vsphere-esxi-vcenter-server-55-storage-guide

vSphere StorageWhen writing data to storage, multiple systems or virtual machines might attempt to fill their links. AsDropped Packets shows, when this happens, the switch between the systems and the storage system has todrop data. This happens because, while it has a single connection to the storage device, it has more traffic tosend to the storage system than a single link can carry. In this case, the switch drops network packetsbecause the amount of data it can transmit is limited by the speed of the link between it and the storagesystem.Figure 14‐2. Dropped Packets1 Gbit1 Gbit1 Gbitdropped packetsRecovering from dropped network packets results in large performance degradation. In addition to timespent determining that data was dropped, the retransmission uses network bandwidth that could otherwisebe used for current transactions.iSCSI traffic is carried on the network by the Transmission Control Protocol (TCP). TCP is a reliabletransmission protocol that ensures that dropped packets are retried and eventually reach their destination.TCP is designed to recover from dropped packets and retransmits them quickly and seamlessly. However,when the switch discards packets with any regularity, network throughput suffers significantly. Thenetwork becomes congested with requests to resend data and with the resent packets, and less data isactually transferred than in a network without congestion.Most Ethernet switches can buffer, or store, data and give every device attempting to send data an equalchance to get to the destination. This ability to buffer some transmissions, combined with many systemslimiting the number of outstanding commands, allows small bursts from several systems to be sent to astorage system in turn.If the transactions are large and multiple servers are trying to send data through a single switch port, aswitch's ability to buffer one request while another is transmitted can be exceeded. In this case, the switchdrops the data it cannot send, and the storage system must request retransmission of the dropped packet.For example, if an Ethernet switch can buffer 32KB on an input port, but the server connected to it thinks itcan send 256KB to the storage device, some of the data is dropped.Most managed switches provide information on dropped packets, similar to the following:*: interface is upIHQ: pkts in input hold queueOHQ: pkts in output hold queueRXBS: rx rate (bits/sec)TXBS: tx rate (bits/sec)TRTL: throttle countIQD: pkts dropped from input queueOQD: pkts dropped from output queueRXPS: rx rate (pkts/sec)TXPS: tx rate (pkts/sec)Table 14‐1. Sample Switch InformationInterface IHQ IQD OHQ OQD RXBS RXPS TXBS TXPS TRTL*GigabitEthernet0/13 9922 0 0 47630300062273 47784000063677 0In this example from a Cisco switch, the bandwidth used is 476303000 bits/second, which is less than half ofwire speed. In spite of this, the port is buffering incoming packets and has dropped quite a few packets. Thefinal line of this interface summary indicates that this port has already dropped almost 10,000 inboundpackets in the IQD column.118 VMware, Inc.