You are viewing a plain text version of this content. The canonical link for it is here.
Posted to users@httpd.apache.org by jo...@bt.com on 2011/01/22 01:53:47 UTC
[users@httpd] mod_ssl, erratic performance
Solaris 10
Apache version: 2.2.11 & 2.2.17 (32 &64 bit)
We recently moved our production webserver from a sparc platform (T2000) to an x86/64 platform (x2270-m2) and we have noticed an erratic response time for downloads of files using SSL. This seems to randomly occur with any files about 10k or larger. For instance, I have been using a test file of 140K, and it can take 0.5 or 4.8 seconds to transfer. When using the sparc platform, it always only takes 0.5 seconds.
I noticed this as we are using an external monitoring system (Gomez.com) and we started seeing these wildly varying times for transaction processing.
I have tried a cut down SSL setup for testing, and examined every directive and option, and I can't make sense of the problem. I'm using the following configuration string, and I'd be happy to include the configuration setups..
./configure --prefix=/app/www/apache-2.2.11_32 --with-mpm=worker --enable-ssl --with-apr=/app/apr-1.3.3-32 --with-apr-util=/app/apr-1.3.3-32 --enable-mods-shared="headers expires deflate"
Server version: Apache/2.2.17 (Unix)
Server built: Jan 5 2011 15:56:01
Server's Module Magic Number: 20051115:25
Server loaded: APR 1.3.3, APR-Util 1.3.4
Compiled using: APR 1.3.3, APR-Util 1.3.4
Architecture: 32-bit
Server MPM: Worker
threaded: yes (fixed thread count)
forked: yes (variable process count)
Server compiled with....
-D APACHE_MPM_DIR="server/mpm/worker"
-D APR_HAS_SENDFILE
-D APR_HAS_MMAP
-D APR_HAVE_IPV6 (IPv4-mapped addresses enabled)
-D APR_USE_FCNTL_SERIALIZE
-D APR_USE_PTHREAD_SERIALIZE
-D SINGLE_LISTEN_UNSERIALIZED_ACCEPT
-D APR_HAS_OTHER_CHILD
-D AP_HAVE_RELIABLE_PIPED_LOGS
-D DYNAMIC_MODULE_LIMIT=128
-D HTTPD_ROOT="/app/www/apache-2.2.17_32"
-D SUEXEC_BIN="/app/www/apache-2.2.17_32/bin/suexec"
-D DEFAULT_SCOREBOARD="logs/apache_runtime_status"
-D DEFAULT_ERRORLOG="logs/error_log"
-D AP_TYPES_CONFIG_FILE="conf/mime.types"
-D SERVER_CONFIG_FILE="conf/httpd.conf"
I can move the bare-bones configuration between the sparc and x86 platforms and get normal response on the sparc, and irregular on the x86.
Any help would be appreciated.
John Newton
---------------------------------------------------------------------
The official User-To-User support forum of the Apache HTTP Server Project.
See <URL:http://httpd.apache.org/userslist.html> for more info.
To unsubscribe, e-mail: users-unsubscribe@httpd.apache.org
" from the digest: users-digest-unsubscribe@httpd.apache.org
For additional commands, e-mail: users-help@httpd.apache.org
RE: [users@httpd] mod_ssl, erratic performance
Posted by jo...@bt.com.
On Thursday, January 27, 2011 11:24 AM,
>Am 27.01.2011 16:34, schrieb Matus UHLAR - fantomas:
>> On 22.01.11 00:53, john.3.newton@bt.com wrote:
>>>
>>> We recently moved our production webserver from a sparc platform (T2000)
>>> to an x86/64 platform (x2270-m2) and we have noticed an erratic response
>>> time for downloads of files using SSL. This seems to randomly occur with
>>> any files about 10k or larger. For instance, I have been using a test file
>>> of 140K, and it can take 0.5 or 4.8 seconds to transfer. When using the
>>> sparc platform, it always only takes 0.5 seconds.
>>>
>>> I noticed this as we are using an external monitoring system (Gomez.com)
>>> and we started seeing these wildly varying times for transaction
>>> processing.
>>>
>>> I have tried a cut down SSL setup for testing, and examined every
>>> directive and option, and I can't make sense of the problem. I'm using the
>>> following configuration string, and I'd be happy to include the
>>> configuration setups..
>>>
>>> I can move the bare-bones configuration between the sparc and x86
>>> platforms and get normal response on the sparc, and irregular on the x86.
>>
>> random device can make a huge difference. What do you use for random data?
>> /dev/random or /dev/urandom? If the rofmer, try the latter if it helps.
>
>Good point. But to have some prove at hand, don't change the random
>device yet - instead monitor /proc/sys/kernel/random/entropy_avail with
>e.g. watch. If your're going of of random bytes - ka-ching :)
>
>Regards,
>Edgar
Good idea. I was wondering if not enough entropy was the problem, but didn't know how to verify that. I'll give your suggestion a go when I'm testing connections next, and see what it does.
Thanks for the suggestion, and I'll let you know what I find out.
John Newton
---------------------------------------------------------------------
The official User-To-User support forum of the Apache HTTP Server Project.
See <URL:http://httpd.apache.org/userslist.html> for more info.
To unsubscribe, e-mail: users-unsubscribe@httpd.apache.org
" from the digest: users-digest-unsubscribe@httpd.apache.org
For additional commands, e-mail: users-help@httpd.apache.org
Re: [users@httpd] mod_ssl, erratic performance
Posted by Edgar Frank <ef...@email.de>.
Am 27.01.2011 16:34, schrieb Matus UHLAR - fantomas:
> On 22.01.11 00:53, john.3.newton@bt.com wrote:
>>
>> We recently moved our production webserver from a sparc platform (T2000)
>> to an x86/64 platform (x2270-m2) and we have noticed an erratic response
>> time for downloads of files using SSL. This seems to randomly occur with
>> any files about 10k or larger. For instance, I have been using a test file
>> of 140K, and it can take 0.5 or 4.8 seconds to transfer. When using the
>> sparc platform, it always only takes 0.5 seconds.
>>
>> I noticed this as we are using an external monitoring system (Gomez.com)
>> and we started seeing these wildly varying times for transaction
>> processing.
>>
>> I have tried a cut down SSL setup for testing, and examined every
>> directive and option, and I can't make sense of the problem. I'm using the
>> following configuration string, and I'd be happy to include the
>> configuration setups..
>>
>> I can move the bare-bones configuration between the sparc and x86
>> platforms and get normal response on the sparc, and irregular on the x86.
>
> random device can make a huge difference. What do you use for random data?
> /dev/random or /dev/urandom? If the rofmer, try the latter if it helps.
Good point. But to have some prove at hand, don't change the random
device yet - instead monitor /proc/sys/kernel/random/entropy_avail with
e.g. watch. If your're going of of random bytes - ka-ching :)
Regards,
Edgar
---------------------------------------------------------------------
The official User-To-User support forum of the Apache HTTP Server Project.
See <URL:http://httpd.apache.org/userslist.html> for more info.
To unsubscribe, e-mail: users-unsubscribe@httpd.apache.org
" from the digest: users-digest-unsubscribe@httpd.apache.org
For additional commands, e-mail: users-help@httpd.apache.org
RE: [users@httpd] mod_ssl, erratic performance
Posted by jo...@bt.com.
<SNIP>
>
>random device can make a huge difference. What do you use for random data?
>/dev/random or /dev/urandom? If the rofmer, try the latter if it helps.
>--
>Matus UHLAR - fantomas, uhlar@fantomas.sk ; http://www.fantomas.sk/
Matus -
I have actually tried both, as well as builtin. I have also varied these based on startup or connect. I didn't see any difference in performance.
John Newton
---------------------------------------------------------------------
The official User-To-User support forum of the Apache HTTP Server Project.
See <URL:http://httpd.apache.org/userslist.html> for more info.
To unsubscribe, e-mail: users-unsubscribe@httpd.apache.org
" from the digest: users-digest-unsubscribe@httpd.apache.org
For additional commands, e-mail: users-help@httpd.apache.org
Re: [users@httpd] mod_ssl, erratic performance
Posted by Matus UHLAR - fantomas <uh...@fantomas.sk>.
On 22.01.11 00:53, john.3.newton@bt.com wrote:
>
> We recently moved our production webserver from a sparc platform (T2000)
> to an x86/64 platform (x2270-m2) and we have noticed an erratic response
> time for downloads of files using SSL. This seems to randomly occur with
> any files about 10k or larger. For instance, I have been using a test file
> of 140K, and it can take 0.5 or 4.8 seconds to transfer. When using the
> sparc platform, it always only takes 0.5 seconds.
>
> I noticed this as we are using an external monitoring system (Gomez.com)
> and we started seeing these wildly varying times for transaction
> processing.
>
> I have tried a cut down SSL setup for testing, and examined every
> directive and option, and I can't make sense of the problem. I'm using the
> following configuration string, and I'd be happy to include the
> configuration setups..
>
> I can move the bare-bones configuration between the sparc and x86
> platforms and get normal response on the sparc, and irregular on the x86.
random device can make a huge difference. What do you use for random data?
/dev/random or /dev/urandom? If the rofmer, try the latter if it helps.
--
Matus UHLAR - fantomas, uhlar@fantomas.sk ; http://www.fantomas.sk/
Warning: I wish NOT to receive e-mail advertising to this address.
Varovanie: na tuto adresu chcem NEDOSTAVAT akukolvek reklamnu postu.
Windows found: (R)emove, (E)rase, (D)elete
---------------------------------------------------------------------
The official User-To-User support forum of the Apache HTTP Server Project.
See <URL:http://httpd.apache.org/userslist.html> for more info.
To unsubscribe, e-mail: users-unsubscribe@httpd.apache.org
" from the digest: users-digest-unsubscribe@httpd.apache.org
For additional commands, e-mail: users-help@httpd.apache.org
Re: [users@httpd] Status 3221225480 and restart
Posted by Wo...@geigerus.com.
Sorry!
Did not mean to!
Matus UHLAR - fantomas <uh...@fantomas.sk>
01/27/2011 10:32 AM
Please respond to
users@httpd.apache.org
To
users@httpd.apache.org
cc
Subject
Re: [users@httpd] Status 3221225480 and restart
On 24.01.11 11:09, Wolfgang.Miska@geigerus.com wrote:
> In-Reply-To:
> <E71BAE31C16E784380444F62AFD383C306F6141AB9@EMV02-UKBR.domain1.systemhos
> t.net>
> References:
> <E71BAE31C16E784380444F62AFD383C304FF0B38AD@EMV02-UKBR.domain1.systemhos
> t.net>
<AA...@mail.gmail.com>
> <E71BAE31C16E784380444F62AFD383C306F6141AB9@EMV02-UKBR.domain1.systemhos
> t.net>
> To: users@httpd.apache.org
> From: Wolfgang.Miska@geigerus.com
> Subject: [users@httpd] Status 3221225480 and restart
>
> Hi All,
>
> I am running Apache 2.2.17 on a Windows XP and repeatedly I get the
> following message:
>
> [notice] Parent: child process exited with status 3221225480 --
> Restarting.
>
> And Apache restarts.
>
> What does status 3221225480 mean?
Is this somehow related to the SSL problem you were replying to?
If not, please stop hijacking threads - send a new mail, not a reply.
--
Matus UHLAR - fantomas, uhlar@fantomas.sk ; http://www.fantomas.sk/
Warning: I wish NOT to receive e-mail advertising to this address.
Varovanie: na tuto adresu chcem NEDOSTAVAT akukolvek reklamnu postu.
LSD will make your ECS screen display 16.7 million colors
---------------------------------------------------------------------
The official User-To-User support forum of the Apache HTTP Server Project.
See <URL:http://httpd.apache.org/userslist.html> for more info.
To unsubscribe, e-mail: users-unsubscribe@httpd.apache.org
" from the digest: users-digest-unsubscribe@httpd.apache.org
For additional commands, e-mail: users-help@httpd.apache.org
Re: [users@httpd] Status 3221225480 and restart
Posted by Matus UHLAR - fantomas <uh...@fantomas.sk>.
On 24.01.11 11:09, Wolfgang.Miska@geigerus.com wrote:
> In-Reply-To:
> <E71BAE31C16E784380444F62AFD383C306F6141AB9@EMV02-UKBR.domain1.systemhos
> t.net>
> References:
> <E71BAE31C16E784380444F62AFD383C304FF0B38AD@EMV02-UKBR.domain1.systemhos
> t.net> <AA...@mail.gmail.com>
> <E71BAE31C16E784380444F62AFD383C306F6141AB9@EMV02-UKBR.domain1.systemhos
> t.net>
> To: users@httpd.apache.org
> From: Wolfgang.Miska@geigerus.com
> Subject: [users@httpd] Status 3221225480 and restart
>
> Hi All,
>
> I am running Apache 2.2.17 on a Windows XP and repeatedly I get the
> following message:
>
> [notice] Parent: child process exited with status 3221225480 --
> Restarting.
>
> And Apache restarts.
>
> What does status 3221225480 mean?
Is this somehow related to the SSL problem you were replying to?
If not, please stop hijacking threads - send a new mail, not a reply.
--
Matus UHLAR - fantomas, uhlar@fantomas.sk ; http://www.fantomas.sk/
Warning: I wish NOT to receive e-mail advertising to this address.
Varovanie: na tuto adresu chcem NEDOSTAVAT akukolvek reklamnu postu.
LSD will make your ECS screen display 16.7 million colors
---------------------------------------------------------------------
The official User-To-User support forum of the Apache HTTP Server Project.
See <URL:http://httpd.apache.org/userslist.html> for more info.
To unsubscribe, e-mail: users-unsubscribe@httpd.apache.org
" from the digest: users-digest-unsubscribe@httpd.apache.org
For additional commands, e-mail: users-help@httpd.apache.org
[users@httpd] Status 3221225480 and restart
Posted by Wo...@geigerus.com.
Hi All,
I am running Apache 2.2.17 on a Windows XP and repeatedly I get the
following message:
[notice] Parent: child process exited with status 3221225480 --
Restarting.
And Apache restarts.
What does status 3221225480 mean?
Wolfgang
RE: [users@httpd] mod_ssl, erratic performance
Posted by jo...@bt.com.
Thanks for the suggestion, but I have KeepAlive On, and it doesn't make a difference.
Do you have any other suggestions?
John Newton
-----Original Message-----
From: Devraj Mukherjee [mailto:devraj@gmail.com]
Sent: Saturday, January 22, 2011 3:57 PM
To: users@httpd.apache.org
Subject: Re: [users@httpd] mod_ssl, erratic performance
I found that turning KeepAlive On makes a huge difference to SSL
performance (or performance in general).
On Sat, Jan 22, 2011 at 11:53 AM, <jo...@bt.com> wrote:
> Solaris 10
> Apache version: 2.2.11 & 2.2.17 (32 &64 bit)
>
> We recently moved our production webserver from a sparc platform (T2000) to an x86/64 platform (x2270-m2) and we have noticed an erratic response time for downloads of files using SSL. This seems to randomly occur with any files about 10k or larger. For instance, I have been using a test file of 140K, and it can take 0.5 or 4.8 seconds to transfer. When using the sparc platform, it always only takes 0.5 seconds.
>
> I noticed this as we are using an external monitoring system (Gomez.com) and we started seeing these wildly varying times for transaction processing.
>
> I have tried a cut down SSL setup for testing, and examined every directive and option, and I can't make sense of the problem. I'm using the following configuration string, and I'd be happy to include the configuration setups..
>
> ./configure --prefix=/app/www/apache-2.2.11_32 --with-mpm=worker --enable-ssl --with-apr=/app/apr-1.3.3-32 --with-apr-util=/app/apr-1.3.3-32 --enable-mods-shared="headers expires deflate"
>
> Server version: Apache/2.2.17 (Unix)
> Server built: Jan 5 2011 15:56:01
> Server's Module Magic Number: 20051115:25
> Server loaded: APR 1.3.3, APR-Util 1.3.4
> Compiled using: APR 1.3.3, APR-Util 1.3.4
> Architecture: 32-bit
> Server MPM: Worker
> threaded: yes (fixed thread count)
> forked: yes (variable process count)
> Server compiled with....
> -D APACHE_MPM_DIR="server/mpm/worker"
> -D APR_HAS_SENDFILE
> -D APR_HAS_MMAP
> -D APR_HAVE_IPV6 (IPv4-mapped addresses enabled)
> -D APR_USE_FCNTL_SERIALIZE
> -D APR_USE_PTHREAD_SERIALIZE
> -D SINGLE_LISTEN_UNSERIALIZED_ACCEPT
> -D APR_HAS_OTHER_CHILD
> -D AP_HAVE_RELIABLE_PIPED_LOGS
> -D DYNAMIC_MODULE_LIMIT=128
> -D HTTPD_ROOT="/app/www/apache-2.2.17_32"
> -D SUEXEC_BIN="/app/www/apache-2.2.17_32/bin/suexec"
> -D DEFAULT_SCOREBOARD="logs/apache_runtime_status"
> -D DEFAULT_ERRORLOG="logs/error_log"
> -D AP_TYPES_CONFIG_FILE="conf/mime.types"
> -D SERVER_CONFIG_FILE="conf/httpd.conf"
>
> I can move the bare-bones configuration between the sparc and x86 platforms and get normal response on the sparc, and irregular on the x86.
>
> Any help would be appreciated.
>
> John Newton
>
>
>
> ---------------------------------------------------------------------
> The official User-To-User support forum of the Apache HTTP Server Project.
> See <URL:http://httpd.apache.org/userslist.html> for more info.
> To unsubscribe, e-mail: users-unsubscribe@httpd.apache.org
> " from the digest: users-digest-unsubscribe@httpd.apache.org
> For additional commands, e-mail: users-help@httpd.apache.org
>
>
---------------------------------------------------------------------
The official User-To-User support forum of the Apache HTTP Server Project.
See <URL:http://httpd.apache.org/userslist.html> for more info.
To unsubscribe, e-mail: users-unsubscribe@httpd.apache.org
" from the digest: users-digest-unsubscribe@httpd.apache.org
For additional commands, e-mail: users-help@httpd.apache.org
---------------------------------------------------------------------
The official User-To-User support forum of the Apache HTTP Server Project.
See <URL:http://httpd.apache.org/userslist.html> for more info.
To unsubscribe, e-mail: users-unsubscribe@httpd.apache.org
" from the digest: users-digest-unsubscribe@httpd.apache.org
For additional commands, e-mail: users-help@httpd.apache.org
Re: [users@httpd] mod_ssl, erratic performance
Posted by Devraj Mukherjee <de...@gmail.com>.
I found that turning KeepAlive On makes a huge difference to SSL
performance (or performance in general).
On Sat, Jan 22, 2011 at 11:53 AM, <jo...@bt.com> wrote:
> Solaris 10
> Apache version: 2.2.11 & 2.2.17 (32 &64 bit)
>
> We recently moved our production webserver from a sparc platform (T2000) to an x86/64 platform (x2270-m2) and we have noticed an erratic response time for downloads of files using SSL. This seems to randomly occur with any files about 10k or larger. For instance, I have been using a test file of 140K, and it can take 0.5 or 4.8 seconds to transfer. When using the sparc platform, it always only takes 0.5 seconds.
>
> I noticed this as we are using an external monitoring system (Gomez.com) and we started seeing these wildly varying times for transaction processing.
>
> I have tried a cut down SSL setup for testing, and examined every directive and option, and I can't make sense of the problem. I'm using the following configuration string, and I'd be happy to include the configuration setups..
>
> ./configure --prefix=/app/www/apache-2.2.11_32 --with-mpm=worker --enable-ssl --with-apr=/app/apr-1.3.3-32 --with-apr-util=/app/apr-1.3.3-32 --enable-mods-shared="headers expires deflate"
>
> Server version: Apache/2.2.17 (Unix)
> Server built: Jan 5 2011 15:56:01
> Server's Module Magic Number: 20051115:25
> Server loaded: APR 1.3.3, APR-Util 1.3.4
> Compiled using: APR 1.3.3, APR-Util 1.3.4
> Architecture: 32-bit
> Server MPM: Worker
> threaded: yes (fixed thread count)
> forked: yes (variable process count)
> Server compiled with....
> -D APACHE_MPM_DIR="server/mpm/worker"
> -D APR_HAS_SENDFILE
> -D APR_HAS_MMAP
> -D APR_HAVE_IPV6 (IPv4-mapped addresses enabled)
> -D APR_USE_FCNTL_SERIALIZE
> -D APR_USE_PTHREAD_SERIALIZE
> -D SINGLE_LISTEN_UNSERIALIZED_ACCEPT
> -D APR_HAS_OTHER_CHILD
> -D AP_HAVE_RELIABLE_PIPED_LOGS
> -D DYNAMIC_MODULE_LIMIT=128
> -D HTTPD_ROOT="/app/www/apache-2.2.17_32"
> -D SUEXEC_BIN="/app/www/apache-2.2.17_32/bin/suexec"
> -D DEFAULT_SCOREBOARD="logs/apache_runtime_status"
> -D DEFAULT_ERRORLOG="logs/error_log"
> -D AP_TYPES_CONFIG_FILE="conf/mime.types"
> -D SERVER_CONFIG_FILE="conf/httpd.conf"
>
> I can move the bare-bones configuration between the sparc and x86 platforms and get normal response on the sparc, and irregular on the x86.
>
> Any help would be appreciated.
>
> John Newton
>
>
>
> ---------------------------------------------------------------------
> The official User-To-User support forum of the Apache HTTP Server Project.
> See <URL:http://httpd.apache.org/userslist.html> for more info.
> To unsubscribe, e-mail: users-unsubscribe@httpd.apache.org
> " from the digest: users-digest-unsubscribe@httpd.apache.org
> For additional commands, e-mail: users-help@httpd.apache.org
>
>
---------------------------------------------------------------------
The official User-To-User support forum of the Apache HTTP Server Project.
See <URL:http://httpd.apache.org/userslist.html> for more info.
To unsubscribe, e-mail: users-unsubscribe@httpd.apache.org
" from the digest: users-digest-unsubscribe@httpd.apache.org
For additional commands, e-mail: users-help@httpd.apache.org