diff mbox

[10/17] migration: create ram_multifd_page

Message ID 1485207141-1941-11-git-send-email-quintela@redhat.com
State New
Headers show

Commit Message

Juan Quintela Jan. 23, 2017, 9:32 p.m. UTC
The function still don't use multifd, but we have simplified
ram_save_page, xbzrle and RDMA stuff is gone.  We have added a new
counter and a new flag for this type of pages.

Signed-off-by: Juan Quintela <quintela@redhat.com>
---
 hmp.c                         |  2 ++
 include/migration/migration.h |  1 +
 migration/migration.c         |  1 +
 migration/ram.c               | 51 ++++++++++++++++++++++++++++++++++++++++++-
 qapi-schema.json              |  4 +++-
 5 files changed, 57 insertions(+), 2 deletions(-)

Comments

Dr. David Alan Gilbert Jan. 27, 2017, 6:02 p.m. UTC | #1
* Juan Quintela (quintela@redhat.com) wrote:
> The function still don't use multifd, but we have simplified
> ram_save_page, xbzrle and RDMA stuff is gone.  We have added a new
> counter and a new flag for this type of pages.
> 
> Signed-off-by: Juan Quintela <quintela@redhat.com>
> ---
>  hmp.c                         |  2 ++
>  include/migration/migration.h |  1 +
>  migration/migration.c         |  1 +
>  migration/ram.c               | 51 ++++++++++++++++++++++++++++++++++++++++++-
>  qapi-schema.json              |  4 +++-
>  5 files changed, 57 insertions(+), 2 deletions(-)
> 
> diff --git a/hmp.c b/hmp.c
> index e579766..76bc8c7 100644
> --- a/hmp.c
> +++ b/hmp.c
> @@ -222,6 +222,8 @@ void hmp_info_migrate(Monitor *mon, const QDict *qdict)
>              monitor_printf(mon, "postcopy request count: %" PRIu64 "\n",
>                             info->ram->postcopy_requests);
>          }
> +        monitor_printf(mon, "multifd: %" PRIu64 " pages\n",
> +                       info->ram->multifd);
>      }
> 
>      if (info->has_disk) {
> diff --git a/include/migration/migration.h b/include/migration/migration.h
> index 3989bd6..b3e4f31 100644
> --- a/include/migration/migration.h
> +++ b/include/migration/migration.h
> @@ -282,6 +282,7 @@ uint64_t xbzrle_mig_pages_transferred(void);
>  uint64_t xbzrle_mig_pages_overflow(void);
>  uint64_t xbzrle_mig_pages_cache_miss(void);
>  double xbzrle_mig_cache_miss_rate(void);
> +uint64_t multifd_mig_pages_transferred(void);
> 
>  void ram_handle_compressed(void *host, uint8_t ch, uint64_t size);
>  void ram_debug_dump_bitmap(unsigned long *todump, bool expected);
> diff --git a/migration/migration.c b/migration/migration.c
> index ab48f06..1d62b91 100644
> --- a/migration/migration.c
> +++ b/migration/migration.c
> @@ -652,6 +652,7 @@ static void populate_ram_info(MigrationInfo *info, MigrationState *s)
>      info->ram->mbps = s->mbps;
>      info->ram->dirty_sync_count = s->dirty_sync_count;
>      info->ram->postcopy_requests = s->postcopy_requests;
> +    info->ram->multifd = multifd_mig_pages_transferred();
> 
>      if (s->state != MIGRATION_STATUS_COMPLETED) {
>          info->ram->remaining = ram_bytes_remaining();
> diff --git a/migration/ram.c b/migration/ram.c
> index 5ad7cb3..c71929e 100644
> --- a/migration/ram.c
> +++ b/migration/ram.c
> @@ -61,6 +61,7 @@ static uint64_t bitmap_sync_count;
>  #define RAM_SAVE_FLAG_XBZRLE   0x40
>  /* 0x80 is reserved in migration.h start with 0x100 next */
>  #define RAM_SAVE_FLAG_COMPRESS_PAGE    0x100
> +#define RAM_SAVE_FLAG_MULTIFD_PAGE     0x200

I think a similar reminder from the last iteration of this patch;
I think we're out of bits here - I'm not sure if 0x200 is even
available.

>  static uint8_t *ZERO_TARGET_PAGE;
> 
> @@ -141,6 +142,7 @@ typedef struct AccountingInfo {
>      uint64_t dup_pages;
>      uint64_t skipped_pages;
>      uint64_t norm_pages;
> +    uint64_t multifd_pages;
>      uint64_t iterations;
>      uint64_t xbzrle_bytes;
>      uint64_t xbzrle_pages;
> @@ -211,6 +213,11 @@ uint64_t xbzrle_mig_pages_overflow(void)
>      return acct_info.xbzrle_overflows;
>  }
> 
> +uint64_t multifd_mig_pages_transferred(void)
> +{
> +    return acct_info.multifd_pages;
> +}
> +
>  /* This is the last block that we have visited serching for dirty pages
>   */
>  static RAMBlock *last_seen_block;
> @@ -990,6 +997,33 @@ static int ram_save_page(QEMUFile *f, PageSearchStatus *pss,
>      return pages;
>  }
> 
> +static int ram_multifd_page(QEMUFile *f, PageSearchStatus *pss,
> +                            bool last_stage, uint64_t *bytes_transferred)
> +{
> +    int pages;
> +    uint8_t *p;
> +    RAMBlock *block = pss->block;
> +    ram_addr_t offset = pss->offset;
> +
> +    p = block->host + offset;
> +
> +    if (block == last_sent_block) {
> +        offset |= RAM_SAVE_FLAG_CONTINUE;
> +    }
> +    pages = save_zero_page(f, block, offset, p, bytes_transferred);
> +    if (pages == -1) {
> +        *bytes_transferred +=
> +            save_page_header(f, block, offset | RAM_SAVE_FLAG_MULTIFD_PAGE);
> +        qemu_put_buffer(f, p, TARGET_PAGE_SIZE);
> +        *bytes_transferred += TARGET_PAGE_SIZE;
> +        pages = 1;
> +        acct_info.norm_pages++;
> +        acct_info.multifd_pages++;
> +    }
> +
> +    return pages;
> +}
> +
>  static int do_compress_ram_page(QEMUFile *f, RAMBlock *block,
>                                  ram_addr_t offset)
>  {
> @@ -1427,6 +1461,8 @@ static int ram_save_target_page(MigrationState *ms, QEMUFile *f,
>              res = ram_save_compressed_page(f, pss,
>                                             last_stage,
>                                             bytes_transferred);
> +        } else if (migrate_use_multifd()) {
> +            res = ram_multifd_page(f, pss, last_stage, bytes_transferred);

I'm curious whether it's best to pick the destination fd at this level or one level
higher; for example would it be good to keep all the components of a host page or huge
page together on the same fd? If so then it would be best to pick the fd
at ram_save_host_page level.

Dave

>          } else {
>              res = ram_save_page(f, pss, last_stage,
>                                  bytes_transferred);
> @@ -2678,6 +2714,10 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
>      if (!migrate_use_compression()) {
>          invalid_flags |= RAM_SAVE_FLAG_COMPRESS_PAGE;
>      }
> +
> +    if (!migrate_use_multifd()) {
> +        invalid_flags |= RAM_SAVE_FLAG_MULTIFD_PAGE;
> +    }
>      /* This RCU critical section can be very long running.
>       * When RCU reclaims in the code start to become numerous,
>       * it will be necessary to reduce the granularity of this
> @@ -2705,13 +2745,17 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
>              if (flags & invalid_flags  & RAM_SAVE_FLAG_COMPRESS_PAGE) {
>                  error_report("Received an unexpected compressed page");
>              }
> +            if (flags & invalid_flags  & RAM_SAVE_FLAG_MULTIFD_PAGE) {
> +                error_report("Received an unexpected multifd page");
> +            }
> 
>              ret = -EINVAL;
>              break;
>          }
> 
>          if (flags & (RAM_SAVE_FLAG_COMPRESS | RAM_SAVE_FLAG_PAGE |
> -                     RAM_SAVE_FLAG_COMPRESS_PAGE | RAM_SAVE_FLAG_XBZRLE)) {
> +                     RAM_SAVE_FLAG_COMPRESS_PAGE | RAM_SAVE_FLAG_XBZRLE |
> +                     RAM_SAVE_FLAG_MULTIFD_PAGE)) {
>              RAMBlock *block = ram_block_from_stream(f, flags);
> 
>              host = host_from_ram_block_offset(block, addr);
> @@ -2786,6 +2830,11 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
>                  break;
>              }
>              break;
> +
> +        case RAM_SAVE_FLAG_MULTIFD_PAGE:
> +            qemu_get_buffer(f, host, TARGET_PAGE_SIZE);
> +            break;
> +
>          case RAM_SAVE_FLAG_EOS:
>              /* normal exit */
>              break;
> diff --git a/qapi-schema.json b/qapi-schema.json
> index 54232ee..3e93f7f 100644
> --- a/qapi-schema.json
> +++ b/qapi-schema.json
> @@ -574,6 +574,7 @@
>  #
>  # @postcopy-requests: The number of page requests received from the destination
>  #        (since 2.7)
> +# @multifd: number of pages sent with multifd (since 2.9)
>  #
>  # Since: 0.14.0
>  ##
> @@ -582,7 +583,8 @@
>             'duplicate': 'int', 'skipped': 'int', 'normal': 'int',
>             'normal-bytes': 'int', 'dirty-pages-rate' : 'int',
>             'mbps' : 'number', 'dirty-sync-count' : 'int',
> -           'postcopy-requests' : 'int' } }
> +           'postcopy-requests' : 'int',
> +           'multifd' : 'int'} }

>  ##
>  # @XBZRLECacheStats:
> -- 
> 2.9.3
> 
--
Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK
Juan Quintela Jan. 30, 2017, 10:06 a.m. UTC | #2
"Dr. David Alan Gilbert" <dgilbert@redhat.com> wrote:
> * Juan Quintela (quintela@redhat.com) wrote:
>> The function still don't use multifd, but we have simplified
>> ram_save_page, xbzrle and RDMA stuff is gone.  We have added a new
>> counter and a new flag for this type of pages.
>> 
>> Signed-off-by: Juan Quintela <quintela@redhat.com>

>> --- a/migration/ram.c
>> +++ b/migration/ram.c
>> @@ -61,6 +61,7 @@ static uint64_t bitmap_sync_count;
>>  #define RAM_SAVE_FLAG_XBZRLE   0x40
>>  /* 0x80 is reserved in migration.h start with 0x100 next */
>>  #define RAM_SAVE_FLAG_COMPRESS_PAGE    0x100
>> +#define RAM_SAVE_FLAG_MULTIFD_PAGE     0x200
>
> I think a similar reminder from the last iteration of this patch;
> I think we're out of bits here - I'm not sure if 0x200 is even
> available.

In previous iteration, I used *two* bits.  As per your recomendation, I
"reused" and old one for doing the synchronization.


Later, Juan.
Dr. David Alan Gilbert Feb. 2, 2017, 11:04 a.m. UTC | #3
* Juan Quintela (quintela@redhat.com) wrote:
> "Dr. David Alan Gilbert" <dgilbert@redhat.com> wrote:
> > * Juan Quintela (quintela@redhat.com) wrote:
> >> The function still don't use multifd, but we have simplified
> >> ram_save_page, xbzrle and RDMA stuff is gone.  We have added a new
> >> counter and a new flag for this type of pages.
> >> 
> >> Signed-off-by: Juan Quintela <quintela@redhat.com>
> 
> >> --- a/migration/ram.c
> >> +++ b/migration/ram.c
> >> @@ -61,6 +61,7 @@ static uint64_t bitmap_sync_count;
> >>  #define RAM_SAVE_FLAG_XBZRLE   0x40
> >>  /* 0x80 is reserved in migration.h start with 0x100 next */
> >>  #define RAM_SAVE_FLAG_COMPRESS_PAGE    0x100
> >> +#define RAM_SAVE_FLAG_MULTIFD_PAGE     0x200
> >
> > I think a similar reminder from the last iteration of this patch;
> > I think we're out of bits here - I'm not sure if 0x200 is even
> > available.
> 
> In previous iteration, I used *two* bits.  As per your recomendation, I
> "reused" and old one for doing the synchronization.

Hmm OK, but that's still the last free bit; given TARGET_PAGE_BITS 10
on 3 targets, we can't use 0x400.
I guess the next user of a new bit will need to use RAM_SAVE_FLAG_FULL
which has never really been used and that will have to be some
magic that caused another block of bits to be read.

Dave

> 
> Later, Juan.
--
Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK
Dr. David Alan Gilbert Feb. 2, 2017, 11:20 a.m. UTC | #4
* Juan Quintela (quintela@redhat.com) wrote:
> The function still don't use multifd, but we have simplified
> ram_save_page, xbzrle and RDMA stuff is gone.  We have added a new
> counter and a new flag for this type of pages.
> 
> Signed-off-by: Juan Quintela <quintela@redhat.com>

Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>

Dave

> ---
>  hmp.c                         |  2 ++
>  include/migration/migration.h |  1 +
>  migration/migration.c         |  1 +
>  migration/ram.c               | 51 ++++++++++++++++++++++++++++++++++++++++++-
>  qapi-schema.json              |  4 +++-
>  5 files changed, 57 insertions(+), 2 deletions(-)
> 
> diff --git a/hmp.c b/hmp.c
> index e579766..76bc8c7 100644
> --- a/hmp.c
> +++ b/hmp.c
> @@ -222,6 +222,8 @@ void hmp_info_migrate(Monitor *mon, const QDict *qdict)
>              monitor_printf(mon, "postcopy request count: %" PRIu64 "\n",
>                             info->ram->postcopy_requests);
>          }
> +        monitor_printf(mon, "multifd: %" PRIu64 " pages\n",
> +                       info->ram->multifd);
>      }
> 
>      if (info->has_disk) {
> diff --git a/include/migration/migration.h b/include/migration/migration.h
> index 3989bd6..b3e4f31 100644
> --- a/include/migration/migration.h
> +++ b/include/migration/migration.h
> @@ -282,6 +282,7 @@ uint64_t xbzrle_mig_pages_transferred(void);
>  uint64_t xbzrle_mig_pages_overflow(void);
>  uint64_t xbzrle_mig_pages_cache_miss(void);
>  double xbzrle_mig_cache_miss_rate(void);
> +uint64_t multifd_mig_pages_transferred(void);
> 
>  void ram_handle_compressed(void *host, uint8_t ch, uint64_t size);
>  void ram_debug_dump_bitmap(unsigned long *todump, bool expected);
> diff --git a/migration/migration.c b/migration/migration.c
> index ab48f06..1d62b91 100644
> --- a/migration/migration.c
> +++ b/migration/migration.c
> @@ -652,6 +652,7 @@ static void populate_ram_info(MigrationInfo *info, MigrationState *s)
>      info->ram->mbps = s->mbps;
>      info->ram->dirty_sync_count = s->dirty_sync_count;
>      info->ram->postcopy_requests = s->postcopy_requests;
> +    info->ram->multifd = multifd_mig_pages_transferred();
> 
>      if (s->state != MIGRATION_STATUS_COMPLETED) {
>          info->ram->remaining = ram_bytes_remaining();
> diff --git a/migration/ram.c b/migration/ram.c
> index 5ad7cb3..c71929e 100644
> --- a/migration/ram.c
> +++ b/migration/ram.c
> @@ -61,6 +61,7 @@ static uint64_t bitmap_sync_count;
>  #define RAM_SAVE_FLAG_XBZRLE   0x40
>  /* 0x80 is reserved in migration.h start with 0x100 next */
>  #define RAM_SAVE_FLAG_COMPRESS_PAGE    0x100
> +#define RAM_SAVE_FLAG_MULTIFD_PAGE     0x200
> 
>  static uint8_t *ZERO_TARGET_PAGE;
> 
> @@ -141,6 +142,7 @@ typedef struct AccountingInfo {
>      uint64_t dup_pages;
>      uint64_t skipped_pages;
>      uint64_t norm_pages;
> +    uint64_t multifd_pages;
>      uint64_t iterations;
>      uint64_t xbzrle_bytes;
>      uint64_t xbzrle_pages;
> @@ -211,6 +213,11 @@ uint64_t xbzrle_mig_pages_overflow(void)
>      return acct_info.xbzrle_overflows;
>  }
> 
> +uint64_t multifd_mig_pages_transferred(void)
> +{
> +    return acct_info.multifd_pages;
> +}
> +
>  /* This is the last block that we have visited serching for dirty pages
>   */
>  static RAMBlock *last_seen_block;
> @@ -990,6 +997,33 @@ static int ram_save_page(QEMUFile *f, PageSearchStatus *pss,
>      return pages;
>  }
> 
> +static int ram_multifd_page(QEMUFile *f, PageSearchStatus *pss,
> +                            bool last_stage, uint64_t *bytes_transferred)
> +{
> +    int pages;
> +    uint8_t *p;
> +    RAMBlock *block = pss->block;
> +    ram_addr_t offset = pss->offset;
> +
> +    p = block->host + offset;
> +
> +    if (block == last_sent_block) {
> +        offset |= RAM_SAVE_FLAG_CONTINUE;
> +    }
> +    pages = save_zero_page(f, block, offset, p, bytes_transferred);
> +    if (pages == -1) {
> +        *bytes_transferred +=
> +            save_page_header(f, block, offset | RAM_SAVE_FLAG_MULTIFD_PAGE);
> +        qemu_put_buffer(f, p, TARGET_PAGE_SIZE);
> +        *bytes_transferred += TARGET_PAGE_SIZE;
> +        pages = 1;
> +        acct_info.norm_pages++;
> +        acct_info.multifd_pages++;
> +    }
> +
> +    return pages;
> +}
> +
>  static int do_compress_ram_page(QEMUFile *f, RAMBlock *block,
>                                  ram_addr_t offset)
>  {
> @@ -1427,6 +1461,8 @@ static int ram_save_target_page(MigrationState *ms, QEMUFile *f,
>              res = ram_save_compressed_page(f, pss,
>                                             last_stage,
>                                             bytes_transferred);
> +        } else if (migrate_use_multifd()) {
> +            res = ram_multifd_page(f, pss, last_stage, bytes_transferred);
>          } else {
>              res = ram_save_page(f, pss, last_stage,
>                                  bytes_transferred);
> @@ -2678,6 +2714,10 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
>      if (!migrate_use_compression()) {
>          invalid_flags |= RAM_SAVE_FLAG_COMPRESS_PAGE;
>      }
> +
> +    if (!migrate_use_multifd()) {
> +        invalid_flags |= RAM_SAVE_FLAG_MULTIFD_PAGE;
> +    }
>      /* This RCU critical section can be very long running.
>       * When RCU reclaims in the code start to become numerous,
>       * it will be necessary to reduce the granularity of this
> @@ -2705,13 +2745,17 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
>              if (flags & invalid_flags  & RAM_SAVE_FLAG_COMPRESS_PAGE) {
>                  error_report("Received an unexpected compressed page");
>              }
> +            if (flags & invalid_flags  & RAM_SAVE_FLAG_MULTIFD_PAGE) {
> +                error_report("Received an unexpected multifd page");
> +            }
> 
>              ret = -EINVAL;
>              break;
>          }
> 
>          if (flags & (RAM_SAVE_FLAG_COMPRESS | RAM_SAVE_FLAG_PAGE |
> -                     RAM_SAVE_FLAG_COMPRESS_PAGE | RAM_SAVE_FLAG_XBZRLE)) {
> +                     RAM_SAVE_FLAG_COMPRESS_PAGE | RAM_SAVE_FLAG_XBZRLE |
> +                     RAM_SAVE_FLAG_MULTIFD_PAGE)) {
>              RAMBlock *block = ram_block_from_stream(f, flags);
> 
>              host = host_from_ram_block_offset(block, addr);
> @@ -2786,6 +2830,11 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
>                  break;
>              }
>              break;
> +
> +        case RAM_SAVE_FLAG_MULTIFD_PAGE:
> +            qemu_get_buffer(f, host, TARGET_PAGE_SIZE);
> +            break;
> +
>          case RAM_SAVE_FLAG_EOS:
>              /* normal exit */
>              break;
> diff --git a/qapi-schema.json b/qapi-schema.json
> index 54232ee..3e93f7f 100644
> --- a/qapi-schema.json
> +++ b/qapi-schema.json
> @@ -574,6 +574,7 @@
>  #
>  # @postcopy-requests: The number of page requests received from the destination
>  #        (since 2.7)
> +# @multifd: number of pages sent with multifd (since 2.9)
>  #
>  # Since: 0.14.0
>  ##
> @@ -582,7 +583,8 @@
>             'duplicate': 'int', 'skipped': 'int', 'normal': 'int',
>             'normal-bytes': 'int', 'dirty-pages-rate' : 'int',
>             'mbps' : 'number', 'dirty-sync-count' : 'int',
> -           'postcopy-requests' : 'int' } }
> +           'postcopy-requests' : 'int',
> +           'multifd' : 'int'} }
> 
>  ##
>  # @XBZRLECacheStats:
> -- 
> 2.9.3
> 
> 
--
Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK
Juan Quintela Feb. 13, 2017, 4:36 p.m. UTC | #5
"Dr. David Alan Gilbert" <dgilbert@redhat.com> wrote:
> * Juan Quintela (quintela@redhat.com) wrote:
>> The function still don't use multifd, but we have simplified
>> ram_save_page, xbzrle and RDMA stuff is gone.  We have added a new
>> counter and a new flag for this type of pages.


>> +static int ram_multifd_page(QEMUFile *f, PageSearchStatus *pss,
>> +                            bool last_stage, uint64_t *bytes_transferred)
>> +{
>> +    int pages;
>> +    uint8_t *p;
>> +    RAMBlock *block = pss->block;
>> +    ram_addr_t offset = pss->offset;
>> +
>> +    p = block->host + offset;
>> +
>> +    if (block == last_sent_block) {
>> +        offset |= RAM_SAVE_FLAG_CONTINUE;
>> +    }
>> +    pages = save_zero_page(f, block, offset, p, bytes_transferred);
>> +    if (pages == -1) {
>> +        *bytes_transferred +=
>> +            save_page_header(f, block, offset | RAM_SAVE_FLAG_MULTIFD_PAGE);
>> +        qemu_put_buffer(f, p, TARGET_PAGE_SIZE);
>> +        *bytes_transferred += TARGET_PAGE_SIZE;
>> +        pages = 1;
>> +        acct_info.norm_pages++;
>> +        acct_info.multifd_pages++;
>> +    }
>> +
>> +    return pages;
>> +}
>> +
>>  static int do_compress_ram_page(QEMUFile *f, RAMBlock *block,
>>                                  ram_addr_t offset)
>>  {
>> @@ -1427,6 +1461,8 @@ static int ram_save_target_page(MigrationState *ms, QEMUFile *f,
>>              res = ram_save_compressed_page(f, pss,
>>                                             last_stage,
>>                                             bytes_transferred);
>> +        } else if (migrate_use_multifd()) {
>> +            res = ram_multifd_page(f, pss, last_stage, bytes_transferred);
>
> I'm curious whether it's best to pick the destination fd at this level or one level
> higher; for example would it be good to keep all the components of a
> host page or huge
> page together on the same fd? If so then it would be best to pick the fd
> at ram_save_host_page level.

my plan here would be to change the migration code to be able to call
with a bigger sizes, not page by page, and then the problem is solved by
itself?

Later, Juan.
Dr. David Alan Gilbert Feb. 14, 2017, 11:26 a.m. UTC | #6
* Juan Quintela (quintela@redhat.com) wrote:
> "Dr. David Alan Gilbert" <dgilbert@redhat.com> wrote:
> > * Juan Quintela (quintela@redhat.com) wrote:
> >> The function still don't use multifd, but we have simplified
> >> ram_save_page, xbzrle and RDMA stuff is gone.  We have added a new
> >> counter and a new flag for this type of pages.
> 
> 
> >> +static int ram_multifd_page(QEMUFile *f, PageSearchStatus *pss,
> >> +                            bool last_stage, uint64_t *bytes_transferred)
> >> +{
> >> +    int pages;
> >> +    uint8_t *p;
> >> +    RAMBlock *block = pss->block;
> >> +    ram_addr_t offset = pss->offset;
> >> +
> >> +    p = block->host + offset;
> >> +
> >> +    if (block == last_sent_block) {
> >> +        offset |= RAM_SAVE_FLAG_CONTINUE;
> >> +    }
> >> +    pages = save_zero_page(f, block, offset, p, bytes_transferred);
> >> +    if (pages == -1) {
> >> +        *bytes_transferred +=
> >> +            save_page_header(f, block, offset | RAM_SAVE_FLAG_MULTIFD_PAGE);
> >> +        qemu_put_buffer(f, p, TARGET_PAGE_SIZE);
> >> +        *bytes_transferred += TARGET_PAGE_SIZE;
> >> +        pages = 1;
> >> +        acct_info.norm_pages++;
> >> +        acct_info.multifd_pages++;
> >> +    }
> >> +
> >> +    return pages;
> >> +}
> >> +
> >>  static int do_compress_ram_page(QEMUFile *f, RAMBlock *block,
> >>                                  ram_addr_t offset)
> >>  {
> >> @@ -1427,6 +1461,8 @@ static int ram_save_target_page(MigrationState *ms, QEMUFile *f,
> >>              res = ram_save_compressed_page(f, pss,
> >>                                             last_stage,
> >>                                             bytes_transferred);
> >> +        } else if (migrate_use_multifd()) {
> >> +            res = ram_multifd_page(f, pss, last_stage, bytes_transferred);
> >
> > I'm curious whether it's best to pick the destination fd at this level or one level
> > higher; for example would it be good to keep all the components of a
> > host page or huge
> > page together on the same fd? If so then it would be best to pick the fd
> > at ram_save_host_page level.
> 
> my plan here would be to change the migration code to be able to call
> with a bigger sizes, not page by page, and then the problem is solved by
> itself?

Yes it might be, but you may have to be careful to keep all your FDs busy;
for example, imagine that we're using huge pages, and you try and stuff
an entire hugepage down one FD, for 2MB hugepages that's about half of the
write buffer (tcp-wmem?) so there's a fair chance it'll block.  But thereagain
I think it's probably the right thing to do as long as you can get
different pages down different FDs.

Dave

> Later, Juan.
> 
--
Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK
diff mbox

Patch

diff --git a/hmp.c b/hmp.c
index e579766..76bc8c7 100644
--- a/hmp.c
+++ b/hmp.c
@@ -222,6 +222,8 @@  void hmp_info_migrate(Monitor *mon, const QDict *qdict)
             monitor_printf(mon, "postcopy request count: %" PRIu64 "\n",
                            info->ram->postcopy_requests);
         }
+        monitor_printf(mon, "multifd: %" PRIu64 " pages\n",
+                       info->ram->multifd);
     }

     if (info->has_disk) {
diff --git a/include/migration/migration.h b/include/migration/migration.h
index 3989bd6..b3e4f31 100644
--- a/include/migration/migration.h
+++ b/include/migration/migration.h
@@ -282,6 +282,7 @@  uint64_t xbzrle_mig_pages_transferred(void);
 uint64_t xbzrle_mig_pages_overflow(void);
 uint64_t xbzrle_mig_pages_cache_miss(void);
 double xbzrle_mig_cache_miss_rate(void);
+uint64_t multifd_mig_pages_transferred(void);

 void ram_handle_compressed(void *host, uint8_t ch, uint64_t size);
 void ram_debug_dump_bitmap(unsigned long *todump, bool expected);
diff --git a/migration/migration.c b/migration/migration.c
index ab48f06..1d62b91 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -652,6 +652,7 @@  static void populate_ram_info(MigrationInfo *info, MigrationState *s)
     info->ram->mbps = s->mbps;
     info->ram->dirty_sync_count = s->dirty_sync_count;
     info->ram->postcopy_requests = s->postcopy_requests;
+    info->ram->multifd = multifd_mig_pages_transferred();

     if (s->state != MIGRATION_STATUS_COMPLETED) {
         info->ram->remaining = ram_bytes_remaining();
diff --git a/migration/ram.c b/migration/ram.c
index 5ad7cb3..c71929e 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -61,6 +61,7 @@  static uint64_t bitmap_sync_count;
 #define RAM_SAVE_FLAG_XBZRLE   0x40
 /* 0x80 is reserved in migration.h start with 0x100 next */
 #define RAM_SAVE_FLAG_COMPRESS_PAGE    0x100
+#define RAM_SAVE_FLAG_MULTIFD_PAGE     0x200

 static uint8_t *ZERO_TARGET_PAGE;

@@ -141,6 +142,7 @@  typedef struct AccountingInfo {
     uint64_t dup_pages;
     uint64_t skipped_pages;
     uint64_t norm_pages;
+    uint64_t multifd_pages;
     uint64_t iterations;
     uint64_t xbzrle_bytes;
     uint64_t xbzrle_pages;
@@ -211,6 +213,11 @@  uint64_t xbzrle_mig_pages_overflow(void)
     return acct_info.xbzrle_overflows;
 }

+uint64_t multifd_mig_pages_transferred(void)
+{
+    return acct_info.multifd_pages;
+}
+
 /* This is the last block that we have visited serching for dirty pages
  */
 static RAMBlock *last_seen_block;
@@ -990,6 +997,33 @@  static int ram_save_page(QEMUFile *f, PageSearchStatus *pss,
     return pages;
 }

+static int ram_multifd_page(QEMUFile *f, PageSearchStatus *pss,
+                            bool last_stage, uint64_t *bytes_transferred)
+{
+    int pages;
+    uint8_t *p;
+    RAMBlock *block = pss->block;
+    ram_addr_t offset = pss->offset;
+
+    p = block->host + offset;
+
+    if (block == last_sent_block) {
+        offset |= RAM_SAVE_FLAG_CONTINUE;
+    }
+    pages = save_zero_page(f, block, offset, p, bytes_transferred);
+    if (pages == -1) {
+        *bytes_transferred +=
+            save_page_header(f, block, offset | RAM_SAVE_FLAG_MULTIFD_PAGE);
+        qemu_put_buffer(f, p, TARGET_PAGE_SIZE);
+        *bytes_transferred += TARGET_PAGE_SIZE;
+        pages = 1;
+        acct_info.norm_pages++;
+        acct_info.multifd_pages++;
+    }
+
+    return pages;
+}
+
 static int do_compress_ram_page(QEMUFile *f, RAMBlock *block,
                                 ram_addr_t offset)
 {
@@ -1427,6 +1461,8 @@  static int ram_save_target_page(MigrationState *ms, QEMUFile *f,
             res = ram_save_compressed_page(f, pss,
                                            last_stage,
                                            bytes_transferred);
+        } else if (migrate_use_multifd()) {
+            res = ram_multifd_page(f, pss, last_stage, bytes_transferred);
         } else {
             res = ram_save_page(f, pss, last_stage,
                                 bytes_transferred);
@@ -2678,6 +2714,10 @@  static int ram_load(QEMUFile *f, void *opaque, int version_id)
     if (!migrate_use_compression()) {
         invalid_flags |= RAM_SAVE_FLAG_COMPRESS_PAGE;
     }
+
+    if (!migrate_use_multifd()) {
+        invalid_flags |= RAM_SAVE_FLAG_MULTIFD_PAGE;
+    }
     /* This RCU critical section can be very long running.
      * When RCU reclaims in the code start to become numerous,
      * it will be necessary to reduce the granularity of this
@@ -2705,13 +2745,17 @@  static int ram_load(QEMUFile *f, void *opaque, int version_id)
             if (flags & invalid_flags  & RAM_SAVE_FLAG_COMPRESS_PAGE) {
                 error_report("Received an unexpected compressed page");
             }
+            if (flags & invalid_flags  & RAM_SAVE_FLAG_MULTIFD_PAGE) {
+                error_report("Received an unexpected multifd page");
+            }

             ret = -EINVAL;
             break;
         }

         if (flags & (RAM_SAVE_FLAG_COMPRESS | RAM_SAVE_FLAG_PAGE |
-                     RAM_SAVE_FLAG_COMPRESS_PAGE | RAM_SAVE_FLAG_XBZRLE)) {
+                     RAM_SAVE_FLAG_COMPRESS_PAGE | RAM_SAVE_FLAG_XBZRLE |
+                     RAM_SAVE_FLAG_MULTIFD_PAGE)) {
             RAMBlock *block = ram_block_from_stream(f, flags);

             host = host_from_ram_block_offset(block, addr);
@@ -2786,6 +2830,11 @@  static int ram_load(QEMUFile *f, void *opaque, int version_id)
                 break;
             }
             break;
+
+        case RAM_SAVE_FLAG_MULTIFD_PAGE:
+            qemu_get_buffer(f, host, TARGET_PAGE_SIZE);
+            break;
+
         case RAM_SAVE_FLAG_EOS:
             /* normal exit */
             break;
diff --git a/qapi-schema.json b/qapi-schema.json
index 54232ee..3e93f7f 100644
--- a/qapi-schema.json
+++ b/qapi-schema.json
@@ -574,6 +574,7 @@ 
 #
 # @postcopy-requests: The number of page requests received from the destination
 #        (since 2.7)
+# @multifd: number of pages sent with multifd (since 2.9)
 #
 # Since: 0.14.0
 ##
@@ -582,7 +583,8 @@ 
            'duplicate': 'int', 'skipped': 'int', 'normal': 'int',
            'normal-bytes': 'int', 'dirty-pages-rate' : 'int',
            'mbps' : 'number', 'dirty-sync-count' : 'int',
-           'postcopy-requests' : 'int' } }
+           'postcopy-requests' : 'int',
+           'multifd' : 'int'} }

 ##
 # @XBZRLECacheStats: