You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@httpd.apache.org by Jim Jagielski <ji...@jaguNET.com> on 2013/09/05 15:08:03 UTC
Planning for 2.4.7 in Oct
It would be nice to release 2.4.7 next month, which would
make it 3 months since the 2.4.6 release... Yeah, it's
next month, but it's never too early to start planning.
Are there items that we'd *really* like to see in 2.4.7
that we should try to prioritize? Personally, UDS support
for mod_proxy, as well as the websocket improvements in
trunk (and the corresponding ap_mpm_register_socket_callback)
look quite viable.
Re: Planning for 2.4.7 in Oct
Posted by Ben Reser <be...@reser.org>.
On 9/5/13 6:08 AM, Jim Jagielski wrote:
> Are there items that we'd *really* like to see in 2.4.7
> that we should try to prioritize?
I'd really like to have a fix for the following bug included:
https://issues.apache.org/bugzilla/show_bug.cgi?id=55397
I've started work on it but it's causing some strange behavior and I haven't
gotten back to it due to other things eating up my time. Should be able to get
to it this next week.
Basic driver here is several mod_dav changes in 2.2.25/2.4.6 created problems
for Subversion users such that I'm actually having to suggest that they revert
some changes that were included. Suggesting they use previous versions isn't
really helpful either. E.G.
https://mail-archives.apache.org/mod_mbox/subversion-dev/201308.mbox/%3C5220C502.7060401%40reser.org%3E
Re: event MPM (Was: Re: Planning for 2.4.7 in Oct)
Posted by Rainer Jung <ra...@kippdata.de>.
On 15.09.2013 20:23, Marion & Christophe JAILLET wrote:
>
> Le 15/09/2013 16:30, Rainer Jung a écrit :
>> I'm pretty sure from those pictures you would not be able to find the
>> point in time where I switched 2.4.6 and 2.4.7-dev between the servers.
>
> In other words, does it mean that no special performance improvement is
> to be expected ?
>
> I remember to have read somewhere some numbers showing that the gain
> should be visible. (but I can't find the discussion any more...)
The pictures do now show response times and both servers are far from
being saturated. The load mix isn't similar enough and constant enough
to derive anything from the response times we could extract from the
access logs. I doubt that we can measure the benefits in this scenario,
but we can check, whether in a pretty complex situation the skiplist
based event mpm runs stable without hickups and without noticeable
growth in resource usage.
Regards,
Rainer
Re: Add skiplist to APR 1.5 (Was: Re: event MPM (Was: Re: Planning for 2.4.7 in Oct))
Posted by Jim Jagielski <ji...@jaguNET.com>.
Now that skiplist is being added to APR 1.5, I will start
the process of moving trunk to use it and will propose
a backport for 2.4...
Re: Add skiplist to APR 1.5 (Was: Re: event MPM (Was: Re: Planning for 2.4.7 in Oct))
Posted by Jim Jagielski <ji...@jaguNET.com>.
+1...
On Sep 28, 2013, at 12:12 PM, Graham Leggett <mi...@sharp.fm> wrote:
>
>> On 26 Sep 2013, at 15:44, Jim Jagielski <ji...@jaguNET.com> wrote:
>>
>> Like I said, I think that skiplist fits better in APR; in
>> fact there are a few other things in httpd that would be
>> "better" in APR, but APR and httpd are 2 sep projects and so
>> we can't "force" things.
>>
>> In fact, I'm adding dev@apr to the To: line :)
>
> +1 on apr, it seems a sensible addition alongside the hash and table implementations.
>
> Regards,
> Graham
> --
>
Re: Add skiplist to APR 1.5 (Was: Re: event MPM (Was: Re: Planning
for 2.4.7 in Oct))
Posted by "William A. Rowe Jr." <wm...@gmail.com>.
+1 to moving ap skiplist to apr (trunk + 1.5 future release branch)
On Sep 28, 2013 11:12 AM, "Graham Leggett" <mi...@sharp.fm> wrote:
>
> > On 26 Sep 2013, at 15:44, Jim Jagielski <ji...@jaguNET.com> wrote:
> >
> > Like I said, I think that skiplist fits better in APR; in
> > fact there are a few other things in httpd that would be
> > "better" in APR, but APR and httpd are 2 sep projects and so
> > we can't "force" things.
> >
> > In fact, I'm adding dev@apr to the To: line :)
>
> +1 on apr, it seems a sensible addition alongside the hash and table
> implementations.
>
> Regards,
> Graham
> --
>
>
Re: Add skiplist to APR 1.5 (Was: Re: event MPM (Was: Re: Planning for 2.4.7 in Oct))
Posted by Jim Jagielski <ji...@jaguNET.com>.
+1...
On Sep 28, 2013, at 12:12 PM, Graham Leggett <mi...@sharp.fm> wrote:
>
>> On 26 Sep 2013, at 15:44, Jim Jagielski <ji...@jaguNET.com> wrote:
>>
>> Like I said, I think that skiplist fits better in APR; in
>> fact there are a few other things in httpd that would be
>> "better" in APR, but APR and httpd are 2 sep projects and so
>> we can't "force" things.
>>
>> In fact, I'm adding dev@apr to the To: line :)
>
> +1 on apr, it seems a sensible addition alongside the hash and table implementations.
>
> Regards,
> Graham
> --
>
Re: Add skiplist to APR 1.5 (Was: Re: event MPM (Was: Re: Planning for 2.4.7 in Oct))
Posted by Graham Leggett <mi...@sharp.fm>.
> On 26 Sep 2013, at 15:44, Jim Jagielski <ji...@jaguNET.com> wrote:
>
> Like I said, I think that skiplist fits better in APR; in
> fact there are a few other things in httpd that would be
> "better" in APR, but APR and httpd are 2 sep projects and so
> we can't "force" things.
>
> In fact, I'm adding dev@apr to the To: line :)
+1 on apr, it seems a sensible addition alongside the hash and table implementations.
Regards,
Graham
--
Re: Add skiplist to APR 1.5 (Was: Re: event MPM (Was: Re: Planning for 2.4.7 in Oct))
Posted by Graham Leggett <mi...@sharp.fm>.
> On 26 Sep 2013, at 15:44, Jim Jagielski <ji...@jaguNET.com> wrote:
>
> Like I said, I think that skiplist fits better in APR; in
> fact there are a few other things in httpd that would be
> "better" in APR, but APR and httpd are 2 sep projects and so
> we can't "force" things.
>
> In fact, I'm adding dev@apr to the To: line :)
+1 on apr, it seems a sensible addition alongside the hash and table implementations.
Regards,
Graham
--
Add skiplist to APR 1.5 (Was: Re: event MPM (Was: Re: Planning for 2.4.7 in Oct))
Posted by Jim Jagielski <ji...@jaguNET.com>.
On Sep 26, 2013, at 10:20 AM, William A. Rowe Jr. <wr...@rowe-clan.net> wrote:
> On Thu, 26 Sep 2013 08:25:46 -0400
> Jim Jagielski <ji...@jaguNET.com> wrote:
>
>>
>> On Sep 25, 2013, at 8:07 PM, William A. Rowe Jr. <wm...@gmail.com>
>> wrote:
>>
>>> Before we incorporate it... can we have some sense of the impact of
>>> the optimization? So far we don't have much data to go on.
>>
>> From the orig post: "My benchmarks show decreased latency and a
>> performance boost of ~5% (on avg)"
>
> I remember that... so we are strictly speaking of response latency and
> response fulfillment metrics (as opposed to load?) 'Performance' was
> a little ambiguous, just want to confirm what we are measuring here :)
rps.
>
>>> There is talk of releasing some apr 1.5 enhancements. I'd
>>> personally favor adding skip list to apr rather than -util or
>>> httpd, since it could be useful core functionality, and 2.0 drops
>>> the distinction anyways.
>>
>> Fine, in fact, I agree that it "really" belongs in apr,
>> but it means that 2.4.7 will be required apr 1.5.
>>
>> Is the httpd PMC OK with that?
>
> I made the comment earlier that mod_ssl requiring openssl 0.9.8 in
> moving forward was fine. APR is a similar dependency. That said, we
> are maintaining binary compatibility because APR assures us that 1.5.x
> will maintain compatibility with 1.3.x/1.4.x. Plus we pick up apr unix
> domain socket support in the process for httpd.
>
> So I'm +1, I thought we did this during 2.2 (can't remember for certain)
> and throughout 2.0's lifespan we did this a number of times relative
> to apr 0.9.
>
> Others' thoughts?
>
Like I said, I think that skiplist fits better in APR; in
fact there are a few other things in httpd that would be
"better" in APR, but APR and httpd are 2 sep projects and so
we can't "force" things.
In fact, I'm adding dev@apr to the To: line :)
Add skiplist to APR 1.5 (Was: Re: event MPM (Was: Re: Planning for 2.4.7 in Oct))
Posted by Jim Jagielski <ji...@jaguNET.com>.
On Sep 26, 2013, at 10:20 AM, William A. Rowe Jr. <wr...@rowe-clan.net> wrote:
> On Thu, 26 Sep 2013 08:25:46 -0400
> Jim Jagielski <ji...@jaguNET.com> wrote:
>
>>
>> On Sep 25, 2013, at 8:07 PM, William A. Rowe Jr. <wm...@gmail.com>
>> wrote:
>>
>>> Before we incorporate it... can we have some sense of the impact of
>>> the optimization? So far we don't have much data to go on.
>>
>> From the orig post: "My benchmarks show decreased latency and a
>> performance boost of ~5% (on avg)"
>
> I remember that... so we are strictly speaking of response latency and
> response fulfillment metrics (as opposed to load?) 'Performance' was
> a little ambiguous, just want to confirm what we are measuring here :)
rps.
>
>>> There is talk of releasing some apr 1.5 enhancements. I'd
>>> personally favor adding skip list to apr rather than -util or
>>> httpd, since it could be useful core functionality, and 2.0 drops
>>> the distinction anyways.
>>
>> Fine, in fact, I agree that it "really" belongs in apr,
>> but it means that 2.4.7 will be required apr 1.5.
>>
>> Is the httpd PMC OK with that?
>
> I made the comment earlier that mod_ssl requiring openssl 0.9.8 in
> moving forward was fine. APR is a similar dependency. That said, we
> are maintaining binary compatibility because APR assures us that 1.5.x
> will maintain compatibility with 1.3.x/1.4.x. Plus we pick up apr unix
> domain socket support in the process for httpd.
>
> So I'm +1, I thought we did this during 2.2 (can't remember for certain)
> and throughout 2.0's lifespan we did this a number of times relative
> to apr 0.9.
>
> Others' thoughts?
>
Like I said, I think that skiplist fits better in APR; in
fact there are a few other things in httpd that would be
"better" in APR, but APR and httpd are 2 sep projects and so
we can't "force" things.
In fact, I'm adding dev@apr to the To: line :)
Re: event MPM (Was: Re: Planning for 2.4.7 in Oct)
Posted by "William A. Rowe Jr." <wr...@rowe-clan.net>.
On Thu, 26 Sep 2013 08:25:46 -0400
Jim Jagielski <ji...@jaguNET.com> wrote:
>
> On Sep 25, 2013, at 8:07 PM, William A. Rowe Jr. <wm...@gmail.com>
> wrote:
>
> > Before we incorporate it... can we have some sense of the impact of
> > the optimization? So far we don't have much data to go on.
>
> From the orig post: "My benchmarks show decreased latency and a
> performance boost of ~5% (on avg)"
I remember that... so we are strictly speaking of response latency and
response fulfillment metrics (as opposed to load?) 'Performance' was
a little ambiguous, just want to confirm what we are measuring here :)
> > There is talk of releasing some apr 1.5 enhancements. I'd
> > personally favor adding skip list to apr rather than -util or
> > httpd, since it could be useful core functionality, and 2.0 drops
> > the distinction anyways.
>
> Fine, in fact, I agree that it "really" belongs in apr,
> but it means that 2.4.7 will be required apr 1.5.
>
> Is the httpd PMC OK with that?
I made the comment earlier that mod_ssl requiring openssl 0.9.8 in
moving forward was fine. APR is a similar dependency. That said, we
are maintaining binary compatibility because APR assures us that 1.5.x
will maintain compatibility with 1.3.x/1.4.x. Plus we pick up apr unix
domain socket support in the process for httpd.
So I'm +1, I thought we did this during 2.2 (can't remember for certain)
and throughout 2.0's lifespan we did this a number of times relative
to apr 0.9.
Others' thoughts?
Re: event MPM (Was: Re: Planning for 2.4.7 in Oct)
Posted by Jim Jagielski <ji...@jaguNET.com>.
Still missing 1 more vote... this has been running on our infra
with NO problems.
On Sep 26, 2013, at 8:25 AM, Jim Jagielski <ji...@jaguNET.com> wrote:
>
> On Sep 25, 2013, at 8:07 PM, William A. Rowe Jr. <wm...@gmail.com> wrote:
>
>> Before we incorporate it... can we have some sense of the impact of the optimization? So far we don't have much data to go on.
>
> From the orig post: "My benchmarks show decreased latency and a performance boost of ~5% (on avg)"
>
Re: event MPM (Was: Re: Planning for 2.4.7 in Oct)
Posted by Jim Jagielski <ji...@jaguNET.com>.
On Sep 25, 2013, at 8:07 PM, William A. Rowe Jr. <wm...@gmail.com> wrote:
> Before we incorporate it... can we have some sense of the impact of the optimization? So far we don't have much data to go on.
From the orig post: "My benchmarks show decreased latency and a performance boost of ~5% (on avg)"
>
> There is talk of releasing some apr 1.5 enhancements. I'd personally favor adding skip list to apr rather than -util or httpd, since it could be useful core functionality, and 2.0 drops the distinction anyways.
>
Fine, in fact, I agree that it "really" belongs in apr,
but it means that 2.4.7 will be required apr 1.5.
Is the httpd PMC OK with that?
Re: event MPM (Was: Re: Planning for 2.4.7 in Oct)
Posted by "William A. Rowe Jr." <wm...@gmail.com>.
Before we incorporate it... can we have some sense of the impact of the
optimization? So far we don't have much data to go on.
There is talk of releasing some apr 1.5 enhancements. I'd personally favor
adding skip list to apr rather than -util or httpd, since it could be
useful core functionality, and 2.0 drops the distinction anyways.
On Sep 25, 2013 1:37 PM, "Jim Jagielski" <ji...@jagunet.com> wrote:
> Bueller? Bueller?
>
> On Sep 19, 2013, at 12:17 PM, Jim Jagielski <ji...@jaguNET.com> wrote:
>
> > With the successful running, does anyone wish to add
> > some votes to STATUS to allow the backport to be
> > approved? :)
> >
> > On Sep 16, 2013, at 9:27 AM, Jim Jagielski <ji...@jaguNET.com> wrote:
> >
> >> visible if pushed, yes.
> >>
> >> On Sep 15, 2013, at 2:23 PM, Marion & Christophe JAILLET <
> christophe.jaillet@wanadoo.fr> wrote:
> >>
> >>>
> >>> Le 15/09/2013 16:30, Rainer Jung a écrit :
> >>>> I'm pretty sure from those pictures you would not be able to find the
> point in time where I switched 2.4.6 and 2.4.7-dev between the servers.
> >>>
> >>> In other words, does it mean that no special performance improvement
> is to be expected ?
> >>>
> >>> I remember to have read somewhere some numbers showing that the gain
> should be visible. (but I can't find the discussion any more...)
> >>>
> >>> CJ
> >>>
> >>
> >
>
>
Re: event MPM (Was: Re: Planning for 2.4.7 in Oct)
Posted by Jim Jagielski <ji...@jaguNET.com>.
Bueller? Bueller?
On Sep 19, 2013, at 12:17 PM, Jim Jagielski <ji...@jaguNET.com> wrote:
> With the successful running, does anyone wish to add
> some votes to STATUS to allow the backport to be
> approved? :)
>
> On Sep 16, 2013, at 9:27 AM, Jim Jagielski <ji...@jaguNET.com> wrote:
>
>> visible if pushed, yes.
>>
>> On Sep 15, 2013, at 2:23 PM, Marion & Christophe JAILLET <ch...@wanadoo.fr> wrote:
>>
>>>
>>> Le 15/09/2013 16:30, Rainer Jung a écrit :
>>>> I'm pretty sure from those pictures you would not be able to find the point in time where I switched 2.4.6 and 2.4.7-dev between the servers.
>>>
>>> In other words, does it mean that no special performance improvement is to be expected ?
>>>
>>> I remember to have read somewhere some numbers showing that the gain should be visible. (but I can't find the discussion any more...)
>>>
>>> CJ
>>>
>>
>
Re: event MPM (Was: Re: Planning for 2.4.7 in Oct)
Posted by Jim Jagielski <ji...@jaguNET.com>.
With the successful running, does anyone wish to add
some votes to STATUS to allow the backport to be
approved? :)
On Sep 16, 2013, at 9:27 AM, Jim Jagielski <ji...@jaguNET.com> wrote:
> visible if pushed, yes.
>
> On Sep 15, 2013, at 2:23 PM, Marion & Christophe JAILLET <ch...@wanadoo.fr> wrote:
>
>>
>> Le 15/09/2013 16:30, Rainer Jung a écrit :
>>> I'm pretty sure from those pictures you would not be able to find the point in time where I switched 2.4.6 and 2.4.7-dev between the servers.
>>
>> In other words, does it mean that no special performance improvement is to be expected ?
>>
>> I remember to have read somewhere some numbers showing that the gain should be visible. (but I can't find the discussion any more...)
>>
>> CJ
>>
>
Re: event MPM (Was: Re: Planning for 2.4.7 in Oct)
Posted by Jim Jagielski <ji...@jaguNET.com>.
visible if pushed, yes.
On Sep 15, 2013, at 2:23 PM, Marion & Christophe JAILLET <ch...@wanadoo.fr> wrote:
>
> Le 15/09/2013 16:30, Rainer Jung a écrit :
>> I'm pretty sure from those pictures you would not be able to find the point in time where I switched 2.4.6 and 2.4.7-dev between the servers.
>
> In other words, does it mean that no special performance improvement is to be expected ?
>
> I remember to have read somewhere some numbers showing that the gain should be visible. (but I can't find the discussion any more...)
>
> CJ
>
Re: event MPM (Was: Re: Planning for 2.4.7 in Oct)
Posted by Marion & Christophe JAILLET <ch...@wanadoo.fr>.
Le 15/09/2013 16:30, Rainer Jung a écrit :
> I'm pretty sure from those pictures you would not be able to find the
> point in time where I switched 2.4.6 and 2.4.7-dev between the servers.
In other words, does it mean that no special performance improvement is
to be expected ?
I remember to have read somewhere some numbers showing that the gain
should be visible. (but I can't find the discussion any more...)
CJ
Re: event MPM (Was: Re: Planning for 2.4.7 in Oct)
Posted by Rainer Jung <ra...@kippdata.de>.
On 15.09.2013 05:31, Rainer Jung wrote:
> On 10.09.2013 16:13, Jim Jagielski wrote:
>> For completeness, a full, combined patch is:
>>
>> http://people.apache.org/~jim/patches/httpd-2.4-event-test.patch
>>
>> It requires a patch that knows about creating new files
>> when encountering /dev/null...
>
> The code (plus r1410004) runs on eos (US incarnation of www.apache.org)
> since a few hours. It runs stably without noticable hickups.
>
> .4.7-dev-r1523261-skiplist: http://www.us.apache.org/server-status
> 2.4.6: http://www.eu.apache.org/server-status
>
> Currently usr cpu is 60% higher per request, sys cpu is 30% lower, total
> cpu is 27% higher. This might be due to differences in the request mix
> between the US and EU incarnation, hardware, config etc. are the same. I
> plan toswitch the versions between the two and do the comparison again.
>
> Note that I'm not talking about the CPU percentage value in
> server-status which is for the whole system. There the numbers differ a
> lot because eos also carries the wiki but that runs outside of the httpd
> processes. I'm only measuring the httpd process cpu time per request.
I switched versions between EU and US mirror (aurora and eos) and the
differences in CPU are due to the servers and/or request mixes, not due
to the new httpd version.
You can have a look yourself:
Load in requests/s: http://people.apache.org/~rjung/skiplist/load.png
usr cpu per request: http://people.apache.org/~rjung/skiplist/usr.png
sys cpu per request: http://people.apache.org/~rjung/skiplist/sys.png
total cpu per request: http://people.apache.org/~rjung/skiplist/total.png
I'm pretty sure from those pictures you would not be able to find the
point in time where I switched 2.4.6 and 2.4.7-dev between the servers.
It was on 2013-09-15 at 10:36.
Here are the pictures showing only one hour around the switch:
Load in requests/s: http://people.apache.org/~rjung/skiplist/load_detail.png
usr cpu per request: http://people.apache.org/~rjung/skiplist/usr_detail.png
sys cpu per request: http://people.apache.org/~rjung/skiplist/sys_detail.png
total cpu per request:
http://people.apache.org/~rjung/skiplist/total_detail.png
Regards,
Rainer
>> On Sep 10, 2013, at 9:52 AM, Jim Jagielski <ji...@jaguNET.com> wrote:
>>
>>> For the testing, we need:
>>>
>>> http://people.apache.org/~jim/patches/httpd-2.4-skiplist.patch
>>> http://people.apache.org/~jim/patches/httpd-2.4-podx.patch
>>> http://people.apache.org/~jim/patches/httpd-2.4-event.patch
>>>
>>> This includes all the performance/sync updates
>>>
>>> Can we get infra to test that out somewhere?
>>>
>>> On Sep 6, 2013, at 7:19 AM, Jim Jagielski <ji...@jaguNET.com> wrote:
>>>
>>>>
>>>> On Sep 5, 2013, at 5:46 PM, Rainer Jung <ra...@kippdata.de> wrote:
>>>>
>>>>> On 05.09.2013 16:35, Jim Jagielski wrote:
>>>>>> BTW, the main diff between event in trunk and 2.4 is
>>>>>> the use of skiplist. My benchmarks show decreased latency
>>>>>> and a performance boost of ~5% (on avg). Can anyone confirm?
>>>>>> It would be nice to possibly get that in 2.4.7 as well.
>>>>>
>>>>> I can offer to negotiate with infra to run 2.4 head plus event patches
>>>>> for skiplist use on www.a.o EU if that helps collecting votes.
>>>>>
>>>>> I did the httpd updates on www.a.o during the last months and in
>>>>> previous years running non-released stuff there was a common practice,
>>>>> so I hope infra will trust our opinion on whether the code should be
>>>>> ready for prime time or not.
>>>>>
>>>>> If we want to see the code running there, I would appreciate a patch
>>>>> ready to apply to 2.4 event.c. I currently feel not in the position to
>>>>> judge, whether running that code on www.a.o actually is a good idea or
>>>>> not. Opinions?
>>>>
>>>>
>>>> Great idea. I can create the 2.4 patch. (and add it to STATUS) ;)
Re: event MPM (Was: Re: Planning for 2.4.7 in Oct)
Posted by Rainer Jung <ra...@kippdata.de>.
On 10.09.2013 16:13, Jim Jagielski wrote:
> For completeness, a full, combined patch is:
>
> http://people.apache.org/~jim/patches/httpd-2.4-event-test.patch
>
> It requires a patch that knows about creating new files
> when encountering /dev/null...
The code (plus r1410004) runs on eos (US incarnation of www.apache.org)
since a few hours. It runs stably without noticable hickups.
.4.7-dev-r1523261-skiplist: http://www.us.apache.org/server-status
2.4.6: http://www.eu.apache.org/server-status
Currently usr cpu is 60% higher per request, sys cpu is 30% lower, total
cpu is 27% higher. This might be due to differences in the request mix
between the US and EU incarnation, hardware, config etc. are the same. I
plan toswitch the versions between the two and do the comparison again.
Note that I'm not talking about the CPU percentage value in
server-status which is for the whole system. There the numbers differ a
lot because eos also carries the wiki but that runs outside of the httpd
processes. I'm only measuring the httpd process cpu time per request.
Regards,
Rainer
> On Sep 10, 2013, at 9:52 AM, Jim Jagielski <ji...@jaguNET.com> wrote:
>
>> For the testing, we need:
>>
>> http://people.apache.org/~jim/patches/httpd-2.4-skiplist.patch
>> http://people.apache.org/~jim/patches/httpd-2.4-podx.patch
>> http://people.apache.org/~jim/patches/httpd-2.4-event.patch
>>
>> This includes all the performance/sync updates
>>
>> Can we get infra to test that out somewhere?
>>
>> On Sep 6, 2013, at 7:19 AM, Jim Jagielski <ji...@jaguNET.com> wrote:
>>
>>>
>>> On Sep 5, 2013, at 5:46 PM, Rainer Jung <ra...@kippdata.de> wrote:
>>>
>>>> On 05.09.2013 16:35, Jim Jagielski wrote:
>>>>> BTW, the main diff between event in trunk and 2.4 is
>>>>> the use of skiplist. My benchmarks show decreased latency
>>>>> and a performance boost of ~5% (on avg). Can anyone confirm?
>>>>> It would be nice to possibly get that in 2.4.7 as well.
>>>>
>>>> I can offer to negotiate with infra to run 2.4 head plus event patches
>>>> for skiplist use on www.a.o EU if that helps collecting votes.
>>>>
>>>> I did the httpd updates on www.a.o during the last months and in
>>>> previous years running non-released stuff there was a common practice,
>>>> so I hope infra will trust our opinion on whether the code should be
>>>> ready for prime time or not.
>>>>
>>>> If we want to see the code running there, I would appreciate a patch
>>>> ready to apply to 2.4 event.c. I currently feel not in the position to
>>>> judge, whether running that code on www.a.o actually is a good idea or
>>>> not. Opinions?
>>>
>>>
>>> Great idea. I can create the 2.4 patch. (and add it to STATUS) ;)
>>>
>>
>
--
kippdata
informationstechnologie GmbH Tel: 0228 98549 -0
Bornheimer Str. 33a Fax: 0228 98549 -50
53111 Bonn www.kippdata.de
HRB 8018 Amtsgericht Bonn / USt.-IdNr. DE 196 457 417
Geschäftsführer: Dr. Thomas Höfer, Rainer Jung, Sven Maurmann
Re: event MPM (Was: Re: Planning for 2.4.7 in Oct)
Posted by Jim Jagielski <ji...@jaguNET.com>.
For completeness, a full, combined patch is:
http://people.apache.org/~jim/patches/httpd-2.4-event-test.patch
It requires a patch that knows about creating new files
when encountering /dev/null...
On Sep 10, 2013, at 9:52 AM, Jim Jagielski <ji...@jaguNET.com> wrote:
> For the testing, we need:
>
> http://people.apache.org/~jim/patches/httpd-2.4-skiplist.patch
> http://people.apache.org/~jim/patches/httpd-2.4-podx.patch
> http://people.apache.org/~jim/patches/httpd-2.4-event.patch
>
> This includes all the performance/sync updates
>
> Can we get infra to test that out somewhere?
>
> On Sep 6, 2013, at 7:19 AM, Jim Jagielski <ji...@jaguNET.com> wrote:
>
>>
>> On Sep 5, 2013, at 5:46 PM, Rainer Jung <ra...@kippdata.de> wrote:
>>
>>> On 05.09.2013 16:35, Jim Jagielski wrote:
>>>> BTW, the main diff between event in trunk and 2.4 is
>>>> the use of skiplist. My benchmarks show decreased latency
>>>> and a performance boost of ~5% (on avg). Can anyone confirm?
>>>> It would be nice to possibly get that in 2.4.7 as well.
>>>
>>> I can offer to negotiate with infra to run 2.4 head plus event patches
>>> for skiplist use on www.a.o EU if that helps collecting votes.
>>>
>>> I did the httpd updates on www.a.o during the last months and in
>>> previous years running non-released stuff there was a common practice,
>>> so I hope infra will trust our opinion on whether the code should be
>>> ready for prime time or not.
>>>
>>> If we want to see the code running there, I would appreciate a patch
>>> ready to apply to 2.4 event.c. I currently feel not in the position to
>>> judge, whether running that code on www.a.o actually is a good idea or
>>> not. Opinions?
>>
>>
>> Great idea. I can create the 2.4 patch. (and add it to STATUS) ;)
>>
>
Re: event MPM (Was: Re: Planning for 2.4.7 in Oct)
Posted by Jim Jagielski <ji...@jaguNET.com>.
For the testing, we need:
http://people.apache.org/~jim/patches/httpd-2.4-skiplist.patch
http://people.apache.org/~jim/patches/httpd-2.4-podx.patch
http://people.apache.org/~jim/patches/httpd-2.4-event.patch
This includes all the performance/sync updates
Can we get infra to test that out somewhere?
On Sep 6, 2013, at 7:19 AM, Jim Jagielski <ji...@jaguNET.com> wrote:
>
> On Sep 5, 2013, at 5:46 PM, Rainer Jung <ra...@kippdata.de> wrote:
>
>> On 05.09.2013 16:35, Jim Jagielski wrote:
>>> BTW, the main diff between event in trunk and 2.4 is
>>> the use of skiplist. My benchmarks show decreased latency
>>> and a performance boost of ~5% (on avg). Can anyone confirm?
>>> It would be nice to possibly get that in 2.4.7 as well.
>>
>> I can offer to negotiate with infra to run 2.4 head plus event patches
>> for skiplist use on www.a.o EU if that helps collecting votes.
>>
>> I did the httpd updates on www.a.o during the last months and in
>> previous years running non-released stuff there was a common practice,
>> so I hope infra will trust our opinion on whether the code should be
>> ready for prime time or not.
>>
>> If we want to see the code running there, I would appreciate a patch
>> ready to apply to 2.4 event.c. I currently feel not in the position to
>> judge, whether running that code on www.a.o actually is a good idea or
>> not. Opinions?
>
>
> Great idea. I can create the 2.4 patch. (and add it to STATUS) ;)
>
Re: event MPM (Was: Re: Planning for 2.4.7 in Oct)
Posted by Jim Jagielski <ji...@jaguNET.com>.
On Sep 5, 2013, at 5:46 PM, Rainer Jung <ra...@kippdata.de> wrote:
> On 05.09.2013 16:35, Jim Jagielski wrote:
>> BTW, the main diff between event in trunk and 2.4 is
>> the use of skiplist. My benchmarks show decreased latency
>> and a performance boost of ~5% (on avg). Can anyone confirm?
>> It would be nice to possibly get that in 2.4.7 as well.
>
> I can offer to negotiate with infra to run 2.4 head plus event patches
> for skiplist use on www.a.o EU if that helps collecting votes.
>
> I did the httpd updates on www.a.o during the last months and in
> previous years running non-released stuff there was a common practice,
> so I hope infra will trust our opinion on whether the code should be
> ready for prime time or not.
>
> If we want to see the code running there, I would appreciate a patch
> ready to apply to 2.4 event.c. I currently feel not in the position to
> judge, whether running that code on www.a.o actually is a good idea or
> not. Opinions?
Great idea. I can create the 2.4 patch. (and add it to STATUS) ;)
Re: event MPM (Was: Re: Planning for 2.4.7 in Oct)
Posted by Stefan Fritsch <sf...@sfritsch.de>.
Am Donnerstag, 5. September 2013, 23:46:21 schrieb Rainer Jung:
> In addition: what about eventopt?
AFAICT, the problem that the listener thread busy-loops if there are
not enough worker threads is still unfixed [1]. Or did I miss the fix?
[1] http://mail-archives.apache.org/mod_mbox/httpd-dev/201111.mbox/%3Calpine.DEB.2.00.1111151823490.24043%40eru.sfritsch.de%3E
Re: event MPM (Was: Re: Planning for 2.4.7 in Oct)
Posted by Rainer Jung <ra...@kippdata.de>.
On 05.09.2013 16:35, Jim Jagielski wrote:
> BTW, the main diff between event in trunk and 2.4 is
> the use of skiplist. My benchmarks show decreased latency
> and a performance boost of ~5% (on avg). Can anyone confirm?
> It would be nice to possibly get that in 2.4.7 as well.
I can offer to negotiate with infra to run 2.4 head plus event patches
for skiplist use on www.a.o EU if that helps collecting votes.
I did the httpd updates on www.a.o during the last months and in
previous years running non-released stuff there was a common practice,
so I hope infra will trust our opinion on whether the code should be
ready for prime time or not.
If we want to see the code running there, I would appreciate a patch
ready to apply to 2.4 event.c. I currently feel not in the position to
judge, whether running that code on www.a.o actually is a good idea or
not. Opinions?
In addition: what about eventopt?
Regards,
Rainer
event MPM (Was: Re: Planning for 2.4.7 in Oct)
Posted by Jim Jagielski <ji...@jaguNET.com>.
BTW, the main diff between event in trunk and 2.4 is
the use of skiplist. My benchmarks show decreased latency
and a performance boost of ~5% (on avg). Can anyone confirm?
It would be nice to possibly get that in 2.4.7 as well.
On Sep 5, 2013, at 9:08 AM, Jim Jagielski <ji...@jaguNET.com> wrote:
> It would be nice to release 2.4.7 next month, which would
> make it 3 months since the 2.4.6 release... Yeah, it's
> next month, but it's never too early to start planning.
>
> Are there items that we'd *really* like to see in 2.4.7
> that we should try to prioritize? Personally, UDS support
> for mod_proxy, as well as the websocket improvements in
> trunk (and the corresponding ap_mpm_register_socket_callback)
> look quite viable.
>
Re: Planning for 2.4.7 in Oct
Posted by Arkadiusz Miśkiewicz <ar...@maven.pl>.
On Thursday 05 of September 2013, Jim Jagielski wrote:
> It would be nice to release 2.4.7 next month, which would
> make it 3 months since the 2.4.6 release... Yeah, it's
> next month, but it's never too early to start planning.
>
> Are there items that we'd *really* like to see in 2.4.7
> that we should try to prioritize?
I would love to see https://issues.apache.org/bugzilla/show_bug.cgi?id=54852
bug fixed.
The reason why that problem happens is known, there are hacky solutions and
the only thing needed now is someone with internals knowledge to implement
clean and nice fix (like sending signals only to living processes based on
scoreboard instead of blindly sending to every process until current
max_daemons_limit).
--
Arkadiusz Miśkiewicz, arekm / maven.pl
Re: Planning for 2.4.7 in Oct
Posted by Jim Jagielski <ji...@jaguNET.com>.
On Sep 5, 2013, at 9:41 PM, Daniel Ruggeri <DR...@primary.net> wrote:
> On 9/5/2013 8:08 AM, Jim Jagielski wrote:
>> ... UDS support
>> for mod_proxy ...
>
> votes++
>
> ... speaking of which. Have you decided on a direction to take the
> config string syntax/tested it out? I have a test environment ready to
> try out any patches if you'd like another set of eyes.
>
I've been somewhat lax there (background: it looks like my
Mom will need to get her right knee replaced as well, so
all that has been keeping me somewhat busy), but all my
dev branches use the 'sock://var/run/server.sock|http://localhost/foo/bar'
URL flavor. It makes things much easier when we need to
parse the "actual" URL and do canon stuff.
Re: Planning for 2.4.7 in Oct
Posted by Daniel Ruggeri <DR...@primary.net>.
On 9/5/2013 8:08 AM, Jim Jagielski wrote:
> ... UDS support
> for mod_proxy ...
votes++
... speaking of which. Have you decided on a direction to take the
config string syntax/tested it out? I have a test environment ready to
try out any patches if you'd like another set of eyes.
--
Daniel Ruggeri