Re: httpd 2.4.25, mpm_event, ssl: segfaults

On Thu, Feb 16, 2017 at 12:31 AM, Yann Ylavic wrote: > > Actually this is 16K (the maximum size of a TLS record) ... these are the outputs (records) splitted/produced by SSL_write() when given inputs (plain text) greater than 16K (at once).

Re: httpd 2.4.25, mpm_event, ssl: segfaults

On Thu, Feb 16, 2017 at 12:06 AM, Jacob Champion wrote: > On 02/15/2017 02:03 PM, Yann Ylavic wrote: > >> Assuming so :) there is also the fact that mod_ssl will encrypt/pass >> 8K buckets at a time, while the core output filter tries to send the >> whole mmap()ed file,

Re: httpd 2.4.25, mpm_event, ssl: segfaults

On 02/15/2017 02:03 PM, Yann Ylavic wrote: On Wed, Feb 15, 2017 at 9:50 PM, Jacob Champion wrote: For the next step, I want to find out why TLS connections see such a big performance hit when I switch off mmap(), but unencrypted connections don't... it's such a huge

Re: httpd 2.4.25, mpm_event, ssl: segfaults

On Wed, Feb 15, 2017 at 9:50 PM, Jacob Champion wrote: > > For the next step, I want to find out why TLS connections see such a big > performance hit when I switch off mmap(), but unencrypted connections > don't... it's such a huge difference that I feel like I must be

Re: httpd 2.4.25, mpm_event, ssl: segfaults

On 02/07/2017 02:32 AM, Niklas Edmundsson wrote: O_DIRECT also bypasses any read-ahead logic, so you'll have to do nice and big IO etc to get good performance. Yep, confirmed... my naive approach to O_DIRECT, which reads from the file in the 8K chunks we're used to from the file bucket

Re: release v1.9.0

Hi, still no segfaults. @Yann Are those patches (the addon on top of v7) and the one on top of mod_ssl still correct / needed? Stefan Am 15.02.2017 um 12:45 schrieb Stefan Priebe - Profihost AG: > Hi, > Am 15.02.2017 um 12:19 schrieb Yann Ylavic: >> Hi Stefan, >> >> On Wed, Feb 15, 2017 at

AW: svn commit: r1707087 - /httpd/httpd/trunk/modules/debugging/mod_bucketeer.c

> -Ursprüngliche Nachricht- > Von: Yann Ylavic [mailto:ylavic@gmail.com] > Gesendet: Mittwoch, 15. Februar 2017 14:08 > An: httpd-dev > Betreff: Re: svn commit: r1707087 - > /httpd/httpd/trunk/modules/debugging/mod_bucketeer.c > > [with the patch] > > On Wed,

Re: mod_remoteip and mod_http2 combined

On Wed, Feb 15, 2017 at 9:02 AM, Sander Hoentjen wrote: > > mod_remote ip has: > /* mod_proxy creates outgoing connections - we don't want those */ > if (!remoteip_is_server_port(c->local_addr->port)) { > return DECLINED; > } > I am guessing something

Re: mod_remoteip and mod_http2 combined

On 02/15/2017 12:19 PM, Jordan Gigov wrote: > On 15 February 2017 at 12:50, Sander Hoentjen wrote: >> Hey guys, >> >> I am trying to use both mod_remoteip with ProxyProtocol and mod_http2. >> It looks like mod_http2 gets handed the connection before mod_remoteip, >> so things

Re: svn commit: r1707087 - /httpd/httpd/trunk/modules/debugging/mod_bucketeer.c

[with the patch] On Wed, Feb 15, 2017 at 2:07 PM, Yann Ylavic wrote: > On Tue, Feb 14, 2017 at 10:21 PM, Jacob Champion wrote: >> > > , hence the (default_)handler probably returned >> >>> Admittedly bucketeer_out_filter() is not very nice because it

Re: svn commit: r1707087 - /httpd/httpd/trunk/modules/debugging/mod_bucketeer.c

On Tue, Feb 14, 2017 at 10:21 PM, Jacob Champion wrote: > , hence the (default_)handler probably returned > >> Admittedly bucketeer_out_filter() is not very nice because it does not >> "consume" its given brigade (nor does default_handler() clear it >> afterward), but that

Re: svn commit: r1782875 [1/3] - in /httpd/httpd/trunk: ./ modules/http2/

> Am 15.02.2017 um 13:07 schrieb Yann Ylavic : > >> On Mon, Feb 13, 2017 at 10:00 PM, wrote: >> Author: icing >> Date: Mon Feb 13 21:00:30 2017 >> New Revision: 1782875 >> >> URL: http://svn.apache.org/viewvc?rev=1782875=rev >> Log: >> On the trunk: >>

Re: svn commit: r1782875 [1/3] - in /httpd/httpd/trunk: ./ modules/http2/

On Mon, Feb 13, 2017 at 10:00 PM, wrote: > Author: icing > Date: Mon Feb 13 21:00:30 2017 > New Revision: 1782875 > > URL: http://svn.apache.org/viewvc?rev=1782875=rev > Log: > On the trunk: > > mod_http2: rework of stream states and cleanup handling. Nice work Stefan!

Re: release v1.9.0

Hi, Am 15.02.2017 um 12:19 schrieb Yann Ylavic: > Hi Stefan, > > On Wed, Feb 15, 2017 at 9:34 AM, Stefan Priebe - Profihost AG > wrote: >> Current status: no segfaults. > > Is this with or without the mpm_event's wakeup and/or allocator patches? it's with the

Re: release v1.9.0

Hi Stefan, On Wed, Feb 15, 2017 at 9:34 AM, Stefan Priebe - Profihost AG wrote: > Current status: no segfaults. Is this with or without the mpm_event's wakeup and/or allocator patches? Regards, Yann.

Re: mod_remoteip and mod_http2 combined

Try modules/http2/h2_h2.c line 550 add "mod_remoteip.c" after "mod_ssl.c". This reminds me since remoteip is being updated, maybe it should also specify some before and after mods to avoid. On 15 February 2017 at 12:50, Sander Hoentjen wrote: > Hey guys, > > I am trying to

mod_remoteip and mod_http2 combined

Hey guys, I am trying to use both mod_remoteip with ProxyProtocol and mod_http2. It looks like mod_http2 gets handed the connection before mod_remoteip, so things don't work as they should. ProxyProtocol should always be handled first, since it is prepended to the stream. Any pointers to where in

Gitignore for migration

While complete migration itself seems to be a few centuries away, I did work on importing the svn:ignore properties and converting to a gitignore format. I'll try attaching it for anyone interested, but if that doesn't work just ask and I'll paste it directly. httpd.gitignore Description:

Re: release v1.9.0

Also here windows up and running on AL: mod_http2 (v1.9.0-git, feats=, nghttp2 1.19.0), initializing... Steffen On Wednesday 15/02/2017 at 10:17, Stefan Eissing wrote: Thanks. Am 15.02.2017 um 09:34 schrieb Stefan Priebe - Profihost AG : Current status: no

Re: release v1.9.0

Thanks. > Am 15.02.2017 um 09:34 schrieb Stefan Priebe - Profihost AG > : > > Current status: no segfaults. > >> Am 14.02.2017 um 19:59 schrieb Stefan Priebe - Profihost AG: >> Hi, >> >> up and running - Thanks! >> >> Greets, >> Stefan >> >>> Am 14.02.2017 um 17:05

Re: release v1.9.0

Current status: no segfaults. Am 14.02.2017 um 19:59 schrieb Stefan Priebe - Profihost AG: > Hi, > > up and running - Thanks! > > Greets, > Stefan > > Am 14.02.2017 um 17:05 schrieb Stefan Eissing: >> Stefan, >> >> if you'd like, please throw >>