Re: [RFC] Proposal for ptrace improvements

[Denys Vlasenko]

On Fri, Mar 4, 2011 at 3:07 PM, Tejun Heo <tj@xxxxxxxxxx> wrote:
> Hello,
>
> On Fri, Mar 04, 2011 at 02:59:32PM +0100, Denys Vlasenko wrote:
>> I would rather speed strace up than slow it down further, even if
>> slightly.
>
> The question to ask is at what cost?  If mostly unnoticeable slow down
> makes the API cleaner, I'll go that way.  Everything is a tradeoff.

# time sh -c 'ls -lR /usr/share >/dev/null'
real	0m2.633s
user	0m0.540s
sys	0m2.047s

strace without PTRACE_GETSIGINFO:

# time sh -c './strace -e trace=exit_group ls -lR /usr/share >/dev/null'
exit_group(0)                           = ?
real	0m47.023s
user	0m3.843s
sys	0m29.050s
# time sh -c './strace -e trace=exit_group ls -lR /usr/share >/dev/null'
exit_group(0)                           = ?
real	0m48.799s
user	0m3.808s
sys	0m29.736s
# time sh -c './strace -e trace=exit_group ls -lR /usr/share >/dev/null'
exit_group(0)                           = ?
real	0m47.695s
user	0m3.965s
sys	0m29.047s

strace with PTRACE_GETSIGINFO:

# time sh -c './strace -e trace=exit_group ls -lR /usr/share >/dev/null'
exit_group(0)                           = ?
real	0m51.958s
user	0m3.899s
sys	0m31.584s
# time sh -c './strace -e trace=exit_group ls -lR /usr/share >/dev/null'
exit_group(0)                           = ?
real	0m53.773s
user	0m3.920s
sys	0m29.713s
# time sh -c './strace -e trace=exit_group ls -lR /usr/share >/dev/null'
exit_group(0)                           = ?
real	0m51.625s
user	0m3.961s
sys	0m30.970s

-- 
vda
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/