Skip site navigation (1)Skip section navigation (2)
Date:      Tue, 18 Feb 2003 22:11:41 +0100
From:      Erik Trulsson <ertr1013@student.uu.se>
To:        Paolo Pisati <p.pisati@oltrelinux.com>
Cc:        FreeBSD_Hackers <freebsd-hackers@FreeBSD.ORG>
Subject:   Re: Simple question about profiling
Message-ID:  <20030218211141.GA3499@falcon.midgard.homeip.net>
In-Reply-To: <20030217141034.GA3706@law3.usr.dsi.unimi.it>
References:  <20030217141034.GA3706@law3.usr.dsi.unimi.it>

next in thread | previous in thread | raw e-mail | index | archive | help
On Mon, Feb 17, 2003 at 03:10:34PM +0100, Paolo Pisati wrote:
> 
> I've to confess this my first serious profile session, and
> i found something really strange (at least for me... =P)
> 
> [flag@law3 src]$ gprof proto3
> [snip]
>  %   cumulative   self              self     total
>  time   seconds   seconds    calls  ms/call  ms/call  name
>  74.4      39.26    39.26                             .mcount (83)
>   6.7      42.82     3.56 111575600     0.00     0.00  checkRule2d [4]
>   6.6      46.30     3.48     1024     3.39    12.30  buildTree2d [3]
>   3.8      48.29     1.99 117334464     0.00     0.00  add_tail [6]
>   3.7      50.25     1.96 117234464     0.00     0.00  rem [7]
>   1.8      51.18     0.93 117234464     0.00     0.00  rem_head [5]
>   0.6      51.51     0.33  1600004     0.00     0.00  __qdivrem [13]
>   0.5      51.75     0.24   800004     0.00     0.00  __svfscanf [9]
>   0.4      51.96     0.21     9037     0.02     0.09  buildTree1d [10]
>   0.3      52.14     0.18   800000     0.00     0.00  strtoumax [12]
>   0.3      52.28     0.14  1078414     0.00     0.00  memset [20]
>   0.2      52.41     0.12  5658864     0.00     0.00  checkRule1d [21]
>   0.1      52.47     0.07   250129     0.00     0.00  count [23]
>   0.1      52.52     0.05   537809     0.00     0.00  malloc_bytes <cycle 1> [22
> ]
>   0.1      52.56     0.04  1166299     0.00     0.00  append_lists [25]
>   0.1      52.59     0.03  2411019     0.00     0.00  new_list [26]
>   0.1      52.62     0.03   536551     0.00     0.00  calloc [14]
>   0.0      52.64     0.02       70     0.24     0.42  tree2dHeight [29]
> [snip]
> 
> i think this is the beef: what the hell is .mcount?!?!
> if i read the table correctly, .mcount is the guilty, isn't it?
> 
> any help or pointer is appreciated, thank you... =)

[This should probably have been sent to -questions instead of -hackers.]

I believe .mcount belongs to the profiling code itself and is part of
the profiling overhead.
Just ignore it.



-- 
<Insert your favourite quote here.>
Erik Trulsson
ertr1013@student.uu.se

To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-hackers" in the body of the message




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20030218211141.GA3499>