httpd-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Ryan Bloom <>
Subject Re: Concatenation of small buckets in core_output_filter Re: cvs commit: httpd-2.0/server core.c
Date Mon, 26 Nov 2001 17:40:09 GMT
On Monday 26 November 2001 09:28 am, Brian Pane wrote:
> The current logic for concatenating small buckets in core_output_filter()
> will have performance problems in two cases that I can think of:
> * If you have a brigade consisting of several dozen small buckets,
>   each one can get copied several times (because we only concatenate
>   MAX_IOVEC_TO_WRITE of them at at time).
> * If the brigade consists of, say, MAX_IOVEC_TO_WRITE+1 buckets of
>   size 1MB each, the code will do a huge memory copy to (needlessly)
>   concatenate the first MAX_IOVEC_TO_WRITE of them.
> My proposed solution is to change the logic as follows:
> * Skip the concatenation if there's >= 8KB of data already
>   referenced in the iovec.

Do we really concatenate in that case?  Whoops, yeah we do.  That is
a mistake, and should be fixed.

> * Rather than creating a temporary brigade for concatenation,
>   create a heap bucket.  Make it big enough to hold 8KB.  Pop
>   the small buckets from the brigade, concatenate their contents
>   into the heap bucket, and push the heap bucket onto the brigade.

This is exactly what the apr_brigade_write function does. If you stop
using that function, you are just duplicating logic.

> * If we end up in the concatenation again during the foreach loop
>   through the brigade, add the small buckets to the end of the
>   previously allocated heap bucket.  If the heap bucket size is
>   about to exceed 8KB, stop.

This should be done by moving the first bucket into a separate brigade
and using the brigade_write functions again.

Please don't create separate logic to create a buffering bucket, we already
have it.

Ryan Bloom
Covalent Technologies

View raw message