| Previous | Table of Contents | Next |
by Steve Burnett
This chapter will first discuss some of the general issues of electronic mail and the Internet in general: concepts and definitions, the mail standards as defined in the RFCs (Requests for Comment) that sendmail and other applications have tried to address, and several of the protocols defined for use in electronic messaging. The chapter will then cover sendmail, the UNIX-based subsystem in widest use on the Internet.
This section presents a broad overview of electronic messaging. First will be a discussion of some of the general concepts of electronic mail, including two basic kinds of mail software, and where sendmail belongs in that division. The next part of this section will present the RFCs (Request for Comment), where the protocols used to communicate within and across networks are defined. The last part of this section explains some of the protocols used to define electronic messages.
One of the first widely used office mail systems was IBM’s PROFS. A mainframe-based system, PROFS had features similar to modern e-mail systems such as Microsoft Exchange and Lotus Notes. Such features included:
PROFS and other messaging systems of the time shared several similarities. Whether mainframe- or UNIX-based, they were text-based and were considered host-based centralized messaging systems. Because PROFS was scalable and adaptable, IBM only recently switched away from it for its enterprise mail use.
As personal computers grew in acceptance and became widely used throughout corporations, people started to take advantage of the shift in computing power from the mainframe to the desktop. An early application of personal computer networks was file sharing, which made use of a central file server and a shared universally accessible network drive. Shortly thereafter, messaging systems began to take advantage of the new power on users’ desktops. So host-based messaging shifted (in some cases) to LAN-based messaging.
cc:Mail is an example of LAN-based messaging, which is also called shared-file messaging. In the shared-file messaging model, the desktop client has all the power and all the control. A client sends messages to a mailbox on a server and polls the server to retrieve mail from its specified mailbox directory. The server is passive, only storing messages. It performs no processing or sorting and has no provisions for setting rules to control message flow. Shared-file messaging provided the following gains over host-based messaging:
However, shared-file messaging systems introduced new problems. Because each user needed full access to the file system, including other users’ mailboxes, security was an issue. Also, because each client had to poll a server to get new mail, network traffic increased. Network bandwidth is a bottleneck more often than server or client bandwidth are.
The client/server messaging system divided the tasks of message processing between the desktop workstations and the servers. Using a push model for messages, mail clients no longer clogged the network by constantly polling for new messages. Client/server messaging also improved on shared-file messaging by improving security so that users would have more difficulty reading others’ mail. The more intelligent server enabled the sorting and processing of messages to be performed before messages were transferred across the network to a client.
| Previous | Table of Contents | Next |