On 07/01/2010 11:22 PM, Charlie Brady wrote: >> "Filtered packets are dropped by the hardware when they don't match the >> L2 perfect match filters, mcast hash filters and broadcast filter. >> These filters are programmed based on the NIC's MAC address, multicast >> list from the stack and broadcast is always enabled." >> >> Under normal operation I believe the counter will go up... > > What would cause it to go up in normal operation? I think it's going to depend on your switch, I have a p-t-p connection that shows zero, but one to a switch showing 20K, so I'd assume it's periodically going into flood mode when systems go up/down, etc. >> Are you seeing any particular type of packets being dropped? For example, >> can you send/receive both IPv4 and IPv6 "pings" on that NIC? > > I don't know what is being dropped. I do know that cluster heartbeat > traffic between the two nodes sometimes stops, leading to cluster failover > and fencing. I don't know what is causing the traffic stalls, but NIC > driver issues is high on the suspicion list. Platform is CentOS 5, not > fully updates - kernel is 2.6.18-128.1.6.el5. There have been a number of updates to the driver since then... -Brian -- To unsubscribe from this list: send the line "unsubscribe linux-net" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
