Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 27 May 2009 01:30:23 +0000 (UTC)
From:      Stacey Son <sson@FreeBSD.org>
To:        src-committers@freebsd.org, svn-src-all@freebsd.org, svn-src-head@freebsd.org
Subject:   svn commit: r192867 - in head/cddl: contrib/opensolaris/cmd/lockstat usr.sbin usr.sbin/lockstat
Message-ID:  <200905270130.n4R1UNxC079783@svn.freebsd.org>

next in thread | raw e-mail | index | archive | help
Author: sson
Date: Wed May 27 01:30:23 2009
New Revision: 192867
URL: http://svn.freebsd.org/changeset/base/192867

Log:
  Add the OpenSolaris lockstat(1M) command.  Requires the dtrace driver,
  the lockstat provider, and the ksyms(4) pseudo driver kernel modules.
  
  Approved by:	gnn (mentor)

Added:
  head/cddl/contrib/opensolaris/cmd/lockstat/
  head/cddl/contrib/opensolaris/cmd/lockstat/lockstat.1   (contents, props changed)
  head/cddl/contrib/opensolaris/cmd/lockstat/lockstat.c   (contents, props changed)
  head/cddl/contrib/opensolaris/cmd/lockstat/sym.c   (contents, props changed)
  head/cddl/usr.sbin/lockstat/
  head/cddl/usr.sbin/lockstat/Makefile   (contents, props changed)
Modified:
  head/cddl/usr.sbin/Makefile

Added: head/cddl/contrib/opensolaris/cmd/lockstat/lockstat.1
==============================================================================
--- /dev/null	00:00:00 1970	(empty, because file is newly added)
+++ head/cddl/contrib/opensolaris/cmd/lockstat/lockstat.1	Wed May 27 01:30:23 2009	(r192867)
@@ -0,0 +1,875 @@
+'\" te
+.\" CDDL HEADER START
+.\"
+.\" The contents of this file are subject to the terms of the
+.\" Common Development and Distribution License (the "License").  
+.\" You may not use this file except in compliance with the License.
+.\"
+.\" You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
+.\" or http://www.opensolaris.org/os/licensing.
+.\" See the License for the specific language governing permissions
+.\" and limitations under the License.
+.\"
+.\" When distributing Covered Code, include this CDDL HEADER in each
+.\" file and include the License file at usr/src/OPENSOLARIS.LICENSE.
+.\" If applicable, add the following below this CDDL HEADER, with the
+.\" fields enclosed by brackets "[]" replaced with your own identifying
+.\" information: Portions Copyright [yyyy] [name of copyright owner]
+.\"
+.\" CDDL HEADER END
+.\" Copyright (c) 2008, Sun Microsystems, Inc. All Rights Reserved.
+.TH lockstat 1M "28 Feb 2008" "SunOS 5.11" "System Administration Commands"
+.SH NAME
+lockstat \- report kernel lock and profiling statistics
+.SH SYNOPSIS
+.LP
+.nf
+\fBlockstat\fR [\fB-ACEHI\fR] [\fB-e\fR \fIevent_list\fR] [\fB-i\fR \fIrate\fR] 
+    [\fB-b\fR | \fB-t\fR | \fB-h\fR | \fB-s\fR \fIdepth\fR] [\fB-n\fR \fInrecords\fR] 
+    [\fB-l\fR \fIlock\fR [, \fIsize\fR]] [\fB-d\fR \fIduration\fR] 
+    [\fB-f\fR \fIfunction\fR [, \fIsize\fR]] [\fB-T\fR] [\fB-ckgwWRpP\fR] [\fB-D\fR \fIcount\fR] 
+    [\fB-o\fR \fIfilename\fR] [\fB-x\fR \fIopt\fR [=val]] \fIcommand\fR [\fIargs\fR]
+.fi
+
+.SH DESCRIPTION
+.sp
+.LP
+The \fBlockstat\fR utility gathers and displays kernel locking and profiling statistics. \fBlockstat\fR allows you to specify which events to watch (for example, spin on adaptive mutex, block on read access to rwlock due to waiting writers, and so forth) how much
+data to gather for each event, and how to display the data. By default, \fBlockstat\fR monitors all lock contention events, gathers frequency and timing data about those events, and displays the data in decreasing frequency order, so that the most common events appear first.
+.sp
+.LP
+\fBlockstat\fR gathers data until the specified command completes. For example, to gather statistics for a fixed-time interval, use \fBsleep\fR(1) as
+the command, as follows:
+.sp
+.LP
+\fBexample#\fR \fBlockstat\fR \fBsleep\fR \fB5\fR
+.sp
+.LP
+When the \fB-I\fR option is specified, \fBlockstat\fR establishes a per-processor high-level periodic interrupt source to gather profiling data. The interrupt handler simply generates a \fBlockstat\fR event whose caller is the interrupted PC (program counter).
+The profiling event is just like any other \fBlockstat\fR event, so all of the normal \fBlockstat\fR options are applicable.
+.sp
+.LP
+\fBlockstat\fR relies on DTrace to modify the running kernel's text to intercept events of interest. This imposes a small but measurable overhead on all system activity, so access to \fBlockstat\fR is restricted to super-user by default. The system administrator
+can permit other users to use \fBlockstat\fR by granting them additional DTrace privileges. Refer to the \fISolaris Dynamic Tracing Guide\fR for more information about DTrace security features.
+.SH OPTIONS
+.sp
+.LP
+The following options are supported: 
+.SS "Event Selection"
+.sp
+.LP
+If no event selection options are specified, the default is \fB-C\fR.
+.sp
+.ne 2
+.mk
+.na
+\fB\fB-A\fR\fR
+.ad
+.sp .6
+.RS 4n
+Watch all lock events. \fB-A\fR is equivalent to \fB-CH\fR.
+.RE
+
+.sp
+.ne 2
+.mk
+.na
+\fB\fB-C\fR\fR
+.ad
+.sp .6
+.RS 4n
+Watch contention events. 
+.RE
+
+.sp
+.ne 2
+.mk
+.na
+\fB\fB-E\fR\fR
+.ad
+.sp .6
+.RS 4n
+Watch error events.
+.RE
+
+.sp
+.ne 2
+.mk
+.na
+\fB\fB\fR\fB-e\fR \fIevent_list\fR\fR
+.ad
+.sp .6
+.RS 4n
+Only watch the specified events. \fIevent\fR \fIlist\fR is a comma-separated list of events or ranges of events such as 1,4-7,35. Run \fBlockstat\fR with no arguments to get a brief description of all events.
+.RE
+
+.sp
+.ne 2
+.mk
+.na
+\fB\fB-H\fR\fR
+.ad
+.sp .6
+.RS 4n
+Watch hold events.
+.RE
+
+.sp
+.ne 2
+.mk
+.na
+\fB\fB-I\fR\fR
+.ad
+.sp .6
+.RS 4n
+Watch profiling interrupt events.
+.RE
+
+.sp
+.ne 2
+.mk
+.na
+\fB\fB\fR\fB-i\fR \fIrate\fR\fR
+.ad
+.sp .6
+.RS 4n
+Interrupt rate (per second) for \fB-I\fR. The default is 97 Hz, so that profiling doesn't run in lockstep with the clock interrupt (which runs at 100 Hz).
+.RE
+
+.SS "Data Gathering"
+.sp
+.ne 2
+.mk
+.na
+\fB\fB-x\fR \fIarg\fR[=\fIval\fR]\fR
+.ad
+.sp .6
+.RS 4n
+Enable or modify a DTrace runtime option or D compiler option. The list of options is found in the \fI\fR. Boolean options are enabled by specifying their name. Options with values are set by separating the option name and
+value with an equals sign (=).
+.RE
+
+.SS "Data Gathering (Mutually Exclusive)"
+.sp
+.ne 2
+.mk
+.na
+\fB\fB-b\fR\fR
+.ad
+.sp .6
+.RS 4n
+Basic statistics: lock, caller, number of events.
+.RE
+
+.sp
+.ne 2
+.mk
+.na
+\fB\fB-h\fR\fR
+.ad
+.sp .6
+.RS 4n
+Histogram: Timing plus time-distribution histograms.
+.RE
+
+.sp
+.ne 2
+.mk
+.na
+\fB\fB\fR\fB-s\fR \fIdepth\fR\fR
+.ad
+.sp .6
+.RS 4n
+Stack trace: Histogram plus stack traces up to \fIdepth\fR frames deep.
+.RE
+
+.sp
+.ne 2
+.mk
+.na
+\fB\fB-t\fR\fR
+.ad
+.sp .6
+.RS 4n
+Timing: Basic plus timing for all events [default].
+.RE
+
+.SS "Data Filtering"
+.sp
+.ne 2
+.mk
+.na
+\fB\fB\fR\fB-d\fR \fIduration\fR\fR
+.ad
+.sp .6
+.RS 4n
+Only watch events longer than \fIduration\fR.
+.RE
+
+.sp
+.ne 2
+.mk
+.na
+\fB\fB\fR\fB-f\fR \fIfunc[,size]\fR\fR
+.ad
+.sp .6
+.RS 4n
+Only watch events generated by \fIfunc\fR, which can be specified as a symbolic name or hex address. \fIsize\fR defaults to the \fBELF\fR symbol size if available, or \fB1\fR if not.
+.RE
+
+.sp
+.ne 2
+.mk
+.na
+\fB\fB\fR\fB-l\fR \fIlock[,size]\fR\fR
+.ad
+.sp .6
+.RS 4n
+Only watch \fIlock\fR, which can be specified as a symbolic name or hex address. \fBsize\fR defaults to the \fBELF\fR symbol size or \fB1\fR if the symbol size is not available.
+.RE
+
+.sp
+.ne 2
+.mk
+.na
+\fB\fB\fR\fB-n\fR \fInrecords\fR\fR
+.ad
+.sp .6
+.RS 4n
+Maximum number of data records.
+.RE
+
+.sp
+.ne 2
+.mk
+.na
+\fB\fB-T\fR\fR
+.ad
+.sp .6
+.RS 4n
+Trace (rather than sample) events [off by default].
+.RE
+
+.SS "Data Reporting"
+.sp
+.ne 2
+.mk
+.na
+\fB\fB-c\fR\fR
+.ad
+.sp .6
+.RS 4n
+Coalesce lock data for lock arrays (for example, \fBpse_mutex[]\fR).
+.RE
+
+.sp
+.ne 2
+.mk
+.na
+\fB\fB\fR\fB-D\fR \fIcount\fR\fR
+.ad
+.sp .6
+.RS 4n
+Only display the top \fIcount\fR events of each type.
+.RE
+
+.sp
+.ne 2
+.mk
+.na
+\fB\fB-g\fR\fR
+.ad
+.sp .6
+.RS 4n
+Show total events generated by function. For example, if \fBfoo()\fR calls \fBbar()\fR in a loop, the work done by \fBbar()\fR counts as work generated by \fBfoo()\fR (along with any work done by \fBfoo()\fR itself).
+The \fB-g\fR option works by counting the total number of stack frames in which each function appears. This implies two things: (1) the data reported by \fB-g\fR can be misleading if the stack traces are not deep enough, and (2) functions that are called recursively might show
+greater than 100% activity. In light of issue (1), the default data gathering mode when using \fB-g\fR is \fB-s\fR \fB50\fR.
+.RE
+
+.sp
+.ne 2
+.mk
+.na
+\fB\fB-k\fR\fR
+.ad
+.sp .6
+.RS 4n
+Coalesce PCs within functions.
+.RE
+
+.sp
+.ne 2
+.mk
+.na
+\fB\fB\fR\fB-o\fR \fIfilename\fR\fR
+.ad
+.sp .6
+.RS 4n
+Direct output to \fIfilename\fR.
+.RE
+
+.sp
+.ne 2
+.mk
+.na
+\fB\fB-P\fR\fR
+.ad
+.sp .6
+.RS 4n
+Sort data by (\fIcount * time\fR) product.
+.RE
+
+.sp
+.ne 2
+.mk
+.na
+\fB\fB-p\fR\fR
+.ad
+.sp .6
+.RS 4n
+Parsable output format.
+.RE
+
+.sp
+.ne 2
+.mk
+.na
+\fB\fB-R\fR\fR
+.ad
+.sp .6
+.RS 4n
+Display rates (events per second) rather than counts.
+.RE
+
+.sp
+.ne 2
+.mk
+.na
+\fB\fB-W\fR\fR
+.ad
+.sp .6
+.RS 4n
+Whichever: distinguish events only by caller, not by lock.
+.RE
+
+.sp
+.ne 2
+.mk
+.na
+\fB\fB-w\fR\fR
+.ad
+.sp .6
+.RS 4n
+Wherever: distinguish events only by lock, not by caller.
+.RE
+
+.SH DISPLAY FORMATS
+.sp
+.LP
+The following headers appear over various columns of data.
+.sp
+.ne 2
+.mk
+.na
+\fB\fBCount\fR or \fBops/s\fR\fR
+.ad
+.sp .6
+.RS 4n
+Number of times this event occurred, or the rate (times per second) if \fB-R\fR was specified.
+.RE
+
+.sp
+.ne 2
+.mk
+.na
+\fB\fBindv\fR\fR
+.ad
+.sp .6
+.RS 4n
+Percentage of all events represented by this individual event.
+.RE
+
+.sp
+.ne 2
+.mk
+.na
+\fB\fBgenr\fR\fR
+.ad
+.sp .6
+.RS 4n
+Percentage of all events generated by this function.
+.RE
+
+.sp
+.ne 2
+.mk
+.na
+\fB\fBcuml\fR\fR
+.ad
+.sp .6
+.RS 4n
+Cumulative percentage; a running total of the individuals.
+.RE
+
+.sp
+.ne 2
+.mk
+.na
+\fB\fBrcnt\fR\fR
+.ad
+.sp .6
+.RS 4n
+Average reference count. This will always be \fB1\fR for exclusive locks (mutexes, spin locks, rwlocks held as writer) but can be greater than \fB1\fR for shared locks (rwlocks held as reader).
+.RE
+
+.sp
+.ne 2
+.mk
+.na
+\fB\fBnsec\fR\fR
+.ad
+.sp .6
+.RS 4n
+Average duration of the events in nanoseconds, as appropriate for the event. For the profiling event, duration means interrupt latency.
+.RE
+
+.sp
+.ne 2
+.mk
+.na
+\fB\fBLock\fR\fR
+.ad
+.sp .6
+.RS 4n
+Address of the lock; displayed symbolically if possible.
+.RE
+
+.sp
+.ne 2
+.mk
+.na
+\fB\fBCPU+PIL\fR\fR
+.ad
+.sp .6
+.RS 4n
+\fBCPU\fR plus processor interrupt level (\fBPIL\fR). For example, if \fBCPU\fR 4 is interrupted while at \fBPIL\fR 6, this will be reported as \fBcpu[4]+6\fR.
+.RE
+
+.sp
+.ne 2
+.mk
+.na
+\fB\fBCaller\fR\fR
+.ad
+.sp .6
+.RS 4n
+Address of the caller; displayed symbolically if possible.
+.RE
+
+.SH EXAMPLES
+.LP
+\fBExample 1 \fRMeasuring Kernel Lock Contention
+.sp
+.in +2
+.nf
+example# \fBlockstat sleep 5\fR
+Adaptive mutex spin: 2210 events in 5.055 seconds (437 events/sec)
+.fi
+.in -2
+.sp
+
+.sp
+.in +2
+.nf
+Count indv cuml rcnt     nsec Lock                Caller
+------------------------------------------------------------------------
+ 269  12%  12% 1.00     2160 service_queue       background+0xdc
+ 249  11%  23% 1.00       86 service_queue       qenable_locked+0x64
+ 228  10%  34% 1.00      131 service_queue       background+0x15c
+  68   3%  37% 1.00       79 0x30000024070       untimeout+0x1c
+  59   3%  40% 1.00      384 0x300066fa8e0       background+0xb0
+  43   2%  41% 1.00       30 rqcred_lock         svc_getreq+0x3c
+  42   2%  43% 1.00      341 0x30006834eb8       background+0xb0
+  41   2%  45% 1.00      135 0x30000021058       untimeout+0x1c
+  40   2%  47% 1.00       39 rqcred_lock         svc_getreq+0x260
+  37   2%  49% 1.00     2372 0x300068e83d0       hmestart+0x1c4
+  36   2%  50% 1.00       77 0x30000021058       timeout_common+0x4
+  36   2%  52% 1.00      354 0x300066fa120       background+0xb0
+  32   1%  53% 1.00       97 0x30000024070       timeout_common+0x4
+  31   1%  55% 1.00     2923 0x300069883d0       hmestart+0x1c4
+  29   1%  56% 1.00      366 0x300066fb290       background+0xb0
+  28   1%  57% 1.00      117 0x3000001e040       untimeout+0x1c
+  25   1%  59% 1.00       93 0x3000001e040       timeout_common+0x4
+  22   1%  60% 1.00       25 0x30005161110       sync_stream_buf+0xdc
+  21   1%  60% 1.00      291 0x30006834eb8       putq+0xa4
+  19   1%  61% 1.00       43 0x3000515dcb0       mdf_alloc+0xc
+  18   1%  62% 1.00      456 0x30006834eb8       qenable+0x8
+  18   1%  63% 1.00       61 service_queue       queuerun+0x168
+  17   1%  64% 1.00      268 0x30005418ee8       vmem_free+0x3c
+[...]
+
+R/W reader blocked by writer: 76 events in 5.055 seconds (15 events/sec)
+
+Count indv cuml rcnt     nsec Lock                Caller
+------------------------------------------------------------------------
+  23  30%  30% 1.00 22590137 0x300098ba358       ufs_dirlook+0xd0
+  17  22%  53% 1.00  5820995 0x3000ad815e8       find_bp+0x10
+  13  17%  70% 1.00  2639918 0x300098ba360       ufs_iget+0x198
+   4   5%  75% 1.00  3193015 0x300098ba360       ufs_getattr+0x54
+   3   4%  79% 1.00  7953418 0x3000ad817c0       find_bp+0x10
+   3   4%  83% 1.00   935211 0x3000ad815e8       find_read_lof+0x14
+   2   3%  86% 1.00 16357310 0x300073a4720       find_bp+0x10
+   2   3%  88% 1.00  2072433 0x300073a4720       find_read_lof+0x14
+   2   3%  91% 1.00  1606153 0x300073a4370       find_bp+0x10
+   1   1%  92% 1.00  2656909 0x300107e7400       ufs_iget+0x198
+[...]
+.fi
+.in -2
+.sp
+
+.LP
+\fBExample 2 \fRMeasuring Hold Times
+.sp
+.in +2
+.nf
+example# \fBlockstat -H -D 10 sleep 1\fR
+Adaptive mutex spin: 513 events
+.fi
+.in -2
+.sp
+
+.sp
+.in +2
+.nf
+Count indv cuml rcnt     nsec Lock                Caller
+-------------------------------------------------------------------------
+ 480   5%   5% 1.00     1136 0x300007718e8       putnext+0x40
+ 286   3%   9% 1.00      666 0x3000077b430       getf+0xd8
+ 271   3%  12% 1.00      537 0x3000077b430       msgio32+0x2fc
+ 270   3%  15% 1.00     3670 0x300007718e8       strgetmsg+0x3d4
+ 270   3%  18% 1.00     1016 0x300007c38b0       getq_noenab+0x200
+ 264   3%  20% 1.00     1649 0x300007718e8       strgetmsg+0xa70
+ 216   2%  23% 1.00     6251 tcp_mi_lock         tcp_snmp_get+0xfc
+ 206   2%  25% 1.00      602 thread_free_lock    clock+0x250
+ 138   2%  27% 1.00      485 0x300007c3998       putnext+0xb8
+ 138   2%  28% 1.00     3706 0x300007718e8       strrput+0x5b8
+-------------------------------------------------------------------------
+[...]
+.fi
+.in -2
+.sp
+
+.LP
+\fBExample 3 \fRMeasuring Hold Times for Stack Traces Containing a Specific Function
+.sp
+.in +2
+.nf
+example# \fBlockstat -H -f tcp_rput_data -s 50 -D 10 sleep 1\fR
+Adaptive mutex spin: 11 events in 1.023 seconds (11
+events/sec)
+.fi
+.in -2
+.sp
+
+.sp
+.in +2
+.nf
+-------------------------------------------------------------------------
+Count indv cuml rcnt     nsec Lock                   Caller
+   9  82%  82% 1.00     2540 0x30000031380          tcp_rput_data+0x2b90
+
+     nsec ------ Time Distribution ------ count     Stack
+      256 |@@@@@@@@@@@@@@@@               5         tcp_rput_data+0x2b90
+      512 |@@@@@@                         2         putnext+0x78
+     1024 |@@@                            1         ip_rput+0xec4
+     2048 |                               0         _c_putnext+0x148
+     4096 |                               0         hmeread+0x31c
+     8192 |                               0         hmeintr+0x36c
+    16384 |@@@                            1
+sbus_intr_wrapper+0x30
+[...]
+
+Count indv cuml rcnt     nsec Lock                   Caller
+   1   9%  91% 1.00     1036 0x30000055380          freemsg+0x44
+
+     nsec ------ Time Distribution ------ count     Stack
+     1024 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ 1         freemsg+0x44
+                                                    tcp_rput_data+0x2fd0
+                                                    putnext+0x78
+                                                    ip_rput+0xec4
+                                                    _c_putnext+0x148
+                                                    hmeread+0x31c
+                                                    hmeintr+0x36c
+
+sbus_intr_wrapper+0x30
+-------------------------------------------------------------------------
+[...]
+.fi
+.in -2
+.sp
+
+.LP
+\fBExample 4 \fRBasic Kernel Profiling
+.sp
+.LP
+For basic profiling, we don't care whether the profiling interrupt sampled \fBfoo()\fR\fB+0x4c\fR or \fBfoo()\fR\fB+0x78\fR; we care only that it sampled somewhere in \fBfoo()\fR, so we use \fB-k\fR. The \fBCPU\fR and \fBPIL\fR aren't relevant to basic profiling because we are measuring the system as a whole, not a particular \fBCPU\fR or interrupt level, so we use \fB-W\fR.
+
+.sp
+.in +2
+.nf
+example# \fBlockstat -kIW -D 20 ./polltest\fR
+Profiling interrupt: 82 events in 0.424 seconds (194
+events/sec)
+.fi
+.in -2
+.sp
+
+.sp
+.in +2
+.nf
+Count indv cuml rcnt     nsec Hottest CPU+PIL     Caller
+-----------------------------------------------------------------------
+   8  10%  10% 1.00      698 cpu[1]              utl0
+   6   7%  17% 1.00      299 cpu[0]              read
+   5   6%  23% 1.00      124 cpu[1]              getf
+   4   5%  28% 1.00      327 cpu[0]              fifo_read
+   4   5%  33% 1.00      112 cpu[1]              poll
+   4   5%  38% 1.00      212 cpu[1]              uiomove
+   4   5%  43% 1.00      361 cpu[1]              mutex_tryenter
+   3   4%  46% 1.00      682 cpu[0]              write
+   3   4%  50% 1.00       89 cpu[0]              pcache_poll
+   3   4%  54% 1.00      118 cpu[1]              set_active_fd
+   3   4%  57% 1.00      105 cpu[0]              syscall_trap32
+   3   4%  61% 1.00      640 cpu[1]              (usermode)
+   2   2%  63% 1.00      127 cpu[1]              fifo_poll
+   2   2%  66% 1.00      300 cpu[1]              fifo_write
+   2   2%  68% 1.00      669 cpu[0]              releasef
+   2   2%  71% 1.00      112 cpu[1]              bt_getlowbit
+   2   2%  73% 1.00      247 cpu[1]              splx
+   2   2%  76% 1.00      503 cpu[0]              mutex_enter
+   2   2%  78% 1.00      467 cpu[0]+10           disp_lock_enter
+   2   2%  80% 1.00      139 cpu[1]              default_copyin
+-----------------------------------------------------------------------
+[...]
+.fi
+.in -2
+.sp
+
+.LP
+\fBExample 5 \fRGenerated-load Profiling
+.sp
+.LP
+In the example above, 5% of the samples were in \fBpoll()\fR. This tells us how much time was spent inside \fBpoll()\fR itself, but tells us nothing about how much work was \fBgenerated\fR by \fBpoll()\fR; that is, how much time we spent
+in functions called by \fBpoll()\fR. To determine that, we use the \fB-g\fR option. The example below shows that although \fBpolltest\fR spends only 5% of its time in \fBpoll()\fR itself, \fBpoll()\fR-induced work accounts for 34% of
+the load.
+
+.sp
+.LP
+Note that the functions that generate the profiling interrupt (\fBlockstat_intr()\fR, \fBcyclic_fire()\fR, and so forth) appear in every stack trace, and therefore are considered to have generated 100% of the load. This illustrates an important point: the generated
+load percentages do \fBnot\fR add up to 100% because they are not independent. If 72% of all stack traces contain both \fBfoo()\fR and \fBbar()\fR, then both \fBfoo()\fR and \fBbar()\fR are 72% load generators.
+
+.sp
+.in +2
+.nf
+example# \fBlockstat -kgIW -D 20 ./polltest\fR
+Profiling interrupt: 80 events in 0.412 seconds (194 events/sec)
+.fi
+.in -2
+.sp
+
+.sp
+.in +2
+.nf
+Count genr cuml rcnt     nsec Hottest CPU+PIL     Caller
+-------------------------------------------------------------------------
+  80 100% ---- 1.00      310 cpu[1]              lockstat_intr
+  80 100% ---- 1.00      310 cpu[1]              cyclic_fire
+  80 100% ---- 1.00      310 cpu[1]              cbe_level14
+  80 100% ---- 1.00      310 cpu[1]              current_thread
+  27  34% ---- 1.00      176 cpu[1]              poll
+  20  25% ---- 1.00      221 cpu[0]              write
+  19  24% ---- 1.00      249 cpu[1]              read
+  17  21% ---- 1.00      232 cpu[0]              write32
+  17  21% ---- 1.00      207 cpu[1]              pcache_poll
+  14  18% ---- 1.00      319 cpu[0]              fifo_write
+  13  16% ---- 1.00      214 cpu[1]              read32
+  10  12% ---- 1.00      208 cpu[1]              fifo_read
+  10  12% ---- 1.00      787 cpu[1]              utl0
+   9  11% ---- 1.00      178 cpu[0]              pcacheset_resolve
+   9  11% ---- 1.00      262 cpu[0]              uiomove
+   7   9% ---- 1.00      506 cpu[1]              (usermode)
+   5   6% ---- 1.00      195 cpu[1]              fifo_poll
+   5   6% ---- 1.00      136 cpu[1]              syscall_trap32
+   4   5% ---- 1.00      139 cpu[0]              releasef
+   3   4% ---- 1.00      277 cpu[1]              polllock
+-------------------------------------------------------------------------
+[...]
+.fi
+.in -2
+.sp
+
+.LP
+\fBExample 6 \fRGathering Lock Contention and Profiling Data for a Specific Module
+.sp
+.LP
+In this example we use the \fB-f\fR option not to specify a single function, but rather to specify the entire text space of the \fBsbus\fR module. We gather both lock contention and profiling statistics so that contention can be correlated with overall load on the
+module. 
+
+.sp
+.in +2
+.nf
+example# \fBmodinfo | grep sbus\fR
+24 102a8b6f   b8b4  59   1  sbus (SBus (sysio) nexus driver)
+.fi
+.in -2
+.sp
+
+.sp
+.in +2
+.nf
+example# \fBlockstat -kICE -f 0x102a8b6f,0xb8b4 sleep 10\fR
+Adaptive mutex spin: 39 events in 10.042 seconds (4 events/sec)
+.fi
+.in -2
+.sp
+
+.sp
+.in +2
+.nf
+Count indv cuml rcnt     nsec Lock               Caller
+-------------------------------------------------------------------------
+  15  38%  38% 1.00      206 0x30005160528      sync_stream_buf
+   7  18%  56% 1.00       14 0x30005160d18      sync_stream_buf
+   6  15%  72% 1.00       27 0x300060c3118      sync_stream_buf
+   5  13%  85% 1.00       24 0x300060c3510      sync_stream_buf
+   2   5%  90% 1.00       29 0x300060c2d20      sync_stream_buf
+   2   5%  95% 1.00       24 0x30005161cf8      sync_stream_buf
+   1   3%  97% 1.00       21 0x30005161110      sync_stream_buf
+   1   3% 100% 1.00       23 0x30005160130      sync_stream_buf
+[...]
+
+Adaptive mutex block: 9 events in 10.042 seconds (1 events/sec)
+
+Count indv cuml rcnt     nsec Lock               Caller
+-------------------------------------------------------------------------
+   4  44%  44% 1.00   156539 0x30005160528      sync_stream_buf
+   2  22%  67% 1.00   763516 0x30005160d18      sync_stream_buf
+   1  11%  78% 1.00   462130 0x300060c3510      sync_stream_buf
+   1  11%  89% 1.00   288749 0x30005161110      sync_stream_buf
+   1  11% 100% 1.00  1015374 0x30005160130      sync_stream_buf
+[...]
+
+Profiling interrupt: 229 events in 10.042 seconds (23 events/sec)
+
+Count indv cuml rcnt     nsec Hottest CPU+PIL    Caller
+
+-------------------------------------------------------------------------
+  89  39%  39% 1.00      426 cpu[0]+6           sync_stream_buf
+  64  28%  67% 1.00      398 cpu[0]+6           sbus_intr_wrapper
+  23  10%  77% 1.00      324 cpu[0]+6           iommu_dvma_kaddr_load
+  21   9%  86% 1.00      512 cpu[0]+6           iommu_tlb_flush
+  14   6%  92% 1.00      342 cpu[0]+6           iommu_dvma_unload
+  13   6%  98% 1.00      306 cpu[1]             iommu_dvma_sync
+   5   2% 100% 1.00      389 cpu[1]             iommu_dma_bindhdl
+-------------------------------------------------------------------------
+[...]
+.fi
+.in -2
+.sp
+
+.LP
+\fBExample 7 \fRDetermining the Average PIL (processor interrupt level) for a CPU
+.sp
+.in +2
+.nf
+example# \fBlockstat -Iw -l cpu[3] ./testprog\fR
+
+Profiling interrupt: 14791 events in 152.463 seconds (97 events/sec)
+
+Count indv cuml rcnt     nsec CPU+PIL             Hottest Caller
+
+-----------------------------------------------------------------------
+13641  92%  92% 1.00      253 cpu[3]              (usermode)
+ 579   4%  96% 1.00      325 cpu[3]+6            ip_ocsum+0xe8
+ 375   3%  99% 1.00      411 cpu[3]+10           splx
+ 154   1% 100% 1.00      527 cpu[3]+4            fas_intr_svc+0x80
+  41   0% 100% 1.00      293 cpu[3]+13           send_mondo+0x18
+   1   0% 100% 1.00      266 cpu[3]+12           zsa_rxint+0x400
+-----------------------------------------------------------------------
+[...]
+.fi
+.in -2
+.sp
+
+.LP
+\fBExample 8 \fRDetermining which Subsystem is Causing the System to be Busy
+.sp
+.in +2
+.nf
+example# \fBlockstat -s 10 -I sleep 20\fR
+
+Profiling interrupt: 4863 events in 47.375 seconds (103 events/sec)
+
+Count indv cuml rcnt     nsec CPU+PIL          Caller
+
+-----------------------------------------------------------------------
+1929   40%  40% 0.00     3215 cpu[0]           usec_delay+0x78
+ nsec ------ Time Distribution ------ count   Stack
+ 4096 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@  1872    ata_wait+0x90
+ 8192 |                               27      acersb_get_intr_status+0x34     
+16384 |                               29      ata_set_feature+0x124
+32768 |                               1       ata_disk_start+0x15c
+                                              ata_hba_start+0xbc
+                                              ghd_waitq_process_and \e
+                                              _mutex_hold+0x70
+                                              ghd_waitq_process_and \e
+                                              _mutex_exit+0x4
+                                              ghd_transport+0x12c
+                                              ata_disk_tran_start+0x108
+-----------------------------------------------------------------------
+[...]
+.fi
+.in -2
+.sp
+
+.SH ATTRIBUTES
+.sp
+.LP
+See \fBattributes\fR(5) for descriptions of the following attributes:
+.sp
+
+.sp
+.TS
+tab() box;
+cw(2.75i) |cw(2.75i) 
+lw(2.75i) |lw(2.75i) 
+.
+ATTRIBUTE TYPEATTRIBUTE VALUE
+_
+AvailabilitySUNWdtrc
+.TE
+
+.SH SEE ALSO
+.sp
+.LP
+\fBdtrace\fR(1M), \fBplockstat\fR(1M), \fBattributes\fR(5), \fBlockstat\fR(7D), \fBmutex\fR(9F), \fBrwlock\fR(9F)
+.sp
+.LP
+\fISolaris Dynamic Tracing Guide\fR
+.SH NOTES
+.sp
+.LP
+The profiling support provided by \fBlockstat\fR \fB-I\fR replaces the old (and undocumented) \fB/usr/bin/kgmon\fR and \fB/dev/profile\fR.
+.sp
+.LP
+Tail-call elimination can affect call sites. For example, if \fBfoo()\fR\fB+0x50\fR calls \fBbar()\fR and the last thing \fBbar()\fR does is call \fBmutex_exit()\fR, the compiler can arrange for \fBbar()\fR to
+branch to \fBmutex_exit()\fRwith a return address of \fBfoo()\fR\fB+0x58\fR. Thus, the \fBmutex_exit()\fR in \fBbar()\fR will appear as though it occurred at \fBfoo()\fR\fB+0x58\fR.
+.sp
+.LP
+The \fBPC\fR in the stack frame in which an interrupt occurs can be bogus because, between function calls, the compiler is free to use the return address register for local storage.
+.sp
+.LP
+When using the \fB-I\fR and \fB-s\fR options together, the interrupted PC will usually not appear anywhere in the stack since the interrupt handler is entered asynchronously, not by a function call from that \fBPC\fR.
+.sp
+.LP
+The \fBlockstat\fR technology is provided on an as-is basis. The format and content of \fBlockstat\fR output reflect the current Solaris kernel implementation and are therefore subject to change in future releases.

Added: head/cddl/contrib/opensolaris/cmd/lockstat/lockstat.c
==============================================================================
--- /dev/null	00:00:00 1970	(empty, because file is newly added)
+++ head/cddl/contrib/opensolaris/cmd/lockstat/lockstat.c	Wed May 27 01:30:23 2009	(r192867)
@@ -0,0 +1,1917 @@
+/*
+ * CDDL HEADER START
+ *
+ * The contents of this file are subject to the terms of the
+ * Common Development and Distribution License (the "License").
+ * You may not use this file except in compliance with the License.
+ *
+ * You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
+ * or http://www.opensolaris.org/os/licensing.
+ * See the License for the specific language governing permissions
+ * and limitations under the License.
+ *
+ * When distributing Covered Code, include this CDDL HEADER in each
+ * file and include the License file at usr/src/OPENSOLARIS.LICENSE.
+ * If applicable, add the following below this CDDL HEADER, with the
+ * fields enclosed by brackets "[]" replaced with your own identifying
+ * information: Portions Copyright [yyyy] [name of copyright owner]
+ *
+ * CDDL HEADER END
+ */
+/*
+ * Copyright 2008 Sun Microsystems, Inc.  All rights reserved.
+ * Use is subject to license terms.
+ */
+
+#pragma ident	"%Z%%M%	%I%	%E% SMI"
+
+#include <stdio.h>
+#include <stddef.h>
+#include <stdlib.h>
+#include <stdarg.h>
+#include <string.h>
+#include <strings.h>
+#include <ctype.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <errno.h>
+#include <limits.h>
+#include <sys/types.h>
+#include <sys/modctl.h>
+#include <sys/stat.h>
+#include <sys/wait.h>
+#include <dtrace.h>
+#include <sys/lockstat.h>
+#include <alloca.h>
+#include <signal.h>
+#include <assert.h>
+
+#if !defined(sun)
+/* needed for FreeBSD */ 
+#include <sys/time.h>
+#include <sys/resource.h>
+typedef uintptr_t pc_t;
+
+#define mergesort(a, b, c, d)	lsmergesort(a, b, c, d)
+#endif
+
+#define	LOCKSTAT_OPTSTR	"x:bths:n:d:i:l:f:e:ckwWgCHEATID:RpPo:V"
+
+#define	LS_MAX_STACK_DEPTH	50
+#define	LS_MAX_EVENTS		64
+
+typedef struct lsrec {
+	struct lsrec	*ls_next;	/* next in hash chain */
+	uintptr_t	ls_lock;	/* lock address */
+	uintptr_t	ls_caller;	/* caller address */
+	uint32_t	ls_count;	/* cumulative event count */
+	uint32_t	ls_event;	/* type of event */
+	uintptr_t	ls_refcnt;	/* cumulative reference count */
+	uint64_t	ls_time;	/* cumulative event duration */
+	uint32_t	ls_hist[64];	/* log2(duration) histogram */
+	uintptr_t	ls_stack[LS_MAX_STACK_DEPTH];
+} lsrec_t;
+
+typedef struct lsdata {
+	struct lsrec	*lsd_next;	/* next available */
+	int		lsd_count;	/* number of records */
+} lsdata_t;
+
+/*
+ * Definitions for the types of experiments which can be run.  They are
+ * listed in increasing order of memory cost and processing time cost.
+ * The numerical value of each type is the number of bytes needed per record.
+ */
+#define	LS_BASIC	offsetof(lsrec_t, ls_time)
+#define	LS_TIME		offsetof(lsrec_t, ls_hist[0])
+#define	LS_HIST		offsetof(lsrec_t, ls_stack[0])
+#define	LS_STACK(depth)	offsetof(lsrec_t, ls_stack[depth])
+
+static void report_stats(FILE *, lsrec_t **, size_t, uint64_t, uint64_t);
+static void report_trace(FILE *, lsrec_t **);
+
+extern int symtab_init(void);
+extern char *addr_to_sym(uintptr_t, uintptr_t *, size_t *);
+extern uintptr_t sym_to_addr(char *name);
+extern size_t sym_size(char *name);
+extern char *strtok_r(char *, const char *, char **);
+
+#define	DEFAULT_NRECS	10000
+#define	DEFAULT_HZ	97
+#define	MAX_HZ		1000
+#define	MIN_AGGSIZE	(16 * 1024)
+#define	MAX_AGGSIZE	(32 * 1024 * 1024)
+
+static int g_stkdepth;
+static int g_topn = INT_MAX;
+static hrtime_t g_elapsed;
+static int g_rates = 0;
+static int g_pflag = 0;
+static int g_Pflag = 0;
+static int g_wflag = 0;
+static int g_Wflag = 0;
+static int g_cflag = 0;
+static int g_kflag = 0;
+static int g_gflag = 0;
+static int g_Vflag = 0;
+static int g_tracing = 0;
+static size_t g_recsize;
+static size_t g_nrecs;

*** DIFF OUTPUT TRUNCATED AT 1000 LINES ***



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200905270130.n4R1UNxC079783>