linux-toradex.git/net/rds/ib_rdma.c, branch v4.4.86

RDS: IB: split mr pool to improve 8K messages performance

2015-10-05T18:19:02+00:00

8K message sizes are pretty important usecase for RDS current
workloads so we make provison to have 8K mrs available from the pool.
Based on number of SG's in the RDS message, we pick a pool to use.

Also to make sure that we don't under utlise mrs when say 8k messages
are dominating which could lead to 8k pull being exhausted, we fall-back
to 1m pool till 8k pool recovers for use.

This helps to at least push ~55 kB/s bidirectional data which
is a nice improvement.

Signed-off-by: Santosh Shilimkar 
Signed-off-by: Santosh Shilimkar

RDS: IB: mark rds_ib_fmr_wq static

2015-10-05T18:19:02+00:00

Fix below warning by marking rds_ib_fmr_wq static

net/rds/ib_rdma.c:87:25: warning: symbol 'rds_ib_fmr_wq' was not declared. Should it be static?

Signed-off-by: Santosh Shilimkar 
Signed-off-by: Santosh Shilimkar

RDS: IB: use already available pool handle from ibmr

2015-10-05T18:19:02+00:00

rds_ib_mr already keeps the pool handle which it associates
with. Lets use that instead of round about way of fetching
it from rds_ib_device.

No functional change.

Signed-off-by: Santosh Shilimkar 
Signed-off-by: Santosh Shilimkar

RDS: IB: fix the rds_ib_fmr_wq kick call

2015-10-05T18:19:01+00:00

RDS IB mr pool has its own workqueue 'rds_ib_fmr_wq', so we need
to use queue_delayed_work() to kick the work. This was hurting
the performance since pool maintenance was less often triggered
from other path.

Signed-off-by: Santosh Shilimkar 
Signed-off-by: Santosh Shilimkar

RDS: use kfree_rcu in rds_ib_remove_ipaddr

2015-09-30T16:43:24+00:00

synchronize_rcu() slowing down un-necessarily the socket shutdown
path. It is used just kfree() the ip addresses in rds_ib_remove_ipaddr()
which is perfect usecase for kfree_rcu();

So lets use that to gain some speedup.

Signed-off-by: Santosh Shilimkar 
Signed-off-by: Santosh Shilimkar

RDS: remove superfluous from rds_ib_alloc_fmr()

2015-08-25T23:28:11+00:00

Memory allocated for 'ibmr' uses kzalloc_node() which already
initialises the memory to zero. There is no need to do
memset() 0 on that memory.

Signed-off-by: Santosh Shilimkar 
Signed-off-by: Santosh Shilimkar 
Signed-off-by: David S. Miller

RDS: flush the FMR pool less often

2015-08-25T23:28:11+00:00

FMR flush is an expensive and time consuming operation. Reduce the
frequency of FMR pool flush by 50% so that more FMR work gets accumulated
for more efficient flushing.

Signed-off-by: Santosh Shilimkar 
Signed-off-by: Santosh Shilimkar 
Signed-off-by: David S. Miller

RDS: push FMR pool flush work to its own worker

2015-08-25T23:28:11+00:00

RDS FMR flush operation and also it races with connect/reconect
which happes a lot with RDS. FMR flush being on common rds_wq aggrevates
the problem. Lets push RDS FMR pool flush work to its own worker.

Signed-off-by: Santosh Shilimkar 
Signed-off-by: Santosh Shilimkar 
Signed-off-by: David S. Miller

RDS: fix fmr pool dirty_count

2015-08-25T23:28:11+00:00

In rds_ib_flush_mr_pool(), dirty_count accounts the clean ones
which is wrong. This can lead to a negative dirty count value.

Lets fix it.

Signed-off-by: Wengang Wang 
Signed-off-by: Santosh Shilimkar 
Signed-off-by: Santosh Shilimkar 
Signed-off-by: David S. Miller

RDS: Fix assertion level from fatal to warning

2015-08-25T20:35:31+00:00

Fix the asserion level since its not fatal and can be hit
in normal execution paths. There is no need to take the
system down.

We keep the WARN_ON() to detect the condition if we get
here with bad pages.

Reviewed-by: Ajaykumar Hotchandani 
Signed-off-by: Santosh Shilimkar 
Signed-off-by: Santosh Shilimkar 
Signed-off-by: David S. Miller