LDMLoadbalancingSupport

Revision 12 as of 2007-10-29 16:49:20

Clear message

Summary

This specification is about extending LTSP to support multiple application servers.

Rationale

To support larger rollouts of LTSP, you could use a bigger machine, or adding many smaller ones. The later is related to the idea of Bewolf clusters, that are made of commodity hardware. The goal is to make it possible to add any number of additional secondary application servers to the network, and dispatch users on them.

Use Cases

Rudolfo has 1400 thin clients and 30 application servers. He would like to balance users sessions across the available application servers. He want to be able to add new servers while the needs growth.

Margot teaches computer science at a school in a rural area, and she has 17 recycled thin clients available for her lab, but she does not have a server available to support the 17 TCs. Instead, she has scraped together three desktop class machines for this purpose, and she wants to be able to support all 17 TCs with concurrent logins.

Scope

This spec is concerned with load balancing login sessions across multiple application servers. It covers :

  • Support many load distribution algorithms
  • This spec is about LDM, but XDMCP should be supported also
  • The integration of ltsp-loadbalancer
  • Make sure that other tools are working in such setup

Design

In LDM, the script $CHROOT/usr/lib/ltsp/get_hosts, if exists, will return the server or the server list for login. This script has to be written by the administrator in gutsy.

A default implementation should be provided, with those algorithms :

  • ltsp-loadbalancer client
  • randomized : take one server randomly
  • best rated : take the best server
  • weightned best rated : randomize, but give more probability to best rated servers
  • fixed : load balancing disabled

For advanced loadbalancing, ltsp-loadbalancer would be used. Smaller setups could use other algorithms to easy the administration. The algorithm selection will be done by setting a variable in lts.conf file.

The get_hosts programm should be keept small and efficient, because it runs on the thin-client.

LDM can display several servers in the GUI.

For XDMCP setups, only the first server in the list will be used for query.

Implementation

Outstanding Issues

BoF agenda and discussion

Prototype (deprecated)

The first iteration of the implementation is available at: http://ltsp.mindtouchsoftware.com/ltsp-loadbalance.

It consists of a stand alone server component (ltsp-server-advertise) that is able to provide clients with statistics to resources available. This is implemented in python as a daemon. The application waits for incoming inquisitions on port (currently 377). It returns a xml document with the statistics and closes the socket.

A client component is mostly self contained in it's own (mostly self contained) module (pickserver.py). This module is integrated with ldm where it periodically (right now the default is 5 seconds, a more sensible would be every 30 seconds or a minute) queries the servers from a predefined list of servers. As soon as the user logs in the best server is already available. Changes required to ldm are minimally invasive since most of the code (as state above) is split into a separate module.

It's very hard to pick the "best" server. Here are some options:

  1. Implemented: The other option provides the administrator some tunable parameters like to ignore servers that are swapping, ignore servers that take x ms to respond, ignore servers that have a load higher then x (normalized to number of processors). Random is uses on the remaining servers. If no candidates available, it pick the random server from the list of servers that responded.
  2. Implemented: Throw away the non responding servers, pick a random one from the remaining servers (random tends to make a good choice a high percentage of the time).
  3. Unimplemented: Each client uses the same server (dynamically eliminating unresponsive servers from the list of what's available) every session. This can be done by hashing the TC MAC address and taking a modulus into the list of available servers.
  4. Unimplemented: The user is presented with a list of available servers (preferably with some stats about the server load) and chooses the preferred server. One server can be automatically recommended. (This is a variation of the first option, above.)
    • Status info may include: "Down", "Idle", "Busy", "Swapped"
    • The chooser should auto-refresh periodically.
  5. We will modify ltsp-update-sshkeys to make configuration of additional servers easy, it will check if /etc/ltsp/extraservers exists, if so it will connect to the listed servers, retrieve the keys and append them to the ssh_known_hosts file in the chroot.

Because the existing code for querying servers is in Python and the next generation greeter is written in C it's impossible to the already written module directly. Also, there's plans for future non Gtk greater (Qt comes to mind). The solution for this is to use a IPC mechanism between ldm and the greeter where ldm can provide information about the servers to the greeter. The mechanism that comes to mind are POSIX message queues.


CategorySpec