prelink performance gains

[Tristan Santore]

On 14/10/13 17:42, Dhiru Kholia wrote:
> Hi,
> 
> During the development of "unSPEC" [1] benchmarking suite, I made some
> interesting observations regarding prelink.
> 
> - Here are some measurements (for LibreOffice [2] loading time in
>   seconds) done using the "unSPEC" bench-marking suite. These numbers
>   are repeatable and you are encouraged to try "unSPEC" to do
>   independent validation of these numbers.
> 
>   - hkario (modern SSD based system, cache flushed): (1.816, 1.811,
>     1.797, 1.827 with prelink), (2.034, 2.042, 2.027, 2.016 without
>     prelink)
> 
>   - hkario (modern SSD based system, cache intact): (2.155, 2.121,
>     2.101, 2.299 with prelink), (2.311, 2.052, 2.047, 2.037 without
>     prelink)
> 
>   - halfie (T430s): (10.725, 10.095, 10.378, 10.568 with prelink),
>     (8.901, 8.993, 9.075, 9.448, 9.489 without prelink)
> 
>   - danpb (T530): I see basically no measurable difference in times with
>     or without prelink - quite a lot of variation, but all in same
>     ballpark, (8.374, 7.849, 8.457, 7.673, 7.608, 8.031, 8.350, 8.183,
>     7.381 with prelink), (7.366, 8.009, 7.500, 7.949, 8.208, 8.351,
>     7.849, without prelink).
> 
> - For building kernels (using the "kernel-bench" [3] component of unSPEC
>   suite), prelink saved <= 250 ms over the non-prelink environment
>   (which took 1m19.138s). hkario even reports worse performance numbers
>   for the prelink environment. Additionally, we have specialized
>   softwares like ccache and distcc to solve long-compilation-time
>   problems.
> 
> In short, we could not distinguish the performance gains of prelink over
> the "background noise" in many (or even most) cases.
> 
> So, I was wondering if you are aware of any use-cases where prelink
> provides measurable benefits. It would be awesome if you could run
> unSPEC on your systems and report back the numbers.
> 
> unSPEC is easy to use and doesn't take much time (or steps) to run. For
> more information, please see the following links.
> 
> References:
> 
> [1] https://github.com/kholia/unSPEC
> [2] https://github.com/kholia/unSPEC/tree/master/LibreOffice
> [3] https://github.com/kholia/unSPEC/tree/master/kernel-bench
> 
> --
> Dhiru
> --
> security mailing list
> security at lists.fedoraproject.org
> https://admin.fedoraproject.org/mailman/listinfo/security
> 
All very well and nice, but what does this have to do with the Security
List ?

Also, most people will switch off pre-linking on servers, due to
erroneous reports of lib and binary changes, that are caused by pre-linking.

Regards,

Tristan

-- 

Tristan Santore BSc MBCS
TS4523-RIPE
Network and Infrastructure Operations
InterNexusConnect
Mobile +44-78-55069812
Tristan.Santore at internexusconnect.net

Former Thawte Notary
(Please note: Thawte has closed its WoT programme down,
and I am therefore no longer able to accredit trust)

For Fedora related issues, please email me at:
TSantore at fedoraproject.org