Date: Fri, 03 Apr 1998 22:10:25 +0200 From: Poul-Henning Kamp <phk@critter.freebsd.dk> To: =?koi8-r?B?4c7E0sXKIP7F0s7P1w==?= <ache@nagual.pp.ru> Cc: "Alok K. Dhir" <adhir@worldbank.org>, current@FreeBSD.ORG, adkin003@tc.umn.edu Subject: Re: Working patch *with* splhigh() (Was Re: More info RE: X slowdown in -current) Message-ID: <3396.891634225@critter.freebsd.dk> In-Reply-To: Your message of "Sat, 04 Apr 1998 00:04:25 %2B0400." <19980404000425.64904@nagual.pp.ru>
next in thread | previous in thread | raw e-mail | index | archive | help
In message <19980404000425.64904@nagual.pp.ru>, =?koi8-r?B?4c7E0sXKIP7F0s7P1w==
?= writes:
>On Fri, Apr 03, 1998 at 09:52:12PM +0200, Poul-Henning Kamp wrote:
>> My xserver is remote, but it still doesn't make any difference :-(
>
>local xserver needed for testing.
Hmm, why would that be...
>> >> Does "systat :vm" show abnormally many syscalls ?
>
>How many is 'abnormally many'? Maybe I'll send you just systat output so
>you can determine?
'abnormally many' as in "select is really screwed up"
>> The problem is that time must somehow become zero when we reach
>> tsleep() where it should have been non-zero. I'd be damned if I
>> can see how that can happen.
>
>Do you know any place for debugging printf which just detect error and not
>overflow messages? I can insert it there and test. Or maybe temporarily
>use some sysctl variable...
right before tsleep:
if (!timo) printf("proc %d sleeping indefenitely", curproc->p_pid);
Netscape should not be amongst them, you'll maybe see inetd and a couple
like that...
>> Anybody else see this problem with version 1.35 ?
>
>This whole thread *is* about 1.35 version, if you start to read from first
>messages they are 'the code claimed to be fixed but I still got slowness'.
The operative word in my question isn't 1.35 but "anybody else" :-)
--
Poul-Henning Kamp FreeBSD coreteam member
phk@FreeBSD.ORG "Real hackers run -current on their laptop."
"Drink MONO-tonic, it goes down but it will NEVER come back up!"
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-current" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?3396.891634225>