From: Akhil Goyal <gakhil@marvell.com>
To: <dev@dpdk.org>
Cc: <suanmingm@nvidia.com>, <anoobj@marvell.com>, <kai.ji@intel.com>,
<hemant.agrawal@nxp.com>, <brian.dooley@intel.com>,
Akhil Goyal <gakhil@marvell.com>
Subject: [PATCH] doc: add limitation in using segment-sz in crypto-perf
Date: Fri, 16 May 2025 17:40:43 +0530 [thread overview]
Message-ID: <20250516121043.145572-1-gakhil@marvell.com> (raw)
When segment-sz is given as parameter,
use buffer-sz in descending order.
The reason is, same scatter gather buffer list is being used
for all packet sizes which is initialized once in the beginning.
Now if a small packet case is run first,
mbuf SG list will be trimmed to a smaller number of SG and
rest of the SGs are lost resulting in segfault.
Buffers cannot be re-initialized as that will come in datapath and
will be costly.
So to workaround this, if segment-sz is passed as argument,
use values in buffer-sz in descending order.
Signed-off-by: Akhil Goyal <gakhil@marvell.com>
---
doc/guides/tools/cryptoperf.rst | 1 +
1 file changed, 1 insertion(+)
diff --git a/doc/guides/tools/cryptoperf.rst b/doc/guides/tools/cryptoperf.rst
index e53e2d0ebf..a3d35f6a50 100644
--- a/doc/guides/tools/cryptoperf.rst
+++ b/doc/guides/tools/cryptoperf.rst
@@ -139,6 +139,7 @@ The following are the application command-line options:
* ``--segment-sz <n>``
Set the size of the segment to use, for Scatter Gather List testing.
+ Use list of values in buffer-sz in descending order if segment-sz is used.
By default, it is set to the size of the maximum buffer size, including the digest size,
so a single segment is created.
--
2.25.1
next reply other threads:[~2025-05-16 12:10 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-05-16 12:10 Akhil Goyal [this message]
2025-05-16 14:41 ` Anoob Joseph
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=20250516121043.145572-1-gakhil@marvell.com \
--to=gakhil@marvell.com \
--cc=anoobj@marvell.com \
--cc=brian.dooley@intel.com \
--cc=dev@dpdk.org \
--cc=hemant.agrawal@nxp.com \
--cc=kai.ji@intel.com \
--cc=suanmingm@nvidia.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).