Skip to main content

Browse the archive

Revision 511e19b9e2112463c33a744ecb8a798056074408 authored by Namhyung Kim on 19 December 2022, 20:17:30 UTC, committed by Arnaldo Carvalho de Melo on 21 December 2022, 17:52:39 UTC 
perf lock contention: Add -L/--lock-filter option
 
The -L/--lock-filter option is to filter only given locks.  The locks
can be specified by address or name (if exists).

  $ sudo ./perf lock record -a  sleep 1

  $ sudo ./perf lock con -l
   contended  total wait  max wait  avg wait           address  symbol

          57     1.11 ms  42.83 us  19.54 us  ffff9f4140059000
          15   280.88 us  23.51 us  18.73 us  ffffffff9d007a40  jiffies_lock
           1    20.49 us  20.49 us  20.49 us  ffffffff9d0d50c0  rcu_state
           1     9.02 us   9.02 us   9.02 us  ffff9f41759e9ba0

  $ sudo ./perf lock con -L jiffies_lock,rcu_state
   contended  total wait  max wait  avg wait      type  caller

          15   280.88 us  23.51 us  18.73 us  spinlock  tick_sched_do_timer+0x93
           1    20.49 us  20.49 us  20.49 us  spinlock  __softirqentry_text_start+0xeb

  $ sudo ./perf lock con -L ffff9f4140059000
   contended  total wait  max wait  avg wait      type  caller

          38   779.40 us  42.83 us  20.51 us  spinlock  worker_thread+0x50
          11   216.30 us  39.87 us  19.66 us  spinlock  queue_work_on+0x39
           8   118.13 us  20.51 us  14.77 us  spinlock  kthread+0xe5

Committer testing:

  # uname -a
  Linux quaco 6.0.12-200.fc36.x86_64 #1 SMP PREEMPT_DYNAMIC Thu Dec 8 17:15:53 UTC 2022 x86_64 x86_64 x86_64 GNU/Linux
  # perf lock record
  ^C[ perf record: Woken up 1 times to write data ]
  # perf lock con -L jiffies_lock,rcu_state
   contended   total wait     max wait     avg wait         type   caller

  # perf lock con
   contended   total wait     max wait     avg wait         type   caller

           1      9.06 us      9.06 us      9.06 us     spinlock   call_timer_fn+0x24
  # perf lock con -L call
  ignore unknown symbol: call
   contended   total wait     max wait     avg wait         type   caller

           1      9.06 us      9.06 us      9.06 us     spinlock   call_timer_fn+0x24
  #

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Blake Jones <blakejones@google.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Song Liu <song@kernel.org>
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20221219201732.460111-5-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
1 parent 529772c
Raw File
jobserver-exec 
#!/usr/bin/env python3
# SPDX-License-Identifier: GPL-2.0+
#
# This determines how many parallel tasks "make" is expecting, as it is
# not exposed via an special variables, reserves them all, runs a subprocess
# with PARALLELISM environment variable set, and releases the jobs back again.
#
# https://www.gnu.org/software/make/manual/html_node/POSIX-Jobserver.html#POSIX-Jobserver
from __future__ import print_function
import os, sys, errno
import subprocess

# Extract and prepare jobserver file descriptors from environment.
claim = 0
jobs = b""
try:
	# Fetch the make environment options.
	flags = os.environ['MAKEFLAGS']

	# Look for "--jobserver=R,W"
	# Note that GNU Make has used --jobserver-fds and --jobserver-auth
	# so this handles all of them.
	opts = [x for x in flags.split(" ") if x.startswith("--jobserver")]

	# Parse out R,W file descriptor numbers and set them nonblocking.
	fds = opts[0].split("=", 1)[1]
	reader, writer = [int(x) for x in fds.split(",", 1)]
	# Open a private copy of reader to avoid setting nonblocking
	# on an unexpecting process with the same reader fd.
	reader = os.open("/proc/self/fd/%d" % (reader),
			 os.O_RDONLY | os.O_NONBLOCK)

	# Read out as many jobserver slots as possible.
	while True:
		try:
			slot = os.read(reader, 8)
			jobs += slot
		except (OSError, IOError) as e:
			if e.errno == errno.EWOULDBLOCK:
				# Stop at the end of the jobserver queue.
				break
			# If something went wrong, give back the jobs.
			if len(jobs):
				os.write(writer, jobs)
			raise e
	# Add a bump for our caller's reserveration, since we're just going
	# to sit here blocked on our child.
	claim = len(jobs) + 1
except (KeyError, IndexError, ValueError, OSError, IOError) as e:
	# Any missing environment strings or bad fds should result in just
	# not being parallel.
	pass

# We can only claim parallelism if there was a jobserver (i.e. a top-level
# "-jN" argument) and there were no other failures. Otherwise leave out the
# environment variable and let the child figure out what is best.
if claim > 0:
	os.environ['PARALLELISM'] = '%d' % (claim)

rc = subprocess.call(sys.argv[1:])

# Return all the reserved slots.
if len(jobs):
	os.write(writer, jobs)

sys.exit(rc)
back to top