diff options
Diffstat (limited to 'tools/cgroup')
| -rw-r--r-- | tools/cgroup/Makefile | 11 | ||||
| -rw-r--r-- | tools/cgroup/cgroup_event_listener.c | 83 | ||||
| -rw-r--r-- | tools/cgroup/iocost_monitor.py | 79 | ||||
| -rw-r--r-- | tools/cgroup/memcg_shrinker.py | 70 | ||||
| -rw-r--r-- | tools/cgroup/memcg_slabinfo.py | 226 |
5 files changed, 331 insertions, 138 deletions
diff --git a/tools/cgroup/Makefile b/tools/cgroup/Makefile deleted file mode 100644 index ffca068e4a76..000000000000 --- a/tools/cgroup/Makefile +++ /dev/null @@ -1,11 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# Makefile for cgroup tools - -CFLAGS = -Wall -Wextra - -all: cgroup_event_listener -%: %.c - $(CC) $(CFLAGS) -o $@ $^ - -clean: - $(RM) cgroup_event_listener diff --git a/tools/cgroup/cgroup_event_listener.c b/tools/cgroup/cgroup_event_listener.c deleted file mode 100644 index 3d70dc831a76..000000000000 --- a/tools/cgroup/cgroup_event_listener.c +++ /dev/null @@ -1,83 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * cgroup_event_listener.c - Simple listener of cgroup events - * - * Copyright (C) Kirill A. Shutemov <kirill@shutemov.name> - */ - -#include <assert.h> -#include <err.h> -#include <errno.h> -#include <fcntl.h> -#include <libgen.h> -#include <limits.h> -#include <stdio.h> -#include <string.h> -#include <unistd.h> - -#include <sys/eventfd.h> - -#define USAGE_STR "Usage: cgroup_event_listener <path-to-control-file> <args>" - -int main(int argc, char **argv) -{ - int efd = -1; - int cfd = -1; - int event_control = -1; - char event_control_path[PATH_MAX]; - char line[LINE_MAX]; - int ret; - - if (argc != 3) - errx(1, "%s", USAGE_STR); - - cfd = open(argv[1], O_RDONLY); - if (cfd == -1) - err(1, "Cannot open %s", argv[1]); - - ret = snprintf(event_control_path, PATH_MAX, "%s/cgroup.event_control", - dirname(argv[1])); - if (ret >= PATH_MAX) - errx(1, "Path to cgroup.event_control is too long"); - - event_control = open(event_control_path, O_WRONLY); - if (event_control == -1) - err(1, "Cannot open %s", event_control_path); - - efd = eventfd(0, 0); - if (efd == -1) - err(1, "eventfd() failed"); - - ret = snprintf(line, LINE_MAX, "%d %d %s", efd, cfd, argv[2]); - if (ret >= LINE_MAX) - errx(1, "Arguments string is too long"); - - ret = write(event_control, line, strlen(line) + 1); - if (ret == -1) - err(1, "Cannot write to cgroup.event_control"); - - while (1) { - uint64_t result; - - ret = read(efd, &result, sizeof(result)); - if (ret == -1) { - if (errno == EINTR) - continue; - err(1, "Cannot read from eventfd"); - } - assert(ret == sizeof(result)); - - ret = access(event_control_path, W_OK); - if ((ret == -1) && (errno == ENOENT)) { - puts("The cgroup seems to have removed."); - break; - } - - if (ret == -1) - err(1, "cgroup.event_control is not accessible any more"); - - printf("%s %s: crossed\n", argv[1], argv[2]); - } - - return 0; -} diff --git a/tools/cgroup/iocost_monitor.py b/tools/cgroup/iocost_monitor.py index 3c21de88af9e..933c750b319b 100644 --- a/tools/cgroup/iocost_monitor.py +++ b/tools/cgroup/iocost_monitor.py @@ -45,8 +45,7 @@ except: err('The kernel does not have iocost enabled') IOC_RUNNING = prog['IOC_RUNNING'].value_() -NR_USAGE_SLOTS = prog['NR_USAGE_SLOTS'].value_() -HWEIGHT_WHOLE = prog['HWEIGHT_WHOLE'].value_() +WEIGHT_ONE = prog['WEIGHT_ONE'].value_() VTIME_PER_SEC = prog['VTIME_PER_SEC'].value_() VTIME_PER_USEC = prog['VTIME_PER_USEC'].value_() AUTOP_SSD_FAST = prog['AUTOP_SSD_FAST'].value_() @@ -62,6 +61,11 @@ autop_names = { } class BlkgIterator: + def __init__(self, root_blkcg, q_id, include_dying=False): + self.include_dying = include_dying + self.blkgs = [] + self.walk(root_blkcg, q_id, '') + def blkcg_name(blkcg): return blkcg.css.cgroup.kn.name.string_().decode('utf-8') @@ -83,11 +87,6 @@ class BlkgIterator: blkcg.css.children.address_of_(), 'css.sibling'): self.walk(c, q_id, path) - def __init__(self, root_blkcg, q_id, include_dying=False): - self.include_dying = include_dying - self.blkgs = [] - self.walk(root_blkcg, q_id, '') - def __iter__(self): return iter(self.blkgs) @@ -100,7 +99,8 @@ class IocStat: self.period_ms = ioc.period_us.value_() / 1_000 self.period_at = ioc.period_at.value_() / 1_000_000 self.vperiod_at = ioc.period_at_vtime.value_() / VTIME_PER_SEC - self.vrate_pct = ioc.vtime_rate.counter.value_() * 100 / VTIME_PER_USEC + self.vrate_pct = ioc.vtime_base_rate.value_() * 100 / VTIME_PER_USEC + self.ivrate_pct = ioc.vtime_rate.counter.value_() * 100 / VTIME_PER_USEC self.busy_level = ioc.busy_level.value_() self.autop_idx = ioc.autop_idx.value_() self.user_cost_model = ioc.user_cost_model.value_() @@ -120,7 +120,9 @@ class IocStat: 'period_at' : self.period_at, 'period_vtime_at' : self.vperiod_at, 'busy_level' : self.busy_level, - 'vrate_pct' : self.vrate_pct, } + 'vrate_pct' : self.vrate_pct, + 'ivrate_pct' : self.ivrate_pct, + } def table_preamble_str(self): state = ('RUN' if self.running else 'IDLE') if self.enabled else 'OFF' @@ -128,7 +130,7 @@ class IocStat: f'per={self.period_ms}ms ' \ f'cur_per={self.period_at:.3f}:v{self.vperiod_at:.3f} ' \ f'busy={self.busy_level:+3} ' \ - f'vrate={self.vrate_pct:6.2f}% ' \ + f'vrate={self.vrate_pct:6.2f}%:{self.ivrate_pct:6.2f}% ' \ f'params={self.autop_name}' if self.user_cost_model or self.user_qos_params: output += f'({"C" if self.user_cost_model else ""}{"Q" if self.user_qos_params else ""})' @@ -136,7 +138,7 @@ class IocStat: def table_header_str(self): return f'{"":25} active {"weight":>9} {"hweight%":>13} {"inflt%":>6} ' \ - f'{"dbt":>3} {"delay":>6} {"usages%"}' + f'{"usage%":>6} {"wait":>7} {"debt":>7} {"delay":>7}' class IocgStat: def __init__(self, iocg): @@ -144,11 +146,11 @@ class IocgStat: blkg = iocg.pd.blkg self.is_active = not list_empty(iocg.active_list.address_of_()) - self.weight = iocg.weight.value_() - self.active = iocg.active.value_() - self.inuse = iocg.inuse.value_() - self.hwa_pct = iocg.hweight_active.value_() * 100 / HWEIGHT_WHOLE - self.hwi_pct = iocg.hweight_inuse.value_() * 100 / HWEIGHT_WHOLE + self.weight = iocg.weight.value_() / WEIGHT_ONE + self.active = iocg.active.value_() / WEIGHT_ONE + self.inuse = iocg.inuse.value_() / WEIGHT_ONE + self.hwa_pct = iocg.hweight_active.value_() * 100 / WEIGHT_ONE + self.hwi_pct = iocg.hweight_inuse.value_() * 100 / WEIGHT_ONE self.address = iocg.value_() vdone = iocg.done_vtime.counter.value_() @@ -160,23 +162,15 @@ class IocgStat: else: self.inflight_pct = 0 - # vdebt used to be an atomic64_t and is now u64, support both - try: - self.debt_ms = iocg.abs_vdebt.counter.value_() / VTIME_PER_USEC / 1000 - except: - self.debt_ms = iocg.abs_vdebt.value_() / VTIME_PER_USEC / 1000 - - self.use_delay = blkg.use_delay.counter.value_() - self.delay_ms = blkg.delay_nsec.counter.value_() / 1_000_000 - - usage_idx = iocg.usage_idx.value_() - self.usages = [] - self.usage = 0 - for i in range(NR_USAGE_SLOTS): - usage = iocg.usages[(usage_idx + i) % NR_USAGE_SLOTS].value_() - upct = usage * 100 / HWEIGHT_WHOLE - self.usages.append(upct) - self.usage = max(self.usage, upct) + self.usage = (100 * iocg.usage_delta_us.value_() / + ioc.period_us.value_()) if self.active else 0 + self.wait_ms = (iocg.stat.wait_us.value_() - + iocg.last_stat.wait_us.value_()) / 1000 + self.debt_ms = iocg.abs_vdebt.value_() / VTIME_PER_USEC / 1000 + if blkg.use_delay.counter.value_() != 0: + self.delay_ms = blkg.delay_nsec.counter.value_() / 1_000_000 + else: + self.delay_ms = 0 def dict(self, now, path): out = { 'cgroup' : path, @@ -188,26 +182,23 @@ class IocgStat: 'hweight_active_pct' : self.hwa_pct, 'hweight_inuse_pct' : self.hwi_pct, 'inflight_pct' : self.inflight_pct, + 'usage_pct' : self.usage, + 'wait_ms' : self.wait_ms, 'debt_ms' : self.debt_ms, - 'use_delay' : self.use_delay, 'delay_ms' : self.delay_ms, - 'usage_pct' : self.usage, 'address' : self.address } - for i in range(len(self.usages)): - out[f'usage_pct_{i}'] = str(self.usages[i]) return out def table_row_str(self, path): out = f'{path[-28:]:28} ' \ f'{"*" if self.is_active else " "} ' \ - f'{self.inuse:5}/{self.active:5} ' \ + f'{round(self.inuse):5}/{round(self.active):5} ' \ f'{self.hwi_pct:6.2f}/{self.hwa_pct:6.2f} ' \ f'{self.inflight_pct:6.2f} ' \ - f'{min(math.ceil(self.debt_ms), 999):3} ' \ - f'{min(self.use_delay, 99):2}*'\ - f'{min(math.ceil(self.delay_ms), 999):03} ' - for u in self.usages: - out += f'{min(round(u), 999):03d}:' + f'{min(self.usage, 999):6.2f} ' \ + f'{self.wait_ms:7.2f} ' \ + f'{self.debt_ms:7.2f} ' \ + f'{self.delay_ms:7.2f}' out = out.rstrip(':') return out @@ -237,7 +228,7 @@ ioc = None for i, ptr in radix_tree_for_each(blkcg_root.blkg_tree.address_of_()): blkg = drgn.Object(prog, 'struct blkcg_gq', address=ptr) try: - if devname == blkg.q.kobj.parent.name.string_().decode('utf-8'): + if devname == blkg.q.mq_kobj.parent.name.string_().decode('utf-8'): q_id = blkg.q.id.value_() if blkg.pd[plid]: root_iocg = container_of(blkg.pd[plid], 'struct ioc_gq', 'pd') diff --git a/tools/cgroup/memcg_shrinker.py b/tools/cgroup/memcg_shrinker.py new file mode 100644 index 000000000000..e81c3017ada9 --- /dev/null +++ b/tools/cgroup/memcg_shrinker.py @@ -0,0 +1,70 @@ +#!/usr/bin/env python3 +# +# Copyright (C) 2022 Roman Gushchin <roman.gushchin@linux.dev> +# Copyright (C) 2022 Meta + +import os +import argparse + + +def scan_cgroups(cgroup_root): + cgroups = {} + + for root, subdirs, _ in os.walk(cgroup_root): + for cgroup in subdirs: + path = os.path.join(root, cgroup) + ino = os.stat(path).st_ino + cgroups[ino] = path + + # (memcg ino, path) + return cgroups + + +def scan_shrinkers(shrinker_debugfs): + shrinkers = [] + + for root, subdirs, _ in os.walk(shrinker_debugfs): + for shrinker in subdirs: + count_path = os.path.join(root, shrinker, "count") + with open(count_path) as f: + for line in f.readlines(): + items = line.split(' ') + ino = int(items[0]) + # (count, shrinker, memcg ino) + shrinkers.append((int(items[1]), shrinker, ino)) + return shrinkers + + +def main(): + parser = argparse.ArgumentParser(description='Display biggest shrinkers') + parser.add_argument('-n', '--lines', type=int, help='Number of lines to print') + + args = parser.parse_args() + + cgroups = scan_cgroups("/sys/fs/cgroup/") + shrinkers = scan_shrinkers("/sys/kernel/debug/shrinker/") + shrinkers.sort(reverse = True, key = lambda x: x[0]) + + n = 0 + for s in shrinkers: + count, name, ino = (s[0], s[1], s[2]) + if count == 0: + break + + if ino == 0 or ino == 1: + cg = "/" + else: + try: + cg = cgroups[ino] + except KeyError: + cg = "unknown (%d)" % ino + + print("%-8s %-20s %s" % (count, name, cg)) + + n += 1 + if args.lines and n >= args.lines: + break + + +if __name__ == '__main__': + main() diff --git a/tools/cgroup/memcg_slabinfo.py b/tools/cgroup/memcg_slabinfo.py new file mode 100644 index 000000000000..1d3a90d93fe2 --- /dev/null +++ b/tools/cgroup/memcg_slabinfo.py @@ -0,0 +1,226 @@ +#!/usr/bin/env drgn +# +# Copyright (C) 2020 Roman Gushchin <guro@fb.com> +# Copyright (C) 2020 Facebook + +from os import stat +import argparse +import sys + +from drgn.helpers.linux import list_for_each_entry, list_empty +from drgn.helpers.linux import for_each_page +from drgn.helpers.linux.cpumask import for_each_online_cpu +from drgn.helpers.linux.percpu import per_cpu_ptr +from drgn import container_of, FaultError, Object, cast + + +DESC = """ +This is a drgn script to provide slab statistics for memory cgroups. +It supports cgroup v2 and v1 and can emulate memory.kmem.slabinfo +interface of cgroup v1. +For drgn, visit https://github.com/osandov/drgn. +""" + + +MEMCGS = {} + +OO_SHIFT = 16 +OO_MASK = ((1 << OO_SHIFT) - 1) + + +def err(s): + print('slabinfo.py: error: %s' % s, file=sys.stderr, flush=True) + sys.exit(1) + + +def find_memcg_ids(css=prog['root_mem_cgroup'].css, prefix=''): + if not list_empty(css.children.address_of_()): + for css in list_for_each_entry('struct cgroup_subsys_state', + css.children.address_of_(), + 'sibling'): + name = prefix + '/' + css.cgroup.kn.name.string_().decode('utf-8') + memcg = container_of(css, 'struct mem_cgroup', 'css') + MEMCGS[css.cgroup.kn.id.value_()] = memcg + find_memcg_ids(css, name) + + +def is_root_cache(s): + try: + return False if s.memcg_params.root_cache else True + except AttributeError: + return True + + +def cache_name(s): + if is_root_cache(s): + return s.name.string_().decode('utf-8') + else: + return s.memcg_params.root_cache.name.string_().decode('utf-8') + + +# SLUB + +def oo_order(s): + return s.oo.x >> OO_SHIFT + + +def oo_objects(s): + return s.oo.x & OO_MASK + + +def count_partial(n, fn): + nr_objs = 0 + for slab in list_for_each_entry('struct slab', n.partial.address_of_(), + 'slab_list'): + nr_objs += fn(slab) + return nr_objs + + +def count_free(slab): + return slab.objects - slab.inuse + + +def slub_get_slabinfo(s, cfg): + nr_slabs = 0 + nr_objs = 0 + nr_free = 0 + + for node in range(cfg['nr_nodes']): + n = s.node[node] + nr_slabs += n.nr_slabs.counter.value_() + nr_objs += n.total_objects.counter.value_() + nr_free += count_partial(n, count_free) + + return {'active_objs': nr_objs - nr_free, + 'num_objs': nr_objs, + 'active_slabs': nr_slabs, + 'num_slabs': nr_slabs, + 'objects_per_slab': oo_objects(s), + 'cache_order': oo_order(s), + 'limit': 0, + 'batchcount': 0, + 'shared': 0, + 'shared_avail': 0} + + +def cache_show(s, cfg, objs): + if cfg['allocator'] == 'SLUB': + sinfo = slub_get_slabinfo(s, cfg) + else: + err('SLAB isn\'t supported yet') + + if cfg['shared_slab_pages']: + sinfo['active_objs'] = objs + sinfo['num_objs'] = objs + + print('%-17s %6lu %6lu %6u %4u %4d' + ' : tunables %4u %4u %4u' + ' : slabdata %6lu %6lu %6lu' % ( + cache_name(s), sinfo['active_objs'], sinfo['num_objs'], + s.size, sinfo['objects_per_slab'], 1 << sinfo['cache_order'], + sinfo['limit'], sinfo['batchcount'], sinfo['shared'], + sinfo['active_slabs'], sinfo['num_slabs'], + sinfo['shared_avail'])) + + +def detect_kernel_config(): + cfg = {} + + cfg['nr_nodes'] = prog['nr_online_nodes'].value_() + + if prog.type('struct kmem_cache').members[1].name == 'flags': + cfg['allocator'] = 'SLUB' + elif prog.type('struct kmem_cache').members[1].name == 'batchcount': + cfg['allocator'] = 'SLAB' + else: + err('Can\'t determine the slab allocator') + + cfg['shared_slab_pages'] = False + try: + if prog.type('struct obj_cgroup'): + cfg['shared_slab_pages'] = True + except: + pass + + return cfg + + +def for_each_slab(prog): + PGSlab = 1 << prog.constant('PG_slab') + PGHead = 1 << prog.constant('PG_head') + + for page in for_each_page(prog): + try: + if page.flags.value_() & PGSlab: + yield cast('struct slab *', page) + except FaultError: + pass + + +def main(): + parser = argparse.ArgumentParser(description=DESC, + formatter_class= + argparse.RawTextHelpFormatter) + parser.add_argument('cgroup', metavar='CGROUP', + help='Target memory cgroup') + args = parser.parse_args() + + try: + cgroup_id = stat(args.cgroup).st_ino + find_memcg_ids() + memcg = MEMCGS[cgroup_id] + except KeyError: + err('Can\'t find the memory cgroup') + + cfg = detect_kernel_config() + + print('# name <active_objs> <num_objs> <objsize> <objperslab> <pagesperslab>' + ' : tunables <limit> <batchcount> <sharedfactor>' + ' : slabdata <active_slabs> <num_slabs> <sharedavail>') + + if cfg['shared_slab_pages']: + obj_cgroups = set() + stats = {} + caches = {} + + # find memcg pointers belonging to the specified cgroup + obj_cgroups.add(memcg.objcg.value_()) + for ptr in list_for_each_entry('struct obj_cgroup', + memcg.objcg_list.address_of_(), + 'list'): + obj_cgroups.add(ptr.value_()) + + # look over all slab folios and look for objects belonging + # to the given memory cgroup + for slab in for_each_slab(prog): + objcg_vec_raw = slab.memcg_data.value_() + if objcg_vec_raw == 0: + continue + cache = slab.slab_cache + if not cache: + continue + addr = cache.value_() + caches[addr] = cache + # clear the lowest bit to get the true obj_cgroups + objcg_vec = Object(prog, 'struct obj_cgroup **', + value=objcg_vec_raw & ~1) + + if addr not in stats: + stats[addr] = 0 + + for i in range(oo_objects(cache)): + if objcg_vec[i].value_() in obj_cgroups: + stats[addr] += 1 + + for addr in caches: + if stats[addr] > 0: + cache_show(caches[addr], cfg, stats[addr]) + + else: + for s in list_for_each_entry('struct kmem_cache', + memcg.kmem_caches.address_of_(), + 'memcg_params.kmem_caches_node'): + cache_show(s, cfg, None) + + +main() |