Coda File System

Re: Memory consumption

From: Kurt Huwig <kurt_at_huwig.de>
Date: Tue, 14 Dec 1999 11:54:38 +0100


Jan Harkes schrieb:
>
> On Mon, Dec 13, 1999 at 07:14:00PM +0100, Kurt Huwig wrote:
> > We have a machine here with 16G diskspace and another with 40G+.
> > Physical RAM is 64/128MB. How much physical RAM do we need to have it
> > work fine?
>
> It is the amount of VM that matters, with the private mmapings there
> should be a lot less disk trashing when the RVM size exceeds the amount
> of physical ram, as unmodified pages are not swapped out/in but simply
> paged in from the RVM data file.
>
> One problem we still have is that on linux it is not yet possible to
> do a private mmap of a raw device, but hopefully that will be resolved
> soon in the development kernels. Talk about implementing it has already
> started.

As I get it right now, I need the space for the Metadata several times:

  1. Ext2-Metadata for '/vicepa'
  2. Coda-DATA-partition
  3. Virtual-Memory containing the DATA-partition

I encountered some inconsistencies with Coda:

Machine 1 (kurti): Write-disconnected, 10MB venus-cache Machine 2 (tanja): Write-connected

I copied a file with size > cachesize from kurti onto the coda fs.


kurt_at_kurti:/coda/home/kurt > time cp ~/down/cc32e47.exe . 11:45:54 Cache Overflow: (407, -28685)

real 0m10.351s
user 0m0.000s
sys 0m0.470s
kurt_at_kurti:/coda/home/kurt > cfs lv .
  Status of volume 0x7f000001 (2130706433) named "Users:kurt"   Volume type is ReadWrite
  Connection State is WriteDisconnected
  Minimum quota is 0, maximum quota is unlimited   Current blocks used are 19796
  The partition has 2021547 blocks available out of 2065397   Write-back is disabled
  There are 4 CML entries pending for reintegration

kurt_at_kurti:/coda/home/kurt > l
total 19798 

drwxrwxrwx   2 root     nogroup       512 Dec 14 11:45 ./
drwxr-xr-x   2 codaroot nogroup       512 Dec 13 17:44 ../
-rw-r--r--   1 kurt     nogroup  20268141 Dec 14 11:45 cc32e47.exe
kurt_at_kurti:/coda/home/kurt > md5sum cc32e47.exe 0ee094d3373b84f25282fcdd191514a1 cc32e47.exe kurt_at_kurti:/coda/home/kurt > 11:46:26 Cache Overflow: (407, -29591) 
11:46:48 Reintegrate: Users:kurt, 2/4 records, result = SUCCESS
11:46:56 Cache Overflow: (408, -9797)
11:47:05 Reintegrate: Users:kurt, 2/2 records, result = SUCCESS
11:47:26 Cache Overflow: (408, -9797)

****************************

kurt_at_tanja:/coda/home/kurt > md5sum cc32e47.exe 0ee094d3373b84f25282fcdd191514a1 cc32e47.exe kurt_at_tanja:/coda/home/kurt > time md5sum cc32e47.exe d41d8cd98f00b204e9800998ecf8427e cc32e47.exe <-------!!!!! 
real    0m0.434s
user    0m0.000s
sys     0m0.000s

kurt_at_tanja:/coda/home/kurt > time md5sum cc32e47.exe 0ee094d3373b84f25282fcdd191514a1 cc32e47.exe

real 0m16.209s
user 0m1.250s
sys 0m0.390s

How could this happen?

I want to use the coda-machine as a fileserver in a SMB-network. Do you plan to have a 'non-caching-very-small-footprint-venus-version', so I can do this without the triple cache of files?

Kurt 

-- 
----------------------------------------------------------------------
Don't talk that much about yourself - we do it when you are not here!
Received on 1999-12-14 06:01:57