From: mrhines@linux.vnet.ibm.com
To: qemu-devel@nongnu.org
Cc: aliguori@us.ibm.com, quintela@redhat.com, knoel@redhat.com,
owasserm@redhat.com, abali@us.ibm.com, mrhines@us.ibm.com,
gokul@us.ibm.com, pbonzini@redhat.com, chegu_vinod@hp.com
Subject: [Qemu-devel] [PATCH v9 02/14] rdma: introduce qemu_update_position()
Date: Fri, 14 Jun 2013 16:35:41 -0400 [thread overview]
Message-ID: <1371242153-11262-3-git-send-email-mrhines@linux.vnet.ibm.com> (raw)
In-Reply-To: <1371242153-11262-1-git-send-email-mrhines@linux.vnet.ibm.com>
From: "Michael R. Hines" <mrhines@us.ibm.com>
RDMA writes happen asynchronously, and thus the performance accounting
also needs to be able to occur asynchronously. This allows anybody
to call into savevm.c to update both f->pos as well as into arch_init.c
to update the acct_info structure with up-to-date values when
the RDMA transfer actually completes.
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Michael R. Hines <mrhines@us.ibm.com>
---
arch_init.c | 12 ++++++++++++
include/migration/migration.h | 2 ++
include/migration/qemu-file.h | 1 +
savevm.c | 5 +++++
4 files changed, 20 insertions(+)
diff --git a/arch_init.c b/arch_init.c
index 5d32ecf..819ca5a 100644
--- a/arch_init.c
+++ b/arch_init.c
@@ -498,6 +498,18 @@ static int ram_save_block(QEMUFile *f, bool last_stage)
static uint64_t bytes_transferred;
+void acct_update_position(QEMUFile *f, size_t size, bool zero)
+{
+ uint64_t pages = size / TARGET_PAGE_SIZE;
+ if (zero) {
+ acct_info.dup_pages += pages;
+ } else {
+ acct_info.norm_pages += pages;
+ bytes_transferred += size;
+ qemu_update_position(f, size);
+ }
+}
+
static ram_addr_t ram_save_remaining(void)
{
return migration_dirty_pages;
diff --git a/include/migration/migration.h b/include/migration/migration.h
index e2acec6..0be28a2 100644
--- a/include/migration/migration.h
+++ b/include/migration/migration.h
@@ -92,6 +92,8 @@ uint64_t ram_bytes_remaining(void);
uint64_t ram_bytes_transferred(void);
uint64_t ram_bytes_total(void);
+void acct_update_position(QEMUFile *f, size_t size, bool zero);
+
extern SaveVMHandlers savevm_ram_handlers;
uint64_t dup_mig_bytes_transferred(void);
diff --git a/include/migration/qemu-file.h b/include/migration/qemu-file.h
index 7519464..8fab0dd 100644
--- a/include/migration/qemu-file.h
+++ b/include/migration/qemu-file.h
@@ -93,6 +93,7 @@ void qemu_put_be32(QEMUFile *f, unsigned int v);
void qemu_put_be64(QEMUFile *f, uint64_t v);
int qemu_get_buffer(QEMUFile *f, uint8_t *buf, int size);
int qemu_get_byte(QEMUFile *f);
+void qemu_update_position(QEMUFile *f, size_t size);
static inline unsigned int qemu_get_ubyte(QEMUFile *f)
{
diff --git a/savevm.c b/savevm.c
index 2ce439f..2983905 100644
--- a/savevm.c
+++ b/savevm.c
@@ -670,6 +670,11 @@ int qemu_get_fd(QEMUFile *f)
return -1;
}
+void qemu_update_position(QEMUFile *f, size_t size)
+{
+ f->pos += size;
+}
+
/** Closes the file
*
* Returns negative error value if any error happened on previous operations or
--
1.7.10.4
next prev parent reply other threads:[~2013-06-14 20:40 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-06-14 20:35 [Qemu-devel] [PATCH v9 00/14] rdma: migration support mrhines
2013-06-14 20:35 ` [Qemu-devel] [PATCH v9 01/14] rdma: add documentation mrhines
2013-06-14 20:35 ` mrhines [this message]
2013-06-14 20:35 ` [Qemu-devel] [PATCH v9 03/14] rdma: export yield_until_fd_readable() mrhines
2013-06-14 20:35 ` [Qemu-devel] [PATCH v9 04/14] rdma: export throughput w/ MigrationStats QMP mrhines
2013-06-15 9:09 ` Eric Blake
2013-06-16 4:04 ` Michael R. Hines
2013-06-14 20:35 ` [Qemu-devel] [PATCH v9 05/14] rdma: introduce qemu_file_mode_is_not_valid() mrhines
2013-06-14 20:35 ` [Qemu-devel] [PATCH v9 06/14] rdma: export qemu_fflush() mrhines
2013-06-14 20:35 ` [Qemu-devel] [PATCH v9 07/14] rdma: introduce ram_handle_compressed() mrhines
2013-06-14 20:35 ` [Qemu-devel] [PATCH v9 08/14] rdma: introduce qemu_ram_foreach_block() mrhines
2013-06-14 20:35 ` [Qemu-devel] [PATCH v9 09/14] rdma: new QEMUFileOps hooks mrhines
2013-06-14 20:35 ` [Qemu-devel] [PATCH v9 10/14] rdma: introduce capability x-rdma-pin-all mrhines
2013-06-15 9:05 ` Eric Blake
2013-06-16 4:04 ` Michael R. Hines
2013-06-14 20:35 ` [Qemu-devel] [PATCH v9 11/14] rdma: core logic mrhines
2013-06-14 20:35 ` [Qemu-devel] [PATCH v9 12/14] rdma: send pc.ram mrhines
2013-06-14 20:35 ` [Qemu-devel] [PATCH v9 13/14] rdma: fix mlock() freezes and accounting mrhines
2013-06-14 20:35 ` [Qemu-devel] [PATCH v9 14/14] rdma: add pin-all accounting timestamp to QMP statistics mrhines
2013-06-15 9:06 ` Eric Blake
2013-06-15 17:32 ` Paolo Bonzini
2013-06-16 4:06 ` Michael R. Hines
2013-06-16 4:05 ` Michael R. Hines
2013-06-16 18:37 ` Chegu Vinod
2013-06-18 20:17 ` Michael R. Hines
2013-06-15 22:51 ` [Qemu-devel] [PATCH v9 00/14] rdma: migration support Chegu Vinod
2013-06-16 4:07 ` Michael R. Hines
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=1371242153-11262-3-git-send-email-mrhines@linux.vnet.ibm.com \
--to=mrhines@linux.vnet.ibm.com \
--cc=abali@us.ibm.com \
--cc=aliguori@us.ibm.com \
--cc=chegu_vinod@hp.com \
--cc=gokul@us.ibm.com \
--cc=knoel@redhat.com \
--cc=mrhines@us.ibm.com \
--cc=owasserm@redhat.com \
--cc=pbonzini@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 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).