linux-trace-devel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: John Kacur <jkacur@redhat.com>
To: Phil Auld <pauld@redhat.com>
Cc: Slavomir Kaslev <kaslevs@vmware.com>,
	rostedt@goodmis.org, linux-trace-devel@vger.kernel.org,
	ykaradzhov@vmware.com, jbacik@fb.com, tstoyanov@vmware.com,
	slavomir.kaslev@gmail.com
Subject: Re: [PATCH v4 1/2] trace-cmd: Optimize how pid filters are expressed
Date: Wed, 17 Apr 2019 16:18:50 +0200 (CEST)	[thread overview]
Message-ID: <alpine.LFD.2.21.1904171616010.6386@planxty> (raw)
In-Reply-To: <20190417135858.GD6118@pauld.bos.csb>



On Wed, 17 Apr 2019, Phil Auld wrote:

> On Wed, Apr 17, 2019 at 04:09:58PM +0300 Slavomir Kaslev wrote:
> > Express pid filters as allowed/disallowed filter ranges
> > 
> >   (pid>=100&&pid<=103)
> > 
> > instead of specifying them per pid
> > 
> >   (pid==100||pid==101||pid==102||pid==103)
> > 
> > This makes the size of the resulting filter smaller (and faster) and avoids
> > overflowing the filter size limit of one page which we can hit on bigger
> > machines (say >160 CPUs).
> 
> This one works as well :)
> 
> I finally hit a case where my trace-cmd pids were non-contiguous and 
> this split the range up correctly. 
> 
> 
> FILTER write /sys/kernel/debug/tracing/events/sched/sched_kthread_stop/filter (len 74) value "(common_pid<21420||common_pid>21425)&&(common_pid<21265||common_pid>21418)"
> FILTER write /sys/kernel/debug/tracing/events/sched/sched_kthread_stop_ret/filter (len 74) value "(common_pid<21420||common_pid>21425)&&(common_pid<21265||common_pid>21418)"
> ...
> FILTER write /sys/kernel/debug/tracing/events/sched/sched_switch/filter (len 142) value "(common_pid<21420||common_pid>21425)&&(common_pid<21265||common_pid>21418)||(next_pid<21420||next_pid>21425)&&(next_pid<21265||next_pid>21418)"

It seems crazy that we write "common_pid", instead of "pid" or "cpid", or 
something like that.



> 
> 
> The latter is correct given precendce of && before || but I wonder if () don't make sense? I always have to look
> that one up :)
> 
> If I were writing that in code I'd probably put in the extra ()s, but since it's generated and no
> one actually sees it, probably okay and simpler as is. 
> 
>  
> Having seen that and having tried it on a few other machines I'd be more willing to have a
> 
> Tested-by: Phil Auld <pauld@redhat.com>  
> 
> on it, if you want it.
> 
> Cheers,
> Phil
> 
> 
> > 
> > Signed-off-by: Slavomir Kaslev <kaslevs@vmware.com>
> > Reported-by: Phil Auld <pauld@redhat.com>
> > Suggested-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
> > ---
> >  tracecmd/trace-record.c | 117 +++++++++++++++++++++++++++-------------
> >  1 file changed, 81 insertions(+), 36 deletions(-)
> > 
> > diff --git a/tracecmd/trace-record.c b/tracecmd/trace-record.c
> > index a3a34f1..4523128 100644
> > --- a/tracecmd/trace-record.c
> > +++ b/tracecmd/trace-record.c
> > @@ -951,10 +951,63 @@ static void update_ftrace_pids(int reset)
> >  static void update_event_filters(struct buffer_instance *instance);
> >  static void update_pid_event_filters(struct buffer_instance *instance);
> >  
> > +static void append_filter_pid_range(char **filter, int *curr_len,
> > +				    const char *field,
> > +				    int start_pid, int end_pid, bool exclude)
> > +{
> > +	const char *op = "", *op1, *op2, *op3;
> > +	int len;
> > +
> > +	if (*filter && **filter)
> > +		op = exclude ? "&&" : "||";
> > +
> > +	/* Handle thus case explicitly so that we get `pid==3` instead of
> > +	 * `pid>=3&&pid<=3` for singleton ranges
> > +	 */
> > +	if (start_pid == end_pid) {
> > +#define FMT	"%s(%s%s%d)"
> > +		len = snprintf(NULL, 0, FMT, op,
> > +			       field, exclude ? "!=" : "==", start_pid);
> > +		*filter = realloc(*filter, *curr_len + len + 1);
> > +		if (!*filter)
> > +			die("realloc");
> > +
> > +		len = snprintf(*filter + *curr_len, len + 1, FMT, op,
> > +			       field, exclude ? "!=" : "==", start_pid);
> > +		*curr_len += len;
> > +
> > +		return;
> > +#undef FMT
> > +	}
> > +
> > +	if (exclude) {
> > +		op1 = "<";
> > +		op2 = "||";
> > +		op3 = ">";
> > +	} else {
> > +		op1 = ">=";
> > +		op2 = "&&";
> > +		op3 = "<=";
> > +	}
> > +
> > +#define FMT	"%s(%s%s%d%s%s%s%d)"
> > +	len = snprintf(NULL, 0, FMT, op,
> > +		       field, op1, start_pid, op2,
> > +		       field, op3, end_pid);
> > +	*filter = realloc(*filter, *curr_len + len + 1);
> > +	if (!*filter)
> > +		die("realloc");
> > +
> > +	len = snprintf(*filter + *curr_len, len + 1, FMT, op,
> > +		       field, op1, start_pid, op2,
> > +		       field, op3, end_pid);
> > +	*curr_len += len;
> > +}
> > +
> >  /**
> >   * make_pid_filter - create a filter string to all pids against @field
> >   * @curr_filter: Append to a previous filter (may realloc). Can be NULL
> > - * @field: The fild to compare the pids against
> > + * @field: The field to compare the pids against
> >   *
> >   * Creates a new string or appends to an existing one if @curr_filter
> >   * is not NULL. The new string will contain a filter with all pids
> > @@ -964,54 +1017,46 @@ static void update_pid_event_filters(struct buffer_instance *instance);
> >   */
> >  static char *make_pid_filter(char *curr_filter, const char *field)
> >  {
> > +	int start_pid = -1, last_pid = -1;
> > +	int last_exclude = -1;
> >  	struct filter_pids *p;
> > -	char *filter;
> > -	char *orit;
> > -	char *match;
> > -	char *str;
> > +	char *filter = NULL;
> >  	int curr_len = 0;
> > -	int len;
> >  
> >  	/* Use the new method if possible */
> >  	if (have_set_event_pid)
> >  		return NULL;
> >  
> > -	len = len_filter_pids + (strlen(field) + strlen("(==)||")) * nr_filter_pids;
> > -
> > -	if (curr_filter) {
> > -		curr_len = strlen(curr_filter);
> > -		filter = realloc(curr_filter, curr_len + len + strlen("(&&())"));
> > -		if (!filter)
> > -			die("realloc");
> > -		memmove(filter+1, curr_filter, curr_len);
> > -		filter[0] = '(';
> > -		strcat(filter, ")&&(");
> > -		curr_len = strlen(filter);
> > -	} else
> > -		filter = malloc(len);
> > -	if (!filter)
> > -		die("Failed to allocate pid filter");
> > -
> > -	/* Last '||' that is not used will cover the \0 */
> > -	str = filter + curr_len;
> > +	if (!filter_pids)
> > +		return curr_filter;
> >  
> >  	for (p = filter_pids; p; p = p->next) {
> > -		if (p->exclude) {
> > -			match = "!=";
> > -			orit = "&&";
> > -		} else {
> > -			match = "==";
> > -			orit = "||";
> > +		/*
> > +		 * PIDs are inserted in `filter_pids` from the front and that's
> > +		 * why we expect them in descending order here.
> > +		 */
> > +		if (p->pid == last_pid - 1 && p->exclude == last_exclude) {
> > +			last_pid = p->pid;
> > +			continue;
> >  		}
> > -		if (p == filter_pids)
> > -			orit = "";
> >  
> > -		len = sprintf(str, "%s(%s%s%d)", orit, field, match, p->pid);
> > -		str += len;
> > +		if (start_pid != -1)
> > +			append_filter_pid_range(&filter, &curr_len, field,
> > +						last_pid, start_pid,
> > +						last_exclude);
> > +
> > +		start_pid = last_pid = p->pid;
> > +		last_exclude = p->exclude;
> > +
> >  	}
> > +	append_filter_pid_range(&filter, &curr_len, field,
> > +				last_pid, start_pid, last_exclude);
> >  
> > -	if (curr_len)
> > -		sprintf(str, ")");
> > +	if (curr_filter) {
> > +		char *save = filter;
> > +		asprintf(&filter, "(%s)&&(%s)", curr_filter, filter);
> > +		free(save);
> > +	}
> >  
> >  	return filter;
> >  }
> > -- 
> > 2.19.1
> > 
> 
> -- 
> 

  reply	other threads:[~2019-04-17 14:19 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-04-17 13:09 [PATCH v4 0/2] Optimize pid filters Slavomir Kaslev
2019-04-17 13:09 ` [PATCH v4 1/2] trace-cmd: Optimize how pid filters are expressed Slavomir Kaslev
2019-04-17 13:58   ` Phil Auld
2019-04-17 14:18     ` John Kacur [this message]
2019-04-17 14:25       ` Phil Auld
2019-04-17 14:52         ` Steven Rostedt
2019-04-17 14:52     ` Steven Rostedt
2019-04-17 14:54     ` Steven Rostedt
2019-04-17 13:09 ` [PATCH v4 2/2] trace-cmd: Document record --no-filter option in record's man page Slavomir Kaslev
2019-04-17 14:05   ` Phil Auld
2019-04-17 16:19   ` Steven Rostedt
2019-04-17 16:24     ` Steven Rostedt

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=alpine.LFD.2.21.1904171616010.6386@planxty \
    --to=jkacur@redhat.com \
    --cc=jbacik@fb.com \
    --cc=kaslevs@vmware.com \
    --cc=linux-trace-devel@vger.kernel.org \
    --cc=pauld@redhat.com \
    --cc=rostedt@goodmis.org \
    --cc=slavomir.kaslev@gmail.com \
    --cc=tstoyanov@vmware.com \
    --cc=ykaradzhov@vmware.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).