Home
last modified time | relevance | path

Searched refs:cgroups (Results 1 – 25 of 78) sorted by relevance

1234

/linux-6.15/tools/testing/selftests/bpf/prog_tests/
H A Dcgroup_hierarchical_stats.c54 } cgroups[] = { variable
64 #define N_CGROUPS ARRAY_SIZE(cgroups)
133 fd = create_and_get_cgroup(cgroups[i].path); in setup_cgroups()
137 cgroups[i].fd = fd; in setup_cgroups()
138 cgroups[i].id = get_cgroup_id(cgroups[i].path); in setup_cgroups()
147 close(cgroups[i].fd); in cleanup_cgroups()
175 if (join_parent_cgroup(cgroups[i].path)) in attach_processes()
220 attach_counters[i] = get_attach_counter(cgroups[i].id, in check_attach_counters()
221 cgroups[i].name); in check_attach_counters()
288 err = setup_cgroup_iter(*skel, cgroups[i].fd, cgroups[i].name); in setup_progs()
[all …]
/linux-6.15/tools/cgroup/
H A Dmemcg_shrinker.py11 cgroups = {}
17 cgroups[ino] = path
20 return cgroups
44 cgroups = scan_cgroups("/sys/fs/cgroup/")
58 cg = cgroups[ino]
/linux-6.15/Documentation/admin-guide/cgroup-v1/
H A Dcgroups.rst21 1.1 What are cgroups ?
22 1.2 Why are cgroups needed ?
23 1.3 How are cgroups implemented ?
26 1.6 How do I use cgroups ?
41 1.1 What are cgroups ?
85 1.2 Why are cgroups needed ?
107 cgroups.
152 proliferation of such cgroups.
172 1.3 How are cgroups implemented ?
311 1.6 How do I use cgroups ?
[all …]
H A Dnet_cls.rst9 different priorities to packets from different cgroups.
13 Creating a net_cls cgroups instance creates a net_cls.classid file.
H A Ddevices.rst43 Any task can move itself between cgroups. This clearly won't
60 device cgroups maintain hierarchy by making sure a cgroup never has more
121 not be possible once the device cgroups has children.
126 device cgroups is implemented internally using a behavior (ALLOW, DENY) and a
H A Dfreezer-subsystem.rst9 whole. The cgroup freezer uses cgroups to describe the set of tasks to
57 tasks belonging to the cgroup and all its descendant cgroups. Each
73 to the cgroup or one of its descendant cgroups until the new task is
79 descendant cgroups.
H A Dindex.rst10 cgroups
H A Dmemory.rst293 The reclaim algorithm has not been modified for cgroups, except that
409 2. Prepare the cgroups (see :ref:`Why are cgroups needed?
410 <cgroups-why-needed>` for the background information)::
681 The hierarchy is created by creating the appropriate cgroups in the
745 reclaiming memory for balancing between memory cgroups
765 API (see cgroups.txt). It allows to register multiple memory and memsw
790 API (See cgroups.txt). It allows to register multiple OOM notification
944 .. [3] Emelianov, Pavel. Resource controllers based on process cgroups
946 .. [4] Emelianov, Pavel. RSS controller based on process cgroups (v2)
948 .. [5] Emelianov, Pavel. RSS controller based on process cgroups (v3)
[all …]
/linux-6.15/tools/perf/util/
H A Dcgroup.c569 down_write(&env->cgroups.lock); in cgroup__findnew()
570 cgrp = __cgroup__findnew(&env->cgroups.tree, id, true, path); in cgroup__findnew()
571 up_write(&env->cgroups.lock); in cgroup__findnew()
584 down_read(&env->cgroups.lock); in cgroup__find()
585 cgrp = __cgroup__findnew(&env->cgroups.tree, id, false, NULL); in cgroup__find()
586 up_read(&env->cgroups.lock); in cgroup__find()
595 down_write(&env->cgroups.lock); in perf_env__purge_cgroups()
596 while (!RB_EMPTY_ROOT(&env->cgroups.tree)) { in perf_env__purge_cgroups()
597 node = rb_first(&env->cgroups.tree); in perf_env__purge_cgroups()
600 rb_erase(node, &env->cgroups.tree); in perf_env__purge_cgroups()
[all …]
H A Dbpf_lock_contention.c286 read_all_cgroups(&con->cgroups); in lock_contention_prepare()
519 struct cgroup *cgrp = __cgroup__find(&con->cgroups, cgrp_id); in lock_contention_get_name()
737 while (!RB_EMPTY_ROOT(&con->cgroups)) { in lock_contention_finish()
738 struct rb_node *node = rb_first(&con->cgroups); in lock_contention_finish()
741 rb_erase(node, &con->cgroups); in lock_contention_finish()
H A Dcgroup.h31 int evlist__expand_cgroup(struct evlist *evlist, const char *cgroups,
H A Dlock-contention.h144 struct rb_root cgroups; member
/linux-6.15/tools/testing/selftests/bpf/progs/
H A Dpercpu_alloc_cgrp_local_storage.c30 e = bpf_cgrp_storage_get(&cgrp, task->cgroups->dfl_cgrp, 0, in BPF_PROG()
56 e = bpf_cgrp_storage_get(&cgrp, task->cgroups->dfl_cgrp, 0, 0); in BPF_PROG()
89 e = bpf_cgrp_storage_get(&cgrp, task->cgroups->dfl_cgrp, 0, 0); in BPF_PROG()
H A Drcu_read_lock.c33 struct css_set *cgroups; in get_cgroup_id() local
41 cgroups = task->cgroups; in get_cgroup_id()
42 if (!cgroups) in get_cgroup_id()
44 cgroup_id = cgroups->dfl_cgrp->kn->id; in get_cgroup_id()
H A Dcgrp_ls_recursion.c59 __on_update(task->cgroups->dfl_cgrp); in BPF_PROG()
92 __on_enter(regs, id, task->cgroups->dfl_cgrp); in BPF_PROG()
H A Dcgrp_ls_sleepable.c86 __no_rcu_lock(task->cgroups->dfl_cgrp); in no_rcu_lock()
118 cgrp = task->cgroups->dfl_cgrp; in yes_rcu_lock()
H A Dcgrp_ls_tp_btf.c86 __on_enter(regs, id, task->cgroups->dfl_cgrp); in BPF_PROG()
124 __on_exit(regs, id, task->cgroups->dfl_cgrp); in BPF_PROG()
/linux-6.15/Documentation/admin-guide/
H A Dcgroup-v2.rst432 both cgroups.
850 cgroups.
872 all cgroups.
898 all cgroups.
923 cgroups.
1008 of any ancestor cgroups. If any of ancestor cgroups is frozen, the
1019 create new sub-cgroups.
1234 cgroups.
1717 cgroups.
1782 cgroups.
[all …]
/linux-6.15/tools/perf/Documentation/
H A Dperf-bench.txt128 --cgroups=::
129 Names of cgroups for sender and receiver, separated by a comma.
131 Note that perf doesn't create nor delete the cgroups, so users should
132 make sure that the cgroups exist and are accessible before use.
154 (executing 1000000 pipe operations between cgroups)
/linux-6.15/block/
H A DKconfig.iosched38 (cgroups-v1) or io (cgroups-v2) controller.
/linux-6.15/Documentation/gpu/
H A Ddrm-compute.rst38 controlling resources. The standard kernel way of doing so is cgroups.
40 This creates a third option, using cgroups to prevent eviction. Both GPU and
43 into cgroups, that will allow jobs to run next to each other without
/linux-6.15/tools/perf/util/bpf_skel/
H A Doff_cpu.bpf.c126 return BPF_CORE_READ(t, cgroups, dfl_cgrp, kn, id); in get_cgroup_id()
137 cgrp = BPF_CORE_READ(t, cgroups, subsys[perf_subsys_id], cgroup); in get_cgroup_id()
/linux-6.15/include/linux/
H A Dpsi.h63 rcu_assign_pointer(p->cgroups, to); in cgroup_move_task()
/linux-6.15/Documentation/bpf/
H A Dmap_cgrp_storage.rst9 storage for cgroups. It is only available with ``CONFIG_CGROUPS``.
56 ptr = bpf_cgrp_storage_get(&cgrp_storage, task->cgroups->dfl_cgrp, 0,
H A Dmap_cgroup_storage.rst10 attach to cgroups; the programs are made available by the same Kconfig. The
16 cgroups on their own.
132 that uses the map. A program may be attached to multiple cgroups or have

1234