diff options
| author | Kai Shen <KaiShen@linux.alibaba.com> | 2023-03-17 03:21:32 +0000 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2023-03-17 08:59:01 +0000 |
| commit | 79a22238b4f22c45cadd3b4040d644f4de320d1b (patch) | |
| tree | d2615b104eee4ca8404dfb4afd1eb488f64a0f81 /net/smc/smc_core.h | |
| parent | d27d367d3b7861d9d6c852450d935507ba4044ee (diff) | |
| download | linux-79a22238b4f22c45cadd3b4040d644f4de320d1b.tar.gz linux-79a22238b4f22c45cadd3b4040d644f4de320d1b.tar.bz2 linux-79a22238b4f22c45cadd3b4040d644f4de320d1b.zip | |
net/smc: Use percpu ref for wr tx reference
The refcount wr_tx_refcnt may cause cache thrashing problems among
cores and we can use percpu ref to mitigate this issue here. We
gain some performance improvement with percpu ref here on our
customized smc-r verion. Applying cache alignment may also mitigate
this problem but it seem more reasonable to use percpu ref here.
We can also replace wr_reg_refcnt with one percpu reference like
wr_tx_refcnt.
redis-benchmark on smc-r with atomic wr_tx_refcnt:
SET: 525707.06 requests per second, p50=0.087 msec
GET: 554877.38 requests per second, p50=0.087 msec
redis-benchmark on the percpu_ref version:
SET: 540482.06 requests per second, p50=0.087 msec
GET: 570711.12 requests per second, p50=0.079 msec
Cases are like "redis-benchmark -h x.x.x.x -q -t set,get -P 1 -n
5000000 -c 50 -d 10 --threads 4".
Signed-off-by: Kai Shen <KaiShen@linux.alibaba.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/smc/smc_core.h')
| -rw-r--r-- | net/smc/smc_core.h | 10 |
1 files changed, 8 insertions, 2 deletions
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 08b457c2d294..1645fba0d2d3 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -106,7 +106,10 @@ struct smc_link { unsigned long *wr_tx_mask; /* bit mask of used indexes */ u32 wr_tx_cnt; /* number of WR send buffers */ wait_queue_head_t wr_tx_wait; /* wait for free WR send buf */ - atomic_t wr_tx_refcnt; /* tx refs to link */ + struct { + struct percpu_ref wr_tx_refs; + } ____cacheline_aligned_in_smp; + struct completion tx_ref_comp; struct smc_wr_buf *wr_rx_bufs; /* WR recv payload buffers */ struct ib_recv_wr *wr_rx_ibs; /* WR recv meta data */ @@ -122,7 +125,10 @@ struct smc_link { struct ib_reg_wr wr_reg; /* WR register memory region */ wait_queue_head_t wr_reg_wait; /* wait for wr_reg result */ - atomic_t wr_reg_refcnt; /* reg refs to link */ + struct { + struct percpu_ref wr_reg_refs; + } ____cacheline_aligned_in_smp; + struct completion reg_ref_comp; enum smc_wr_reg_state wr_reg_state; /* state of wr_reg request */ u8 gid[SMC_GID_SIZE];/* gid matching used vlan id*/ |