Based on kernel version 4.16.1. Page generated on 2018-04-09 11:52 EST.
1 CPUSETS 2 ------- 3 4 Copyright (C) 2004 BULL SA. 5 Written by Simon.Derr@bull.net 6 7 Portions Copyright (c) 2004-2006 Silicon Graphics, Inc. 8 Modified by Paul Jackson <firstname.lastname@example.org> 9 Modified by Christoph Lameter <email@example.com> 10 Modified by Paul Menage <firstname.lastname@example.org> 11 Modified by Hidetoshi Seto <email@example.com> 12 13 CONTENTS: 14 ========= 15 16 1. Cpusets 17 1.1 What are cpusets ? 18 1.2 Why are cpusets needed ? 19 1.3 How are cpusets implemented ? 20 1.4 What are exclusive cpusets ? 21 1.5 What is memory_pressure ? 22 1.6 What is memory spread ? 23 1.7 What is sched_load_balance ? 24 1.8 What is sched_relax_domain_level ? 25 1.9 How do I use cpusets ? 26 2. Usage Examples and Syntax 27 2.1 Basic Usage 28 2.2 Adding/removing cpus 29 2.3 Setting flags 30 2.4 Attaching processes 31 3. Questions 32 4. Contact 33 34 1. Cpusets 35 ========== 36 37 1.1 What are cpusets ? 38 ---------------------- 39 40 Cpusets provide a mechanism for assigning a set of CPUs and Memory 41 Nodes to a set of tasks. In this document "Memory Node" refers to 42 an on-line node that contains memory. 43 44 Cpusets constrain the CPU and Memory placement of tasks to only 45 the resources within a task's current cpuset. They form a nested 46 hierarchy visible in a virtual file system. These are the essential 47 hooks, beyond what is already present, required to manage dynamic 48 job placement on large systems. 49 50 Cpusets use the generic cgroup subsystem described in 51 Documentation/cgroup-v1/cgroups.txt. 52 53 Requests by a task, using the sched_setaffinity(2) system call to 54 include CPUs in its CPU affinity mask, and using the mbind(2) and 55 set_mempolicy(2) system calls to include Memory Nodes in its memory 56 policy, are both filtered through that task's cpuset, filtering out any 57 CPUs or Memory Nodes not in that cpuset. The scheduler will not 58 schedule a task on a CPU that is not allowed in its cpus_allowed 59 vector, and the kernel page allocator will not allocate a page on a 60 node that is not allowed in the requesting task's mems_allowed vector. 61 62 User level code may create and destroy cpusets by name in the cgroup 63 virtual file system, manage the attributes and permissions of these 64 cpusets and which CPUs and Memory Nodes are assigned to each cpuset, 65 specify and query to which cpuset a task is assigned, and list the 66 task pids assigned to a cpuset. 67 68 69 1.2 Why are cpusets needed ? 70 ---------------------------- 71 72 The management of large computer systems, with many processors (CPUs), 73 complex memory cache hierarchies and multiple Memory Nodes having 74 non-uniform access times (NUMA) presents additional challenges for 75 the efficient scheduling and memory placement of processes. 76 77 Frequently more modest sized systems can be operated with adequate 78 efficiency just by letting the operating system automatically share 79 the available CPU and Memory resources amongst the requesting tasks. 80 81 But larger systems, which benefit more from careful processor and 82 memory placement to reduce memory access times and contention, 83 and which typically represent a larger investment for the customer, 84 can benefit from explicitly placing jobs on properly sized subsets of 85 the system. 86 87 This can be especially valuable on: 88 89 * Web Servers running multiple instances of the same web application, 90 * Servers running different applications (for instance, a web server 91 and a database), or 92 * NUMA systems running large HPC applications with demanding 93 performance characteristics. 94 95 These subsets, or "soft partitions" must be able to be dynamically 96 adjusted, as the job mix changes, without impacting other concurrently 97 executing jobs. The location of the running jobs pages may also be moved 98 when the memory locations are changed. 99 100 The kernel cpuset patch provides the minimum essential kernel 101 mechanisms required to efficiently implement such subsets. It 102 leverages existing CPU and Memory Placement facilities in the Linux 103 kernel to avoid any additional impact on the critical scheduler or 104 memory allocator code. 105 106 107 1.3 How are cpusets implemented ? 108 --------------------------------- 109 110 Cpusets provide a Linux kernel mechanism to constrain which CPUs and 111 Memory Nodes are used by a process or set of processes. 112 113 The Linux kernel already has a pair of mechanisms to specify on which 114 CPUs a task may be scheduled (sched_setaffinity) and on which Memory 115 Nodes it may obtain memory (mbind, set_mempolicy). 116 117 Cpusets extends these two mechanisms as follows: 118 119 - Cpusets are sets of allowed CPUs and Memory Nodes, known to the 120 kernel. 121 - Each task in the system is attached to a cpuset, via a pointer 122 in the task structure to a reference counted cgroup structure. 123 - Calls to sched_setaffinity are filtered to just those CPUs 124 allowed in that task's cpuset. 125 - Calls to mbind and set_mempolicy are filtered to just 126 those Memory Nodes allowed in that task's cpuset. 127 - The root cpuset contains all the systems CPUs and Memory 128 Nodes. 129 - For any cpuset, one can define child cpusets containing a subset 130 of the parents CPU and Memory Node resources. 131 - The hierarchy of cpusets can be mounted at /dev/cpuset, for 132 browsing and manipulation from user space. 133 - A cpuset may be marked exclusive, which ensures that no other 134 cpuset (except direct ancestors and descendants) may contain 135 any overlapping CPUs or Memory Nodes. 136 - You can list all the tasks (by pid) attached to any cpuset. 137 138 The implementation of cpusets requires a few, simple hooks 139 into the rest of the kernel, none in performance critical paths: 140 141 - in init/main.c, to initialize the root cpuset at system boot. 142 - in fork and exit, to attach and detach a task from its cpuset. 143 - in sched_setaffinity, to mask the requested CPUs by what's 144 allowed in that task's cpuset. 145 - in sched.c migrate_live_tasks(), to keep migrating tasks within 146 the CPUs allowed by their cpuset, if possible. 147 - in the mbind and set_mempolicy system calls, to mask the requested 148 Memory Nodes by what's allowed in that task's cpuset. 149 - in page_alloc.c, to restrict memory to allowed nodes. 150 - in vmscan.c, to restrict page recovery to the current cpuset. 151 152 You should mount the "cgroup" filesystem type in order to enable 153 browsing and modifying the cpusets presently known to the kernel. No 154 new system calls are added for cpusets - all support for querying and 155 modifying cpusets is via this cpuset file system. 156 157 The /proc/<pid>/status file for each task has four added lines, 158 displaying the task's cpus_allowed (on which CPUs it may be scheduled) 159 and mems_allowed (on which Memory Nodes it may obtain memory), 160 in the two formats seen in the following example: 161 162 Cpus_allowed: ffffffff,ffffffff,ffffffff,ffffffff 163 Cpus_allowed_list: 0-127 164 Mems_allowed: ffffffff,ffffffff 165 Mems_allowed_list: 0-63 166 167 Each cpuset is represented by a directory in the cgroup file system 168 containing (on top of the standard cgroup files) the following 169 files describing that cpuset: 170 171 - cpuset.cpus: list of CPUs in that cpuset 172 - cpuset.mems: list of Memory Nodes in that cpuset 173 - cpuset.memory_migrate flag: if set, move pages to cpusets nodes 174 - cpuset.cpu_exclusive flag: is cpu placement exclusive? 175 - cpuset.mem_exclusive flag: is memory placement exclusive? 176 - cpuset.mem_hardwall flag: is memory allocation hardwalled 177 - cpuset.memory_pressure: measure of how much paging pressure in cpuset 178 - cpuset.memory_spread_page flag: if set, spread page cache evenly on allowed nodes 179 - cpuset.memory_spread_slab flag: if set, spread slab cache evenly on allowed nodes 180 - cpuset.sched_load_balance flag: if set, load balance within CPUs on that cpuset 181 - cpuset.sched_relax_domain_level: the searching range when migrating tasks 182 183 In addition, only the root cpuset has the following file: 184 - cpuset.memory_pressure_enabled flag: compute memory_pressure? 185 186 New cpusets are created using the mkdir system call or shell 187 command. The properties of a cpuset, such as its flags, allowed 188 CPUs and Memory Nodes, and attached tasks, are modified by writing 189 to the appropriate file in that cpusets directory, as listed above. 190 191 The named hierarchical structure of nested cpusets allows partitioning 192 a large system into nested, dynamically changeable, "soft-partitions". 193 194 The attachment of each task, automatically inherited at fork by any 195 children of that task, to a cpuset allows organizing the work load 196 on a system into related sets of tasks such that each set is constrained 197 to using the CPUs and Memory Nodes of a particular cpuset. A task 198 may be re-attached to any other cpuset, if allowed by the permissions 199 on the necessary cpuset file system directories. 200 201 Such management of a system "in the large" integrates smoothly with 202 the detailed placement done on individual tasks and memory regions 203 using the sched_setaffinity, mbind and set_mempolicy system calls. 204 205 The following rules apply to each cpuset: 206 207 - Its CPUs and Memory Nodes must be a subset of its parents. 208 - It can't be marked exclusive unless its parent is. 209 - If its cpu or memory is exclusive, they may not overlap any sibling. 210 211 These rules, and the natural hierarchy of cpusets, enable efficient 212 enforcement of the exclusive guarantee, without having to scan all 213 cpusets every time any of them change to ensure nothing overlaps a 214 exclusive cpuset. Also, the use of a Linux virtual file system (vfs) 215 to represent the cpuset hierarchy provides for a familiar permission 216 and name space for cpusets, with a minimum of additional kernel code. 217 218 The cpus and mems files in the root (top_cpuset) cpuset are 219 read-only. The cpus file automatically tracks the value of 220 cpu_online_mask using a CPU hotplug notifier, and the mems file 221 automatically tracks the value of node_states[N_MEMORY]--i.e., 222 nodes with memory--using the cpuset_track_online_nodes() hook. 223 224 225 1.4 What are exclusive cpusets ? 226 -------------------------------- 227 228 If a cpuset is cpu or mem exclusive, no other cpuset, other than 229 a direct ancestor or descendant, may share any of the same CPUs or 230 Memory Nodes. 231 232 A cpuset that is cpuset.mem_exclusive *or* cpuset.mem_hardwall is "hardwalled", 233 i.e. it restricts kernel allocations for page, buffer and other data 234 commonly shared by the kernel across multiple users. All cpusets, 235 whether hardwalled or not, restrict allocations of memory for user 236 space. This enables configuring a system so that several independent 237 jobs can share common kernel data, such as file system pages, while 238 isolating each job's user allocation in its own cpuset. To do this, 239 construct a large mem_exclusive cpuset to hold all the jobs, and 240 construct child, non-mem_exclusive cpusets for each individual job. 241 Only a small amount of typical kernel memory, such as requests from 242 interrupt handlers, is allowed to be taken outside even a 243 mem_exclusive cpuset. 244 245 246 1.5 What is memory_pressure ? 247 ----------------------------- 248 The memory_pressure of a cpuset provides a simple per-cpuset metric 249 of the rate that the tasks in a cpuset are attempting to free up in 250 use memory on the nodes of the cpuset to satisfy additional memory 251 requests. 252 253 This enables batch managers monitoring jobs running in dedicated 254 cpusets to efficiently detect what level of memory pressure that job 255 is causing. 256 257 This is useful both on tightly managed systems running a wide mix of 258 submitted jobs, which may choose to terminate or re-prioritize jobs that 259 are trying to use more memory than allowed on the nodes assigned to them, 260 and with tightly coupled, long running, massively parallel scientific 261 computing jobs that will dramatically fail to meet required performance 262 goals if they start to use more memory than allowed to them. 263 264 This mechanism provides a very economical way for the batch manager 265 to monitor a cpuset for signs of memory pressure. It's up to the 266 batch manager or other user code to decide what to do about it and 267 take action. 268 269 ==> Unless this feature is enabled by writing "1" to the special file 270 /dev/cpuset/memory_pressure_enabled, the hook in the rebalance 271 code of __alloc_pages() for this metric reduces to simply noticing 272 that the cpuset_memory_pressure_enabled flag is zero. So only 273 systems that enable this feature will compute the metric. 274 275 Why a per-cpuset, running average: 276 277 Because this meter is per-cpuset, rather than per-task or mm, 278 the system load imposed by a batch scheduler monitoring this 279 metric is sharply reduced on large systems, because a scan of 280 the tasklist can be avoided on each set of queries. 281 282 Because this meter is a running average, instead of an accumulating 283 counter, a batch scheduler can detect memory pressure with a 284 single read, instead of having to read and accumulate results 285 for a period of time. 286 287 Because this meter is per-cpuset rather than per-task or mm, 288 the batch scheduler can obtain the key information, memory 289 pressure in a cpuset, with a single read, rather than having to 290 query and accumulate results over all the (dynamically changing) 291 set of tasks in the cpuset. 292 293 A per-cpuset simple digital filter (requires a spinlock and 3 words 294 of data per-cpuset) is kept, and updated by any task attached to that 295 cpuset, if it enters the synchronous (direct) page reclaim code. 296 297 A per-cpuset file provides an integer number representing the recent 298 (half-life of 10 seconds) rate of direct page reclaims caused by 299 the tasks in the cpuset, in units of reclaims attempted per second, 300 times 1000. 301 302 303 1.6 What is memory spread ? 304 --------------------------- 305 There are two boolean flag files per cpuset that control where the 306 kernel allocates pages for the file system buffers and related in 307 kernel data structures. They are called 'cpuset.memory_spread_page' and 308 'cpuset.memory_spread_slab'. 309 310 If the per-cpuset boolean flag file 'cpuset.memory_spread_page' is set, then 311 the kernel will spread the file system buffers (page cache) evenly 312 over all the nodes that the faulting task is allowed to use, instead 313 of preferring to put those pages on the node where the task is running. 314 315 If the per-cpuset boolean flag file 'cpuset.memory_spread_slab' is set, 316 then the kernel will spread some file system related slab caches, 317 such as for inodes and dentries evenly over all the nodes that the 318 faulting task is allowed to use, instead of preferring to put those 319 pages on the node where the task is running. 320 321 The setting of these flags does not affect anonymous data segment or 322 stack segment pages of a task. 323 324 By default, both kinds of memory spreading are off, and memory 325 pages are allocated on the node local to where the task is running, 326 except perhaps as modified by the task's NUMA mempolicy or cpuset 327 configuration, so long as sufficient free memory pages are available. 328 329 When new cpusets are created, they inherit the memory spread settings 330 of their parent. 331 332 Setting memory spreading causes allocations for the affected page 333 or slab caches to ignore the task's NUMA mempolicy and be spread 334 instead. Tasks using mbind() or set_mempolicy() calls to set NUMA 335 mempolicies will not notice any change in these calls as a result of 336 their containing task's memory spread settings. If memory spreading 337 is turned off, then the currently specified NUMA mempolicy once again 338 applies to memory page allocations. 339 340 Both 'cpuset.memory_spread_page' and 'cpuset.memory_spread_slab' are boolean flag 341 files. By default they contain "0", meaning that the feature is off 342 for that cpuset. If a "1" is written to that file, then that turns 343 the named feature on. 344 345 The implementation is simple. 346 347 Setting the flag 'cpuset.memory_spread_page' turns on a per-process flag 348 PFA_SPREAD_PAGE for each task that is in that cpuset or subsequently 349 joins that cpuset. The page allocation calls for the page cache 350 is modified to perform an inline check for this PFA_SPREAD_PAGE task 351 flag, and if set, a call to a new routine cpuset_mem_spread_node() 352 returns the node to prefer for the allocation. 353 354 Similarly, setting 'cpuset.memory_spread_slab' turns on the flag 355 PFA_SPREAD_SLAB, and appropriately marked slab caches will allocate 356 pages from the node returned by cpuset_mem_spread_node(). 357 358 The cpuset_mem_spread_node() routine is also simple. It uses the 359 value of a per-task rotor cpuset_mem_spread_rotor to select the next 360 node in the current task's mems_allowed to prefer for the allocation. 361 362 This memory placement policy is also known (in other contexts) as 363 round-robin or interleave. 364 365 This policy can provide substantial improvements for jobs that need 366 to place thread local data on the corresponding node, but that need 367 to access large file system data sets that need to be spread across 368 the several nodes in the jobs cpuset in order to fit. Without this 369 policy, especially for jobs that might have one thread reading in the 370 data set, the memory allocation across the nodes in the jobs cpuset 371 can become very uneven. 372 373 1.7 What is sched_load_balance ? 374 -------------------------------- 375 376 The kernel scheduler (kernel/sched/core.c) automatically load balances 377 tasks. If one CPU is underutilized, kernel code running on that 378 CPU will look for tasks on other more overloaded CPUs and move those 379 tasks to itself, within the constraints of such placement mechanisms 380 as cpusets and sched_setaffinity. 381 382 The algorithmic cost of load balancing and its impact on key shared 383 kernel data structures such as the task list increases more than 384 linearly with the number of CPUs being balanced. So the scheduler 385 has support to partition the systems CPUs into a number of sched 386 domains such that it only load balances within each sched domain. 387 Each sched domain covers some subset of the CPUs in the system; 388 no two sched domains overlap; some CPUs might not be in any sched 389 domain and hence won't be load balanced. 390 391 Put simply, it costs less to balance between two smaller sched domains 392 than one big one, but doing so means that overloads in one of the 393 two domains won't be load balanced to the other one. 394 395 By default, there is one sched domain covering all CPUs, including those 396 marked isolated using the kernel boot time "isolcpus=" argument. However, 397 the isolated CPUs will not participate in load balancing, and will not 398 have tasks running on them unless explicitly assigned. 399 400 This default load balancing across all CPUs is not well suited for 401 the following two situations: 402 1) On large systems, load balancing across many CPUs is expensive. 403 If the system is managed using cpusets to place independent jobs 404 on separate sets of CPUs, full load balancing is unnecessary. 405 2) Systems supporting realtime on some CPUs need to minimize 406 system overhead on those CPUs, including avoiding task load 407 balancing if that is not needed. 408 409 When the per-cpuset flag "cpuset.sched_load_balance" is enabled (the default 410 setting), it requests that all the CPUs in that cpusets allowed 'cpuset.cpus' 411 be contained in a single sched domain, ensuring that load balancing 412 can move a task (not otherwised pinned, as by sched_setaffinity) 413 from any CPU in that cpuset to any other. 414 415 When the per-cpuset flag "cpuset.sched_load_balance" is disabled, then the 416 scheduler will avoid load balancing across the CPUs in that cpuset, 417 --except-- in so far as is necessary because some overlapping cpuset 418 has "sched_load_balance" enabled. 419 420 So, for example, if the top cpuset has the flag "cpuset.sched_load_balance" 421 enabled, then the scheduler will have one sched domain covering all 422 CPUs, and the setting of the "cpuset.sched_load_balance" flag in any other 423 cpusets won't matter, as we're already fully load balancing. 424 425 Therefore in the above two situations, the top cpuset flag 426 "cpuset.sched_load_balance" should be disabled, and only some of the smaller, 427 child cpusets have this flag enabled. 428 429 When doing this, you don't usually want to leave any unpinned tasks in 430 the top cpuset that might use non-trivial amounts of CPU, as such tasks 431 may be artificially constrained to some subset of CPUs, depending on 432 the particulars of this flag setting in descendant cpusets. Even if 433 such a task could use spare CPU cycles in some other CPUs, the kernel 434 scheduler might not consider the possibility of load balancing that 435 task to that underused CPU. 436 437 Of course, tasks pinned to a particular CPU can be left in a cpuset 438 that disables "cpuset.sched_load_balance" as those tasks aren't going anywhere 439 else anyway. 440 441 There is an impedance mismatch here, between cpusets and sched domains. 442 Cpusets are hierarchical and nest. Sched domains are flat; they don't 443 overlap and each CPU is in at most one sched domain. 444 445 It is necessary for sched domains to be flat because load balancing 446 across partially overlapping sets of CPUs would risk unstable dynamics 447 that would be beyond our understanding. So if each of two partially 448 overlapping cpusets enables the flag 'cpuset.sched_load_balance', then we 449 form a single sched domain that is a superset of both. We won't move 450 a task to a CPU outside its cpuset, but the scheduler load balancing 451 code might waste some compute cycles considering that possibility. 452 453 This mismatch is why there is not a simple one-to-one relation 454 between which cpusets have the flag "cpuset.sched_load_balance" enabled, 455 and the sched domain configuration. If a cpuset enables the flag, it 456 will get balancing across all its CPUs, but if it disables the flag, 457 it will only be assured of no load balancing if no other overlapping 458 cpuset enables the flag. 459 460 If two cpusets have partially overlapping 'cpuset.cpus' allowed, and only 461 one of them has this flag enabled, then the other may find its 462 tasks only partially load balanced, just on the overlapping CPUs. 463 This is just the general case of the top_cpuset example given a few 464 paragraphs above. In the general case, as in the top cpuset case, 465 don't leave tasks that might use non-trivial amounts of CPU in 466 such partially load balanced cpusets, as they may be artificially 467 constrained to some subset of the CPUs allowed to them, for lack of 468 load balancing to the other CPUs. 469 470 CPUs in "cpuset.isolcpus" were excluded from load balancing by the 471 isolcpus= kernel boot option, and will never be load balanced regardless 472 of the value of "cpuset.sched_load_balance" in any cpuset. 473 474 1.7.1 sched_load_balance implementation details. 475 ------------------------------------------------ 476 477 The per-cpuset flag 'cpuset.sched_load_balance' defaults to enabled (contrary 478 to most cpuset flags.) When enabled for a cpuset, the kernel will 479 ensure that it can load balance across all the CPUs in that cpuset 480 (makes sure that all the CPUs in the cpus_allowed of that cpuset are 481 in the same sched domain.) 482 483 If two overlapping cpusets both have 'cpuset.sched_load_balance' enabled, 484 then they will be (must be) both in the same sched domain. 485 486 If, as is the default, the top cpuset has 'cpuset.sched_load_balance' enabled, 487 then by the above that means there is a single sched domain covering 488 the whole system, regardless of any other cpuset settings. 489 490 The kernel commits to user space that it will avoid load balancing 491 where it can. It will pick as fine a granularity partition of sched 492 domains as it can while still providing load balancing for any set 493 of CPUs allowed to a cpuset having 'cpuset.sched_load_balance' enabled. 494 495 The internal kernel cpuset to scheduler interface passes from the 496 cpuset code to the scheduler code a partition of the load balanced 497 CPUs in the system. This partition is a set of subsets (represented 498 as an array of struct cpumask) of CPUs, pairwise disjoint, that cover 499 all the CPUs that must be load balanced. 500 501 The cpuset code builds a new such partition and passes it to the 502 scheduler sched domain setup code, to have the sched domains rebuilt 503 as necessary, whenever: 504 - the 'cpuset.sched_load_balance' flag of a cpuset with non-empty CPUs changes, 505 - or CPUs come or go from a cpuset with this flag enabled, 506 - or 'cpuset.sched_relax_domain_level' value of a cpuset with non-empty CPUs 507 and with this flag enabled changes, 508 - or a cpuset with non-empty CPUs and with this flag enabled is removed, 509 - or a cpu is offlined/onlined. 510 511 This partition exactly defines what sched domains the scheduler should 512 setup - one sched domain for each element (struct cpumask) in the 513 partition. 514 515 The scheduler remembers the currently active sched domain partitions. 516 When the scheduler routine partition_sched_domains() is invoked from 517 the cpuset code to update these sched domains, it compares the new 518 partition requested with the current, and updates its sched domains, 519 removing the old and adding the new, for each change. 520 521 522 1.8 What is sched_relax_domain_level ? 523 -------------------------------------- 524 525 In sched domain, the scheduler migrates tasks in 2 ways; periodic load 526 balance on tick, and at time of some schedule events. 527 528 When a task is woken up, scheduler try to move the task on idle CPU. 529 For example, if a task A running on CPU X activates another task B 530 on the same CPU X, and if CPU Y is X's sibling and performing idle, 531 then scheduler migrate task B to CPU Y so that task B can start on 532 CPU Y without waiting task A on CPU X. 533 534 And if a CPU run out of tasks in its runqueue, the CPU try to pull 535 extra tasks from other busy CPUs to help them before it is going to 536 be idle. 537 538 Of course it takes some searching cost to find movable tasks and/or 539 idle CPUs, the scheduler might not search all CPUs in the domain 540 every time. In fact, in some architectures, the searching ranges on 541 events are limited in the same socket or node where the CPU locates, 542 while the load balance on tick searches all. 543 544 For example, assume CPU Z is relatively far from CPU X. Even if CPU Z 545 is idle while CPU X and the siblings are busy, scheduler can't migrate 546 woken task B from X to Z since it is out of its searching range. 547 As the result, task B on CPU X need to wait task A or wait load balance 548 on the next tick. For some applications in special situation, waiting 549 1 tick may be too long. 550 551 The 'cpuset.sched_relax_domain_level' file allows you to request changing 552 this searching range as you like. This file takes int value which 553 indicates size of searching range in levels ideally as follows, 554 otherwise initial value -1 that indicates the cpuset has no request. 555 556 -1 : no request. use system default or follow request of others. 557 0 : no search. 558 1 : search siblings (hyperthreads in a core). 559 2 : search cores in a package. 560 3 : search cpus in a node [= system wide on non-NUMA system] 561 4 : search nodes in a chunk of node [on NUMA system] 562 5 : search system wide [on NUMA system] 563 564 The system default is architecture dependent. The system default 565 can be changed using the relax_domain_level= boot parameter. 566 567 This file is per-cpuset and affect the sched domain where the cpuset 568 belongs to. Therefore if the flag 'cpuset.sched_load_balance' of a cpuset 569 is disabled, then 'cpuset.sched_relax_domain_level' have no effect since 570 there is no sched domain belonging the cpuset. 571 572 If multiple cpusets are overlapping and hence they form a single sched 573 domain, the largest value among those is used. Be careful, if one 574 requests 0 and others are -1 then 0 is used. 575 576 Note that modifying this file will have both good and bad effects, 577 and whether it is acceptable or not depends on your situation. 578 Don't modify this file if you are not sure. 579 580 If your situation is: 581 - The migration costs between each cpu can be assumed considerably 582 small(for you) due to your special application's behavior or 583 special hardware support for CPU cache etc. 584 - The searching cost doesn't have impact(for you) or you can make 585 the searching cost enough small by managing cpuset to compact etc. 586 - The latency is required even it sacrifices cache hit rate etc. 587 then increasing 'sched_relax_domain_level' would benefit you. 588 589 590 1.9 How do I use cpusets ? 591 -------------------------- 592 593 In order to minimize the impact of cpusets on critical kernel 594 code, such as the scheduler, and due to the fact that the kernel 595 does not support one task updating the memory placement of another 596 task directly, the impact on a task of changing its cpuset CPU 597 or Memory Node placement, or of changing to which cpuset a task 598 is attached, is subtle. 599 600 If a cpuset has its Memory Nodes modified, then for each task attached 601 to that cpuset, the next time that the kernel attempts to allocate 602 a page of memory for that task, the kernel will notice the change 603 in the task's cpuset, and update its per-task memory placement to 604 remain within the new cpusets memory placement. If the task was using 605 mempolicy MPOL_BIND, and the nodes to which it was bound overlap with 606 its new cpuset, then the task will continue to use whatever subset 607 of MPOL_BIND nodes are still allowed in the new cpuset. If the task 608 was using MPOL_BIND and now none of its MPOL_BIND nodes are allowed 609 in the new cpuset, then the task will be essentially treated as if it 610 was MPOL_BIND bound to the new cpuset (even though its NUMA placement, 611 as queried by get_mempolicy(), doesn't change). If a task is moved 612 from one cpuset to another, then the kernel will adjust the task's 613 memory placement, as above, the next time that the kernel attempts 614 to allocate a page of memory for that task. 615 616 If a cpuset has its 'cpuset.cpus' modified, then each task in that cpuset 617 will have its allowed CPU placement changed immediately. Similarly, 618 if a task's pid is written to another cpuset's 'tasks' file, then its 619 allowed CPU placement is changed immediately. If such a task had been 620 bound to some subset of its cpuset using the sched_setaffinity() call, 621 the task will be allowed to run on any CPU allowed in its new cpuset, 622 negating the effect of the prior sched_setaffinity() call. 623 624 In summary, the memory placement of a task whose cpuset is changed is 625 updated by the kernel, on the next allocation of a page for that task, 626 and the processor placement is updated immediately. 627 628 Normally, once a page is allocated (given a physical page 629 of main memory) then that page stays on whatever node it 630 was allocated, so long as it remains allocated, even if the 631 cpusets memory placement policy 'cpuset.mems' subsequently changes. 632 If the cpuset flag file 'cpuset.memory_migrate' is set true, then when 633 tasks are attached to that cpuset, any pages that task had 634 allocated to it on nodes in its previous cpuset are migrated 635 to the task's new cpuset. The relative placement of the page within 636 the cpuset is preserved during these migration operations if possible. 637 For example if the page was on the second valid node of the prior cpuset 638 then the page will be placed on the second valid node of the new cpuset. 639 640 Also if 'cpuset.memory_migrate' is set true, then if that cpuset's 641 'cpuset.mems' file is modified, pages allocated to tasks in that 642 cpuset, that were on nodes in the previous setting of 'cpuset.mems', 643 will be moved to nodes in the new setting of 'mems.' 644 Pages that were not in the task's prior cpuset, or in the cpuset's 645 prior 'cpuset.mems' setting, will not be moved. 646 647 There is an exception to the above. If hotplug functionality is used 648 to remove all the CPUs that are currently assigned to a cpuset, 649 then all the tasks in that cpuset will be moved to the nearest ancestor 650 with non-empty cpus. But the moving of some (or all) tasks might fail if 651 cpuset is bound with another cgroup subsystem which has some restrictions 652 on task attaching. In this failing case, those tasks will stay 653 in the original cpuset, and the kernel will automatically update 654 their cpus_allowed to allow all online CPUs. When memory hotplug 655 functionality for removing Memory Nodes is available, a similar exception 656 is expected to apply there as well. In general, the kernel prefers to 657 violate cpuset placement, over starving a task that has had all 658 its allowed CPUs or Memory Nodes taken offline. 659 660 There is a second exception to the above. GFP_ATOMIC requests are 661 kernel internal allocations that must be satisfied, immediately. 662 The kernel may drop some request, in rare cases even panic, if a 663 GFP_ATOMIC alloc fails. If the request cannot be satisfied within 664 the current task's cpuset, then we relax the cpuset, and look for 665 memory anywhere we can find it. It's better to violate the cpuset 666 than stress the kernel. 667 668 To start a new job that is to be contained within a cpuset, the steps are: 669 670 1) mkdir /sys/fs/cgroup/cpuset 671 2) mount -t cgroup -ocpuset cpuset /sys/fs/cgroup/cpuset 672 3) Create the new cpuset by doing mkdir's and write's (or echo's) in 673 the /sys/fs/cgroup/cpuset virtual file system. 674 4) Start a task that will be the "founding father" of the new job. 675 5) Attach that task to the new cpuset by writing its pid to the 676 /sys/fs/cgroup/cpuset tasks file for that cpuset. 677 6) fork, exec or clone the job tasks from this founding father task. 678 679 For example, the following sequence of commands will setup a cpuset 680 named "Charlie", containing just CPUs 2 and 3, and Memory Node 1, 681 and then start a subshell 'sh' in that cpuset: 682 683 mount -t cgroup -ocpuset cpuset /sys/fs/cgroup/cpuset 684 cd /sys/fs/cgroup/cpuset 685 mkdir Charlie 686 cd Charlie 687 /bin/echo 2-3 > cpuset.cpus 688 /bin/echo 1 > cpuset.mems 689 /bin/echo $$ > tasks 690 sh 691 # The subshell 'sh' is now running in cpuset Charlie 692 # The next line should display '/Charlie' 693 cat /proc/self/cpuset 694 695 There are ways to query or modify cpusets: 696 - via the cpuset file system directly, using the various cd, mkdir, echo, 697 cat, rmdir commands from the shell, or their equivalent from C. 698 - via the C library libcpuset. 699 - via the C library libcgroup. 700 (http://sourceforge.net/projects/libcg/) 701 - via the python application cset. 702 (http://code.google.com/p/cpuset/) 703 704 The sched_setaffinity calls can also be done at the shell prompt using 705 SGI's runon or Robert Love's taskset. The mbind and set_mempolicy 706 calls can be done at the shell prompt using the numactl command 707 (part of Andi Kleen's numa package). 708 709 2. Usage Examples and Syntax 710 ============================ 711 712 2.1 Basic Usage 713 --------------- 714 715 Creating, modifying, using the cpusets can be done through the cpuset 716 virtual filesystem. 717 718 To mount it, type: 719 # mount -t cgroup -o cpuset cpuset /sys/fs/cgroup/cpuset 720 721 Then under /sys/fs/cgroup/cpuset you can find a tree that corresponds to the 722 tree of the cpusets in the system. For instance, /sys/fs/cgroup/cpuset 723 is the cpuset that holds the whole system. 724 725 If you want to create a new cpuset under /sys/fs/cgroup/cpuset: 726 # cd /sys/fs/cgroup/cpuset 727 # mkdir my_cpuset 728 729 Now you want to do something with this cpuset. 730 # cd my_cpuset 731 732 In this directory you can find several files: 733 # ls 734 cgroup.clone_children cpuset.memory_pressure 735 cgroup.event_control cpuset.memory_spread_page 736 cgroup.procs cpuset.memory_spread_slab 737 cpuset.cpu_exclusive cpuset.mems 738 cpuset.cpus cpuset.sched_load_balance 739 cpuset.mem_exclusive cpuset.sched_relax_domain_level 740 cpuset.mem_hardwall notify_on_release 741 cpuset.memory_migrate tasks 742 743 Reading them will give you information about the state of this cpuset: 744 the CPUs and Memory Nodes it can use, the processes that are using 745 it, its properties. By writing to these files you can manipulate 746 the cpuset. 747 748 Set some flags: 749 # /bin/echo 1 > cpuset.cpu_exclusive 750 751 Add some cpus: 752 # /bin/echo 0-7 > cpuset.cpus 753 754 Add some mems: 755 # /bin/echo 0-7 > cpuset.mems 756 757 Now attach your shell to this cpuset: 758 # /bin/echo $$ > tasks 759 760 You can also create cpusets inside your cpuset by using mkdir in this 761 directory. 762 # mkdir my_sub_cs 763 764 To remove a cpuset, just use rmdir: 765 # rmdir my_sub_cs 766 This will fail if the cpuset is in use (has cpusets inside, or has 767 processes attached). 768 769 Note that for legacy reasons, the "cpuset" filesystem exists as a 770 wrapper around the cgroup filesystem. 771 772 The command 773 774 mount -t cpuset X /sys/fs/cgroup/cpuset 775 776 is equivalent to 777 778 mount -t cgroup -ocpuset,noprefix X /sys/fs/cgroup/cpuset 779 echo "/sbin/cpuset_release_agent" > /sys/fs/cgroup/cpuset/release_agent 780 781 2.2 Adding/removing cpus 782 ------------------------ 783 784 This is the syntax to use when writing in the cpus or mems files 785 in cpuset directories: 786 787 # /bin/echo 1-4 > cpuset.cpus -> set cpus list to cpus 1,2,3,4 788 # /bin/echo 1,2,3,4 > cpuset.cpus -> set cpus list to cpus 1,2,3,4 789 790 To add a CPU to a cpuset, write the new list of CPUs including the 791 CPU to be added. To add 6 to the above cpuset: 792 793 # /bin/echo 1-4,6 > cpuset.cpus -> set cpus list to cpus 1,2,3,4,6 794 795 Similarly to remove a CPU from a cpuset, write the new list of CPUs 796 without the CPU to be removed. 797 798 To remove all the CPUs: 799 800 # /bin/echo "" > cpuset.cpus -> clear cpus list 801 802 2.3 Setting flags 803 ----------------- 804 805 The syntax is very simple: 806 807 # /bin/echo 1 > cpuset.cpu_exclusive -> set flag 'cpuset.cpu_exclusive' 808 # /bin/echo 0 > cpuset.cpu_exclusive -> unset flag 'cpuset.cpu_exclusive' 809 810 2.4 Attaching processes 811 ----------------------- 812 813 # /bin/echo PID > tasks 814 815 Note that it is PID, not PIDs. You can only attach ONE task at a time. 816 If you have several tasks to attach, you have to do it one after another: 817 818 # /bin/echo PID1 > tasks 819 # /bin/echo PID2 > tasks 820 ... 821 # /bin/echo PIDn > tasks 822 823 824 3. Questions 825 ============ 826 827 Q: what's up with this '/bin/echo' ? 828 A: bash's builtin 'echo' command does not check calls to write() against 829 errors. If you use it in the cpuset file system, you won't be 830 able to tell whether a command succeeded or failed. 831 832 Q: When I attach processes, only the first of the line gets really attached ! 833 A: We can only return one error code per call to write(). So you should also 834 put only ONE pid. 835 836 4. Contact 837 ========== 838 839 Web: http://www.bullopensource.org/cpuset