From: Fam Zheng <famz@redhat.com>
To: qemu-devel@nongnu.org
Cc: Paolo Bonzini <pbonzini@redhat.com>,
arei.gonglei@huawei.com, peterx@redhat.com
Subject: [Qemu-devel] [PATCH v2 7/7] exec: Introduce AddressSpaceDispatch.mru_section
Date: Tue, 1 Mar 2016 14:18:24 +0800 [thread overview]
Message-ID: <1456813104-25902-8-git-send-email-famz@redhat.com> (raw)
In-Reply-To: <1456813104-25902-1-git-send-email-famz@redhat.com>
Under heavy workloads the lookup will likely end up with the same
MemoryRegionSection from last time. Using a pointer to cache the result,
like ram_list.mru_block, significantly reduces cost of
address_space_translate.
During address space topology update, as->dispatch will be reallocated
so the pointer is invalidated automatically.
Perf reports a visible drop on the cpu usage, because phys_page_find is
not called. Before:
2.35% qemu-system-x86_64 [.] phys_page_find
0.97% qemu-system-x86_64 [.] address_space_translate_internal
0.95% qemu-system-x86_64 [.] address_space_translate
0.55% qemu-system-x86_64 [.] address_space_lookup_region
After:
0.97% qemu-system-x86_64 [.] address_space_translate_internal
0.97% qemu-system-x86_64 [.] address_space_lookup_region
0.84% qemu-system-x86_64 [.] address_space_translate
Signed-off-by: Fam Zheng <famz@redhat.com>
---
exec.c | 16 ++++++++++++++--
1 file changed, 14 insertions(+), 2 deletions(-)
diff --git a/exec.c b/exec.c
index b4e2eb5..98d7733 100644
--- a/exec.c
+++ b/exec.c
@@ -135,6 +135,7 @@ typedef struct PhysPageMap {
struct AddressSpaceDispatch {
struct rcu_head rcu;
+ MemoryRegionSection *mru_section;
/* This is a multi-level map on the physical address space.
* The bottom level has pointers to MemoryRegionSections.
*/
@@ -350,14 +351,25 @@ static MemoryRegionSection *address_space_lookup_region(AddressSpaceDispatch *d,
hwaddr addr,
bool resolve_subpage)
{
- MemoryRegionSection *section;
+ MemoryRegionSection *section = atomic_read(&d->mru_section);
subpage_t *subpage;
+ bool update;
- section = phys_page_find(d->phys_map, addr, d->map.nodes, d->map.sections);
+ if (section && section != &d->map.sections[PHYS_SECTION_UNASSIGNED] &&
+ section_covers_addr(section, addr)) {
+ update = false;
+ } else {
+ section = phys_page_find(d->phys_map, addr, d->map.nodes,
+ d->map.sections);
+ update = true;
+ }
if (resolve_subpage && section->mr->subpage) {
subpage = container_of(section->mr, subpage_t, iomem);
section = &d->map.sections[subpage->sub_section[SUBPAGE_IDX(addr)]];
}
+ if (update) {
+ atomic_set(&d->mru_section, section);
+ }
return section;
}
--
2.4.3
next prev parent reply other threads:[~2016-03-01 6:19 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-03-01 6:18 [Qemu-devel] [PATCH v2 0/7] memory: Clean up MemoryRegion.ram_addr and optimize address_space_translate Fam Zheng
2016-03-01 6:18 ` [Qemu-devel] [PATCH v2 1/7] exec: Return RAMBlock pointer from allocating functions Fam Zheng
2016-03-01 6:18 ` [Qemu-devel] [PATCH v2 2/7] memory: Move assignment to ram_block to memory_region_init_* Fam Zheng
2016-03-01 6:18 ` [Qemu-devel] [PATCH v2 3/7] memory: Implement memory_region_get_ram_addr with mr->ram_block Fam Zheng
2016-03-01 6:58 ` Gonglei (Arei)
2016-03-01 6:18 ` [Qemu-devel] [PATCH v2 4/7] memory: Drop MemoryRegion.ram_addr Fam Zheng
2016-03-07 9:17 ` [Qemu-devel] [PATCH] scripts: Fix dump-guest-memory.py for MemoryRegion.ram_block removal Fam Zheng
2016-03-07 9:37 ` Laszlo Ersek
2016-03-07 9:45 ` Fam Zheng
2016-03-07 10:08 ` Laszlo Ersek
2016-03-07 13:00 ` Paolo Bonzini
2016-03-07 16:35 ` Janosch Frank
2016-03-08 7:54 ` Janosch Frank
2016-03-08 8:54 ` Fam Zheng
2016-03-01 6:18 ` [Qemu-devel] [PATCH v2 5/7] exec: Pass RAMBlock pointer to qemu_ram_free Fam Zheng
2016-03-01 6:18 ` [Qemu-devel] [PATCH v2 6/7] exec: Factor out section_covers_addr Fam Zheng
2016-03-01 7:23 ` Peter Xu
2016-03-01 9:42 ` Paolo Bonzini
2016-03-02 2:24 ` Fam Zheng
2016-03-01 6:18 ` Fam Zheng [this message]
2016-03-01 9:43 ` [Qemu-devel] [PATCH v2 0/7] memory: Clean up MemoryRegion.ram_addr and optimize address_space_translate Paolo Bonzini
2016-03-07 8:53 ` Laszlo Ersek
2016-03-07 9:04 ` Fam Zheng
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=1456813104-25902-8-git-send-email-famz@redhat.com \
--to=famz@redhat.com \
--cc=arei.gonglei@huawei.com \
--cc=pbonzini@redhat.com \
--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).