DPDK patches and discussions
 help / color / mirror / Atom feed
* [dpdk-dev] [PATCH] mem: close rtemap files
@ 2020-10-19 15:42 Stephen Hemminger
  2020-10-19 16:23 ` Stephen Hemminger
  0 siblings, 1 reply; 2+ messages in thread
From: Stephen Hemminger @ 2020-10-19 15:42 UTC (permalink / raw)
  To: dev; +Cc: Anatoly Burakov, Stephen Hemminger

The memory subsystem is leaving open a file descriptor for each
rtemap file. This can lead to hundreds of extra open file descriptors
which has negative side effects. For example, the application may go
over its maximum file descriptor limit, or the application may be using
limited API's like select that only allow 1024 file descriptors.

The EAL memory subsystem does not need to hold the file open.
Probably the original intention was to keep the file locked, but that is
not necessary. The Linux kernel keeps a reference count on the file,
and the mmap counts is a reference and therefore maintains the file
as locked.

The fix is one line just close the file after it is setup.

Fixes: 582bed1e1d1d ("mem: support mapping hugepages at runtime")
Cc: anatoly.burakov@intel.com
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
---
 lib/librte_eal/linux/eal_memalloc.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/lib/librte_eal/linux/eal_memalloc.c b/lib/librte_eal/linux/eal_memalloc.c
index 6dc1b2baecdc..99600adda568 100644
--- a/lib/librte_eal/linux/eal_memalloc.c
+++ b/lib/librte_eal/linux/eal_memalloc.c
@@ -651,6 +651,12 @@ alloc_seg(struct rte_memseg *ms, void *addr, int socket_id,
 				__func__);
 #endif
 
+	/*
+	 * reference count is held by mmap() now
+	 * don't need to hold file open to keep it locked
+	 */
+	close(fd);
+
 	ms->addr = addr;
 	ms->hugepage_sz = alloc_sz;
 	ms->len = alloc_sz;
-- 
2.27.0


^ permalink raw reply	[flat|nested] 2+ messages in thread

* Re: [dpdk-dev] [PATCH] mem: close rtemap files
  2020-10-19 15:42 [dpdk-dev] [PATCH] mem: close rtemap files Stephen Hemminger
@ 2020-10-19 16:23 ` Stephen Hemminger
  0 siblings, 0 replies; 2+ messages in thread
From: Stephen Hemminger @ 2020-10-19 16:23 UTC (permalink / raw)
  To: dev; +Cc: Anatoly Burakov

On Mon, 19 Oct 2020 08:42:35 -0700
Stephen Hemminger <stephen@networkplumber.org> wrote:

> The memory subsystem is leaving open a file descriptor for each
> rtemap file. This can lead to hundreds of extra open file descriptors
> which has negative side effects. For example, the application may go
> over its maximum file descriptor limit, or the application may be using
> limited API's like select that only allow 1024 file descriptors.
> 
> The EAL memory subsystem does not need to hold the file open.
> Probably the original intention was to keep the file locked, but that is
> not necessary. The Linux kernel keeps a reference count on the file,
> and the mmap counts is a reference and therefore maintains the file
> as locked.
> 
> The fix is one line just close the file after it is setup.
> 
> Fixes: 582bed1e1d1d ("mem: support mapping hugepages at runtime")
> Cc: anatoly.burakov@intel.com
> Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>

This is fixes the open files, but has issues on shutdown.
Will send new version later.

^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2020-10-19 16:23 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-10-19 15:42 [dpdk-dev] [PATCH] mem: close rtemap files Stephen Hemminger
2020-10-19 16:23 ` Stephen Hemminger

DPDK patches and discussions

This inbox may be cloned and mirrored by anyone:

	git clone --mirror https://inbox.dpdk.org/dev/0 dev/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 dev dev/ https://inbox.dpdk.org/dev \
		dev@dpdk.org
	public-inbox-index dev

Example config snippet for mirrors.
Newsgroup available over NNTP:
	nntp://inbox.dpdk.org/inbox.dpdk.dev


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git