DPDK patches and discussions
 help / color / mirror / Atom feed
From: Anatoly Burakov <anatoly.burakov@intel.com>
To: dev@dpdk.org
Cc: ray.kinsella@intel.com, kuralamudhan.ramakrishnan@intel.com,
	louise.m.daly@intel.com, bruce.richardson@intel.com,
	ferruh.yigit@intel.com, konstantin.ananyev@intel.com
Subject: [dpdk-dev] [RFC 04/10] fbarray: support no-shared-files mode
Date: Thu, 31 May 2018 15:32:27 +0100	[thread overview]
Message-ID: <86d28b46ba848dae038431f87ce637f24e32253a.1527776837.git.anatoly.burakov@intel.com> (raw)
In-Reply-To: <cover.1527776837.git.anatoly.burakov@intel.com>
In-Reply-To: <cover.1527776837.git.anatoly.burakov@intel.com>

When using --no-shared-files option, the expectation is that no
multiprocess will be supported as no shared files are created. However,
fbarray still creates some shared files that prevent multiple processes
with the same prefix from starting.

Fix this by avoiding creating shared files whenever noshconf option is
specified. Since virtual areas we get from eal_get_virtual_area() are
read-only, remap them as writable.

Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
---
 lib/librte_eal/common/eal_common_fbarray.c | 71 +++++++++++++---------
 1 file changed, 42 insertions(+), 29 deletions(-)

diff --git a/lib/librte_eal/common/eal_common_fbarray.c b/lib/librte_eal/common/eal_common_fbarray.c
index 019f84c18..69576c8a8 100644
--- a/lib/librte_eal/common/eal_common_fbarray.c
+++ b/lib/librte_eal/common/eal_common_fbarray.c
@@ -434,39 +434,52 @@ rte_fbarray_init(struct rte_fbarray *arr, const char *name, unsigned int len,
 	if (data == NULL)
 		goto fail;
 
-	eal_get_fbarray_path(path, sizeof(path), name);
+	if (internal_config.no_shared_files) {
+		/* remap virtual area as writable */
+		void *new_data = mmap(data, mmap_len, PROT_READ | PROT_WRITE,
+				MAP_FIXED | MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+		if (new_data == MAP_FAILED) {
+			RTE_LOG(DEBUG, EAL, "%s(): couldn't remap anonymous memory: %s\n",
+					__func__, strerror(errno));
+			goto fail;
+		}
+	} else {
+		eal_get_fbarray_path(path, sizeof(path), name);
 
-	/*
-	 * Each fbarray is unique to process namespace, i.e. the filename
-	 * depends on process prefix. Try to take out a lock and see if we
-	 * succeed. If we don't, someone else is using it already.
-	 */
-	fd = open(path, O_CREAT | O_RDWR, 0600);
-	if (fd < 0) {
-		RTE_LOG(DEBUG, EAL, "%s(): couldn't open %s: %s\n", __func__,
-				path, strerror(errno));
-		rte_errno = errno;
-		goto fail;
-	} else if (flock(fd, LOCK_EX | LOCK_NB)) {
-		RTE_LOG(DEBUG, EAL, "%s(): couldn't lock %s: %s\n", __func__,
-				path, strerror(errno));
-		rte_errno = EBUSY;
-		goto fail;
-	}
+		/*
+		 * Each fbarray is unique to process namespace, i.e. the
+		 * filename depends on process prefix. Try to take out a lock
+		 * and see if we succeed. If we don't, someone else is using it
+		 * already.
+		 */
+		fd = open(path, O_CREAT | O_RDWR, 0600);
+		if (fd < 0) {
+			RTE_LOG(DEBUG, EAL, "%s(): couldn't open %s: %s\n",
+					__func__, path, strerror(errno));
+			rte_errno = errno;
+			goto fail;
+		} else if (flock(fd, LOCK_EX | LOCK_NB)) {
+			RTE_LOG(DEBUG, EAL, "%s(): couldn't lock %s: %s\n",
+					__func__, path, strerror(errno));
+			rte_errno = EBUSY;
+			goto fail;
+		}
 
-	/* take out a non-exclusive lock, so that other processes could still
-	 * attach to it, but no other process could reinitialize it.
-	 */
-	if (flock(fd, LOCK_SH | LOCK_NB)) {
-		rte_errno = errno;
-		goto fail;
-	}
+		/* take out a non-exclusive lock, so that other processes could
+		 * still attach to it, but no other process could reinitialize
+		 * it.
+		 */
+		if (flock(fd, LOCK_SH | LOCK_NB)) {
+			rte_errno = errno;
+			goto fail;
+		}
 
-	if (resize_and_map(fd, data, mmap_len))
-		goto fail;
+		if (resize_and_map(fd, data, mmap_len))
+			goto fail;
 
-	/* we've mmap'ed the file, we can now close the fd */
-	close(fd);
+		/* we've mmap'ed the file, we can now close the fd */
+		close(fd);
+	}
 
 	/* initialize the data */
 	memset(data, 0, mmap_len);
-- 
2.17.0

  parent reply	other threads:[~2018-05-31 14:32 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-05-31 14:32 [dpdk-dev] [RFC 00/10] Support running DPDK without hugetlbfs mountpoint Anatoly Burakov
2018-05-31 14:32 ` [dpdk-dev] [RFC 01/10] eal: add --no-shared-files option Anatoly Burakov
2018-05-31 14:32 ` [dpdk-dev] [RFC 02/10] eal: make --no-shconf an alias for --no-shared-files Anatoly Burakov
2018-05-31 14:32 ` [dpdk-dev] [RFC 03/10] eal: make --huge-unlink " Anatoly Burakov
2018-05-31 14:32 ` Anatoly Burakov [this message]
2018-05-31 14:32 ` [dpdk-dev] [RFC 05/10] mem: add support for no-shared-files mode Anatoly Burakov
2018-05-31 14:32 ` [dpdk-dev] [RFC 06/10] ipc: " Anatoly Burakov
2018-05-31 14:32 ` [dpdk-dev] [RFC 07/10] eal: add support for no-shared-files for hugepage info Anatoly Burakov
2018-05-31 14:32 ` [dpdk-dev] [RFC 08/10] eal: add support for no-shared-files in hugepage data file Anatoly Burakov
2018-05-31 14:32 ` [dpdk-dev] [RFC 09/10] eal: do not create runtime dir in no-shared-files mode Anatoly Burakov
2018-05-31 14:32 ` [dpdk-dev] [RFC 10/10] mem: enable memfd-based hugepage allocation Anatoly Burakov

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=86d28b46ba848dae038431f87ce637f24e32253a.1527776837.git.anatoly.burakov@intel.com \
    --to=anatoly.burakov@intel.com \
    --cc=bruce.richardson@intel.com \
    --cc=dev@dpdk.org \
    --cc=ferruh.yigit@intel.com \
    --cc=konstantin.ananyev@intel.com \
    --cc=kuralamudhan.ramakrishnan@intel.com \
    --cc=louise.m.daly@intel.com \
    --cc=ray.kinsella@intel.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).