[Systems] Discovery_One Was a.sl.o migration.
dfarning at sugarlabs.org
Thu Nov 5 16:10:12 EST 2009
On Thu, Nov 5, 2009 at 3:25 AM, Sascha Silbe
<sascha-ml-ui-sugar-systems at silbe.org> wrote:
> On Wed, Nov 04, 2009 at 05:46:54PM -0600, David Farning wrote:
>> The first step will be to add a Squid caching proxy in front of the
>> PHP server. It looks like we will be able to cache all of the images,
> I'm not sure that'll work out as expected. See my mail
> <20091001212816.GB4941 at twin.sascha.silbe.org>:
I could not access that email.
>>> (Currently unreachable via IPv6)
>>> Does two redirections for start page (/ -> /en-US/ -> /en-US/sugar/),
>>> both times with caching disabled and probably incomplete Vary header (only
>>> gives Accept-Encoding, nothing language-related).
>>> Remaining pages: Not cached when using default squid settings because LM
>>> is not given. Does not support IMS.
> (LM=Last-Modified, IMS=If-Modified-Since)
>> I _think_ that our current bottle neck is our Apache server. Because
>> we are running many services, we have several Apache mod_* enabled.
>> This gives us heavy Apache processes.
> In theory, Linux is supposed to create COW (Copy-on-write) mappings on
> fork(), i.e. only memory that gets modified by the child process will be
> newly allocated.
> How well that works in practice with Apache I don't know, but maybe bernie
>> Because we are not using an caching proxy in front of Apache, all of our
>> static content is being handled by these processes.
> Making static pages cachable is always a good idea, of course. :)
>> Adding squid and removing the uneedded mod_* should increase overall
>> system throughput.
> Would (really) be curious to see actual measurements for the latter.
Yes, I am interested too. A well designed php app _should_ max out
the CPU before the load starts climbing.... We will know more when we
can isolate it from the rest of sunjammer.
> CU Sascha
> -----BEGIN PGP SIGNATURE-----
> Version: GnuPG v1.4.9 (GNU/Linux)
> -----END PGP SIGNATURE-----
> Systems mailing list
> Systems at lists.sugarlabs.org
More information about the Systems