Probably it's a chipset specific issue. Just an FYI:
Fixed n b93: 6665738 e1000g issues with some Ethernet controllers 6713685 e1000g:one device id macro should be renamed Fixed in b94: 6335837 e1000g needs to support LSO 6637659 e1000g has problem on transmit hardware checksum support 6659628 Solaris xVM e1000g driver hangs when dom0_mem is not set in /boot/grub/menu.lst Fixed in b95: 6597545 e1000g ESB2 serdes device pciex8086,1098 hangs in network testing 6694279 e1000g driver: internal loopback mode support needed for nic ESB-2 (Intel? 82564EBt, Intel? 82563EB) 6698039 e1000g tx doesn't work on the specific chipset since snv_88 6721574 max number of segments in e1000g_tx_dma_attr need to be updated when LSO is supported Fixed in b98: 6634746 e1000g is missing lint target in Makefile 6705005 e1000g LINK/ACT LED behaviour is not consistent with the EEPROM default 6738552 e1000g rx_lock is not initialized and destroyed in the code Not sure if your problem is related to I/OAT. You may want to check this page: http://www.alekz.net/archives/123 -- This message posted from opensolaris.org
