From 22098763a10d9c1340827fcf6edab66f153b27f0 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 13 Sep 2026 12:27:00 -0700 Subject: Merge tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace Pull tracing fixes from Steven Rostedt: - Don't destroy user event fields when removal fails User event fields are destroyed before the event is removed from visibility. But that can fail leaving the still visible event with no fields. Move the destroying of the fields to after the event is successfully removed from visibility. - Initialize function graph state is fork before calling copy_exec_state() For non-CLONE_VM forks, copy_exec_state() allocates a new task_exec_state. If that allocation fails, ftrace_graph_exit_task() will free the tasks ret_stack pointer. Since that pointer is still using the parent's ret_stack, it mistakenly frees the parent's pointer too. Call ftrace_graph_init() on the task first which will NULL out the new tasks's ret_stack and if the copy fails, it will not free anything. - Remove FGRAPH_MAX_INDEX The macro FGRAPH_MAX_INDEX was added but never used. Remove it. - Save ent_size in function graph printing of nested functions The function graph tracer needs to look at the next event to see if the next event is the return of the current function entry. If it is, it prints a single line: ktime_get(); Otherwise it prints it like a nested function: tick_nohz_irq_exit() { ktime_get(); kcpustat_irq_exit(); } In order to look at the next event, it must save the current event so that it has the information to print from it. It saves the event in the iterator descriptor called "ent". What it doesn't save is the ent_size of the event which is now used to know if the function graph arguments are to be printed. The peek doesn't save the size so the size used happens to be that of the size of the last event that was seen. Save the entry event size in the iterator descriptor so that the correct size is used. - Fix several errors with freeing data in the histogram code The histogram code had a lot of leaked or or incorrect accounting when failures happen. Correct them. - Fix histogram regression of .percent and .graph modifiers Up until 6.3 histogram values could have "percent" or "graph" modifiers that changed how they were printed. But a change that added restricting histograms values from being strings, stack traces and other modifiers inadvertently prevented them from using the percent and graph modifiers, which were legal use cases for values. Put back the percent and graph modifiers. - Fix various typos in the comments - Set the trace_clock before initializing a histogram with clock argument The histogram API allows the user to specific which trace clock to use via a "clock=" string. The histogram is set up first before the clock is checked. If the passed in clock is not valid, it exits without fully fixing up the histogram leaving it on the list and a use-after-free can trigger. Update the clock argument first and if it fails then exit gracefully before the histogram trigger is placed on any lists. - Restore :mod: trailer after parsing in ftrace_set_clr_event The function ftrace_set_clr_event() modifies the parse string and needs to put it back to what was passed in. It searches for ":mod:" via a strsep() but fails to put back the first ':' in the string. Add back the ':' in the passed in string. - Take trace_array reference when opening a tracer options file The options files are dynamically created and some tracers add their own options. When a tracer adds their own list of options, the trace_array holding them has an array to hold the list of options for each tracer. This array increases in size via a krealloc(), and the new entry gets a newly allocated array to hold the options of the new tracer being added. The element in each entry of the tracer's option array holds a pointer back to the trace_array, a pointer to the tracer it is associated to, a pointer to the flags of the option. The issue is that these arrays are freed when the trace_array is freed when its instance it represents is removed from the instances directory. There's a race that an open of one of these options files can happen when the instance is being removed. Add a new helper function to be called by the open function of the options file to iterate all existing trace_arrays under a lock and find the one that has the given option element in one of it's tracer arrays. If found, then update the associated trace_array's reference counter to keep it from being freed. If not found, have the open call return -ENODEV. - Disable interrupts when acquiring the lock in rb_wake_up_waiters() The function rb_wake_up_waiters() assumes it will be called in interrupt context and does not disable irqs when taking cpu_buffer->reader_lock, which can be called in hard interrupt context. The issue is in PREEMPT_RT, this function is called in thread context leaving this lock open to a deadlock. Take the lock with interrupts disabled. - Use rcu_assign_pointer() for tmp_ops filter hash The tmp_ops used in update_ftrace_direct_mod() assigns its filter_hash field directly, but that field is annotated as __rcu and sparse complains. Assign it with rcu_assign_pointer() - Fix use-after-free in enable_trigger_private_data_free() The trace_event_call is accessed through the event_trigger_data's trace_event_file pointer to put the trace_event_call on freeing. The issue is that the trace_event_file data may have been freed already causing a use-after-free. Add a field to the event_trigger_data that points directly to the trace_event_call so that it can decrement its reference directly without needing to go through the trace_event_file. - Fix accounting of buffer data remote headers trace_buffer_desc_size() and trace_remote_alloc_buffer() undercount the number of pages is needed for the asked for size as it doesn't take into account the meta data on each page. Add a helper function to do the calculation properly and use that in these functions. - Catch nr_page_va overflow in ring_buffer_desc sizing The number of pages per remote ring buffer is capped by ring_buffer_desc::nr_page_va (32 bits). A buffer_size large enough to overflow that field would silently allocate a descriptor smaller than what was asked for. - Do not resize the subbuf order if any per_cpu buffer is disabled The mmapping of ring buffers disables resizing the subbuffers, but it is done per-cpu whereas the subbuf size change is done for all the per_cpu buffers under the buffer->mutex. It could change the size of some while the mapping is happening on others. Have the resize of the subbuf order check all the per_cpu buffers under the lock to see if any of them is disabled before starting and causing an inconsistency between buffers that are being mapped. * tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (25 commits) ring-buffer: Check resize_disabled before publishing the new subbuf order tracing/remotes: Catch nr_page_va overflow in ring_buffer_desc sizing tracing/remotes: Account for ring buffer page header in size calculation tracing: Don't dereference trace_event_file in deferred trigger free ftrace: Use rcu_assign_pointer() for tmp_ops filter hash ring-buffer: Acquire the lock with irqsave in rb_wake_up_waiters() tracing: Take trace_array reference when opening a tracer options file tracing: Fix ring_buffer_read_page_size() kernel-doc tracing: Restore :mod: trailer after parsing in ftrace_set_clr_event() tracing: Fix memory corruption from a "STACKTRACE" histogram key tracing: Fix memory corruption from the histogram stacktrace modifier tracing: Undo the registration when enabling the histogram trigger fails tracing: Take the reference before publishing the named histogram trigger tracing: Set the trace clock before registering the histogram trigger tracing: Fix typo "preceeded" in comment tracing: Fix typo "availabe" in comment tracing: Let histogram values keep the percent and graph modifiers tracing: Keep the entry count when the histogram stats allocation fails tracing: Free histogram the field rejected for a bad modifier tracing: Free histogram the var ref when its initialization fails ... --- Documentation/trace/postprocess/decode_msr.py | 37 + .../postprocess/trace-pagealloc-postprocess.pl | 418 ++++++++++++ .../trace/postprocess/trace-vmscan-postprocess.pl | 752 +++++++++++++++++++++ 3 files changed, 1207 insertions(+) create mode 100644 Documentation/trace/postprocess/decode_msr.py create mode 100644 Documentation/trace/postprocess/trace-pagealloc-postprocess.pl create mode 100644 Documentation/trace/postprocess/trace-vmscan-postprocess.pl (limited to 'Documentation/trace/postprocess') diff --git a/Documentation/trace/postprocess/decode_msr.py b/Documentation/trace/postprocess/decode_msr.py new file mode 100644 index 000000000..f5609b16f --- /dev/null +++ b/Documentation/trace/postprocess/decode_msr.py @@ -0,0 +1,37 @@ +#!/usr/bin/env python +# add symbolic names to read_msr / write_msr in trace +# decode_msr msr-index.h < trace +import sys +import re + +msrs = dict() + +with open(sys.argv[1] if len(sys.argv) > 1 else "msr-index.h", "r") as f: + for j in f: + m = re.match(r'#define (MSR_\w+)\s+(0x[0-9a-fA-F]+)', j) + if m: + msrs[int(m.group(2), 16)] = m.group(1) + +extra_ranges = ( + ( "MSR_LASTBRANCH_%d_FROM_IP", 0x680, 0x69F ), + ( "MSR_LASTBRANCH_%d_TO_IP", 0x6C0, 0x6DF ), + ( "LBR_INFO_%d", 0xdc0, 0xddf ), +) + +for j in sys.stdin: + m = re.search(r'(read|write)_msr:\s+([0-9a-f]+)', j) + if m: + r = None + num = int(m.group(2), 16) + if num in msrs: + r = msrs[num] + else: + for er in extra_ranges: + if er[1] <= num <= er[2]: + r = er[0] % (num - er[1],) + break + if r: + j = j.replace(" " + m.group(2), " " + r + "(" + m.group(2) + ")") + print(j) + + diff --git a/Documentation/trace/postprocess/trace-pagealloc-postprocess.pl b/Documentation/trace/postprocess/trace-pagealloc-postprocess.pl new file mode 100644 index 000000000..d16494c5e --- /dev/null +++ b/Documentation/trace/postprocess/trace-pagealloc-postprocess.pl @@ -0,0 +1,418 @@ +#!/usr/bin/env perl +# This is a POC (proof of concept or piece of crap, take your pick) for reading the +# text representation of trace output related to page allocation. It makes an attempt +# to extract some high-level information on what is going on. The accuracy of the parser +# may vary considerably +# +# Example usage: trace-pagealloc-postprocess.pl < /sys/kernel/tracing/trace_pipe +# other options +# --prepend-parent Report on the parent proc and PID +# --read-procstat If the trace lacks process info, get it from /proc +# --ignore-pid Aggregate processes of the same name together +# +# Copyright (c) IBM Corporation 2009 +# Author: Mel Gorman +use strict; +use Getopt::Long; + +# Tracepoint events +use constant MM_PAGE_ALLOC => 1; +use constant MM_PAGE_FREE => 2; +use constant MM_PAGE_FREE_BATCHED => 3; +use constant MM_PAGE_PCPU_DRAIN => 4; +use constant MM_PAGE_ALLOC_ZONE_LOCKED => 5; +use constant MM_PAGE_ALLOC_EXTFRAG => 6; +use constant EVENT_UNKNOWN => 7; + +# Constants used to track state +use constant STATE_PCPU_PAGES_DRAINED => 8; +use constant STATE_PCPU_PAGES_REFILLED => 9; + +# High-level events extrapolated from tracepoints +use constant HIGH_PCPU_DRAINS => 10; +use constant HIGH_PCPU_REFILLS => 11; +use constant HIGH_EXT_FRAGMENT => 12; +use constant HIGH_EXT_FRAGMENT_SEVERE => 13; +use constant HIGH_EXT_FRAGMENT_MODERATE => 14; +use constant HIGH_EXT_FRAGMENT_CHANGED => 15; + +my %perprocesspid; +my %perprocess; +my $opt_ignorepid; +my $opt_read_procstat; +my $opt_prepend_parent; + +# Catch sigint and exit on request +my $sigint_report = 0; +my $sigint_exit = 0; +my $sigint_pending = 0; +my $sigint_received = 0; +sub sigint_handler { + my $current_time = time; + if ($current_time - 2 > $sigint_received) { + print "SIGINT received, report pending. Hit ctrl-c again to exit\n"; + $sigint_report = 1; + } else { + if (!$sigint_exit) { + print "Second SIGINT received quickly, exiting\n"; + } + $sigint_exit++; + } + + if ($sigint_exit > 3) { + print "Many SIGINTs received, exiting now without report\n"; + exit; + } + + $sigint_received = $current_time; + $sigint_pending = 1; +} +$SIG{INT} = "sigint_handler"; + +# Parse command line options +GetOptions( + 'ignore-pid' => \$opt_ignorepid, + 'read-procstat' => \$opt_read_procstat, + 'prepend-parent' => \$opt_prepend_parent, +); + +# Defaults for dynamically discovered regex's +my $regex_fragdetails_default = 'page=([0-9a-f]*) pfn=([0-9]*) alloc_order=([-0-9]*) fallback_order=([-0-9]*) pageblock_order=([-0-9]*) alloc_migratetype=([-0-9]*) fallback_migratetype=([-0-9]*) fragmenting=([-0-9]) change_ownership=([-0-9])'; + +# Dyanically discovered regex +my $regex_fragdetails; + +# Static regex used. Specified like this for readability and for use with /o +# (process_pid) (cpus ) ( time ) (tpoint ) (details) +my $regex_traceevent = '\s*([a-zA-Z0-9-]*)\s*(\[[0-9]*\])\s*([0-9.]*):\s*([a-zA-Z_]*):\s*(.*)'; +my $regex_statname = '[-0-9]*\s\((.*)\).*'; +my $regex_statppid = '[-0-9]*\s\(.*\)\s[A-Za-z]\s([0-9]*).*'; + +sub generate_traceevent_regex { + my $event = shift; + my $default = shift; + my $regex; + + # Read the event format or use the default + if (!open (FORMAT, "/sys/kernel/tracing/events/$event/format")) { + $regex = $default; + } else { + my $line; + while (!eof(FORMAT)) { + $line = ; + if ($line =~ /^print fmt:\s"(.*)",.*/) { + $regex = $1; + $regex =~ s/%p/\([0-9a-f]*\)/g; + $regex =~ s/%d/\([-0-9]*\)/g; + $regex =~ s/%lu/\([0-9]*\)/g; + } + } + } + + # Verify fields are in the right order + my $tuple; + foreach $tuple (split /\s/, $regex) { + my ($key, $value) = split(/=/, $tuple); + my $expected = shift; + if ($key ne $expected) { + print("WARNING: Format not as expected '$key' != '$expected'"); + $regex =~ s/$key=\((.*)\)/$key=$1/; + } + } + + if (defined shift) { + die("Fewer fields than expected in format"); + } + + return $regex; +} +$regex_fragdetails = generate_traceevent_regex("kmem/mm_page_alloc_extfrag", + $regex_fragdetails_default, + "page", "pfn", + "alloc_order", "fallback_order", "pageblock_order", + "alloc_migratetype", "fallback_migratetype", + "fragmenting", "change_ownership"); + +sub read_statline($) { + my $pid = $_[0]; + my $statline; + + if (open(STAT, "/proc/$pid/stat")) { + $statline = ; + close(STAT); + } + + if ($statline eq '') { + $statline = "-1 (UNKNOWN_PROCESS_NAME) R 0"; + } + + return $statline; +} + +sub guess_process_pid($$) { + my $pid = $_[0]; + my $statline = $_[1]; + + if ($pid == 0) { + return "swapper-0"; + } + + if ($statline !~ /$regex_statname/o) { + die("Failed to math stat line for process name :: $statline"); + } + return "$1-$pid"; +} + +sub parent_info($$) { + my $pid = $_[0]; + my $statline = $_[1]; + my $ppid; + + if ($pid == 0) { + return "NOPARENT-0"; + } + + if ($statline !~ /$regex_statppid/o) { + die("Failed to match stat line process ppid:: $statline"); + } + + # Read the ppid stat line + $ppid = $1; + return guess_process_pid($ppid, read_statline($ppid)); +} + +sub process_events { + my $traceevent; + my $process_pid; + my $cpus; + my $timestamp; + my $tracepoint; + my $details; + my $statline; + + # Read each line of the event log +EVENT_PROCESS: + while ($traceevent = ) { + if ($traceevent =~ /$regex_traceevent/o) { + $process_pid = $1; + $tracepoint = $4; + + if ($opt_read_procstat || $opt_prepend_parent) { + $process_pid =~ /(.*)-([0-9]*)$/; + my $process = $1; + my $pid = $2; + + $statline = read_statline($pid); + + if ($opt_read_procstat && $process eq '') { + $process_pid = guess_process_pid($pid, $statline); + } + + if ($opt_prepend_parent) { + $process_pid = parent_info($pid, $statline) . " :: $process_pid"; + } + } + + # Unnecessary in this script. Uncomment if required + # $cpus = $2; + # $timestamp = $3; + } else { + next; + } + + # Perl Switch() sucks majorly + if ($tracepoint eq "mm_page_alloc") { + $perprocesspid{$process_pid}->{MM_PAGE_ALLOC}++; + } elsif ($tracepoint eq "mm_page_free") { + $perprocesspid{$process_pid}->{MM_PAGE_FREE}++ + } elsif ($tracepoint eq "mm_page_free_batched") { + $perprocesspid{$process_pid}->{MM_PAGE_FREE_BATCHED}++; + } elsif ($tracepoint eq "mm_page_pcpu_drain") { + $perprocesspid{$process_pid}->{MM_PAGE_PCPU_DRAIN}++; + $perprocesspid{$process_pid}->{STATE_PCPU_PAGES_DRAINED}++; + } elsif ($tracepoint eq "mm_page_alloc_zone_locked") { + $perprocesspid{$process_pid}->{MM_PAGE_ALLOC_ZONE_LOCKED}++; + $perprocesspid{$process_pid}->{STATE_PCPU_PAGES_REFILLED}++; + } elsif ($tracepoint eq "mm_page_alloc_extfrag") { + + # Extract the details of the event now + $details = $5; + + my ($page, $pfn); + my ($alloc_order, $fallback_order, $pageblock_order); + my ($alloc_migratetype, $fallback_migratetype); + my ($fragmenting, $change_ownership); + + if ($details !~ /$regex_fragdetails/o) { + print "WARNING: Failed to parse mm_page_alloc_extfrag as expected\n"; + next; + } + + $perprocesspid{$process_pid}->{MM_PAGE_ALLOC_EXTFRAG}++; + $page = $1; + $pfn = $2; + $alloc_order = $3; + $fallback_order = $4; + $pageblock_order = $5; + $alloc_migratetype = $6; + $fallback_migratetype = $7; + $fragmenting = $8; + $change_ownership = $9; + + if ($fragmenting) { + $perprocesspid{$process_pid}->{HIGH_EXT_FRAG}++; + if ($fallback_order <= 3) { + $perprocesspid{$process_pid}->{HIGH_EXT_FRAGMENT_SEVERE}++; + } else { + $perprocesspid{$process_pid}->{HIGH_EXT_FRAGMENT_MODERATE}++; + } + } + if ($change_ownership) { + $perprocesspid{$process_pid}->{HIGH_EXT_FRAGMENT_CHANGED}++; + } + } else { + $perprocesspid{$process_pid}->{EVENT_UNKNOWN}++; + } + + # Catch a full pcpu drain event + if ($perprocesspid{$process_pid}->{STATE_PCPU_PAGES_DRAINED} && + $tracepoint ne "mm_page_pcpu_drain") { + + $perprocesspid{$process_pid}->{HIGH_PCPU_DRAINS}++; + $perprocesspid{$process_pid}->{STATE_PCPU_PAGES_DRAINED} = 0; + } + + # Catch a full pcpu refill event + if ($perprocesspid{$process_pid}->{STATE_PCPU_PAGES_REFILLED} && + $tracepoint ne "mm_page_alloc_zone_locked") { + $perprocesspid{$process_pid}->{HIGH_PCPU_REFILLS}++; + $perprocesspid{$process_pid}->{STATE_PCPU_PAGES_REFILLED} = 0; + } + + if ($sigint_pending) { + last EVENT_PROCESS; + } + } +} + +sub dump_stats { + my $hashref = shift; + my %stats = %$hashref; + + # Dump per-process stats + my $process_pid; + my $max_strlen = 0; + + # Get the maximum process name + foreach $process_pid (keys %perprocesspid) { + my $len = length($process_pid); + if ($len > $max_strlen) { + $max_strlen = $len; + } + } + $max_strlen += 2; + + printf("\n"); + printf("%-" . $max_strlen . "s %8s %10s %8s %8s %8s %8s %8s %8s %8s %8s %8s %8s %8s\n", + "Process", "Pages", "Pages", "Pages", "Pages", "PCPU", "PCPU", "PCPU", "Fragment", "Fragment", "MigType", "Fragment", "Fragment", "Unknown"); + printf("%-" . $max_strlen . "s %8s %10s %8s %8s %8s %8s %8s %8s %8s %8s %8s %8s %8s\n", + "details", "allocd", "allocd", "freed", "freed", "pages", "drains", "refills", "Fallback", "Causing", "Changed", "Severe", "Moderate", ""); + + printf("%-" . $max_strlen . "s %8s %10s %8s %8s %8s %8s %8s %8s %8s %8s %8s %8s %8s\n", + "", "", "under lock", "direct", "pagevec", "drain", "", "", "", "", "", "", "", ""); + + foreach $process_pid (keys %stats) { + # Dump final aggregates + if ($stats{$process_pid}->{STATE_PCPU_PAGES_DRAINED}) { + $stats{$process_pid}->{HIGH_PCPU_DRAINS}++; + $stats{$process_pid}->{STATE_PCPU_PAGES_DRAINED} = 0; + } + if ($stats{$process_pid}->{STATE_PCPU_PAGES_REFILLED}) { + $stats{$process_pid}->{HIGH_PCPU_REFILLS}++; + $stats{$process_pid}->{STATE_PCPU_PAGES_REFILLED} = 0; + } + + printf("%-" . $max_strlen . "s %8d %10d %8d %8d %8d %8d %8d %8d %8d %8d %8d %8d %8d\n", + $process_pid, + $stats{$process_pid}->{MM_PAGE_ALLOC}, + $stats{$process_pid}->{MM_PAGE_ALLOC_ZONE_LOCKED}, + $stats{$process_pid}->{MM_PAGE_FREE}, + $stats{$process_pid}->{MM_PAGE_FREE_BATCHED}, + $stats{$process_pid}->{MM_PAGE_PCPU_DRAIN}, + $stats{$process_pid}->{HIGH_PCPU_DRAINS}, + $stats{$process_pid}->{HIGH_PCPU_REFILLS}, + $stats{$process_pid}->{MM_PAGE_ALLOC_EXTFRAG}, + $stats{$process_pid}->{HIGH_EXT_FRAG}, + $stats{$process_pid}->{HIGH_EXT_FRAGMENT_CHANGED}, + $stats{$process_pid}->{HIGH_EXT_FRAGMENT_SEVERE}, + $stats{$process_pid}->{HIGH_EXT_FRAGMENT_MODERATE}, + $stats{$process_pid}->{EVENT_UNKNOWN}); + } +} + +sub aggregate_perprocesspid() { + my $process_pid; + my $process; + undef %perprocess; + + foreach $process_pid (keys %perprocesspid) { + $process = $process_pid; + $process =~ s/-([0-9])*$//; + if ($process eq '') { + $process = "NO_PROCESS_NAME"; + } + + $perprocess{$process}->{MM_PAGE_ALLOC} += $perprocesspid{$process_pid}->{MM_PAGE_ALLOC}; + $perprocess{$process}->{MM_PAGE_ALLOC_ZONE_LOCKED} += $perprocesspid{$process_pid}->{MM_PAGE_ALLOC_ZONE_LOCKED}; + $perprocess{$process}->{MM_PAGE_FREE} += $perprocesspid{$process_pid}->{MM_PAGE_FREE}; + $perprocess{$process}->{MM_PAGE_FREE_BATCHED} += $perprocesspid{$process_pid}->{MM_PAGE_FREE_BATCHED}; + $perprocess{$process}->{MM_PAGE_PCPU_DRAIN} += $perprocesspid{$process_pid}->{MM_PAGE_PCPU_DRAIN}; + $perprocess{$process}->{HIGH_PCPU_DRAINS} += $perprocesspid{$process_pid}->{HIGH_PCPU_DRAINS}; + $perprocess{$process}->{HIGH_PCPU_REFILLS} += $perprocesspid{$process_pid}->{HIGH_PCPU_REFILLS}; + $perprocess{$process}->{MM_PAGE_ALLOC_EXTFRAG} += $perprocesspid{$process_pid}->{MM_PAGE_ALLOC_EXTFRAG}; + $perprocess{$process}->{HIGH_EXT_FRAG} += $perprocesspid{$process_pid}->{HIGH_EXT_FRAG}; + $perprocess{$process}->{HIGH_EXT_FRAGMENT_CHANGED} += $perprocesspid{$process_pid}->{HIGH_EXT_FRAGMENT_CHANGED}; + $perprocess{$process}->{HIGH_EXT_FRAGMENT_SEVERE} += $perprocesspid{$process_pid}->{HIGH_EXT_FRAGMENT_SEVERE}; + $perprocess{$process}->{HIGH_EXT_FRAGMENT_MODERATE} += $perprocesspid{$process_pid}->{HIGH_EXT_FRAGMENT_MODERATE}; + $perprocess{$process}->{EVENT_UNKNOWN} += $perprocesspid{$process_pid}->{EVENT_UNKNOWN}; + } +} + +sub report() { + if (!$opt_ignorepid) { + dump_stats(\%perprocesspid); + } else { + aggregate_perprocesspid(); + dump_stats(\%perprocess); + } +} + +# Process events or signals until neither is available +sub signal_loop() { + my $sigint_processed; + do { + $sigint_processed = 0; + process_events(); + + # Handle pending signals if any + if ($sigint_pending) { + my $current_time = time; + + if ($sigint_exit) { + print "Received exit signal\n"; + $sigint_pending = 0; + } + if ($sigint_report) { + if ($current_time >= $sigint_received + 2) { + report(); + $sigint_report = 0; + $sigint_pending = 0; + $sigint_processed = 1; + } + } + } + } while ($sigint_pending || $sigint_processed); +} + +signal_loop(); +report(); diff --git a/Documentation/trace/postprocess/trace-vmscan-postprocess.pl b/Documentation/trace/postprocess/trace-vmscan-postprocess.pl new file mode 100644 index 000000000..048dc0dbc --- /dev/null +++ b/Documentation/trace/postprocess/trace-vmscan-postprocess.pl @@ -0,0 +1,752 @@ +#!/usr/bin/env perl +# This is a POC for reading the text representation of trace output related to +# page reclaim. It makes an attempt to extract some high-level information on +# what is going on. The accuracy of the parser may vary +# +# Example usage: trace-vmscan-postprocess.pl < /sys/kernel/tracing/trace_pipe +# other options +# --read-procstat If the trace lacks process info, get it from /proc +# --ignore-pid Aggregate processes of the same name together +# +# Copyright (c) IBM Corporation 2009 +# Author: Mel Gorman +use strict; +use Getopt::Long; + +# Tracepoint events +use constant MM_VMSCAN_DIRECT_RECLAIM_BEGIN => 1; +use constant MM_VMSCAN_DIRECT_RECLAIM_END => 2; +use constant MM_VMSCAN_KSWAPD_WAKE => 3; +use constant MM_VMSCAN_KSWAPD_SLEEP => 4; +use constant MM_VMSCAN_LRU_SHRINK_ACTIVE => 5; +use constant MM_VMSCAN_LRU_SHRINK_INACTIVE => 6; +use constant MM_VMSCAN_LRU_ISOLATE => 7; +use constant MM_VMSCAN_WRITEPAGE_FILE_SYNC => 8; +use constant MM_VMSCAN_WRITEPAGE_ANON_SYNC => 9; +use constant MM_VMSCAN_WRITEPAGE_FILE_ASYNC => 10; +use constant MM_VMSCAN_WRITEPAGE_ANON_ASYNC => 11; +use constant MM_VMSCAN_WRITEPAGE_ASYNC => 12; +use constant EVENT_UNKNOWN => 13; + +# Per-order events +use constant MM_VMSCAN_DIRECT_RECLAIM_BEGIN_PERORDER => 11; +use constant MM_VMSCAN_WAKEUP_KSWAPD_PERORDER => 12; +use constant MM_VMSCAN_KSWAPD_WAKE_PERORDER => 13; +use constant HIGH_KSWAPD_REWAKEUP_PERORDER => 14; + +# Constants used to track state +use constant STATE_DIRECT_BEGIN => 15; +use constant STATE_DIRECT_ORDER => 16; +use constant STATE_KSWAPD_BEGIN => 17; +use constant STATE_KSWAPD_ORDER => 18; + +# High-level events extrapolated from tracepoints +use constant HIGH_DIRECT_RECLAIM_LATENCY => 19; +use constant HIGH_KSWAPD_LATENCY => 20; +use constant HIGH_KSWAPD_REWAKEUP => 21; +use constant HIGH_NR_SCANNED => 22; +use constant HIGH_NR_TAKEN => 23; +use constant HIGH_NR_RECLAIMED => 24; +use constant HIGH_NR_FILE_SCANNED => 25; +use constant HIGH_NR_ANON_SCANNED => 26; +use constant HIGH_NR_FILE_RECLAIMED => 27; +use constant HIGH_NR_ANON_RECLAIMED => 28; + +my %perprocesspid; +my %perprocess; +my %last_procmap; +my $opt_ignorepid; +my $opt_read_procstat; + +my $total_wakeup_kswapd; +my ($total_direct_reclaim, $total_direct_nr_scanned); +my ($total_direct_nr_file_scanned, $total_direct_nr_anon_scanned); +my ($total_direct_latency, $total_kswapd_latency); +my ($total_direct_nr_reclaimed); +my ($total_direct_nr_file_reclaimed, $total_direct_nr_anon_reclaimed); +my ($total_direct_writepage_file_sync, $total_direct_writepage_file_async); +my ($total_direct_writepage_anon_sync, $total_direct_writepage_anon_async); +my ($total_kswapd_nr_scanned, $total_kswapd_wake); +my ($total_kswapd_nr_file_scanned, $total_kswapd_nr_anon_scanned); +my ($total_kswapd_writepage_file_sync, $total_kswapd_writepage_file_async); +my ($total_kswapd_writepage_anon_sync, $total_kswapd_writepage_anon_async); +my ($total_kswapd_nr_reclaimed); +my ($total_kswapd_nr_file_reclaimed, $total_kswapd_nr_anon_reclaimed); + +# Catch sigint and exit on request +my $sigint_report = 0; +my $sigint_exit = 0; +my $sigint_pending = 0; +my $sigint_received = 0; +sub sigint_handler { + my $current_time = time; + if ($current_time - 2 > $sigint_received) { + print "SIGINT received, report pending. Hit ctrl-c again to exit\n"; + $sigint_report = 1; + } else { + if (!$sigint_exit) { + print "Second SIGINT received quickly, exiting\n"; + } + $sigint_exit++; + } + + if ($sigint_exit > 3) { + print "Many SIGINTs received, exiting now without report\n"; + exit; + } + + $sigint_received = $current_time; + $sigint_pending = 1; +} +$SIG{INT} = "sigint_handler"; + +# Parse command line options +GetOptions( + 'ignore-pid' => \$opt_ignorepid, + 'read-procstat' => \$opt_read_procstat, +); + +# Defaults for dynamically discovered regex's +my $regex_direct_begin_default = 'order=([0-9]*) gfp_flags=([A-Z_|]*)'; +my $regex_direct_end_default = 'nr_reclaimed=([0-9]*)'; +my $regex_kswapd_wake_default = 'nid=([0-9]*) order=([0-9]*)'; +my $regex_kswapd_sleep_default = 'nid=([0-9]*)'; +my $regex_wakeup_kswapd_default = 'nid=([0-9]*) order=([0-9]*) gfp_flags=([A-Z_|]*)'; +my $regex_lru_isolate_default = 'classzone=([0-9]*) order=([0-9]*) nr_requested=([0-9]*) nr_scanned=([0-9]*) nr_skipped=([0-9]*) nr_taken=([0-9]*) lru=([a-z_]*)'; +my $regex_lru_shrink_inactive_default = 'nid=([0-9]*) nr_scanned=([0-9]*) nr_reclaimed=([0-9]*) nr_dirty=([0-9]*) nr_writeback=([0-9]*) nr_congested=([0-9]*) nr_immediate=([0-9]*) nr_activate_anon=([0-9]*) nr_activate_file=([0-9]*) nr_ref_keep=([0-9]*) nr_unmap_fail=([0-9]*) priority=([0-9]*) flags=([A-Z_|]*)'; +my $regex_lru_shrink_active_default = 'lru=([A-Z_]*) nr_taken=([0-9]*) nr_active=([0-9]*) nr_deactivated=([0-9]*) nr_referenced=([0-9]*) priority=([0-9]*) flags=([A-Z_|]*)' ; +my $regex_writepage_default = 'page=([0-9a-f]*) pfn=([0-9]*) flags=([A-Z_|]*)'; + +# Dyanically discovered regex +my $regex_direct_begin; +my $regex_direct_end; +my $regex_kswapd_wake; +my $regex_kswapd_sleep; +my $regex_wakeup_kswapd; +my $regex_lru_isolate; +my $regex_lru_shrink_inactive; +my $regex_lru_shrink_active; +my $regex_writepage; + +# Static regex used. Specified like this for readability and for use with /o +# (process_pid) (cpus ) ( time ) (tpoint ) (details) +my $regex_traceevent = '\s*([a-zA-Z0-9-]*)\s*(\[[0-9]*\])(\s*[dX.][Nnp.][Hhs.][0-9a-fA-F.]*|)\s*([0-9.]*):\s*([a-zA-Z_]*):\s*(.*)'; +my $regex_statname = '[-0-9]*\s\((.*)\).*'; +my $regex_statppid = '[-0-9]*\s\(.*\)\s[A-Za-z]\s([0-9]*).*'; + +sub generate_traceevent_regex { + my $event = shift; + my $default = shift; + my $regex; + + # Read the event format or use the default + if (!open (FORMAT, "/sys/kernel/tracing/events/$event/format")) { + print("WARNING: Event $event format string not found\n"); + return $default; + } else { + my $line; + while (!eof(FORMAT)) { + $line = ; + $line =~ s/, REC->.*//; + if ($line =~ /^print fmt:\s"(.*)".*/) { + $regex = $1; + $regex =~ s/%s/\([0-9a-zA-Z|_]*\)/g; + $regex =~ s/%p/\([0-9a-f]*\)/g; + $regex =~ s/%d/\([-0-9]*\)/g; + $regex =~ s/%ld/\([-0-9]*\)/g; + $regex =~ s/%lu/\([0-9]*\)/g; + } + } + } + + # Can't handle the print_flags stuff but in the context of this + # script, it really doesn't matter + $regex =~ s/\(REC.*\) \? __print_flags.*//; + + # Verify fields are in the right order + my $tuple; + foreach $tuple (split /\s/, $regex) { + my ($key, $value) = split(/=/, $tuple); + my $expected = shift; + if ($key ne $expected) { + print("WARNING: Format not as expected for event $event '$key' != '$expected'\n"); + $regex =~ s/$key=\((.*)\)/$key=$1/; + } + } + + if (defined shift) { + die("Fewer fields than expected in format"); + } + + return $regex; +} + +$regex_direct_begin = generate_traceevent_regex( + "vmscan/mm_vmscan_direct_reclaim_begin", + $regex_direct_begin_default, + "order", "gfp_flags"); +$regex_direct_end = generate_traceevent_regex( + "vmscan/mm_vmscan_direct_reclaim_end", + $regex_direct_end_default, + "nr_reclaimed"); +$regex_kswapd_wake = generate_traceevent_regex( + "vmscan/mm_vmscan_kswapd_wake", + $regex_kswapd_wake_default, + "nid", "order"); +$regex_kswapd_sleep = generate_traceevent_regex( + "vmscan/mm_vmscan_kswapd_sleep", + $regex_kswapd_sleep_default, + "nid"); +$regex_wakeup_kswapd = generate_traceevent_regex( + "vmscan/mm_vmscan_wakeup_kswapd", + $regex_wakeup_kswapd_default, + "nid", "order", "gfp_flags"); +$regex_lru_isolate = generate_traceevent_regex( + "vmscan/mm_vmscan_lru_isolate", + $regex_lru_isolate_default, + "classzone", "order", + "nr_requested", "nr_scanned", "nr_skipped", "nr_taken", + "lru"); +$regex_lru_shrink_inactive = generate_traceevent_regex( + "vmscan/mm_vmscan_lru_shrink_inactive", + $regex_lru_shrink_inactive_default, + "nid", "nr_scanned", "nr_reclaimed", "nr_dirty", "nr_writeback", + "nr_congested", "nr_immediate", "nr_activate_anon", + "nr_activate_file", "nr_ref_keep", + "nr_unmap_fail", "priority", "flags"); +$regex_lru_shrink_active = generate_traceevent_regex( + "vmscan/mm_vmscan_lru_shrink_active", + $regex_lru_shrink_active_default, + "nid", "nr_taken", "nr_active", "nr_deactivated", "nr_referenced", + "priority", "flags"); +$regex_writepage = generate_traceevent_regex( + "vmscan/mm_vmscan_write_folio", + $regex_writepage_default, + "page", "pfn", "flags"); + +sub read_statline($) { + my $pid = $_[0]; + my $statline; + + if (open(STAT, "/proc/$pid/stat")) { + $statline = ; + close(STAT); + } + + if ($statline eq '') { + $statline = "-1 (UNKNOWN_PROCESS_NAME) R 0"; + } + + return $statline; +} + +sub guess_process_pid($$) { + my $pid = $_[0]; + my $statline = $_[1]; + + if ($pid == 0) { + return "swapper-0"; + } + + if ($statline !~ /$regex_statname/o) { + die("Failed to math stat line for process name :: $statline"); + } + return "$1-$pid"; +} + +# Convert sec.usec timestamp format +sub timestamp_to_ms($) { + my $timestamp = $_[0]; + + my ($sec, $usec) = split (/\./, $timestamp); + return ($sec * 1000) + ($usec / 1000); +} + +sub process_events { + my $traceevent; + my $process_pid; + my $cpus; + my $timestamp; + my $tracepoint; + my $details; + my $statline; + + # Read each line of the event log +EVENT_PROCESS: + while ($traceevent = ) { + if ($traceevent =~ /$regex_traceevent/o) { + $process_pid = $1; + $timestamp = $4; + $tracepoint = $5; + + $process_pid =~ /(.*)-([0-9]*)$/; + my $process = $1; + my $pid = $2; + + if ($process eq "") { + $process = $last_procmap{$pid}; + $process_pid = "$process-$pid"; + } + $last_procmap{$pid} = $process; + + if ($opt_read_procstat) { + $statline = read_statline($pid); + if ($opt_read_procstat && $process eq '') { + $process_pid = guess_process_pid($pid, $statline); + } + } + } else { + next; + } + + # Perl Switch() sucks majorly + if ($tracepoint eq "mm_vmscan_direct_reclaim_begin") { + $timestamp = timestamp_to_ms($timestamp); + $perprocesspid{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN}++; + $perprocesspid{$process_pid}->{STATE_DIRECT_BEGIN} = $timestamp; + + $details = $6; + if ($details !~ /$regex_direct_begin/o) { + print "WARNING: Failed to parse mm_vmscan_direct_reclaim_begin as expected\n"; + print " $details\n"; + print " $regex_direct_begin\n"; + next; + } + my $order = $1; + $perprocesspid{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN_PERORDER}[$order]++; + $perprocesspid{$process_pid}->{STATE_DIRECT_ORDER} = $order; + } elsif ($tracepoint eq "mm_vmscan_direct_reclaim_end") { + # Count the event itself + my $index = $perprocesspid{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_END}; + $perprocesspid{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_END}++; + + # Record how long direct reclaim took this time + if (defined $perprocesspid{$process_pid}->{STATE_DIRECT_BEGIN}) { + $timestamp = timestamp_to_ms($timestamp); + my $order = $perprocesspid{$process_pid}->{STATE_DIRECT_ORDER}; + my $latency = ($timestamp - $perprocesspid{$process_pid}->{STATE_DIRECT_BEGIN}); + $perprocesspid{$process_pid}->{HIGH_DIRECT_RECLAIM_LATENCY}[$index] = "$order-$latency"; + } + } elsif ($tracepoint eq "mm_vmscan_kswapd_wake") { + $details = $6; + if ($details !~ /$regex_kswapd_wake/o) { + print "WARNING: Failed to parse mm_vmscan_kswapd_wake as expected\n"; + print " $details\n"; + print " $regex_kswapd_wake\n"; + next; + } + + my $order = $2; + $perprocesspid{$process_pid}->{STATE_KSWAPD_ORDER} = $order; + if (!$perprocesspid{$process_pid}->{STATE_KSWAPD_BEGIN}) { + $timestamp = timestamp_to_ms($timestamp); + $perprocesspid{$process_pid}->{MM_VMSCAN_KSWAPD_WAKE}++; + $perprocesspid{$process_pid}->{STATE_KSWAPD_BEGIN} = $timestamp; + $perprocesspid{$process_pid}->{MM_VMSCAN_KSWAPD_WAKE_PERORDER}[$order]++; + } else { + $perprocesspid{$process_pid}->{HIGH_KSWAPD_REWAKEUP}++; + $perprocesspid{$process_pid}->{HIGH_KSWAPD_REWAKEUP_PERORDER}[$order]++; + } + } elsif ($tracepoint eq "mm_vmscan_kswapd_sleep") { + + # Count the event itself + my $index = $perprocesspid{$process_pid}->{MM_VMSCAN_KSWAPD_SLEEP}; + $perprocesspid{$process_pid}->{MM_VMSCAN_KSWAPD_SLEEP}++; + + # Record how long kswapd was awake + $timestamp = timestamp_to_ms($timestamp); + my $order = $perprocesspid{$process_pid}->{STATE_KSWAPD_ORDER}; + my $latency = ($timestamp - $perprocesspid{$process_pid}->{STATE_KSWAPD_BEGIN}); + $perprocesspid{$process_pid}->{HIGH_KSWAPD_LATENCY}[$index] = "$order-$latency"; + $perprocesspid{$process_pid}->{STATE_KSWAPD_BEGIN} = 0; + } elsif ($tracepoint eq "mm_vmscan_wakeup_kswapd") { + $perprocesspid{$process_pid}->{MM_VMSCAN_WAKEUP_KSWAPD}++; + + $details = $6; + if ($details !~ /$regex_wakeup_kswapd/o) { + print "WARNING: Failed to parse mm_vmscan_wakeup_kswapd as expected\n"; + print " $details\n"; + print " $regex_wakeup_kswapd\n"; + next; + } + my $order = $2; + $perprocesspid{$process_pid}->{MM_VMSCAN_WAKEUP_KSWAPD_PERORDER}[$order]++; + } elsif ($tracepoint eq "mm_vmscan_lru_isolate") { + $details = $6; + if ($details !~ /$regex_lru_isolate/o) { + print "WARNING: Failed to parse mm_vmscan_lru_isolate as expected\n"; + print " $details\n"; + print " $regex_lru_isolate/o\n"; + next; + } + my $nr_scanned = $4; + my $lru = $7; + + # To closer match vmstat scanning statistics, only count + # inactive lru as scanning + if ($lru =~ /inactive_/) { + $perprocesspid{$process_pid}->{HIGH_NR_SCANNED} += $nr_scanned; + if ($lru =~ /_file/) { + $perprocesspid{$process_pid}->{HIGH_NR_FILE_SCANNED} += $nr_scanned; + } else { + $perprocesspid{$process_pid}->{HIGH_NR_ANON_SCANNED} += $nr_scanned; + } + } + } elsif ($tracepoint eq "mm_vmscan_lru_shrink_inactive") { + $details = $6; + if ($details !~ /$regex_lru_shrink_inactive/o) { + print "WARNING: Failed to parse mm_vmscan_lru_shrink_inactive as expected\n"; + print " $details\n"; + print " $regex_lru_shrink_inactive/o\n"; + next; + } + + my $nr_reclaimed = $3; + my $flags = $13; + my $file = 0; + if ($flags =~ /RECLAIM_WB_FILE/) { + $file = 1; + } + $perprocesspid{$process_pid}->{HIGH_NR_RECLAIMED} += $nr_reclaimed; + if ($file) { + $perprocesspid{$process_pid}->{HIGH_NR_FILE_RECLAIMED} += $nr_reclaimed; + } else { + $perprocesspid{$process_pid}->{HIGH_NR_ANON_RECLAIMED} += $nr_reclaimed; + } + } elsif ($tracepoint eq "mm_vmscan_writepage") { + $details = $6; + if ($details !~ /$regex_writepage/o) { + print "WARNING: Failed to parse mm_vmscan_writepage as expected\n"; + print " $details\n"; + print " $regex_writepage\n"; + next; + } + + my $flags = $3; + my $file = 0; + my $sync_io = 0; + if ($flags =~ /RECLAIM_WB_FILE/) { + $file = 1; + } + if ($flags =~ /RECLAIM_WB_SYNC/) { + $sync_io = 1; + } + if ($sync_io) { + if ($file) { + $perprocesspid{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC}++; + } else { + $perprocesspid{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC}++; + } + } else { + if ($file) { + $perprocesspid{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC}++; + } else { + $perprocesspid{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_ASYNC}++; + } + } + } else { + $perprocesspid{$process_pid}->{EVENT_UNKNOWN}++; + } + + if ($sigint_pending) { + last EVENT_PROCESS; + } + } +} + +sub dump_stats { + my $hashref = shift; + my %stats = %$hashref; + + # Dump per-process stats + my $process_pid; + my $max_strlen = 0; + + # Get the maximum process name + foreach $process_pid (keys %perprocesspid) { + my $len = length($process_pid); + if ($len > $max_strlen) { + $max_strlen = $len; + } + } + $max_strlen += 2; + + # Work out latencies + printf("\n") if !$opt_ignorepid; + printf("Reclaim latencies expressed as order-latency_in_ms\n") if !$opt_ignorepid; + foreach $process_pid (keys %stats) { + + if (!$stats{$process_pid}->{HIGH_DIRECT_RECLAIM_LATENCY}[0] && + !$stats{$process_pid}->{HIGH_KSWAPD_LATENCY}[0]) { + next; + } + + printf "%-" . $max_strlen . "s ", $process_pid if !$opt_ignorepid; + my $index = 0; + while (defined $stats{$process_pid}->{HIGH_DIRECT_RECLAIM_LATENCY}[$index] || + defined $stats{$process_pid}->{HIGH_KSWAPD_LATENCY}[$index]) { + + if ($stats{$process_pid}->{HIGH_DIRECT_RECLAIM_LATENCY}[$index]) { + printf("%s ", $stats{$process_pid}->{HIGH_DIRECT_RECLAIM_LATENCY}[$index]) if !$opt_ignorepid; + my ($dummy, $latency) = split(/-/, $stats{$process_pid}->{HIGH_DIRECT_RECLAIM_LATENCY}[$index]); + $total_direct_latency += $latency; + } else { + printf("%s ", $stats{$process_pid}->{HIGH_KSWAPD_LATENCY}[$index]) if !$opt_ignorepid; + my ($dummy, $latency) = split(/-/, $stats{$process_pid}->{HIGH_KSWAPD_LATENCY}[$index]); + $total_kswapd_latency += $latency; + } + $index++; + } + print "\n" if !$opt_ignorepid; + } + + # Print out process activity + printf("\n"); + printf("%-" . $max_strlen . "s %8s %10s %8s %8s %8s %8s %8s %8s\n", "Process", "Direct", "Wokeup", "Pages", "Pages", "Pages", "Pages", "Time"); + printf("%-" . $max_strlen . "s %8s %10s %8s %8s %8s %8s %8s %8s\n", "details", "Rclms", "Kswapd", "Scanned", "Rclmed", "Sync-IO", "ASync-IO", "Stalled"); + foreach $process_pid (keys %stats) { + + if (!$stats{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN}) { + next; + } + + $total_direct_reclaim += $stats{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN}; + $total_wakeup_kswapd += $stats{$process_pid}->{MM_VMSCAN_WAKEUP_KSWAPD}; + $total_direct_nr_scanned += $stats{$process_pid}->{HIGH_NR_SCANNED}; + $total_direct_nr_file_scanned += $stats{$process_pid}->{HIGH_NR_FILE_SCANNED}; + $total_direct_nr_anon_scanned += $stats{$process_pid}->{HIGH_NR_ANON_SCANNED}; + $total_direct_nr_reclaimed += $stats{$process_pid}->{HIGH_NR_RECLAIMED}; + $total_direct_nr_file_reclaimed += $stats{$process_pid}->{HIGH_NR_FILE_RECLAIMED}; + $total_direct_nr_anon_reclaimed += $stats{$process_pid}->{HIGH_NR_ANON_RECLAIMED}; + $total_direct_writepage_file_sync += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC}; + $total_direct_writepage_anon_sync += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC}; + $total_direct_writepage_file_async += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC}; + + $total_direct_writepage_anon_async += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_ASYNC}; + + my $index = 0; + my $this_reclaim_delay = 0; + while (defined $stats{$process_pid}->{HIGH_DIRECT_RECLAIM_LATENCY}[$index]) { + my ($dummy, $latency) = split(/-/, $stats{$process_pid}->{HIGH_DIRECT_RECLAIM_LATENCY}[$index]); + $this_reclaim_delay += $latency; + $index++; + } + + printf("%-" . $max_strlen . "s %8d %10d %8u %8u %8u %8u %8.3f", + $process_pid, + $stats{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN}, + $stats{$process_pid}->{MM_VMSCAN_WAKEUP_KSWAPD}, + $stats{$process_pid}->{HIGH_NR_SCANNED}, + $stats{$process_pid}->{HIGH_NR_FILE_SCANNED}, + $stats{$process_pid}->{HIGH_NR_ANON_SCANNED}, + $stats{$process_pid}->{HIGH_NR_RECLAIMED}, + $stats{$process_pid}->{HIGH_NR_FILE_RECLAIMED}, + $stats{$process_pid}->{HIGH_NR_ANON_RECLAIMED}, + $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC} + $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC}, + $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC} + $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_ASYNC}, + $this_reclaim_delay / 1000); + + if ($stats{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN}) { + print " "; + for (my $order = 0; $order < 20; $order++) { + my $count = $stats{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN_PERORDER}[$order]; + if ($count != 0) { + print "direct-$order=$count "; + } + } + } + if ($stats{$process_pid}->{MM_VMSCAN_WAKEUP_KSWAPD}) { + print " "; + for (my $order = 0; $order < 20; $order++) { + my $count = $stats{$process_pid}->{MM_VMSCAN_WAKEUP_KSWAPD_PERORDER}[$order]; + if ($count != 0) { + print "wakeup-$order=$count "; + } + } + } + + print "\n"; + } + + # Print out kswapd activity + printf("\n"); + printf("%-" . $max_strlen . "s %8s %10s %8s %8s %8s %8s\n", "Kswapd", "Kswapd", "Order", "Pages", "Pages", "Pages", "Pages"); + printf("%-" . $max_strlen . "s %8s %10s %8s %8s %8s %8s\n", "Instance", "Wakeups", "Re-wakeup", "Scanned", "Rclmed", "Sync-IO", "ASync-IO"); + foreach $process_pid (keys %stats) { + + if (!$stats{$process_pid}->{MM_VMSCAN_KSWAPD_WAKE}) { + next; + } + + $total_kswapd_wake += $stats{$process_pid}->{MM_VMSCAN_KSWAPD_WAKE}; + $total_kswapd_nr_scanned += $stats{$process_pid}->{HIGH_NR_SCANNED}; + $total_kswapd_nr_file_scanned += $stats{$process_pid}->{HIGH_NR_FILE_SCANNED}; + $total_kswapd_nr_anon_scanned += $stats{$process_pid}->{HIGH_NR_ANON_SCANNED}; + $total_kswapd_nr_reclaimed += $stats{$process_pid}->{HIGH_NR_RECLAIMED}; + $total_kswapd_nr_file_reclaimed += $stats{$process_pid}->{HIGH_NR_FILE_RECLAIMED}; + $total_kswapd_nr_anon_reclaimed += $stats{$process_pid}->{HIGH_NR_ANON_RECLAIMED}; + $total_kswapd_writepage_file_sync += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC}; + $total_kswapd_writepage_anon_sync += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC}; + $total_kswapd_writepage_file_async += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC}; + $total_kswapd_writepage_anon_async += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_ASYNC}; + + printf("%-" . $max_strlen . "s %8d %10d %8u %8u %8i %8u", + $process_pid, + $stats{$process_pid}->{MM_VMSCAN_KSWAPD_WAKE}, + $stats{$process_pid}->{HIGH_KSWAPD_REWAKEUP}, + $stats{$process_pid}->{HIGH_NR_SCANNED}, + $stats{$process_pid}->{HIGH_NR_FILE_SCANNED}, + $stats{$process_pid}->{HIGH_NR_ANON_SCANNED}, + $stats{$process_pid}->{HIGH_NR_RECLAIMED}, + $stats{$process_pid}->{HIGH_NR_FILE_RECLAIMED}, + $stats{$process_pid}->{HIGH_NR_ANON_RECLAIMED}, + $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC} + $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC}, + $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC} + $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_ASYNC}); + + if ($stats{$process_pid}->{MM_VMSCAN_KSWAPD_WAKE}) { + print " "; + for (my $order = 0; $order < 20; $order++) { + my $count = $stats{$process_pid}->{MM_VMSCAN_KSWAPD_WAKE_PERORDER}[$order]; + if ($count != 0) { + print "wake-$order=$count "; + } + } + } + if ($stats{$process_pid}->{HIGH_KSWAPD_REWAKEUP}) { + print " "; + for (my $order = 0; $order < 20; $order++) { + my $count = $stats{$process_pid}->{HIGH_KSWAPD_REWAKEUP_PERORDER}[$order]; + if ($count != 0) { + print "rewake-$order=$count "; + } + } + } + printf("\n"); + } + + # Print out summaries + $total_direct_latency /= 1000; + $total_kswapd_latency /= 1000; + print "\nSummary\n"; + print "Direct reclaims: $total_direct_reclaim\n"; + print "Direct reclaim pages scanned: $total_direct_nr_scanned\n"; + print "Direct reclaim file pages scanned: $total_direct_nr_file_scanned\n"; + print "Direct reclaim anon pages scanned: $total_direct_nr_anon_scanned\n"; + print "Direct reclaim pages reclaimed: $total_direct_nr_reclaimed\n"; + print "Direct reclaim file pages reclaimed: $total_direct_nr_file_reclaimed\n"; + print "Direct reclaim anon pages reclaimed: $total_direct_nr_anon_reclaimed\n"; + print "Direct reclaim write file sync I/O: $total_direct_writepage_file_sync\n"; + print "Direct reclaim write anon sync I/O: $total_direct_writepage_anon_sync\n"; + print "Direct reclaim write file async I/O: $total_direct_writepage_file_async\n"; + print "Direct reclaim write anon async I/O: $total_direct_writepage_anon_async\n"; + print "Wake kswapd requests: $total_wakeup_kswapd\n"; + printf "Time stalled direct reclaim: %-1.2f seconds\n", $total_direct_latency; + print "\n"; + print "Kswapd wakeups: $total_kswapd_wake\n"; + print "Kswapd pages scanned: $total_kswapd_nr_scanned\n"; + print "Kswapd file pages scanned: $total_kswapd_nr_file_scanned\n"; + print "Kswapd anon pages scanned: $total_kswapd_nr_anon_scanned\n"; + print "Kswapd pages reclaimed: $total_kswapd_nr_reclaimed\n"; + print "Kswapd file pages reclaimed: $total_kswapd_nr_file_reclaimed\n"; + print "Kswapd anon pages reclaimed: $total_kswapd_nr_anon_reclaimed\n"; + print "Kswapd reclaim write file sync I/O: $total_kswapd_writepage_file_sync\n"; + print "Kswapd reclaim write anon sync I/O: $total_kswapd_writepage_anon_sync\n"; + print "Kswapd reclaim write file async I/O: $total_kswapd_writepage_file_async\n"; + print "Kswapd reclaim write anon async I/O: $total_kswapd_writepage_anon_async\n"; + printf "Time kswapd awake: %-1.2f seconds\n", $total_kswapd_latency; +} + +sub aggregate_perprocesspid() { + my $process_pid; + my $process; + undef %perprocess; + + foreach $process_pid (keys %perprocesspid) { + $process = $process_pid; + $process =~ s/-([0-9])*$//; + if ($process eq '') { + $process = "NO_PROCESS_NAME"; + } + + $perprocess{$process}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN} += $perprocesspid{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN}; + $perprocess{$process}->{MM_VMSCAN_KSWAPD_WAKE} += $perprocesspid{$process_pid}->{MM_VMSCAN_KSWAPD_WAKE}; + $perprocess{$process}->{MM_VMSCAN_WAKEUP_KSWAPD} += $perprocesspid{$process_pid}->{MM_VMSCAN_WAKEUP_KSWAPD}; + $perprocess{$process}->{HIGH_KSWAPD_REWAKEUP} += $perprocesspid{$process_pid}->{HIGH_KSWAPD_REWAKEUP}; + $perprocess{$process}->{HIGH_NR_SCANNED} += $perprocesspid{$process_pid}->{HIGH_NR_SCANNED}; + $perprocess{$process}->{HIGH_NR_FILE_SCANNED} += $perprocesspid{$process_pid}->{HIGH_NR_FILE_SCANNED}; + $perprocess{$process}->{HIGH_NR_ANON_SCANNED} += $perprocesspid{$process_pid}->{HIGH_NR_ANON_SCANNED}; + $perprocess{$process}->{HIGH_NR_RECLAIMED} += $perprocesspid{$process_pid}->{HIGH_NR_RECLAIMED}; + $perprocess{$process}->{HIGH_NR_FILE_RECLAIMED} += $perprocesspid{$process_pid}->{HIGH_NR_FILE_RECLAIMED}; + $perprocess{$process}->{HIGH_NR_ANON_RECLAIMED} += $perprocesspid{$process_pid}->{HIGH_NR_ANON_RECLAIMED}; + $perprocess{$process}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC} += $perprocesspid{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC}; + $perprocess{$process}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC} += $perprocesspid{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC}; + $perprocess{$process}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC} += $perprocesspid{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC}; + $perprocess{$process}->{MM_VMSCAN_WRITEPAGE_ANON_ASYNC} += $perprocesspid{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_ASYNC}; + + for (my $order = 0; $order < 20; $order++) { + $perprocess{$process}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN_PERORDER}[$order] += $perprocesspid{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN_PERORDER}[$order]; + $perprocess{$process}->{MM_VMSCAN_WAKEUP_KSWAPD_PERORDER}[$order] += $perprocesspid{$process_pid}->{MM_VMSCAN_WAKEUP_KSWAPD_PERORDER}[$order]; + $perprocess{$process}->{MM_VMSCAN_KSWAPD_WAKE_PERORDER}[$order] += $perprocesspid{$process_pid}->{MM_VMSCAN_KSWAPD_WAKE_PERORDER}[$order]; + + } + + # Aggregate direct reclaim latencies + my $wr_index = $perprocess{$process}->{MM_VMSCAN_DIRECT_RECLAIM_END}; + my $rd_index = 0; + while (defined $perprocesspid{$process_pid}->{HIGH_DIRECT_RECLAIM_LATENCY}[$rd_index]) { + $perprocess{$process}->{HIGH_DIRECT_RECLAIM_LATENCY}[$wr_index] = $perprocesspid{$process_pid}->{HIGH_DIRECT_RECLAIM_LATENCY}[$rd_index]; + $rd_index++; + $wr_index++; + } + $perprocess{$process}->{MM_VMSCAN_DIRECT_RECLAIM_END} = $wr_index; + + # Aggregate kswapd latencies + my $wr_index = $perprocess{$process}->{MM_VMSCAN_KSWAPD_SLEEP}; + my $rd_index = 0; + while (defined $perprocesspid{$process_pid}->{HIGH_KSWAPD_LATENCY}[$rd_index]) { + $perprocess{$process}->{HIGH_KSWAPD_LATENCY}[$wr_index] = $perprocesspid{$process_pid}->{HIGH_KSWAPD_LATENCY}[$rd_index]; + $rd_index++; + $wr_index++; + } + $perprocess{$process}->{MM_VMSCAN_DIRECT_RECLAIM_END} = $wr_index; + } +} + +sub report() { + if (!$opt_ignorepid) { + dump_stats(\%perprocesspid); + } else { + aggregate_perprocesspid(); + dump_stats(\%perprocess); + } +} + +# Process events or signals until neither is available +sub signal_loop() { + my $sigint_processed; + do { + $sigint_processed = 0; + process_events(); + + # Handle pending signals if any + if ($sigint_pending) { + my $current_time = time; + + if ($sigint_exit) { + print "Received exit signal\n"; + $sigint_pending = 0; + } + if ($sigint_report) { + if ($current_time >= $sigint_received + 2) { + report(); + $sigint_report = 0; + $sigint_pending = 0; + $sigint_processed = 1; + } + } + } + } while ($sigint_pending || $sigint_processed); +} + +signal_loop(); +report(); -- cgit v1.3.1