Greg Ames wrote:
> stoddard@apache.org wrote:
>> - * Rewrite core_output_filter.
> Well I think it's predictable now, but not optimal.
>
> For the simplest request I know how to create, it is entered 3 times:
> 1. HTTP headers
> 2. file + EOS
> 3. FLUSH bucket
> If we haven't seen an EOS or FLUSH yet and the data is too small to send
> immediately, it would be cheaper to just stash the brigade in the
> context rather than doing the setaside at #1.
That is cheaper, but it's not safe in general. I coded this & got seg faults
with Electric Fence serving the httpd FAQ (a heavy SSI user). The subrequests
are probably what's doing it. If I stash a brigade created by a subrequest, its
pool could get cleared between invocations of core_output_filter.
Greg
|