Re: Memory blowout

--MimeMultipartBoundary
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit

Right. Hmm. Guess I'm going to have to chase this one. My boss took down
our most heavily-loaded production server with the cachemanager in
precisely this way (during the peak request period). It took 45 minutes
to revalidate the swap_log. He was most mortified.

D

Chris Wedgwood wrote:
>
> On Tue, Jun 02, 1998 at 07:25:06AM -0600, Alex Rousskov wrote:
>
> > Have you tried b21/b22? Some store fixes in b21 might solve this problem.
>
> b21 still blows out. The process went from 20M to 77M and is still rising,
> no other requests can take place while this is happening.
>
> I expect soon it will hit the swap space, eat that then die....
>
> <pause>
>
> OK - stopped growing once it hits the swap space, presumably constant
> swapping has loswed the growth. This time 'kill' works.
>
> Looking at the b22 patches (it would be really kewl if all hunks were
> unified, not just some of them) and I don't see anything there that will
> help, but I'll give it a whirl anyhow.
>
> <pause>
>
> Nope. b22 also spirals out of control, eating gobs of memory and then
> swapping to death....
>
> -Chris

-- 
-----BEGIN GEEK CODE BLOCK-----
Version: 3.1
GAT d- s++: a C++++$ UL++++B+++S+++C++H++U++V+++$ P+++$ L+++ E-
W+++(--)$ N++ w++$>--- t+ 5++ X+() R+ tv b++++ DI+++ e- h-@ 
------END GEEK CODE BLOCK------
--MimeMultipartBoundary--