuset.memory_migrate Reading them will give you information about the state of this cpuset: the CPUs and Memory Nodes it can use, the processes that are using -- To unsubscribe from this list: send the line "unsubscribe linux-doc" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
