| /Linux-v5.10/Documentation/accounting/ |
| D | taskstats-struct.rst | 9 1) Common and basic accounting fields
11 the common fields and basic accounting fields are collected for
13 2) Delay accounting fields
16 /* Delay accounting fields start */
20 /* Delay accounting fields end */
23 3) Extended accounting fields
26 /* Extended accounting fields start */
30 /* Extended accounting fields end */
36 5) Time accounting for SMT machines
38 6) Extended delay accounting fields for memory reclaim
[all …]
|
| D | delay-accounting.rst | 2 Delay accounting
9 The per-task delay accounting functionality measures
38 Delay accounting uses the taskstats interface which is described
41 statistics. The delay accounting functionality populates specific fields of
46 for a description of the fields pertaining to delay accounting.
60 The getdelays.c userspace utility in tools/accounting directory allows simple
72 Delay accounting is enabled by default at boot up.
|
| D | index.rst | 11 delay-accounting
|
| D | taskstats.rst | 12 - unified interface for multiple accounting subsystems
13 - extensibility for use by future accounting patches
48 for reporting delay accounting statistics. Users can register cpumasks,
62 struct taskstats is the common accounting structure for both per-pid and
63 per-tgid data. It is versioned and can be extended by each accounting subsystem
156 struct too much, requiring disparate userspace accounting utilities to
|
| D | cgroupstats.rst | 21 NOTE: We currently rely on delay accounting for extracting information
|
| /Linux-v5.10/drivers/md/bcache/ |
| D | stats.c | 208 mark_cache_stats(&dc->accounting.collector, hit, bypass); in bch_mark_cache_accounting()
209 mark_cache_stats(&c->accounting.collector, hit, bypass); in bch_mark_cache_accounting()
216 atomic_inc(&dc->accounting.collector.cache_readaheads); in bch_mark_cache_readahead()
217 atomic_inc(&c->accounting.collector.cache_readaheads); in bch_mark_cache_readahead()
224 atomic_inc(&dc->accounting.collector.cache_miss_collisions); in bch_mark_cache_miss_collision()
225 atomic_inc(&c->accounting.collector.cache_miss_collisions); in bch_mark_cache_miss_collision()
231 atomic_add(sectors, &dc->accounting.collector.sectors_bypassed); in bch_mark_sectors_bypassed()
232 atomic_add(sectors, &c->accounting.collector.sectors_bypassed); in bch_mark_sectors_bypassed()
|
| D | bcache.h | 363 struct cache_accounting accounting; member
514 struct cache_accounting accounting; member
|
| /Linux-v5.10/Documentation/admin-guide/cgroup-v1/ |
| D | cpuacct.rst | 5 The CPU accounting controller is used to group tasks using cgroups and
8 The CPU accounting controller supports multi-hierarchy groups. An accounting
16 With the above step, the initial or the parent accounting group becomes
23 New accounting groups can be created under the parent group /sys/fs/cgroup::
|
| D | hugetlb.rst | 62 1. Page fault accounting
79 2. Reservation accounting
99 non-HugeTLB memory for example. In the case of page fault accounting, it's very
103 systems is practically impossible with page fault accounting.
|
| D | net_prio.rst | 22 With the above step, the initial group acting as the parent accounting group
44 said traffic set to the value 5. The parent accounting group also has a
|
| D | memory.rst | 46 - accounting anonymous pages, file caches, swap caches usage and limiting them.
49 - hierarchical accounting
132 3. Kernel user memory accounting and slab control
178 The accounting is done as follows: mem_cgroup_charge_common() is invoked to
196 processes, duplicate accounting is carefully avoided.
208 At page migration, accounting information is kept.
311 Kernel memory accounting is enabled for all memory cgroups by default. But
330 every process consumes some stack pages. By accounting into
360 accounting. Kernel memory is completely ignored.
445 The memory.stat file gives accounting information. Now, the number of
[all …]
|
| /Linux-v5.10/arch/powerpc/include/asm/ |
| D | cputime.h | 47 #define get_accounting(tsk) (&get_paca()->accounting)
48 #define raw_get_accounting(tsk) (&local_paca->accounting)
52 #define get_accounting(tsk) (&task_thread_info(tsk)->accounting)
|
| D | thread_info.h | 56 struct cpu_accounting_data accounting; member
|
| D | paca.h | 233 struct cpu_accounting_data accounting; member
|
| /Linux-v5.10/Documentation/features/time/irq-time-acct/ |
| D | arch-support.txt | 4 # description: arch supports precise IRQ time accounting
|
| /Linux-v5.10/Documentation/features/time/virt-cpuacct/ |
| D | arch-support.txt | 4 # description: arch supports precise virtual CPU time accounting
|
| /Linux-v5.10/Documentation/vm/ |
| D | overcommit-accounting.rst | 67 Additional accounting
82 * SHMfs accounting
|
| D | index.rst | 45 overcommit-accounting
|
| /Linux-v5.10/arch/powerpc/kernel/ |
| D | asm-offsets.c | 287 OFFSET(ACCOUNT_STARTTIME, paca_struct, accounting.starttime); in main()
288 OFFSET(ACCOUNT_STARTTIME_USER, paca_struct, accounting.starttime_user); in main()
289 OFFSET(ACCOUNT_USER_TIME, paca_struct, accounting.utime); in main()
290 OFFSET(ACCOUNT_SYSTEM_TIME, paca_struct, accounting.stime); in main()
297 OFFSET(ACCOUNT_STARTTIME, thread_info, accounting.starttime); in main()
298 OFFSET(ACCOUNT_STARTTIME_USER, thread_info, accounting.starttime_user); in main()
299 OFFSET(ACCOUNT_USER_TIME, thread_info, accounting.utime); in main()
300 OFFSET(ACCOUNT_SYSTEM_TIME, thread_info, accounting.stime); in main()
|
| /Linux-v5.10/Documentation/networking/ |
| D | page_pool.rst | 18 accounting.
22 release the DMA mapping and inflight state accounting.
|
| /Linux-v5.10/init/ |
| D | Kconfig | 440 menu "CPU/Task time and stats accounting"
446 prompt "Cputime accounting"
450 # Kind of a stub config for the pure tick based cputime accounting
452 bool "Simple tick based cputime accounting"
455 This is the basic tick based cputime accounting that maintains
462 bool "Deterministic task and CPU time accounting"
467 accounting. This is done by reading a CPU counter on each
471 this also enables accounting of stolen time on logically-partitioned
475 bool "Full dynticks CPU time accounting"
482 Select this option to enable task and CPU time accounting on full
[all …]
|
| /Linux-v5.10/Documentation/core-api/ |
| D | tracepoint.rst | 22 Thus, the purpose of this document is to provide a clear accounting of
|
| /Linux-v5.10/Documentation/ABI/testing/ |
| D | sysfs-block-dm | 37 accounting. This attribute is not applicable to
|
| /Linux-v5.10/drivers/staging/qlge/ |
| D | TODO | 7 * truesize accounting is incorrect (ex: a 9000B frame has skb->truesize 10280
|
| /Linux-v5.10/arch/powerpc/xmon/ |
| D | xmon.c | 2639 DUMP(p, accounting.utime, "%#-*lx"); in dump_one_paca()
2640 DUMP(p, accounting.stime, "%#-*lx"); in dump_one_paca()
2642 DUMP(p, accounting.utime_scaled, "%#-*lx"); in dump_one_paca()
2644 DUMP(p, accounting.starttime, "%#-*lx"); in dump_one_paca()
2645 DUMP(p, accounting.starttime_user, "%#-*lx"); in dump_one_paca()
2647 DUMP(p, accounting.startspurr, "%#-*lx"); in dump_one_paca()
2648 DUMP(p, accounting.utime_sspurr, "%#-*lx"); in dump_one_paca()
2650 DUMP(p, accounting.steal_time, "%#-*lx"); in dump_one_paca()
|
