em performs worse than igb (latency wise) in 12?

Kris von Mach mach at swishmail.com
Fri Apr 5 19:12:27 UTC 2019


On 4/6/2019 2:56 AM, Pete French wrote:
> Something odd going on there there - I am using 12-STABLE and I have 
> igb just fine, and it attaches to the same hardware that 11 did:

It does work in 12, throughput is great, just that the latency is higher 
than 11.

igb0: flags=8843<UP,BROADCAST,RUNNING,SIMPLEX,MULTICAST> metric 0 mtu 1500
options=e527bb<RXCSUM,TXCSUM,VLAN_MTU,VLAN_HWTAGGING,JUMBO_MTU,VLAN_HWCSUM,TSO4,TSO6,LRO,WOL_MAGIC,VLAN_HWFILTER,VLAN_HWTSO,RXCSUM_IPV6,TXCSUM_IPV6>
         ether 38:ea:a7:8d:c1:6c
         inet 208.72.56.19 netmask 0xfffffc00 broadcast 208.72.59.255
         inet6 fe80::3aea:a7ff:fe8d:c16c%igb0 prefixlen 64 scopeid 0x1
         inet6 2602:ffb8::208:72:56:9 prefixlen 64
         media: Ethernet autoselect (1000baseT <full-duplex>)
         status: active
         nd6 options=21<PERFORMNUD,AUTO_LINKLOCAL>

> Do you have a custom kernel, and if so did you see this note in UPDATING?

Yes I do, but it includes all of GENERIC which includes em drivers, 
otherwise it wouldn't even work with the network card.

my custom kernel:

include GENERIC
ident   CUSTOM
makeoptions WITH_EXTRA_TCP_STACKS=1
options TCPHPTS
options SC_KERNEL_CONS_ATTR=(FG_GREEN|BG_BLACK)
options IPSTEALTH
options       AHC_REG_PRETTY_PRINT  # Print register bitfields in debug
options       AHD_REG_PRETTY_PRINT  # Print register bitfields in debug
device cryptodev
device aesni

I did try without RACK just in case that was the culprit.




More information about the freebsd-stable mailing list