This is the mail archive of the mailing list for the glibc project.

Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

Re: Wish for 2002 ...

 Major snip of the Cc lines... (Thomas Bushnell, BSG) writes:

> Linus claimed to have something approaching "hard data" for the
> proposition that adding functions to the library is inherently bad,
> but he seems to have begged off of the request to tell me where I
> could read more about it.

 Well it's fairly easy to do a simple benchmark of how much time glibc
is taking to startup, take two /bin/true programs one in C and calls
glibc exit() (linked static and strip'd) and the other in nasm from

% time perl -e 'for my $i (1..10_000) { system("/tmp/test", "");}'

 test == nasm
0.46s user 4.16s system 99% cpu 4.631 total
0.50s user 4.09s system 99% cpu 4.596 total
0.45s user 3.93s system 99% cpu 4.388 total

 test == glibc, static striped
0.89s user 5.35s system 98% cpu 6.362 total
0.71s user 5.46s system 99% cpu 6.183 total
0.96s user 5.26s system 99% cpu 6.233 total

test == glibc, static
0.95s user 5.20s system 99% cpu 6.159 total
0.77s user 5.44s system 99% cpu 6.217 total
0.84s user 5.32s system 99% cpu 6.178 total

test == glibc, dynamic
7.91s user 9.99s system 99% cpu 17.933 total
7.84s user 10.00s system 99% cpu 17.862 total
7.85s user 10.16s system 99% cpu 18.118 total

James Antill -- <>
Firewall n.
 1. A bad security program used to make other bad security programs less
baddly in need of security.

Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]