Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 17 Feb 1999 11:31:12 -0800 (PST)
From:      Matthew Dillon <dillon@apollo.backplane.com>
To:        Tor.Egge@fast.no
Cc:        hackers@FreeBSD.ORG
Subject:   Re: Problems in VM structure ?
Message-ID:  <199902171931.LAA10322@apollo.backplane.com>
References:  <199902171744.JAA06913@apollo.backplane.com> <199902171910.UAA17721@midten.fast.no>

next in thread | previous in thread | raw e-mail | index | archive | help
:All zones with ZONE_INTERRUPT flag has preallocated KVA
:and a nonzero max. --> 78 MB.
:
:SMP --> 4 MB per processor private kva
:last page dir entry reserved for alternate page table --> 4 MB
:Kernel text + data + bss --> 1.5 MB
:
:	78 MB + 4 MB + 4 MB + 1.5 MB + 170 MB --> 257.5 MB
:
:When looking at current kernel_map on a 512 MB SMP machine with
:maxusers set to 256, VM_KMEM_SIZE and VM_KMEM_SIZE_MAX set to
:128 MB and NMBCLUSTERS set to 12288:
:
:	(kgdb) print kernel_map->size
:	$1 = 334737408
:
:- Tor Egge

    Ach.

    So why isn't it panicing on boot?  Why does the machine 
    destabilize and die later on with all sorts of problems? 
    Is it trying to use more page table entries then were allocated 
    for the kernel_map?  Is the submap allocator broken?

    Is there some test we can add to panic the machine at boot
    time if KVM is over-reserved?

					-Matt
					Matthew Dillon 
					<dillon@backplane.com>



To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-hackers" in the body of the message




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199902171931.LAA10322>