Re: [PATCH v1 0/3] Optimize NFSD Send completion processing

[PATCH v1 0/3] Optimize NFSD Send completion processing · Chuck Lever <chuck.lever@oracle.com> · 2021-07-26
[PATCH v1 1/3] svcrdma: Fewer calls to wake_up() in Send completion handler · Chuck Lever <chuck.lever@oracle.com> · 2021-07-26
Re: [PATCH v1 1/3] svcrdma: Fewer calls to wake_up() in Send completion handler · Tom Talpey <tom@talpey.com> · 2021-07-26
Re: [PATCH v1 1/3] svcrdma: Fewer calls to wake_up() in Send completion handler · Chuck Lever III <chuck.lever@oracle.com> · 2021-07-26
Re: [PATCH v1 1/3] svcrdma: Fewer calls to wake_up() in Send completion handler · Tom Talpey <tom@talpey.com> · 2021-07-26
[PATCH v1 2/3] svcrdma: Relieve contention on sc_send_lock. · Chuck Lever <chuck.lever@oracle.com> · 2021-07-26
[PATCH v1 3/3] svcrdma: Convert rdma->sc_rw_ctxts to llist · Chuck Lever <chuck.lever@oracle.com> · 2021-07-26
Re: [PATCH v1 0/3] Optimize NFSD Send completion processing · Tom Talpey <tom@talpey.com> · 2021-07-26
Re: [PATCH v1 0/3] Optimize NFSD Send completion processing · Chuck Lever III <chuck.lever@oracle.com> · 2021-07-26

From: Tom Talpey <tom@talpey.com>
Date: 2021-07-26 16:58:08
Also in: linux-nfs

On 7/26/2021 10:46 AM, Chuck Lever wrote:

The following series improves the efficiency of NFSD's Send
completion processing by removing costly operations from the svcrdma
Send completion handlers. Each of these patches reduces the CPU
utilized per RPC by Send completion by an average of 2-3%.

Nice gain. Are the improvements additive, i.e. 5-10% CPU reduction
for all three together?

Tom

`h`	back out one level
`j`	next message in thread
`k`	previous message in thread
`l`	drill in
`Esc`	close help / fold thread tree
`?`	toggle this help