qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Peter Xu <peterx@redhat.com>
To: qemu-devel@nongnu.org, Stefan Hajnoczi <stefanha@redhat.com>
Cc: peterx@redhat.com, Paolo Bonzini <pbonzini@redhat.com>,
	David Hildenbrand <david@redhat.com>,
	Daniil Tatianin <d-tatianin@yandex-team.ru>,
	Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Subject: [PULL 05/14] overcommit: introduce mem-lock=on-fault
Date: Tue, 11 Feb 2025 17:50:49 -0500	[thread overview]
Message-ID: <20250211225059.182533-6-peterx@redhat.com> (raw)
In-Reply-To: <20250211225059.182533-1-peterx@redhat.com>

From: Daniil Tatianin <d-tatianin@yandex-team.ru>

Locking the memory without MCL_ONFAULT instantly prefaults any mmaped
anonymous memory with a write-fault, which introduces a lot of extra
overhead in terms of memory usage when all you want to do is to prevent
kcompactd from migrating and compacting QEMU pages. Add an option to
only lock pages lazily as they're faulted by the process by using
MCL_ONFAULT if asked.

Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Daniil Tatianin <d-tatianin@yandex-team.ru>
Link: https://lore.kernel.org/r/20250123131944.391886-5-d-tatianin@yandex-team.ru
Signed-off-by: Peter Xu <peterx@redhat.com>
---
 include/system/system.h  |  2 ++
 migration/postcopy-ram.c |  2 +-
 system/globals.c         |  7 ++++++-
 system/vl.c              | 34 +++++++++++++++++++++++++++-------
 qemu-options.hx          | 14 +++++++++-----
 5 files changed, 45 insertions(+), 14 deletions(-)

diff --git a/include/system/system.h b/include/system/system.h
index dc7628357a..a7effe7dfd 100644
--- a/include/system/system.h
+++ b/include/system/system.h
@@ -50,9 +50,11 @@ extern QEMUClockType rtc_clock;
 typedef enum {
     MLOCK_OFF = 0,
     MLOCK_ON,
+    MLOCK_ON_FAULT,
 } MlockState;
 
 bool should_mlock(MlockState);
+bool is_mlock_on_fault(MlockState);
 
 extern MlockState mlock_state;
 
diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
index 04068ee039..5d3edfcfec 100644
--- a/migration/postcopy-ram.c
+++ b/migration/postcopy-ram.c
@@ -652,7 +652,7 @@ int postcopy_ram_incoming_cleanup(MigrationIncomingState *mis)
     }
 
     if (should_mlock(mlock_state)) {
-        if (os_mlock(false) < 0) {
+        if (os_mlock(is_mlock_on_fault(mlock_state)) < 0) {
             error_report("mlock: %s", strerror(errno));
             /*
              * It doesn't feel right to fail at this point, we have a valid
diff --git a/system/globals.c b/system/globals.c
index adeff38348..316623bd20 100644
--- a/system/globals.c
+++ b/system/globals.c
@@ -33,7 +33,12 @@
 
 bool should_mlock(MlockState state)
 {
-    return state == MLOCK_ON;
+    return state == MLOCK_ON || state == MLOCK_ON_FAULT;
+}
+
+bool is_mlock_on_fault(MlockState state)
+{
+    return state == MLOCK_ON_FAULT;
 }
 
 enum vga_retrace_method vga_retrace_method = VGA_RETRACE_DUMB;
diff --git a/system/vl.c b/system/vl.c
index 2895824c1a..3c0fa2ff64 100644
--- a/system/vl.c
+++ b/system/vl.c
@@ -351,7 +351,7 @@ static QemuOptsList qemu_overcommit_opts = {
     .desc = {
         {
             .name = "mem-lock",
-            .type = QEMU_OPT_BOOL,
+            .type = QEMU_OPT_STRING,
         },
         {
             .name = "cpu-pm",
@@ -797,7 +797,7 @@ static QemuOptsList qemu_run_with_opts = {
 static void realtime_init(void)
 {
     if (should_mlock(mlock_state)) {
-        if (os_mlock(false) < 0) {
+        if (os_mlock(is_mlock_on_fault(mlock_state)) < 0) {
             error_report("locking memory failed");
             exit(1);
         }
@@ -1878,7 +1878,7 @@ static void object_option_parse(const char *str)
 static void overcommit_parse(const char *str)
 {
     QemuOpts *opts;
-    bool enable_mlock;
+    const char *mem_lock_opt;
 
     opts = qemu_opts_parse_noisily(qemu_find_opts("overcommit"),
                                    str, false);
@@ -1886,11 +1886,31 @@ static void overcommit_parse(const char *str)
         exit(1);
     }
 
-    enable_mlock = qemu_opt_get_bool(opts, "mem-lock",
-                                     should_mlock(mlock_state));
-    mlock_state = enable_mlock ? MLOCK_ON : MLOCK_OFF;
-
     enable_cpu_pm = qemu_opt_get_bool(opts, "cpu-pm", enable_cpu_pm);
+
+    mem_lock_opt = qemu_opt_get(opts, "mem-lock");
+    if (!mem_lock_opt) {
+        return;
+    }
+
+    if (strcmp(mem_lock_opt, "on") == 0) {
+        mlock_state = MLOCK_ON;
+        return;
+    }
+
+    if (strcmp(mem_lock_opt, "off") == 0) {
+        mlock_state = MLOCK_OFF;
+        return;
+    }
+
+    if (strcmp(mem_lock_opt, "on-fault") == 0) {
+        mlock_state = MLOCK_ON_FAULT;
+        return;
+    }
+
+    error_report("parameter 'mem-lock' expects one of "
+                 "'on', 'off', 'on-fault'");
+    exit(1);
 }
 
 /*
diff --git a/qemu-options.hx b/qemu-options.hx
index 1b26ad53bd..61270e3206 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -4632,21 +4632,25 @@ SRST
 ERST
 
 DEF("overcommit", HAS_ARG, QEMU_OPTION_overcommit,
-    "-overcommit [mem-lock=on|off][cpu-pm=on|off]\n"
+    "-overcommit [mem-lock=on|off|on-fault][cpu-pm=on|off]\n"
     "                run qemu with overcommit hints\n"
-    "                mem-lock=on|off controls memory lock support (default: off)\n"
+    "                mem-lock=on|off|on-fault controls memory lock support (default: off)\n"
     "                cpu-pm=on|off controls cpu power management (default: off)\n",
     QEMU_ARCH_ALL)
 SRST
-``-overcommit mem-lock=on|off``
+``-overcommit mem-lock=on|off|on-fault``
   \ 
 ``-overcommit cpu-pm=on|off``
     Run qemu with hints about host resource overcommit. The default is
     to assume that host overcommits all resources.
 
     Locking qemu and guest memory can be enabled via ``mem-lock=on``
-    (disabled by default). This works when host memory is not
-    overcommitted and reduces the worst-case latency for guest.
+    or ``mem-lock=on-fault`` (disabled by default). This works when
+    host memory is not overcommitted and reduces the worst-case latency for
+    guest. The on-fault option is better for reducing the memory footprint
+    since it makes allocations lazy, but the pages still get locked in place
+    once faulted by the guest or QEMU. Note that the two options are mutually
+    exclusive.
 
     Guest ability to manage power state of host cpus (increasing latency
     for other processes on the same host cpu, but decreasing latency for
-- 
2.47.0



  parent reply	other threads:[~2025-02-11 22:52 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-02-11 22:50 [PULL 00/14] Mem next patches Peter Xu
2025-02-11 22:50 ` [PULL 01/14] system/physmem: take into account fd_offset for file fallocate Peter Xu
2025-02-11 22:50 ` [PULL 02/14] os: add an ability to lock memory on_fault Peter Xu
2025-02-12 14:13   ` Stefan Hajnoczi
2025-02-12 14:17     ` Daniil Tatianin
2025-02-11 22:50 ` [PULL 03/14] system/vl: extract overcommit option parsing into a helper Peter Xu
2025-02-11 22:50 ` [PULL 04/14] system: introduce a new MlockState enum Peter Xu
2025-02-11 22:50 ` Peter Xu [this message]
2025-02-11 22:50 ` [PULL 06/14] physmem: factor out memory_region_is_ram_device() check in memory_access_is_direct() Peter Xu
2025-02-11 22:50 ` [PULL 07/14] physmem: factor out RAM/ROMD " Peter Xu
2025-02-11 22:50 ` [PULL 08/14] physmem: factor out direct access check into memory_region_supports_direct_access() Peter Xu
2025-02-11 22:50 ` [PULL 09/14] physmem: disallow direct access to RAM DEVICE in address_space_write_rom() Peter Xu
2025-02-11 22:50 ` [PULL 10/14] memory: pass MemTxAttrs to memory_access_is_direct() Peter Xu
2025-02-11 22:50 ` [PULL 11/14] hmp: use cpu_get_phys_page_debug() in hmp_gva2gpa() Peter Xu
2025-02-11 22:50 ` [PULL 12/14] physmem: teach cpu_memory_rw_debug() to write to more memory regions Peter Xu
2025-02-11 22:50 ` [PULL 13/14] system/physmem: handle hugetlb correctly in qemu_ram_remap() Peter Xu
2025-02-11 22:50 ` [PULL 14/14] system/physmem: poisoned memory discard on reboot 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=20250211225059.182533-6-peterx@redhat.com \
    --to=peterx@redhat.com \
    --cc=d-tatianin@yandex-team.ru \
    --cc=david@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=qemu-devel@nongnu.org \
    --cc=stefanha@redhat.com \
    --cc=vsementsov@yandex-team.ru \
    /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).