DPDK patches and discussions
 help / color / mirror / Atom feed
From: "Mohakud, Amiya Ranjan" <amohakud@rbbn.com>
To: dpdk-dev <dev@dpdk.org>
Cc: "Dey, Souvik" <sodey@rbbn.com>
Subject: [dpdk-dev] Hugepages_rsvd Increasing for DPDK ACL operations
Date: Tue, 19 Oct 2021 16:19:06 +0000	[thread overview]
Message-ID: <MW4PR03MB6602B2CDE45652914CE21270B9BD9@MW4PR03MB6602.namprd03.prod.outlook.com> (raw)

HI All,

I'm currently facing an issue with respect to huge pages memory vs ACL Trie operation.

Problem Statement:
I am doing some ACL TRIE build operations and I can see hugepages_rsvd count is increasing and they are not available for use. As a result, the real available/free huge pages reduces over time and at some point, the trie build fails due to insufficient huge pages.

For addition of just 30 ACL rules, 60 huge pages are going to reserved and 11 ( 136-125) huge pages are getting used up.

No Rules:
HugePages_Total:    1234
HugePages_Free:      136
HugePages_Rsvd:        0
HugePages_Surp:        0

with 30 acl rules:
HugePages_Total:    1234
HugePages_Free:      125
HugePages_Rsvd:       60


Could you please help us provide some more insights into it .

  *   Is this the expected behavior and if yes, what is the reason?
  *   Is there any optimization on this area?
  *   How can we know the worst case memory requirement for ACL Trie?


Thanks in advance.


Regards
Amiya

Notice: This e-mail together with any attachments may contain information of Ribbon Communications Inc. and its Affiliates that is confidential and/or proprietary for the sole use of the intended recipient. Any review, disclosure, reliance or distribution by others or forwarding without express permission is strictly prohibited. If you are not the intended recipient, please notify the sender immediately and then delete all copies, including any attachments.

                 reply	other threads:[~2021-10-19 16:19 UTC|newest]

Thread overview: [no followups] expand[flat|nested]  mbox.gz  Atom feed

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=MW4PR03MB6602B2CDE45652914CE21270B9BD9@MW4PR03MB6602.namprd03.prod.outlook.com \
    --to=amohakud@rbbn.com \
    --cc=dev@dpdk.org \
    --cc=sodey@rbbn.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).