We have a lot of WS-C2960S-48TD-L switches in our network. sw version 12.2(55)SE7
All switches are interconnected through the core-switch.
The number of total output drops is growing on one of the switches.
Every day, three times for 30 minutes, losses begin to grow (attach a graph)
On switches, gigabit copper ports, servers with ESXI VMWARE are connected to them.
On other switches, servers with ESXI VMWARE are also connected and there are no such problems.
Such errors appear even on those ports where there is almost no traffic. I think, This problem does not depend on the amount of traffic
Average switch load 40-50%
The command "SH INT SUM" also shows errors (OQD). At the same time, packets are not visible in the output queue, and increasing the output queue does not solve the problem. (I will attach the output of the command)
sh int summ
*: interface is up
IHQ: pkts in input hold queue IQD: pkts dropped from input queue
OHQ: pkts in output hold queue OQD: pkts dropped from output queue
RXBS: rx rate (bits/sec) RXPS: rx rate (pkts/sec)
TXBS: tx rate (bits/sec) TXPS: tx rate (pkts/sec)
TRTL: throttle count
Interface IHQ IQD OHQ OQD RXBS RXPS TXBS TXPS TRTL
-------------------------------------------------------------------------
Vlan1 0 0 0 0 0 0 0 0 0
* Vlan158 0 0 0 0 24000 40 2000 2 0
FastEthernet0 0 0 0 0 0 0 0 0 0
* GigabitEthernet1/0/1 0 0 0 0 0 0 14000 4 0
* GigabitEthernet1/0/2 0 0 0 2 2502000 236 275000 167 0
* GigabitEthernet1/0/3 0 0 0 121884 524000 36 15000 5 0
* GigabitEthernet1/0/4 0 0 0 8 1382000 101 0 0 0
* GigabitEthernet1/0/5 0 0 0 3444256 34000 23 90000 70 0
* GigabitEthernet1/0/6 0 0 0 3397 50000 24 100000 77 0
GigabitEthernet1/0/7 0 0 0 7613 0 0 0 0 0
GigabitEthernet1/0/8 0 0 0 136915963 0 0 0 0 0
* GigabitEthernet1/0/9 0 0 0 279072287 3365000 5457 951678000 78725 0
Interface IHQ IQD OHQ OQD RXBS RXPS TXBS TXPS TRTL
-------------------------------------------------------------------------
* GigabitEthernet1/0/10 0 0 0 102380897 0 0 932000 631 0
* GigabitEthernet1/0/11 0 0 0 107032615 32211000 7745 37460000 8310 0
* GigabitEthernet1/0/12 0 0 0 36858064 193000 32 2877000 816 0
* GigabitEthernet1/0/13 0 0 0 117757058 3342000 300 1182000 742 0
How ports are configured (example):
interface GigabitEthernet1/0/18
description **ESXI**
switchport mode trunk
switchport nonegotiate
load-interval 120
Output of the iperf3 command during these periods between two servers connected to the switch. Usually there are almost no losses
Maybe this problem is related to switch overload or switch settings?
