diff options
| author | Dust Li <dust.li@linux.alibaba.com> | 2022-03-01 17:44:02 +0800 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2022-03-01 14:25:12 +0000 |
| commit | 6b88af839d204c9283ae09357555e5c4f56c6da5 (patch) | |
| tree | 2da8de087c96a637611ed2b31add76f48dd03e89 /net/smc/smc.h | |
| parent | a505cce6f7cfaf2aa2385aab7286063c96444526 (diff) | |
net/smc: don't send in the BH context if sock_owned_by_user
Send data all the way down to the RDMA device is a time
consuming operation(get a new slot, maybe do RDMA Write
and send a CDC, etc). Moving those operations from BH
to user context is good for performance.
If the sock_lock is hold by user, we don't try to send
data out in the BH context, but just mark we should
send. Since the user will release the sock_lock soon, we
can do the sending there.
Add smc_release_cb() which will be called in release_sock()
and try send in the callback if needed.
This patch moves the sending part out from BH if sock lock
is hold by user. In my testing environment, this saves about
20% softirq in the qperf 4K tcp_bw test in the sender side
with no noticeable throughput drop.
Signed-off-by: Dust Li <dust.li@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/smc/smc.h')
| -rw-r--r-- | net/smc/smc.h | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/net/smc/smc.h b/net/smc/smc.h index e266b04b7585..ea0620529ebe 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -213,6 +213,10 @@ struct smc_connection { * data still pending */ char urg_rx_byte; /* urgent byte */ + bool tx_in_release_sock; + /* flush pending tx data in + * sock release_cb() + */ atomic_t bytes_to_rcv; /* arrived data, * not yet received */ |