Re: binary format loader cache?

Aaron Tiensivu (tiensivu@pilot.msu.edu)
Fri, 4 Apr 1997 11:59:06 -0500

Messages sorted by: [ date ][ thread ][ subject ][ author ]
Next message: Michael O'Reilly: "patch...."
Previous message: Ingo Molnar: "Re: small patch to buffer.c (2.0.x, stop wasting cycles)."

> is anyone working on the above thing? It looks like an overkill to look up
> the very same ~3 binary loaders for every do_exec() in a typical Linux
> system, and wasting some ~300 usecs (or more) per lookup.
>
> or does the new inode.c stuff solve this problem?
>
> plus:
>
> pc5829:~/trace/ktrace/samples$ grep get_empty_filp execve.out
> Trace: c0127da8 <get_empty_filp+10/e4> (50.33)
> Trace: c0127da8 <get_empty_filp+10/e4> (41.72)
>
> thats 100 usecs more overhead per exec() ... get_empty_filp() sucks hard.

Ask and you shall receive.. this is old, but should still work... I've been
running it for quite a while now without trouble. I can't remember which kernel
it is to, but it's an easy cut and paste job anyway.

Old message from kernel list:

Next message: Michael O'Reilly: "patch...."
Previous message: Ingo Molnar: "Re: small patch to buffer.c (2.0.x, stop wasting cycles)."