Searched hist:256218 (Results 1 - 5 of 5) sorted by relevance

/freebsd-10.1-release/sys/net/
H A Dif_lagg.cdiff 256218 Wed Oct 09 17:15:58 MDT 2013 glebius There are some high performance NICs that count statistics in hardware,
and there are ifnets, that do that via counter(9). Provide a flag that
would skip cache line trashing '+=' operation in ether_input().

Sponsored by: Netflix
Sponsored by: Nginx, Inc.
Reviewed by: melifaro, adrian
Approved by: re (marius)
H A Dif.hdiff 256218 Wed Oct 09 17:15:58 MDT 2013 glebius There are some high performance NICs that count statistics in hardware,
and there are ifnets, that do that via counter(9). Provide a flag that
would skip cache line trashing '+=' operation in ether_input().

Sponsored by: Netflix
Sponsored by: Nginx, Inc.
Reviewed by: melifaro, adrian
Approved by: re (marius)
H A Dif_ethersubr.cdiff 256218 Wed Oct 09 17:15:58 MDT 2013 glebius There are some high performance NICs that count statistics in hardware,
and there are ifnets, that do that via counter(9). Provide a flag that
would skip cache line trashing '+=' operation in ether_input().

Sponsored by: Netflix
Sponsored by: Nginx, Inc.
Reviewed by: melifaro, adrian
Approved by: re (marius)
/freebsd-10.1-release/sys/dev/cxgbe/
H A Dt4_main.cdiff 256218 Wed Oct 09 17:15:58 MDT 2013 glebius There are some high performance NICs that count statistics in hardware,
and there are ifnets, that do that via counter(9). Provide a flag that
would skip cache line trashing '+=' operation in ether_input().

Sponsored by: Netflix
Sponsored by: Nginx, Inc.
Reviewed by: melifaro, adrian
Approved by: re (marius)
/freebsd-10.1-release/sys/dev/ixgbe/
H A Dixgbe.cdiff 256218 Wed Oct 09 17:15:58 MDT 2013 glebius There are some high performance NICs that count statistics in hardware,
and there are ifnets, that do that via counter(9). Provide a flag that
would skip cache line trashing '+=' operation in ether_input().

Sponsored by: Netflix
Sponsored by: Nginx, Inc.
Reviewed by: melifaro, adrian
Approved by: re (marius)

Completed in 381 milliseconds