|
|
About
TODO
Blog
RSS
Old blog
Projects
Gallery
Notes
Sun, 20 Apr 2008
Meanwhile at appartment development side.
Moved to the 'Leroy Merlin' development shop to get lots of stuff and
found so huge crowd of people, that decided to run away as quickly as possible.
While walking there found couple of interesting things:
- wood plates from small to 2000x600, which are perfectly polished, have
acceptible for table/shelf/cupboard development thicknes, and have too small price
to resist to buy. When I started my table developemnt there were no such things
in broad usage at all, but I will not stop, just because I found materials,
which allow to build it much faster and simpler. But for usual shelves I will definitely
get it there and will not implement things myself from real wood plates (those
ones are made using glueing technology from much smaller plates, I used similar to
implement thick enough part of my 'L'-style table).
- bath cabins are incredibly ugly and unacceptibly bad-made. I knew that before though.
- found bar installation, which want to setup at home - likely it will be my only
table in kitchen, I like it very much.
- my kitchen (actually right now it is heavily used as joinery only)
has only 3/4 of walls covered with wallpapers, today I've known, that
my wallpaper model will not be sold anymore, so either I will have to reglue most of the
kitchen, or I will create some interesting installation on the remaining part of the walls,
and I think I already know what to put there: just like my blue wall in the room,
I will put some brick-like elements in the kitchen. As a ceiling light I will install a huge
wood beam hinged on chains with attached small lights. Or maybe not, who knows...
At home I attached '_' part of my 'L' table (it is not exactly 'L', but rounded very much),
and started the last painting layer. Also attached holders to the walls where table will be located
(my huge 2000x1500 or so table has only single leg close to the end of the longer part
of letter 'L', other parts are attached to the walls).
Maybe i will even install it today's night if colour will be ready.
/devel/flat :: Link / Comments (0)
Real Jedi does not use kernel.
He writes new or extends existing, but it is from different serie.
This one will tell you how one will be able to build a distributed
and then parallel filesystem using POHMELFS.
Headline says it all: POHMELFS server will not be placed into kernel
so far, since it is already very fast (compared to in-kernel async NFS server),
and userspace programming is a bit easier and mostly because there is no
need to wait about 10 minutes while servers come up after ipmi reboot,
since they are located somewhere I do not know where and there is no posibility
to quickly reboot them by hand, so servers have lots of things to bring themself
up even if something was really screwed, like network boot, add here scsi probing,
possible fsck, initial bios memtest (8GB)...
So, planned POHMELFS server updates:
- PMCC - poor man
cache coherency protocol. Scheduled for the first half of the next week, btw.
- server extension to allow storing data on multiple devices (like creating mirroring),
first by saving data in several local directories (think about server, which mounted remote
dirs over POHMELFS or NFS, and local dirs).
- client/server extension to report lookup and readdir requests not only for local destination,
but also to different addresses, so that reading/writing could be done from different nodes
in parallel.
Somewhere at the beginning there is also a task to extend client to be able to
switch between different servers (if one goes down, client automatically reconnects to second
and so on).
And the most complex task is server parallelization, i.e. ability to have multiple
servers, which handle the same metadata, to work in parallel and be coherent. AFAIK, there
are no such (at least open) solutions, neither Lustre, nor PVFS2, nor Ceph,
nor glusterfs, nor whatever.
There are solutions to have master-slave setup (IIRC, Lustre works that way), Ceph has ability
to spread metadata between multiple servers, but they do not handle the same sets of objects,
so there is no metadata server redundancy.
So far I consider this as the most complex part, and I have not yet come to solution.
/devel/fs :: Link / Comments (0)
|