From 881f1bb5e25c8982ed963b2d319fc0fc732e55db Mon Sep 17 00:00:00 2001 From: Kemeng Shi Date: Tue, 23 Apr 2024 11:46:42 +0800 Subject: writeback: add wb_monitor.py script to monitor writeback info on bdi Add wb_monitor.py script to monitor writeback information on backing dev which makes it easier and more convenient to observe writeback behaviors of running system. The wb_monitor.py script is written based on wq_monitor.py. Following domain hierarchy is tested: global domain (320G) / \ cgroup domain1(10G) cgroup domain2(10G) | | bdi wb1 wb2 The wb_monitor.py script output is as following: ./wb_monitor.py 252:16 -c writeback reclaimable dirtied written avg_bw 252:16_1 0 0 0 0 102400 252:16_4284 672 820064 9230368 8410304 685612 252:16_4325 896 819840 10491264 9671648 652348 252:16 1568 1639904 19721632 18081952 1440360 writeback reclaimable dirtied written avg_bw 252:16_1 0 0 0 0 102400 252:16_4284 672 820064 9230368 8410304 685612 252:16_4325 896 819840 10491264 9671648 652348 252:16 1568 1639904 19721632 18081952 1440360 ... Link: https://lkml.kernel.org/r/20240423034643.141219-5-shikemeng@huaweicloud.com Signed-off-by: Kemeng Shi Suggested-by: Tejun Heo Cc: Brian Foster Cc: David Howells Cc: David Sterba Cc: Jan Kara Cc: Mateusz Guzik Cc: Matthew Wilcox (Oracle) Cc: SeongJae Park Cc: Stephen Rothwell Signed-off-by: Andrew Morton --- tools/writeback/wb_monitor.py | 172 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 172 insertions(+) create mode 100644 tools/writeback/wb_monitor.py (limited to 'tools/writeback/wb_monitor.py') diff --git a/tools/writeback/wb_monitor.py b/tools/writeback/wb_monitor.py new file mode 100644 index 000000000000..5e3591f1f9a9 --- /dev/null +++ b/tools/writeback/wb_monitor.py @@ -0,0 +1,172 @@ +#!/usr/bin/env drgn +# +# Copyright (C) 2024 Kemeng Shi +# Copyright (C) 2024 Huawei Inc + +desc = """ +This is a drgn script based on wq_monitor.py to monitor writeback info on +backing dev. For more info on drgn, visit https://github.com/osandov/drgn. + + writeback(kB) Amount of dirty pages are currently being written back to + disk. + + reclaimable(kB) Amount of pages are currently reclaimable. + + dirtied(kB) Amount of pages have been dirtied. + + wrttien(kB) Amount of dirty pages have been written back to disk. + + avg_wb(kBps) Smoothly estimated write bandwidth of writing dirty pages + back to disk. +""" + +import signal +import re +import time +import json + +import drgn +from drgn.helpers.linux.list import list_for_each_entry + +import argparse +parser = argparse.ArgumentParser(description=desc, + formatter_class=argparse.RawTextHelpFormatter) +parser.add_argument('bdi', metavar='REGEX', nargs='*', + help='Target backing device name patterns (all if empty)') +parser.add_argument('-i', '--interval', metavar='SECS', type=float, default=1, + help='Monitoring interval (0 to print once and exit)') +parser.add_argument('-j', '--json', action='store_true', + help='Output in json') +parser.add_argument('-c', '--cgroup', action='store_true', + help='show writeback of bdi in cgroup') +args = parser.parse_args() + +bdi_list = prog['bdi_list'] + +WB_RECLAIMABLE = prog['WB_RECLAIMABLE'] +WB_WRITEBACK = prog['WB_WRITEBACK'] +WB_DIRTIED = prog['WB_DIRTIED'] +WB_WRITTEN = prog['WB_WRITTEN'] +NR_WB_STAT_ITEMS = prog['NR_WB_STAT_ITEMS'] + +PAGE_SHIFT = prog['PAGE_SHIFT'] + +def K(x): + return x << (PAGE_SHIFT - 10) + +class Stats: + def dict(self, now): + return { 'timestamp' : now, + 'name' : self.name, + 'writeback' : self.stats[WB_WRITEBACK], + 'reclaimable' : self.stats[WB_RECLAIMABLE], + 'dirtied' : self.stats[WB_DIRTIED], + 'written' : self.stats[WB_WRITTEN], + 'avg_wb' : self.avg_bw, } + + def table_header_str(): + return f'{"":>16} {"writeback":>10} {"reclaimable":>12} ' \ + f'{"dirtied":>9} {"written":>9} {"avg_bw":>9}' + + def table_row_str(self): + out = f'{self.name[-16:]:16} ' \ + f'{self.stats[WB_WRITEBACK]:10} ' \ + f'{self.stats[WB_RECLAIMABLE]:12} ' \ + f'{self.stats[WB_DIRTIED]:9} ' \ + f'{self.stats[WB_WRITTEN]:9} ' \ + f'{self.avg_bw:9} ' + return out + + def show_header(): + if Stats.table_fmt: + print() + print(Stats.table_header_str()) + + def show_stats(self): + if Stats.table_fmt: + print(self.table_row_str()) + else: + print(self.dict(Stats.now)) + +class WbStats(Stats): + def __init__(self, wb): + bdi_name = wb.bdi.dev_name.string_().decode() + # avoid to use bdi.wb.memcg_css which is only defined when + # CONFIG_CGROUP_WRITEBACK is enabled + if wb == wb.bdi.wb.address_of_(): + ino = "1" + else: + ino = str(wb.memcg_css.cgroup.kn.id.value_()) + self.name = bdi_name + '_' + ino + + self.stats = [0] * NR_WB_STAT_ITEMS + for i in range(NR_WB_STAT_ITEMS): + if wb.stat[i].count >= 0: + self.stats[i] = int(K(wb.stat[i].count)) + else: + self.stats[i] = 0 + + self.avg_bw = int(K(wb.avg_write_bandwidth)) + +class BdiStats(Stats): + def __init__(self, bdi): + self.name = bdi.dev_name.string_().decode() + self.stats = [0] * NR_WB_STAT_ITEMS + self.avg_bw = 0 + + def collectStats(self, wb_stats): + for i in range(NR_WB_STAT_ITEMS): + self.stats[i] += wb_stats.stats[i] + + self.avg_bw += wb_stats.avg_bw + +exit_req = False + +def sigint_handler(signr, frame): + global exit_req + exit_req = True + +def main(): + # handle args + Stats.table_fmt = not args.json + interval = args.interval + cgroup = args.cgroup + + re_str = None + if args.bdi: + for r in args.bdi: + if re_str is None: + re_str = r + else: + re_str += '|' + r + + filter_re = re.compile(re_str) if re_str else None + + # monitoring loop + signal.signal(signal.SIGINT, sigint_handler) + + while not exit_req: + Stats.now = time.time() + + Stats.show_header() + for bdi in list_for_each_entry('struct backing_dev_info', bdi_list.address_of_(), 'bdi_list'): + bdi_stats = BdiStats(bdi) + if filter_re and not filter_re.search(bdi_stats.name): + continue + + for wb in list_for_each_entry('struct bdi_writeback', bdi.wb_list.address_of_(), 'bdi_node'): + wb_stats = WbStats(wb) + bdi_stats.collectStats(wb_stats) + if cgroup: + wb_stats.show_stats() + + bdi_stats.show_stats() + if cgroup and Stats.table_fmt: + print() + + if interval == 0: + break + time.sleep(interval) + +if __name__ == "__main__": + main() -- cgit v1.2.3 b7644f28bfedc7d284de15&follow=1'>tls: Fix tls_device handling of partial recordsBoris Pismenny3-33/+9 2019-03-03net: phy: remove gen10g_no_soft_resetHeiner Kallweit5-13/+5 2019-03-03net: phy: don't export gen10g_read_statusHeiner Kallweit2-3/+1 2019-03-03net: phy: remove gen10g_config_initHeiner Kallweit4-17/+0 2019-03-03net: phy: remove gen10g_suspend and gen10g_resumeHeiner Kallweit2-16/+0 2019-03-03net: phy: use genphy_c45_aneg_done in genphy_aneg_doneHeiner Kallweit1-8/+4 2019-03-03fsl/fman: Use vsprintf extension %pMJoe Perches1-3/+1 2019-03-03net: ipv6: add socket option IPV6_ROUTER_ALERT_ISOLATEFrancesco Ruggeri4-1/+19 2019-03-03net: fixup address-space warnings in compat_mc_{get,set}sockopt()Ben Dooks1-4/+4 2019-03-03net: dsa: Use prepare/commit phase in dsa_slave_vlan_rx_add_vid()Florian Fainelli1-3/+6 2019-03-03dpaa2-eth: add XDP_REDIRECT supportIoana Radulescu3-14/+176 2019-03-03dpaa2-eth: Add software annotation typesIoana Radulescu2-22/+40 2019-03-03sch_cake: Simplify logic in cake_select_tin()Toke Høiland-Jørgensen1-38/+23 2019-03-03sch_cake: Permit use of connmarks as tin classifiersKevin Darbyshire-Bryant2-7/+28 2019-03-03sch_cake: Make the dual modes fairerGeorge Amanakis1-29/+63 2019-03-03net: macb: Add support for suspend/resume with full power downHarini Katakam1-2/+38 2019-03-03net: macb: Add pm runtime supportHarini Katakam1-36/+112 2019-03-03net: macb: Support clock management for tsu_clkHarini Katakam2-6/+27 2019-03-03net: macb: Check MDIO state before read/write and use timeoutsHarini Katakam2-6/+29 2019-03-03net: dsa: microchip: add KSZ9893 switch supportTristram Ha3-15/+235 2019-03-03net: dsa: add KSZ9893 switch tagging supportTristram Ha4-0/+38 2019-03-03dt-bindings: net: dsa: document additional Microchip KSZ9477 family switchesTristram Ha1-0/+43 2019-03-02selftests: bpf: break up test_progs - miscStanislav Fomichev11-735/+754 2019-03-02selftests: bpf: break up test_progs - spinlockStanislav Fomichev4-103/+106 2019-03-02selftests: bpf: break up test_progs - tracepointStanislav Fomichev5-427/+431 2019-03-02selftests: bpf: break up test_progs - stackmapStanislav Fomichev6-476/+483 2019-03-02selftests: bpf: break up test_progs - xdpStanislav Fomichev5-162/+163 2019-03-02selftests: bpf: break up test_progs - pkt accessStanislav Fomichev3-51/+53 2019-03-02selftests: bpf: break up test_progs - preparationsStanislav Fomichev4-76/+119 2019-03-02Bluetooth: mediatek: add support for MediaTek MT7663U and MT7668U UART devicesSean Wang1-10/+271