Henrik Nordstrom wrote:
> On ons, 2008-06-11 at 12:51 +0300, Mikko Kettunen wrote:
>
>> Yes, I read something about this on squid-users list, there seems to be
>> 8kB buffer for this if I understood right.
>
> The buffer is bigger than that. But not unlimited.
Ok.
> The big change needed is tha
Don't omit the frame pointer in 64 bit mode, it makes walking the stack
for things like profiling callgraphs impossible.
Adrian
On Thu, Jun 12, 2008, Amos Jeffries wrote:
> > Just for the sake of consistency and preference for better
> > troubleshooting and testing, are there any CFLAGS that I
> Just for the sake of consistency and preference for better
> troubleshooting and testing, are there any CFLAGS that I should be using
> during configure and compile of Squid 3HEAD? I was using the same
> options I was using with 2.6, which were:
>
> CFLAGS="-DNUMTHREADS=65 -march=nocona -03 -pipe
On 12/06/2008, at 11:45 AM, Henrik Nordstrom wrote:
On tor, 2008-06-12 at 10:53 +1000, Mark Nottingham wrote:
Any chance of getting the proposed fixes in 2241, 2376 and 2378 into
2.7STABLE3?
2241: yes
Thanks (was Mike's patch, not mine).
2376: if fixed
See followup.
2378: maybe
Do
On Thu, Jun 12, 2008, Henrik Nordstrom wrote:
> On tor, 2008-06-12 at 09:40 +0800, Adrian Chadd wrote:
> > Argh!
> >
> > Please start putting relevant details into:
> >
> > http://wiki.squid-cache.org/Features/VaryProcessing
>
> Why, when there is a bugzilla report for this bug?
>
> It's not a
On tor, 2008-06-12 at 09:40 +0800, Adrian Chadd wrote:
> Argh!
>
> Please start putting relevant details into:
>
> http://wiki.squid-cache.org/Features/VaryProcessing
Why, when there is a bugzilla report for this bug?
It's not a new Vary requirement, it's just a bug in that patch.
Regards
Henr
On tor, 2008-06-12 at 10:53 +1000, Mark Nottingham wrote:
> Any chance of getting the proposed fixes in 2241, 2376 and 2378 into
> 2.7STABLE3?
2241: yes
2376: if fixed
2378: maybe
Regards
Henrik
signature.asc
Description: This is a digitally signed message part
Argh!
Please start putting relevant details into:
http://wiki.squid-cache.org/Features/VaryProcessing
That way we can have a proper list of whats required.
Adrian
On Thu, Jun 12, 2008, Mark Nottingham wrote:
> These issues may be relevant:
> http://tools.ietf.org/wg/httpbis/trac/ticket/37
On tor, 2008-06-12 at 10:57 +1000, Benno Rice wrote:
> On 11/06/2008, at 10:24 PM, Adrian Chadd wrote:
>
> > On Wed, Jun 11, 2008, Henrik Nordstrom wrote:
> >> On ons, 2008-06-11 at 17:50 +0800, Adrian Chadd wrote:
> >>
> >>> Are there any objections to removing this patch from Squid-2.HEAD
> >>
These issues may be relevant:
http://tools.ietf.org/wg/httpbis/trac/ticket/37
http://tools.ietf.org/wg/httpbis/trac/ticket/38
If I understand correctly, Henrik is talking about a case where these
two responses might be seen from an origin:
HTTP/1.1 200 OK
Content-Type: application/foo
Cac
On 11/06/2008, at 10:24 PM, Adrian Chadd wrote:
On Wed, Jun 11, 2008, Henrik Nordstrom wrote:
On ons, 2008-06-11 at 17:50 +0800, Adrian Chadd wrote:
Are there any objections to removing this patch from Squid-2.HEAD
and
documenting this discussion (and other Vary related stuff) on a
wiki p
Any chance of getting the proposed fixes in 2241, 2376 and 2378 into
2.7STABLE3?
Cheers,
--
Mark Nottingham [EMAIL PROTECTED]
Just for the sake of consistency and preference for better
troubleshooting and testing, are there any CFLAGS that I should be using
during configure and compile of Squid 3HEAD? I was using the same
options I was using with 2.6, which were:
CFLAGS="-DNUMTHREADS=65 -march=nocona -03 -pipe -fomit-fr
Greetings to all of the developers,
As per the squid website, I am taking a moment to introduce myself to
the list. My name is Nicholas Ritter, I am a network/systems engineer
working for a small retail chain in the Midwest of the US. I have been
using Linux since about 1997 and squid since about
On Wed, Jun 11, 2008, Henrik Nordstrom wrote:
> On ons, 2008-06-11 at 20:01 +0800, Adrian Chadd wrote:
>
> > What I need to do is get this Sun box actually running Solaris and try to
> > get dtrace to tell me what time is spent in the main thread blocking on
> > disk writes.
>
> On Solaris you de
On ons, 2008-06-11 at 20:01 +0800, Adrian Chadd wrote:
> What I need to do is get this Sun box actually running Solaris and try to
> get dtrace to tell me what time is spent in the main thread blocking on
> disk writes.
On Solaris you defenitely want async writes and closes, as Solaris UFS
by def
On Wed, Jun 11, 2008, Henrik Nordstrom wrote:
> On ons, 2008-06-11 at 17:50 +0800, Adrian Chadd wrote:
>
> > Are there any objections to removing this patch from Squid-2.HEAD and
> > documenting this discussion (and other Vary related stuff) on a wiki page?
>
> No problem.
Ok. I'll commit a reve
On Wed, Jun 11, 2008, Henrik Nordstrom wrote:
> Oh, forgot to say that there is #define's in store_asyncufs.h tuning
> this. But the non-default settings hasn't been tested in a very very
> long time.. (2000 timeframe)
Yeah, I'm testing async write at the moment. But I'm not exactly testing
it wi
On Wed, Jun 11, 2008, Henrik Nordstrom wrote:
> Simply because when testing on Linux they very rarely block, with the fs
> buffers absorbing them fully as long as you don't run too short on
> memory.
Ah.
> But yes, when you reach the absolute limit of what the drives can
> sustain the buffers wi
On ons, 2008-06-11 at 13:14 +0200, Henrik Nordstrom wrote:
> On ons, 2008-06-11 at 17:48 +0800, Adrian Chadd wrote:
> > Subject says it all - open, read and unlink are async, but write and close
> > aren't.
> > Why is at least write not async?
>
> Simply because when testing on Linux they very ra
On ons, 2008-06-11 at 18:43 +0800, Adrian Chadd wrote:
> That wouldn't be terribly difficult. It could then service just
> the queue for that storedir. Hm, ok.
Exactly.
Regards
Henrik
signature.asc
Description: This is a digitally signed message part
On ons, 2008-06-11 at 17:48 +0800, Adrian Chadd wrote:
> Subject says it all - open, read and unlink are async, but write and close
> aren't.
> Why is at least write not async?
Simply because when testing on Linux they very rarely block, with the fs
buffers absorbing them fully as long as you don
On Wed, Jun 11, 2008, Henrik Nordstrom wrote:
> On ons, 2008-06-11 at 17:47 +0800, Adrian Chadd wrote:
> > How would it work? The diskd queues are all sysv msgq's which can't be
> > polled as filedescriptors. What would wake up the main Squid process?
>
> make diskd output something on stdout afte
On ons, 2008-06-11 at 17:50 +0800, Adrian Chadd wrote:
> Are there any objections to removing this patch from Squid-2.HEAD and
> documenting this discussion (and other Vary related stuff) on a wiki page?
No problem.
> A Cacheboy tester has noted that there's a definite drop in hit rate between
>
On ons, 2008-06-11 at 12:51 +0300, Mikko Kettunen wrote:
> Yes, I read something about this on squid-users list, there seems to be
> 8kB buffer for this if I understood right.
The buffer is bigger than that. But not unlimited.
The big change needed is that there currently isn't anything delaying
On ons, 2008-06-11 at 17:47 +0800, Adrian Chadd wrote:
> How would it work? The diskd queues are all sysv msgq's which can't be
> polled as filedescriptors. What would wake up the main Squid process?
make diskd output something on stdout after sending the completion
message to Squid.
Regards
Henr
Henrik Nordstrom wrote:
> On tis, 2008-06-10 at 12:40 +0300, Mikko Kettunen wrote:
>> How could I configure squid to buffer whole POST-request before sending
>> it to peer cache or originserver?
> Good question. It isn't really designed to do this. POST request may be
> almost unbounded in size, an
On Wed, Jun 11, 2008, Henrik Nordstrom wrote:
[snip]
> Probably better to rethink the patch to use the "vary id" as a timestamp
> instead, marking objects with an older update time as stale.
Are there any objections to removing this patch from Squid-2.HEAD and
documenting this discussion (and ot
On tis, 2008-06-10 at 12:40 +0300, Mikko Kettunen wrote:
> How could I configure squid to buffer whole POST-request before sending
> it to peer cache or originserver?
Good question. It isn't really designed to do this. POST request may be
almost unbounded in size, and some streaming over HTTP pro
Subject says it all - open, read and unlink are async, but write and close
aren't.
Why is at least write not async?
Adrian
--
- Xenion - http://www.xenion.com.au/ - VPS Hosting - Commercial Squid Support -
- $25/pm entry-level VPSes w/ capped bandwidth charges available in WA -
On Wed, Jun 11, 2008, Henrik Nordstrom wrote:
> > All the callback does is read into a temp buffer, and re-schedules for
> > read IO.
>
> Yes..
>
> The point of this wakeup is to break the select/poll/epoll/kqueue sleep.
I found that in the CVS history.
> It could obviously be optimized to onl
On ons, 2008-06-11 at 16:31 +0800, Adrian Chadd wrote:
> So perusing the aio code in preparation to disassocate it from the Squid
> fs code, I found that there's a pipe being used as a notification/wakeup
> mechanism.
Yes..
> Basically, thread completion writes a ! into the pipe; this wakes up th
On ons, 2008-06-11 at 01:18 +0800, Adrian Chadd wrote:
> Henrik,
>
> Whats incomplete about the Variant invalidation support in PURGE/CLR in
> Squid-2.HEAD?
There are many common corner cases where the existing vary_id isn't
picked up properly. The worst being if an object goes from not having
Va
So perusing the aio code in preparation to disassocate it from the Squid
fs code, I found that there's a pipe being used as a notification/wakeup
mechanism.
Basically, thread completion writes a ! into the pipe; this wakes up the
main squid loop and calls a PF callback.
All the callback does is r
34 matches
Mail list logo
