DPDK patches and discussions
 help / color / mirror / Atom feed
From: bugzilla@dpdk.org
To: dev@dpdk.org
Subject: [Bug 1227] KNI : memory-leaks, each time kni_rx_burst it is allocates new mbufs even if no needs.
Date: Tue, 09 May 2023 14:24:26 +0000	[thread overview]
Message-ID: <bug-1227-3@http.bugs.dpdk.org/> (raw)

[-- Attachment #1: Type: text/plain, Size: 2040 bytes --]

https://bugs.dpdk.org/show_bug.cgi?id=1227

            Bug ID: 1227
           Summary: KNI : memory-leaks, each time kni_rx_burst it is
                    allocates new mbufs even if no needs.
           Product: DPDK
           Version: 22.11
          Hardware: All
                OS: All
            Status: UNCONFIRMED
          Severity: normal
          Priority: Normal
         Component: ethdev
          Assignee: dev@dpdk.org
          Reporter: yasinncaner@gmail.com
  Target Milestone: ---

Created attachment 251
  --> https://bugs.dpdk.org/attachment.cgi?id=251&action=edit
flow_kni_rx_burst

Hello

I tried to explain memory-leak via graph 

https://pastebin.ubuntu.com/p/s4h5psqtgZ/


scenario : 

1. kni_alloc allocates 32 units (kni->alloc_q) then completes initialization
2. rte_kni_rx_burst receive 1 packet from kernel. 1 of 31 units is filled by
message, 31 units is empty but it is allocated in kni->alloc_q.
3. rte_kni_rx_burst then allocates another 32 units i dont know why but there
is a comment like this."If buffers removed, allocate mbufs and then put them
into alloc_q" ( How to tests buffers are removed or not? there is not any query
in code)
4. 1 message mbuf is transmited via rte_eth_tx_burst . 
5. 1 message mbuf never back to freed and back to original memory pool. 31+32
units memory act like in use but they are not. never back to original memory
pool
6. this cycle goes on to 2 .

? Why there is newer allocation in rte_kni_rx_burst i dont know.
? I tried to free 1 packet via rte_pktmbuf_free but sometimes corrupt to pool
like below. sometimes 1 packet/unit back to original memory pool
[UseCount_mpool:65][avail_mpool:10334]
[UseCount_mpool:4294967135][avail_mpool:10560]
? In my view, after transmiting message to mbufs should be in to kni->free_q.
? in my view, there is missing query in func kni_allocate_mbufs to test alloc_q
is empty or not.
Best regards.

-- 
You are receiving this mail because:
You are the assignee for the bug.

[-- Attachment #2: Type: text/html, Size: 4135 bytes --]

             reply	other threads:[~2023-05-09 14:24 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-05-09 14:24 bugzilla [this message]
2023-05-25  7:16 ` bugzilla

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=bug-1227-3@http.bugs.dpdk.org/ \
    --to=bugzilla@dpdk.org \
    --cc=dev@dpdk.org \
    /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).