qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Fabiano Rosas <farosas@suse.de>
To: qemu-devel@nongnu.org
Cc: berrange@redhat.com, armbru@redhat.com,
	Peter Xu <peterx@redhat.com>, Claudio Fontana <cfontana@suse.de>
Subject: [PATCH v4 28/34] migration/multifd: Add direct-io support
Date: Tue, 20 Feb 2024 19:41:32 -0300	[thread overview]
Message-ID: <20240220224138.24759-29-farosas@suse.de> (raw)
In-Reply-To: <20240220224138.24759-1-farosas@suse.de>

Signed-off-by: Fabiano Rosas <farosas@suse.de>
---
 migration/file.c      | 18 +++++++++++++++++-
 migration/migration.c | 24 ++++++++++++++++++++++++
 migration/options.h   |  1 +
 util/osdep.c          |  9 +++++++++
 4 files changed, 51 insertions(+), 1 deletion(-)

diff --git a/migration/file.c b/migration/file.c
index 27ccfc6a1d..f1c7615fb6 100644
--- a/migration/file.c
+++ b/migration/file.c
@@ -57,10 +57,26 @@ int file_send_channel_destroy(QIOChannel *ioc)
 
 bool file_send_channel_create(gpointer opaque, Error **errp)
 {
-    QIOChannelFile *ioc;
+    QIOChannelFile *ioc = NULL;
     int flags = O_WRONLY;
     int fd = fd_args_get_fd();
 
+    if (migrate_direct_io()) {
+#ifdef O_DIRECT
+        /*
+         * Enable O_DIRECT for the secondary channels. These are used
+         * for sending ram pages and writes should be guaranteed to be
+         * aligned to at least page size.
+         */
+        flags |= O_DIRECT;
+#else
+        error_setg(errp, "System does not support O_DIRECT");
+        error_append_hint(errp,
+                          "Try disabling direct-io migration capability\n");
+        return false;
+#endif
+    }
+
     if (fd && fd != -1) {
         ioc = qio_channel_file_new_fd(fd);
     } else {
diff --git a/migration/migration.c b/migration/migration.c
index ce7e6f5065..ecc07c4847 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -153,6 +153,16 @@ static bool migration_needs_seekable_channel(void)
     return migrate_fixed_ram();
 }
 
+static bool migration_needs_multiple_fds(void)
+{
+    /*
+     * When doing direct-io, multifd requires two different,
+     * non-duplicated file descriptors so we can use one of them for
+     * unaligned IO.
+     */
+    return migrate_multifd() && migrate_direct_io();
+}
+
 static bool transport_supports_seeking(MigrationAddress *addr)
 {
     if (addr->transport == MIGRATION_ADDRESS_TYPE_FILE) {
@@ -171,6 +181,12 @@ static bool transport_supports_seeking(MigrationAddress *addr)
     return false;
 }
 
+static bool transport_supports_multiple_fds(MigrationAddress *addr)
+{
+    /* file: works because QEMU can open it multiple times */
+    return addr->transport == MIGRATION_ADDRESS_TYPE_FILE;
+}
+
 static bool
 migration_channels_and_transport_compatible(MigrationAddress *addr,
                                             Error **errp)
@@ -187,6 +203,14 @@ migration_channels_and_transport_compatible(MigrationAddress *addr,
         return false;
     }
 
+    if (migration_needs_multiple_fds() &&
+        !transport_supports_multiple_fds(addr)) {
+        error_setg(errp,
+                   "Migration with direct-io is incompatible with the fd: URI,"
+                   " use file: instead");
+        return false;
+    }
+
     return true;
 }
 
diff --git a/migration/options.h b/migration/options.h
index 8680a10b79..39cbc171f7 100644
--- a/migration/options.h
+++ b/migration/options.h
@@ -79,6 +79,7 @@ uint8_t migrate_cpu_throttle_increment(void);
 uint8_t migrate_cpu_throttle_initial(void);
 bool migrate_cpu_throttle_tailslow(void);
 int migrate_decompress_threads(void);
+bool migrate_direct_io(void);
 uint64_t migrate_downtime_limit(void);
 uint8_t migrate_max_cpu_throttle(void);
 uint64_t migrate_max_bandwidth(void);
diff --git a/util/osdep.c b/util/osdep.c
index e996c4744a..d0227a60ab 100644
--- a/util/osdep.c
+++ b/util/osdep.c
@@ -277,6 +277,15 @@ int qemu_lock_fd_test(int fd, int64_t start, int64_t len, bool exclusive)
 }
 #endif
 
+bool qemu_has_direct_io(void)
+{
+#ifdef O_DIRECT
+    return true;
+#else
+    return false;
+#endif
+}
+
 static int qemu_open_cloexec(const char *name, int flags, mode_t mode)
 {
     int ret;
-- 
2.35.3



  parent reply	other threads:[~2024-02-20 22:43 UTC|newest]

Thread overview: 79+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-02-20 22:41 [PATCH v4 00/34] migration: File based migration with multifd and fixed-ram Fabiano Rosas
2024-02-20 22:41 ` [PATCH v4 01/34] docs/devel/migration.rst: Document the file transport Fabiano Rosas
2024-02-23  3:01   ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 02/34] tests/qtest/migration: Rename fd_proto test Fabiano Rosas
2024-02-23  3:03   ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 03/34] tests/qtest/migration: Add a fd + file test Fabiano Rosas
2024-02-23  3:08   ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 04/34] migration/multifd: Remove p->quit from recv side Fabiano Rosas
2024-02-23  3:13   ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 05/34] migration/multifd: Release recv sem_sync earlier Fabiano Rosas
2024-02-23  3:16   ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 06/34] io: add and implement QIO_CHANNEL_FEATURE_SEEKABLE for channel file Fabiano Rosas
2024-02-20 22:41 ` [PATCH v4 07/34] io: Add generic pwritev/preadv interface Fabiano Rosas
2024-02-20 22:41 ` [PATCH v4 08/34] io: implement io_pwritev/preadv for QIOChannelFile Fabiano Rosas
2024-02-20 22:41 ` [PATCH v4 09/34] io: fsync before closing a file channel Fabiano Rosas
2024-02-20 22:41 ` [PATCH v4 10/34] migration/qemu-file: add utility methods for working with seekable channels Fabiano Rosas
2024-02-20 22:41 ` [PATCH v4 11/34] migration/ram: Introduce 'fixed-ram' migration capability Fabiano Rosas
2024-02-21  8:41   ` Markus Armbruster
2024-02-21 13:24     ` Fabiano Rosas
2024-02-21 13:50       ` Daniel P. Berrangé
2024-02-21 15:05         ` Fabiano Rosas
2024-02-26  3:07   ` Peter Xu
2024-02-26  3:22   ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 12/34] migration: Add fixed-ram URI compatibility check Fabiano Rosas
2024-02-26  3:11   ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 13/34] migration/ram: Add outgoing 'fixed-ram' migration Fabiano Rosas
2024-02-26  4:03   ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 14/34] migration/ram: Add incoming " Fabiano Rosas
2024-02-26  5:19   ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 15/34] tests/qtest/migration: Add tests for fixed-ram file-based migration Fabiano Rosas
2024-02-20 22:41 ` [PATCH v4 16/34] migration/multifd: Rename MultiFDSend|RecvParams::data to compress_data Fabiano Rosas
2024-02-20 22:41 ` [PATCH v4 17/34] migration/multifd: Decouple recv method from pages Fabiano Rosas
2024-02-20 22:41 ` [PATCH v4 18/34] migration/multifd: Allow multifd without packets Fabiano Rosas
2024-02-26  5:57   ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 19/34] migration/multifd: Allow receiving pages " Fabiano Rosas
2024-02-26  6:58   ` Peter Xu
2024-02-26 19:19     ` Fabiano Rosas
2024-02-26 20:54       ` Fabiano Rosas
2024-02-20 22:41 ` [PATCH v4 20/34] migration/multifd: Add outgoing QIOChannelFile support Fabiano Rosas
2024-02-26  7:10   ` Peter Xu
2024-02-26  7:21   ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 21/34] migration/multifd: Add incoming " Fabiano Rosas
2024-02-26  7:34   ` Peter Xu
2024-02-26  7:53     ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 22/34] migration/multifd: Prepare multifd sync for fixed-ram migration Fabiano Rosas
2024-02-26  7:47   ` Peter Xu
2024-02-26 22:52     ` Fabiano Rosas
2024-02-27  3:52       ` Peter Xu
2024-02-27 14:00         ` Fabiano Rosas
2024-02-27 23:46           ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 23/34] migration/multifd: Support outgoing fixed-ram stream format Fabiano Rosas
2024-02-26  8:08   ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 24/34] migration/multifd: Support incoming " Fabiano Rosas
2024-02-26  8:30   ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 25/34] migration/multifd: Add fixed-ram support to fd: URI Fabiano Rosas
2024-02-26  8:37   ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 26/34] tests/qtest/migration: Add a multifd + fixed-ram migration test Fabiano Rosas
2024-02-26  8:42   ` Peter Xu
2024-02-20 22:41 ` [PATCH v4 27/34] migration: Add direct-io parameter Fabiano Rosas
2024-02-21  9:17   ` Markus Armbruster
2024-02-26  8:50   ` Peter Xu
2024-02-26 13:28     ` Fabiano Rosas
2024-02-20 22:41 ` Fabiano Rosas [this message]
2024-02-20 22:41 ` [PATCH v4 29/34] tests/qtest/migration: Add tests for file migration with direct-io Fabiano Rosas
2024-02-20 22:41 ` [PATCH v4 30/34] monitor: Honor QMP request for fd removal immediately Fabiano Rosas
2024-02-21  9:20   ` Markus Armbruster
2024-02-20 22:41 ` [PATCH v4 31/34] monitor: Extract fdset fd flags comparison into a function Fabiano Rosas
2024-02-20 22:41 ` [PATCH v4 32/34] monitor: fdset: Match against O_DIRECT Fabiano Rosas
2024-02-21  9:27   ` Markus Armbruster
2024-02-21 13:37     ` Fabiano Rosas
2024-02-22  6:56       ` Markus Armbruster
2024-02-22 13:26         ` Fabiano Rosas
2024-02-22 14:44           ` Markus Armbruster
2024-02-20 22:41 ` [PATCH v4 33/34] migration: Add support for fdset with multifd + file Fabiano Rosas
2024-02-20 22:41 ` [PATCH v4 34/34] tests/qtest/migration: Add a test for fixed-ram with passing of fds Fabiano Rosas
2024-02-23  2:59 ` [PATCH v4 00/34] migration: File based migration with multifd and fixed-ram Peter Xu
2024-02-23 13:48   ` Claudio Fontana
2024-02-23 14:22   ` Fabiano Rosas
2024-02-26  6:15 ` Peter Xu

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=20240220224138.24759-29-farosas@suse.de \
    --to=farosas@suse.de \
    --cc=armbru@redhat.com \
    --cc=berrange@redhat.com \
    --cc=cfontana@suse.de \
    --cc=peterx@redhat.com \
    --cc=qemu-devel@nongnu.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).