qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Stefan Hajnoczi <stefanha@redhat.com>
To: qemu-devel@nongnu.org
Cc: Laurent Vivier <lvivier@redhat.com>,
	Peter Maydell <peter.maydell@linaro.org>,
	Thomas Huth <thuth@redhat.com>,
	qemu-block@nongnu.org, Oleksandr Natalenko <oleksandr@redhat.com>,
	Stefan Weil <sw@weilnetz.de>, Max Reitz <mreitz@redhat.com>,
	Alexander Bulekov <alxndr@bu.edu>, Bandan Das <bsd@redhat.com>,
	Stefan Hajnoczi <stefanha@redhat.com>,
	Paolo Bonzini <pbonzini@redhat.com>, Fam Zheng <fam@euphon.net>,
	Kevin Wolf <kwolf@redhat.com>
Subject: [PULL 8/8] aio-posix: disable fdmon-io_uring when GSource is used
Date: Tue, 19 May 2020 09:00:54 +0100	[thread overview]
Message-ID: <20200519080054.146495-9-stefanha@redhat.com> (raw)
In-Reply-To: <20200519080054.146495-1-stefanha@redhat.com>

The glib event loop does not call fdmon_io_uring_wait() so fd handlers
waiting to be submitted build up in the list. There is no benefit is
using io_uring when the glib GSource is being used, so disable it
instead of implementing a more complex fix.

This fixes a memory leak where AioHandlers would build up and increasing
amounts of CPU time were spent iterating them in aio_pending(). The
symptom is that guests become slow when QEMU is built with io_uring
support.

Buglink: https://bugs.launchpad.net/qemu/+bug/1877716
Fixes: 73fd282e7b6dd4e4ea1c3bbb3d302c8db51e4ccf ("aio-posix: add io_uring fd monitoring implementation")
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Tested-by: Oleksandr Natalenko <oleksandr@redhat.com>
Message-id: 20200511183630.279750-3-stefanha@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 include/block/aio.h |  3 +++
 util/aio-posix.c    | 12 ++++++++++++
 util/aio-win32.c    |  4 ++++
 util/async.c        |  1 +
 4 files changed, 20 insertions(+)

diff --git a/include/block/aio.h b/include/block/aio.h
index 62ed954344..b2f703fa3f 100644
--- a/include/block/aio.h
+++ b/include/block/aio.h
@@ -701,6 +701,9 @@ void aio_context_setup(AioContext *ctx);
  */
 void aio_context_destroy(AioContext *ctx);
 
+/* Used internally, do not call outside AioContext code */
+void aio_context_use_g_source(AioContext *ctx);
+
 /**
  * aio_context_set_poll_params:
  * @ctx: the aio context
diff --git a/util/aio-posix.c b/util/aio-posix.c
index 8af334ab19..1b2a3af65b 100644
--- a/util/aio-posix.c
+++ b/util/aio-posix.c
@@ -682,6 +682,18 @@ void aio_context_destroy(AioContext *ctx)
     aio_free_deleted_handlers(ctx);
 }
 
+void aio_context_use_g_source(AioContext *ctx)
+{
+    /*
+     * Disable io_uring when the glib main loop is used because it doesn't
+     * support mixed glib/aio_poll() usage. It relies on aio_poll() being
+     * called regularly so that changes to the monitored file descriptors are
+     * submitted, otherwise a list of pending fd handlers builds up.
+     */
+    fdmon_io_uring_destroy(ctx);
+    aio_free_deleted_handlers(ctx);
+}
+
 void aio_context_set_poll_params(AioContext *ctx, int64_t max_ns,
                                  int64_t grow, int64_t shrink, Error **errp)
 {
diff --git a/util/aio-win32.c b/util/aio-win32.c
index 729d533faf..953c56ab48 100644
--- a/util/aio-win32.c
+++ b/util/aio-win32.c
@@ -414,6 +414,10 @@ void aio_context_destroy(AioContext *ctx)
 {
 }
 
+void aio_context_use_g_source(AioContext *ctx)
+{
+}
+
 void aio_context_set_poll_params(AioContext *ctx, int64_t max_ns,
                                  int64_t grow, int64_t shrink, Error **errp)
 {
diff --git a/util/async.c b/util/async.c
index 3165a28f2f..1319eee3bc 100644
--- a/util/async.c
+++ b/util/async.c
@@ -362,6 +362,7 @@ static GSourceFuncs aio_source_funcs = {
 
 GSource *aio_get_g_source(AioContext *ctx)
 {
+    aio_context_use_g_source(ctx);
     g_source_ref(&ctx->source);
     return &ctx->source;
 }
-- 
2.25.3


  parent reply	other threads:[~2020-05-19  8:10 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-05-19  8:00 [PULL 0/8] Block patches Stefan Hajnoczi
2020-05-19  8:00 ` [PULL 1/8] tests/fuzz/Makefile: Do not link code using unavailable devices Stefan Hajnoczi
2020-05-19  8:00 ` [PULL 2/8] Makefile: List fuzz targets in 'make help' Stefan Hajnoczi
2020-05-19  8:00 ` [PULL 3/8] tests/fuzz: Add missing space in test description Stefan Hajnoczi
2020-05-19  8:00 ` [PULL 4/8] tests/fuzz: Remove unuseful/unused typedefs Stefan Hajnoczi
2020-05-19  8:00 ` [PULL 5/8] tests/fuzz: Extract pciconfig_fuzz_qos() method Stefan Hajnoczi
2020-05-19  8:00 ` [PULL 6/8] tests/fuzz: Extract ioport_fuzz_qtest() method Stefan Hajnoczi
2020-05-19  8:00 ` [PULL 7/8] aio-posix: don't duplicate fd handler deletion in fdmon_io_uring_destroy() Stefan Hajnoczi
2020-05-19  8:00 ` Stefan Hajnoczi [this message]
2020-05-19 15:15 ` [PULL 0/8] Block patches Peter Maydell

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=20200519080054.146495-9-stefanha@redhat.com \
    --to=stefanha@redhat.com \
    --cc=alxndr@bu.edu \
    --cc=bsd@redhat.com \
    --cc=fam@euphon.net \
    --cc=kwolf@redhat.com \
    --cc=lvivier@redhat.com \
    --cc=mreitz@redhat.com \
    --cc=oleksandr@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=peter.maydell@linaro.org \
    --cc=qemu-block@nongnu.org \
    --cc=qemu-devel@nongnu.org \
    --cc=sw@weilnetz.de \
    --cc=thuth@redhat.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).