From: Yann Ylavic <ylavic@apache.org>
Date: Sun, 19 Apr 2015 22:14:34 +0000 (+0000)
Subject: Comment on r1656259.
X-Git-Tag: 2.4.13~179
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=d478937abd1ddadeef5485ac4ae3384817d67fc8;p=apache

Comment on r1656259.

git-svn-id: https://svn.apache.org/repos/asf/httpd/httpd/branches/2.4.x@1674703 13f79535-47bb-0310-9956-ffa450edef68
---

diff --git a/STATUS b/STATUS
index 9d18358936..d2a08db0cd 100644
--- a/STATUS
+++ b/STATUS
@@ -230,6 +230,15 @@ PATCHES PROPOSED TO BACKPORT FROM TRUNK:
                the backend is available to rec' it. I understand the
                error described, but is the fix actually worth it (plus
                it seems to allow for a DDoS vector).
+     ylavic: It seems to me that the problem is real since we reuse the
+             connection before prefetching 16K (either controlled by the
+             client, or by an input filter), we currently always prefetch
+             these bytes already. Regarding performance I don't see any
+             difference (more cycles) compared with the current code.
+             However I think I failed to rebuild the header_brigade when
+             the proxy loop is retried (ping), so I need to rework this.
+             Do you think we'd better remove the prefetch, or maybe just
+             make it nonblocking (by default)?
 
   *) http: Make ap_die() robust against any HTTP error code and not modify
      response status (finally logged) when nothing is to be done. PR 56035.