From: "Chuck Lever" <cel@kernel.org>
To: NeilBrown <neil@brown.name>
Cc: "Jeff Layton" <jlayton@kernel.org>,
"Olga Kornievskaia" <okorniev@redhat.com>,
"Dai Ngo" <Dai.Ngo@oracle.com>, "Tom Talpey" <tom@talpey.com>,
"Rick Macklem" <rmacklem@uoguelph.ca>,
linux-nfs@vger.kernel.org
Subject: Re: [PATCH v5 11/11] NFSD: Remove DRC checksum and payload_misses stat
Date: Sat, 19 Sep 2026 12:11:11 -0400 [thread overview]
Message-ID: <85a7313b-6c69-41bd-9a12-18ab4fec4b5b@app.fastmail.com> (raw)
In-Reply-To: <178977475436.207413.9806283444174908649@noble.neil.brown.name>
On Fri, Sep 18, 2026, at 7:39 PM, NeilBrown wrote:
> If we get a request on a particular transport and it is a good match
> for a request that we recently replied to on the same transport, then
> the chance of it being a timed-out retransmit is 100%. A client that
> re-uses xids that quickly is buggy, isn't it?
> So if nfsd_cacherep_acked() then I think we can ignore the request.
> In fact if the "found" reply was sent on the same xprt that we received
> a new request on, I think we can ignore the new request even if the
> reply hasn't been acked yet.
Just to be clear, by "ignore" do you mean "drop the request" or "reply
with the cached reply" ?
> Everything else in the series is good and I really appreciate how
> thoroughly you have explained the logic in a lot of places.
Thanks, your comments have made this a much better implementation.
--
Chuck Lever (Come to NFS bake-a-thon! https://nfsv4bat.org)
next prev parent reply other threads:[~2026-09-19 16:11 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-09-18 17:21 [PATCH v5 00/11] Improve the scalability of NFSD's classic DRC Chuck Lever
2026-09-18 17:21 ` [PATCH v5 01/11] NFSD: Remove hard cap on duplicate reply cache size Chuck Lever
2026-09-18 23:00 ` NeilBrown
2026-09-20 17:47 ` Chuck Lever
2026-09-20 22:10 ` NeilBrown
2026-09-18 17:21 ` [PATCH v5 02/11] SUNRPC: Assign a unique identifier to each svc_xprt Chuck Lever
2026-09-18 17:21 ` [PATCH v5 03/11] NFSD: Track transport in DRC entries Chuck Lever
2026-09-18 17:21 ` [PATCH v5 04/11] NFSD: Prepare bucket pruning for additional eviction reasons Chuck Lever
2026-09-18 17:21 ` [PATCH v5 05/11] NFSD: Add tracepoints for DRC entry eviction Chuck Lever
2026-09-18 17:21 ` [PATCH v5 06/11] NFSD: Record DRC population in lookup tracepoints Chuck Lever
2026-09-18 17:21 ` [PATCH v5 07/11] SUNRPC: Publish reply positions for upper-layer consumers Chuck Lever
2026-09-18 17:21 ` [PATCH v5 08/11] SUNRPC: Publish TCP reply positions Chuck Lever
2026-09-18 17:21 ` [PATCH v5 09/11] svcrdma: Publish RDMA " Chuck Lever
2026-09-18 17:21 ` [PATCH v5 10/11] NFSD: Evict acknowledged DRC entries Chuck Lever
2026-09-18 17:21 ` [PATCH v5 11/11] NFSD: Remove DRC checksum and payload_misses stat Chuck Lever
2026-09-18 23:39 ` NeilBrown
2026-09-19 16:11 ` Chuck Lever [this message]
2026-09-20 10:37 ` NeilBrown
2026-09-20 17:49 ` Chuck Lever
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=85a7313b-6c69-41bd-9a12-18ab4fec4b5b@app.fastmail.com \
--to=cel@kernel.org \
--cc=Dai.Ngo@oracle.com \
--cc=jlayton@kernel.org \
--cc=linux-nfs@vger.kernel.org \
--cc=neil@brown.name \
--cc=okorniev@redhat.com \
--cc=rmacklem@uoguelph.ca \
--cc=tom@talpey.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.