Hi, I've RTFS and a previous posting of Alexey on the subject and just want some confirmation whether I've understood some details of mmapped packet sockets correctly. If I'm just interested in the first x bytes of each packet, i set the framesize big enough to receive tpacket_hdr, sll and x bytes and the kernel will truncate packets bigger than that and still put them in the ring. If, however, I want all bytes of all packets, I have to recvmsg those packets that won't fit into a ring slot (because framesize is not big enough) and this will be indicated via TP_STATUS_COPY. Correct? Also, what difference is there between mapping 4 blocks of 4K or one block of 16K in PACKET_RX_RING? Thanks, Udo. - : send the line "unsubscribe linux-net" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
