The major performance advantage in using OPTCD=LMPEO to SEND large messages is the significant reduction in path length (the number of instructions executed) achieved when compared to the application program itself splitting a large message and issuing individual SENDs. This advantage should be weighed, however, against the possibility of less efficient use of application program storage by LMPEO.

Application program storage might be used less efficiently because SEND is not posted complete (indicating that the output area is now available) until the whole message has been handled by VTAM®. Pacing might delay the completion of the LMPEO SEND. With OPTCD=NLMPEO, the application program can reuse each SEND's output area as soon as that SEND completes. This assumes that the data is available elsewhere (for example, on a disk) if it must be present.

It is somewhat less efficient to use OPTCD=LMPEO instead of OPTCD=NLMPEO to SEND a message that does not require splitting (if the size of the message to be sent is less than or equal to the maximum RU size). The application program could pretest the size of a message to be sent to decide whether to use OPTCD=LMPEO.