diff options
| author | Eric Dumazet <edumazet@google.com> | 2018-11-27 14:42:03 -0800 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2018-11-30 13:26:54 -0800 |
| commit | 4f693b55c3d2d2239b8a0094b518a1e533cf75d5 (patch) | |
| tree | 3b70704dbf9f7cf27ec16d9321f7c1956b81c3a5 /include/uapi/linux/snmp.h | |
| parent | 85bdf7db5b53cdcc7a901db12bcb3d0063e3866d (diff) | |
| download | lwn-4f693b55c3d2d2239b8a0094b518a1e533cf75d5.tar.gz lwn-4f693b55c3d2d2239b8a0094b518a1e533cf75d5.zip | |
tcp: implement coalescing on backlog queue
In case GRO is not as efficient as it should be or disabled,
we might have a user thread trapped in __release_sock() while
softirq handler flood packets up to the point we have to drop.
This patch balances work done from user thread and softirq,
to give more chances to __release_sock() to complete its work
before new packets are added the the backlog.
This also helps if we receive many ACK packets, since GRO
does not aggregate them.
This patch brings ~60% throughput increase on a receiver
without GRO, but the spectacular gain is really on
1000x release_sock() latency reduction I have measured.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'include/uapi/linux/snmp.h')
| -rw-r--r-- | include/uapi/linux/snmp.h | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index f80135e5feaa..86dc24a96c90 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -243,6 +243,7 @@ enum LINUX_MIB_TCPREQQFULLDROP, /* TCPReqQFullDrop */ LINUX_MIB_TCPRETRANSFAIL, /* TCPRetransFail */ LINUX_MIB_TCPRCVCOALESCE, /* TCPRcvCoalesce */ + LINUX_MIB_TCPBACKLOGCOALESCE, /* TCPBacklogCoalesce */ LINUX_MIB_TCPOFOQUEUE, /* TCPOFOQueue */ LINUX_MIB_TCPOFODROP, /* TCPOFODrop */ LINUX_MIB_TCPOFOMERGE, /* TCPOFOMerge */ |