Then /proc/sys/vm tuning may help.What problem did you see that you traced to LowFree?
I have set this device as a bridge. Higher latency and low throughput seem
to be related to LowFree. There are also packet drops at the interface
when LowFree is too low.
I have another device which has 4G RAM split into 900M LowMem and
the rest as HighMem. In that case also, LowMem goes to a low level, say 8M
and although HighMem has ~2G free, the system gives OOPS (related to
page_alloc failures)
when acting as a bridge (passing packets).
On Wed, Sep 2, 2009 at 3:22 PM, Bill Davidsen<davidsen@xxxxxxx> wrote:
Adayadil Thomas wrote:
Greetings.You can change the parameters in /rpoc/sys/vm if you wish, but what makes
I am running a centos linux with 2.6.20 version kernel. The system has
1G of RAM.
As time goes by the LowFree becomes really low. Right now it shows
137M .. but it goes as low as 8M or so
The command -
echo 3 > /proc/sys/vm/drop_caches
brings back the LowFree to way up high.
The question I have is whether the system by itself release the cache
(drop cache) automatically
to maintain a reasonable LowFree?
Is this configurable?
you think this is needed? Cache is dropped as memory is needed, and
drop_cache in general is a good way to slow the system.
Any information or help is much appreciated.What problem did you see that you traced to LowFree?
cat /proc/meminfo
MemTotal: 1034788 kB
MemFree: 138240 kB
Buffers: 99260 kB
Cached: 177776 kB
SwapCached: 51740 kB
Active: 605172 kB
Inactive: 113572 kB
HighTotal: 130720 kB
HighFree: 252 kB
LowTotal: 904068 kB
LowFree: 137988 kB
SwapTotal: 1048568 kB
SwapFree: 976332 kB
Dirty: 380 kB
Writeback: 0 kB
AnonPages: 441348 kB
Mapped: 15540 kB
Slab: 146088 kB
SReclaimable: 104288 kB
SUnreclaim: 41800 kB
PageTables: 1596 kB
NFS_Unstable: 0 kB
Bounce: 0 kB
CommitLimit: 1565960 kB
Committed_AS: 590576 kB
VmallocTotal: 114680 kB
VmallocUsed: 15052 kB
VmallocChunk: 99348 kB