From: "Dr. David Alan Gilbert (git)" <dgilbert@redhat.com>
To: qemu-devel@nongnu.org, quintela@redhat.com, amit.shah@redhat.com
Cc: aarcange@redhat.com
Subject: [Qemu-devel] [PATCH 15/15] postcopy: Add doc about hugepages and postcopy
Date: Fri, 6 Jan 2017 18:28:23 +0000 [thread overview]
Message-ID: <20170106182823.1960-16-dgilbert@redhat.com> (raw)
In-Reply-To: <20170106182823.1960-1-dgilbert@redhat.com>
From: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
---
docs/migration.txt | 13 +++++++++++++
1 file changed, 13 insertions(+)
diff --git a/docs/migration.txt b/docs/migration.txt
index 6503c17..b462ead 100644
--- a/docs/migration.txt
+++ b/docs/migration.txt
@@ -482,3 +482,16 @@ request for a page that has already been sent is ignored. Duplicate requests
such as this can happen as a page is sent at about the same time the
destination accesses it.
+=== Postcopy with hugepages ===
+
+Postcopy now works with hugetlbfs backed memory:
+ a) The linux kernel on the destination must support userfault on hugepages.
+ b) The huge-page configuration on the source and destination VMs must be
+ identical; i.e. RAMBlocks on both sides must use the same page size.
+ c) Note that -mem-path /dev/hugepages will fall back to allocating normal
+ RAM if it doesn't have enough hugepages, triggering (b) to fail.
+ Using -mem-prealloc enforces the allocation using hugepages.
+ d) Care should be taken with the size of hugepage used; postcopy with 2MB
+ hugepages works well, however 1GB hugepages are likely to be problematic
+ since it takes ~1 second to transfer a 1GB hugepage across a 10Gbps link,
+ and until the full page is transferred the destination thread is blocked.
--
2.9.3
next prev parent reply other threads:[~2017-01-06 18:28 UTC|newest]
Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-01-06 18:28 [Qemu-devel] [PATCH 00/15] Postcopy: Hugepage support Dr. David Alan Gilbert (git)
2017-01-06 18:28 ` [Qemu-devel] [PATCH 01/15] postcopy: Transmit and compare individual page sizes Dr. David Alan Gilbert (git)
2017-01-25 8:01 ` [Qemu-devel] [01/15] " Alexey Perevalov
2017-01-25 18:38 ` Dr. David Alan Gilbert
2017-01-25 9:47 ` [Qemu-devel] [PATCH 01/15] " Juan Quintela
2017-01-25 16:15 ` Dr. David Alan Gilbert
2017-01-06 18:28 ` [Qemu-devel] [PATCH 02/15] postcopy: Transmit ram size summary word Dr. David Alan Gilbert (git)
2017-01-25 9:53 ` Juan Quintela
2017-01-25 16:18 ` Dr. David Alan Gilbert
2017-01-06 18:28 ` [Qemu-devel] [PATCH 03/15] postcopy: Chunk discards for hugepages Dr. David Alan Gilbert (git)
2017-01-25 10:44 ` Juan Quintela
2017-01-06 18:28 ` [Qemu-devel] [PATCH 04/15] Fold postcopy_ram_discard_range into ram_discard_range Dr. David Alan Gilbert (git)
2017-01-25 10:08 ` Juan Quintela
2017-01-25 16:43 ` Dr. David Alan Gilbert
2017-01-06 18:28 ` [Qemu-devel] [PATCH 05/15] postcopy: enhance ram_discard_range for hugepages Dr. David Alan Gilbert (git)
2017-01-25 10:14 ` Juan Quintela
2017-01-30 18:49 ` Dr. David Alan Gilbert
2017-01-30 19:19 ` Juan Quintela
2017-01-06 18:28 ` [Qemu-devel] [PATCH 06/15] postcopy: Record largest page size Dr. David Alan Gilbert (git)
2017-01-25 10:17 ` Juan Quintela
2017-01-30 16:36 ` Dr. David Alan Gilbert
2017-01-30 19:22 ` Juan Quintela
2017-01-06 18:28 ` [Qemu-devel] [PATCH 07/15] postcopy: Plumb pagesize down into place helpers Dr. David Alan Gilbert (git)
2017-01-25 10:25 ` Juan Quintela
2017-01-27 15:49 ` Dr. David Alan Gilbert
2017-01-06 18:28 ` [Qemu-devel] [PATCH 08/15] postcopy: Use temporary for placing zero huge pages Dr. David Alan Gilbert (git)
2017-01-25 10:29 ` Juan Quintela
2017-01-06 18:28 ` [Qemu-devel] [PATCH 09/15] postcopy: Load huge pages in one go Dr. David Alan Gilbert (git)
2017-01-25 10:31 ` Juan Quintela
2017-01-06 18:28 ` [Qemu-devel] [PATCH 10/15] postcopy: Mask fault addresses to huge page boundary Dr. David Alan Gilbert (git)
2017-01-31 13:20 ` Juan Quintela
2017-01-06 18:28 ` [Qemu-devel] [PATCH 11/15] postcopy: Send whole huge pages Dr. David Alan Gilbert (git)
2017-01-31 13:20 ` Juan Quintela
2017-01-06 18:28 ` [Qemu-devel] [PATCH 12/15] postcopy: Allow hugepages Dr. David Alan Gilbert (git)
2017-01-31 13:21 ` Juan Quintela
2017-01-06 18:28 ` [Qemu-devel] [PATCH 13/15] postcopy: Update userfaultfd.h header Dr. David Alan Gilbert (git)
2017-01-31 13:22 ` Juan Quintela
2017-01-06 18:28 ` [Qemu-devel] [PATCH 14/15] postcopy: Check for userfault+hugepage feature Dr. David Alan Gilbert (git)
2017-01-31 13:24 ` Juan Quintela
2017-01-31 16:20 ` Dr. David Alan Gilbert
2017-01-06 18:28 ` Dr. David Alan Gilbert (git) [this message]
2017-01-31 13:25 ` [Qemu-devel] [PATCH 15/15] postcopy: Add doc about hugepages and postcopy Juan Quintela
2017-01-06 18:51 ` [Qemu-devel] [PATCH 00/15] Postcopy: Hugepage support no-reply
2017-01-06 18:59 ` Dr. David Alan Gilbert
2017-01-09 0:55 ` Fam Zheng
2017-01-09 9:03 ` Dr. David Alan Gilbert
2017-01-06 19:02 ` no-reply
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=20170106182823.1960-16-dgilbert@redhat.com \
--to=dgilbert@redhat.com \
--cc=aarcange@redhat.com \
--cc=amit.shah@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=quintela@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.