summaryrefslogtreecommitdiff
path: root/tools
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2019-09-18 02:57:47 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2019-09-18 02:57:47 +0300
commit7ad67ca5534ee7c958559c4ad610f05c4578e361 (patch)
treedc6b6a8a6b70b5f25b07bcdc06d8e77e705f6822 /tools
parent5260c2b863ef1152445ce93476c95d8c8a727eef (diff)
parent9c7eddf1b080f98fed1aadb74fe784f29bf77a08 (diff)
downloadlinux-7ad67ca5534ee7c958559c4ad610f05c4578e361.tar.xz
Merge tag 'for-5.4/block-2019-09-16' of git://git.kernel.dk/linux-block
Pull block updates from Jens Axboe: - Two NVMe pull requests: - ana log parse fix from Anton - nvme quirks support for Apple devices from Ben - fix missing bio completion tracing for multipath stack devices from Hannes and Mikhail - IP TOS settings for nvme rdma and tcp transports from Israel - rq_dma_dir cleanups from Israel - tracing for Get LBA Status command from Minwoo - Some nvme-tcp cleanups from Minwoo, Potnuri and Myself - Some consolidation between the fabrics transports for handling the CAP register - reset race with ns scanning fix for fabrics (move fabrics commands to a dedicated request queue with a different lifetime from the admin request queue)." - controller reset and namespace scan races fixes - nvme discovery log change uevent support - naming improvements from Keith - multiple discovery controllers reject fix from James - some regular cleanups from various people - Series fixing (and re-fixing) null_blk debug printing and nr_devices checks (André) - A few pull requests from Song, with fixes from Andy, Guoqing, Guilherme, Neil, Nigel, and Yufen. - REQ_OP_ZONE_RESET_ALL support (Chaitanya) - Bio merge handling unification (Christoph) - Pick default elevator correctly for devices with special needs (Damien) - Block stats fixes (Hou) - Timeout and support devices nbd fixes (Mike) - Series fixing races around elevator switching and device add/remove (Ming) - sed-opal cleanups (Revanth) - Per device weight support for BFQ (Fam) - Support for blk-iocost, a new model that can properly account cost of IO workloads. (Tejun) - blk-cgroup writeback fixes (Tejun) - paride queue init fixes (zhengbin) - blk_set_runtime_active() cleanup (Stanley) - Block segment mapping optimizations (Bart) - lightnvm fixes (Hans/Minwoo/YueHaibing) - Various little fixes and cleanups * tag 'for-5.4/block-2019-09-16' of git://git.kernel.dk/linux-block: (186 commits) null_blk: format pr_* logs with pr_fmt null_blk: match the type of parameter nr_devices null_blk: do not fail the module load with zero devices block: also check RQF_STATS in blk_mq_need_time_stamp() block: make rq sector size accessible for block stats bfq: Fix bfq linkage error raid5: use bio_end_sector in r5_next_bio raid5: remove STRIPE_OPS_REQ_PENDING md: add feature flag MD_FEATURE_RAID0_LAYOUT md/raid0: avoid RAID0 data corruption due to layout confusion. raid5: don't set STRIPE_HANDLE to stripe which is in batch list raid5: don't increment read_errors on EILSEQ return nvmet: fix a wrong error status returned in error log page nvme: send discovery log page change events to userspace nvme: add uevent variables for controller devices nvme: enable aen regardless of the presence of I/O queues nvme-fabrics: allow discovery subsystems accept a kato nvmet: Use PTR_ERR_OR_ZERO() in nvmet_init_discovery() nvme: Remove redundant assignment of cq vector nvme: Assign subsys instance from first ctrl ...
Diffstat (limited to 'tools')
-rw-r--r--tools/cgroup/iocost_coef_gen.py178
-rw-r--r--tools/cgroup/iocost_monitor.py277
2 files changed, 455 insertions, 0 deletions
diff --git a/tools/cgroup/iocost_coef_gen.py b/tools/cgroup/iocost_coef_gen.py
new file mode 100644
index 000000000000..df17a2ae80e5
--- /dev/null
+++ b/tools/cgroup/iocost_coef_gen.py
@@ -0,0 +1,178 @@
+#!/usr/bin/env python3
+#
+# Copyright (C) 2019 Tejun Heo <tj@kernel.org>
+# Copyright (C) 2019 Andy Newell <newella@fb.com>
+# Copyright (C) 2019 Facebook
+
+desc = """
+Generate linear IO cost model coefficients used by the blk-iocost
+controller. If the target raw testdev is specified, destructive tests
+are performed against the whole device; otherwise, on
+./iocost-coef-fio.testfile. The result can be written directly to
+/sys/fs/cgroup/io.cost.model.
+
+On high performance devices, --numjobs > 1 is needed to achieve
+saturation.
+
+See Documentation/admin-guide/cgroup-v2.rst and block/blk-iocost.c
+for more details.
+"""
+
+import argparse
+import re
+import json
+import glob
+import os
+import sys
+import atexit
+import shutil
+import tempfile
+import subprocess
+
+parser = argparse.ArgumentParser(description=desc,
+ formatter_class=argparse.RawTextHelpFormatter)
+parser.add_argument('--testdev', metavar='DEV',
+ help='Raw block device to use for testing, ignores --testfile-size')
+parser.add_argument('--testfile-size-gb', type=float, metavar='GIGABYTES', default=16,
+ help='Testfile size in gigabytes (default: %(default)s)')
+parser.add_argument('--duration', type=int, metavar='SECONDS', default=120,
+ help='Individual test run duration in seconds (default: %(default)s)')
+parser.add_argument('--seqio-block-mb', metavar='MEGABYTES', type=int, default=128,
+ help='Sequential test block size in megabytes (default: %(default)s)')
+parser.add_argument('--seq-depth', type=int, metavar='DEPTH', default=64,
+ help='Sequential test queue depth (default: %(default)s)')
+parser.add_argument('--rand-depth', type=int, metavar='DEPTH', default=64,
+ help='Random test queue depth (default: %(default)s)')
+parser.add_argument('--numjobs', type=int, metavar='JOBS', default=1,
+ help='Number of parallel fio jobs to run (default: %(default)s)')
+parser.add_argument('--quiet', action='store_true')
+parser.add_argument('--verbose', action='store_true')
+
+def info(msg):
+ if not args.quiet:
+ print(msg)
+
+def dbg(msg):
+ if args.verbose and not args.quiet:
+ print(msg)
+
+# determine ('DEVNAME', 'MAJ:MIN') for @path
+def dir_to_dev(path):
+ # find the block device the current directory is on
+ devname = subprocess.run(f'findmnt -nvo SOURCE -T{path}',
+ stdout=subprocess.PIPE, shell=True).stdout
+ devname = os.path.basename(devname).decode('utf-8').strip()
+
+ # partition -> whole device
+ parents = glob.glob('/sys/block/*/' + devname)
+ if len(parents):
+ devname = os.path.basename(os.path.dirname(parents[0]))
+ rdev = os.stat(f'/dev/{devname}').st_rdev
+ return (devname, f'{os.major(rdev)}:{os.minor(rdev)}')
+
+def create_testfile(path, size):
+ global args
+
+ if os.path.isfile(path) and os.stat(path).st_size == size:
+ return
+
+ info(f'Creating testfile {path}')
+ subprocess.check_call(f'rm -f {path}', shell=True)
+ subprocess.check_call(f'touch {path}', shell=True)
+ subprocess.call(f'chattr +C {path}', shell=True)
+ subprocess.check_call(
+ f'pv -s {size} -pr /dev/urandom {"-q" if args.quiet else ""} | '
+ f'dd of={path} count={size} '
+ f'iflag=count_bytes,fullblock oflag=direct bs=16M status=none',
+ shell=True)
+
+def run_fio(testfile, duration, iotype, iodepth, blocksize, jobs):
+ global args
+
+ eta = 'never' if args.quiet else 'always'
+ outfile = tempfile.NamedTemporaryFile()
+ cmd = (f'fio --direct=1 --ioengine=libaio --name=coef '
+ f'--filename={testfile} --runtime={round(duration)} '
+ f'--readwrite={iotype} --iodepth={iodepth} --blocksize={blocksize} '
+ f'--eta={eta} --output-format json --output={outfile.name} '
+ f'--time_based --numjobs={jobs}')
+ if args.verbose:
+ dbg(f'Running {cmd}')
+ subprocess.check_call(cmd, shell=True)
+ with open(outfile.name, 'r') as f:
+ d = json.loads(f.read())
+ return sum(j['read']['bw_bytes'] + j['write']['bw_bytes'] for j in d['jobs'])
+
+def restore_elevator_nomerges():
+ global elevator_path, nomerges_path, elevator, nomerges
+
+ info(f'Restoring elevator to {elevator} and nomerges to {nomerges}')
+ with open(elevator_path, 'w') as f:
+ f.write(elevator)
+ with open(nomerges_path, 'w') as f:
+ f.write(nomerges)
+
+
+args = parser.parse_args()
+
+missing = False
+for cmd in [ 'findmnt', 'pv', 'dd', 'fio' ]:
+ if not shutil.which(cmd):
+ print(f'Required command "{cmd}" is missing', file=sys.stderr)
+ missing = True
+if missing:
+ sys.exit(1)
+
+if args.testdev:
+ devname = os.path.basename(args.testdev)
+ rdev = os.stat(f'/dev/{devname}').st_rdev
+ devno = f'{os.major(rdev)}:{os.minor(rdev)}'
+ testfile = f'/dev/{devname}'
+ info(f'Test target: {devname}({devno})')
+else:
+ devname, devno = dir_to_dev('.')
+ testfile = 'iocost-coef-fio.testfile'
+ testfile_size = int(args.testfile_size_gb * 2 ** 30)
+ create_testfile(testfile, testfile_size)
+ info(f'Test target: {testfile} on {devname}({devno})')
+
+elevator_path = f'/sys/block/{devname}/queue/scheduler'
+nomerges_path = f'/sys/block/{devname}/queue/nomerges'
+
+with open(elevator_path, 'r') as f:
+ elevator = re.sub(r'.*\[(.*)\].*', r'\1', f.read().strip())
+with open(nomerges_path, 'r') as f:
+ nomerges = f.read().strip()
+
+info(f'Temporarily disabling elevator and merges')
+atexit.register(restore_elevator_nomerges)
+with open(elevator_path, 'w') as f:
+ f.write('none')
+with open(nomerges_path, 'w') as f:
+ f.write('1')
+
+info('Determining rbps...')
+rbps = run_fio(testfile, args.duration, 'read',
+ 1, args.seqio_block_mb * (2 ** 20), args.numjobs)
+info(f'\nrbps={rbps}, determining rseqiops...')
+rseqiops = round(run_fio(testfile, args.duration, 'read',
+ args.seq_depth, 4096, args.numjobs) / 4096)
+info(f'\nrseqiops={rseqiops}, determining rrandiops...')
+rrandiops = round(run_fio(testfile, args.duration, 'randread',
+ args.rand_depth, 4096, args.numjobs) / 4096)
+info(f'\nrrandiops={rrandiops}, determining wbps...')
+wbps = run_fio(testfile, args.duration, 'write',
+ 1, args.seqio_block_mb * (2 ** 20), args.numjobs)
+info(f'\nwbps={wbps}, determining wseqiops...')
+wseqiops = round(run_fio(testfile, args.duration, 'write',
+ args.seq_depth, 4096, args.numjobs) / 4096)
+info(f'\nwseqiops={wseqiops}, determining wrandiops...')
+wrandiops = round(run_fio(testfile, args.duration, 'randwrite',
+ args.rand_depth, 4096, args.numjobs) / 4096)
+info(f'\nwrandiops={wrandiops}')
+restore_elevator_nomerges()
+atexit.unregister(restore_elevator_nomerges)
+info('')
+
+print(f'{devno} rbps={rbps} rseqiops={rseqiops} rrandiops={rrandiops} '
+ f'wbps={wbps} wseqiops={wseqiops} wrandiops={wrandiops}')
diff --git a/tools/cgroup/iocost_monitor.py b/tools/cgroup/iocost_monitor.py
new file mode 100644
index 000000000000..f79b23582a1d
--- /dev/null
+++ b/tools/cgroup/iocost_monitor.py
@@ -0,0 +1,277 @@
+#!/usr/bin/env drgn
+#
+# Copyright (C) 2019 Tejun Heo <tj@kernel.org>
+# Copyright (C) 2019 Facebook
+
+desc = """
+This is a drgn script to monitor the blk-iocost cgroup controller.
+See the comment at the top of block/blk-iocost.c for more details.
+For drgn, visit https://github.com/osandov/drgn.
+"""
+
+import sys
+import re
+import time
+import json
+import math
+
+import drgn
+from drgn import container_of
+from drgn.helpers.linux.list import list_for_each_entry,list_empty
+from drgn.helpers.linux.radixtree import radix_tree_for_each,radix_tree_lookup
+
+import argparse
+parser = argparse.ArgumentParser(description=desc,
+ formatter_class=argparse.RawTextHelpFormatter)
+parser.add_argument('devname', metavar='DEV',
+ help='Target block device name (e.g. sda)')
+parser.add_argument('--cgroup', action='append', metavar='REGEX',
+ help='Regex for target cgroups, ')
+parser.add_argument('--interval', '-i', metavar='SECONDS', type=float, default=1,
+ help='Monitoring interval in seconds')
+parser.add_argument('--json', action='store_true',
+ help='Output in json')
+args = parser.parse_args()
+
+def err(s):
+ print(s, file=sys.stderr, flush=True)
+ sys.exit(1)
+
+try:
+ blkcg_root = prog['blkcg_root']
+ plid = prog['blkcg_policy_iocost'].plid.value_()
+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_()
+VTIME_PER_SEC = prog['VTIME_PER_SEC'].value_()
+VTIME_PER_USEC = prog['VTIME_PER_USEC'].value_()
+AUTOP_SSD_FAST = prog['AUTOP_SSD_FAST'].value_()
+AUTOP_SSD_DFL = prog['AUTOP_SSD_DFL'].value_()
+AUTOP_SSD_QD1 = prog['AUTOP_SSD_QD1'].value_()
+AUTOP_HDD = prog['AUTOP_HDD'].value_()
+
+autop_names = {
+ AUTOP_SSD_FAST: 'ssd_fast',
+ AUTOP_SSD_DFL: 'ssd_dfl',
+ AUTOP_SSD_QD1: 'ssd_qd1',
+ AUTOP_HDD: 'hdd',
+}
+
+class BlkgIterator:
+ def blkcg_name(blkcg):
+ return blkcg.css.cgroup.kn.name.string_().decode('utf-8')
+
+ def walk(self, blkcg, q_id, parent_path):
+ if not self.include_dying and \
+ not (blkcg.css.flags.value_() & prog['CSS_ONLINE'].value_()):
+ return
+
+ name = BlkgIterator.blkcg_name(blkcg)
+ path = parent_path + '/' + name if parent_path else name
+ blkg = drgn.Object(prog, 'struct blkcg_gq',
+ address=radix_tree_lookup(blkcg.blkg_tree, q_id))
+ if not blkg.address_:
+ return
+
+ self.blkgs.append((path if path else '/', blkg))
+
+ for c in list_for_each_entry('struct blkcg',
+ 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)
+
+class IocStat:
+ def __init__(self, ioc):
+ global autop_names
+
+ self.enabled = ioc.enabled.value_()
+ self.running = ioc.running.value_() == IOC_RUNNING
+ 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.busy_level = ioc.busy_level.value_()
+ self.autop_idx = ioc.autop_idx.value_()
+ self.user_cost_model = ioc.user_cost_model.value_()
+ self.user_qos_params = ioc.user_qos_params.value_()
+
+ if self.autop_idx in autop_names:
+ self.autop_name = autop_names[self.autop_idx]
+ else:
+ self.autop_name = '?'
+
+ def dict(self, now):
+ return { 'device' : devname,
+ 'timestamp' : str(now),
+ 'enabled' : str(int(self.enabled)),
+ 'running' : str(int(self.running)),
+ 'period_ms' : str(self.period_ms),
+ 'period_at' : str(self.period_at),
+ 'period_vtime_at' : str(self.vperiod_at),
+ 'busy_level' : str(self.busy_level),
+ 'vrate_pct' : str(self.vrate_pct), }
+
+ def table_preamble_str(self):
+ state = ('RUN' if self.running else 'IDLE') if self.enabled else 'OFF'
+ output = f'{devname} {state:4} ' \
+ 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'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 ""})'
+ return output
+
+ def table_header_str(self):
+ return f'{"":25} active {"weight":>9} {"hweight%":>13} {"inflt%":>6} ' \
+ f'{"dbt":>3} {"delay":>6} {"usages%"}'
+
+class IocgStat:
+ def __init__(self, iocg):
+ ioc = iocg.ioc
+ 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.address = iocg.value_()
+
+ vdone = iocg.done_vtime.counter.value_()
+ vtime = iocg.vtime.counter.value_()
+ vrate = ioc.vtime_rate.counter.value_()
+ period_vtime = ioc.period_us.value_() * vrate
+ if period_vtime:
+ self.inflight_pct = (vtime - vdone) * 100 / period_vtime
+ else:
+ self.inflight_pct = 0
+
+ self.debt_ms = iocg.abs_vdebt.counter.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)
+
+ def dict(self, now, path):
+ out = { 'cgroup' : path,
+ 'timestamp' : str(now),
+ 'is_active' : str(int(self.is_active)),
+ 'weight' : str(self.weight),
+ 'weight_active' : str(self.active),
+ 'weight_inuse' : str(self.inuse),
+ 'hweight_active_pct' : str(self.hwa_pct),
+ 'hweight_inuse_pct' : str(self.hwi_pct),
+ 'inflight_pct' : str(self.inflight_pct),
+ 'debt_ms' : str(self.debt_ms),
+ 'use_delay' : str(self.use_delay),
+ 'delay_ms' : str(self.delay_ms),
+ 'usage_pct' : str(self.usage),
+ 'address' : str(hex(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'{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}:'
+ out = out.rstrip(':')
+ return out
+
+# handle args
+table_fmt = not args.json
+interval = args.interval
+devname = args.devname
+
+if args.json:
+ table_fmt = False
+
+re_str = None
+if args.cgroup:
+ for r in args.cgroup:
+ if re_str is None:
+ re_str = r
+ else:
+ re_str += '|' + r
+
+filter_re = re.compile(re_str) if re_str else None
+
+# Locate the roots
+q_id = None
+root_iocg = None
+ioc = None
+
+for i, ptr in radix_tree_for_each(blkcg_root.blkg_tree):
+ blkg = drgn.Object(prog, 'struct blkcg_gq', address=ptr)
+ try:
+ if devname == blkg.q.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')
+ ioc = root_iocg.ioc
+ break
+ except:
+ pass
+
+if ioc is None:
+ err(f'Could not find ioc for {devname}');
+
+# Keep printing
+while True:
+ now = time.time()
+ iocstat = IocStat(ioc)
+ output = ''
+
+ if table_fmt:
+ output += '\n' + iocstat.table_preamble_str()
+ output += '\n' + iocstat.table_header_str()
+ else:
+ output += json.dumps(iocstat.dict(now))
+
+ for path, blkg in BlkgIterator(blkcg_root, q_id):
+ if filter_re and not filter_re.match(path):
+ continue
+ if not blkg.pd[plid]:
+ continue
+
+ iocg = container_of(blkg.pd[plid], 'struct ioc_gq', 'pd')
+ iocg_stat = IocgStat(iocg)
+
+ if not filter_re and not iocg_stat.is_active:
+ continue
+
+ if table_fmt:
+ output += '\n' + iocg_stat.table_row_str(path)
+ else:
+ output += '\n' + json.dumps(iocg_stat.dict(now, path))
+
+ print(output)
+ sys.stdout.flush()
+ time.sleep(interval)