Hi all,
I’ve been investigating some packet loss within my network and have narrowed it down to our core switches. These are a mix of CRS317-1G-16S+ and CRS326-24S+2Q+. Minimal config with some vlan filtering. Aggregate traffic levels vary on the switches between 2-20Gbps, all switch ports/bridging is happening in hardware.
After discovering TX drops under /interface ethernet print stats-detail I cleared the counters. Within a few minutes this started happening again. (see below)
name="sfpp4-syd-core01-sfpp1" driver-rx-byte=652 084 driver-rx-packet=6 808 driver-tx-byte=315 366 driver-tx-packet=2 753 rx-bytes=1 522 720 877 350 rx-too-short=0 rx-too-long=0 rx-unicast=1 903 064 907
rx-broadcast=2 287 rx-pause=0 rx-multicast=1 999 rx-error-events=0 rx-fcs-error=0 rx-fragment=0 rx-overflow=0 rx-jabber=0 tx-bytes=1 527 398 925 188 tx-unicast=1 910 115 132 tx-broadcast=716 233
tx-pause=0 tx-multicast=524 978 tx-underrun=0 tx-collision=0 tx-late-collision=0 tx-drop=5 410 tx-rx-64=257 006 840 tx-rx-65-127=1 151 810 350 tx-rx-128-255=261 998 154 tx-rx-256-511=127 467 833
tx-rx-512-1023=141 965 713 tx-rx-1024-max=1 874 176 646 tx-queue0-packet=978 822 616 tx-queue1-packet=932 533 725 tx-queue2-packet=0 tx-queue3-packet=0 tx-queue4-packet=0 tx-queue5-packet=0
tx-queue6-packet=0 tx-queue7-packet=0
Any ideas on why this is happening? Additionally I am noticing only the first two TX queues are ever being used.
It’s happening across both DAC cables and 1/10Gb SFP’s which are a mix of Mikrotik and FS.com.