[PATCH 0/2] SUNRPC consumer for the bulk page allocator
flat view
STALE2046d
From: Chuck Lever <hidden>
Date: 2021-03-23 15:11:01
Also in:
linux-mm, linux-nfs, lkml
Subsystem:
kernel nfsd, sunrpc, and lockd servers, networking [general], nfs, sunrpc, and lockd clients, the rest · Maintainers:
Chuck Lever, Jeff Layton, "David S. Miller", Eric Dumazet, Jakub Kicinski, Paolo Abeni, Trond Myklebust, Anna Schumaker, Linus Torvalds
This patch set and the measurements below are based on yesterday's
bulk allocator series:
git://git.kernel.org/pub/scm/linux/kernel/git/mel/linux.git mm-bulk-rebase-v5r9
The patches change SUNRPC to invoke the array-based bulk allocator
instead of alloc_page().
The micro-benchmark results are promising. I ran a mixture of 256KB
reads and writes over NFSv3. The server's kernel is built with KASAN
enabled, so the comparison is exaggerated but I believe it is still
valid.
I instrumented svc_recv() to measure the latency of each call to
svc_alloc_arg() and report it via a trace point. The following
results are averages across the trace events.
Single page: 25.007 us per call over 532,571 calls
Bulk list: 6.258 us per call over 517,034 calls
Bulk array: 4.590 us per call over 517,442 calls
For SUNRPC, the simplicity and better performance of the array-based
API makes it superior to the list-based API.
---
Chuck Lever (2):
SUNRPC: Set rq_page_end differently
SUNRPC: Refresh rq_pages using a bulk page allocator
net/sunrpc/svc_xprt.c | 33 +++++++++++++++++----------------
1 file changed, 17 insertions(+), 16 deletions(-)
--
Chuck Lever