Udp.parsePacket() is slow

[rnamdos]

How fast can I expect Udp.parsePacket() to be? In this example code, I am parsing UDP packets and toggling a GPIO pin to see how fast the code runs IRL. The parsing takes 330nS. I expected (based on the clock speeds and the 100MBps interface) the speeds to be orders of magnitude higher... 330ns is around 550 clock cycles. I just want to know if there is something I can do to improve this or that the library is focused on compatibility, not performance. Thanks!

#include <NativeEthernet.h>

byte mac[] = {0xDE, 0xAD, 0xBE, 0xEF, 0xFE, 0xED};
IPAddress ip(192, 168, 1, 177);
unsigned int localPort = 6454;      // local port to listen on

// buffers for receiving and sending data
#define UDP_TX_PACKET_MAX_SIZE 1480
unsigned char packetBuffer[UDP_TX_PACKET_MAX_SIZE];  // buffer to hold incoming packet,
char ReplyBuffer[] = "acknowledged";        // a string to send back

// An EthernetUDP instance to let us send and receive packets over UDP
EthernetUDP Udp;

const int PIN_0 = 38;
int packetSize = 0;

void setup() {
//  noInterrupts();
  teensyMAC(mac);
  pinMode(PIN_0, OUTPUT);
  Ethernet.begin(mac, ip);
  Udp.begin(localPort);
}

void loop() {

  while (1) {
    digitalToggleFast(PIN_0);
    //delayNanoseconds(1);

    packetSize = Udp.parsePacket();
    if (packetSize) {
      Udp.read(packetBuffer, UDP_TX_PACKET_MAX_SIZE);
    }
  }
}

/*********************** teensyMAC *********************/
void teensyMAC(uint8_t *mac)
{
  for (uint8_t by = 0; by < 2; by++) mac[by] = (HW_OCOTP_MAC1 >> ((1 - by) * 8)) & 0xFF;
  for (uint8_t by = 0; by < 4; by++) mac[by + 2] = (HW_OCOTP_MAC0 >> ((3 - by) * 8)) & 0xFF;
}

[rnamdos]

I forgot to add that commenting out the lines:

    if (packetSize) {
      Udp.read(packetBuffer, UDP_TX_PACKET_MAX_SIZE);
    }

doesn't affect the results... parsing is the bottleneck