* Peter Xu (pet...@redhat.com) wrote:
> On Fri, Sep 22, 2017 at 12:05:42PM +0100, Dr. David Alan Gilbert wrote:
>
> [...]
>
> > > diff --git a/migration/ram.c b/migration/ram.c
> > > index 7e20097..5d938e3 100644
> > > --- a/migration/ram.c
> > > +++ b/migration/ram.c
> > > @@ -182,6 +182,70 @@ void ramblock_recv_bitmap_clear(RAMBlock *rb, void
> > > *host_addr)
> > > clear_bit(ramblock_recv_bitmap_offset(host_addr, rb),
> > > rb->receivedmap);
> > > }
> > >
> > > +#define RAMBLOCK_RECV_BITMAP_ENDING (0x0123456789abcdefULL)
> > > +
> > > +/*
> > > + * Format: bitmap_size (8 bytes) + whole_bitmap (N bytes).
> > > + *
> > > + * Returns >0 if success with sent bytes, or <0 if error.
> > > + */
> > > +int64_t ramblock_recv_bitmap_send(QEMUFile *file,
> > > + const char *block_name)
> > > +{
> > > + RAMBlock *block = qemu_ram_block_by_name(block_name);
> > > + unsigned long *le_bitmap, nbits;
> > > + uint64_t size;
> > > +
> > > + if (!block) {
> > > + error_report("%s: invalid block name: %s", __func__, block_name);
> > > + return -1;
> > > + }
> > > +
> > > + nbits = block->used_length >> TARGET_PAGE_BITS;
> > > +
> > > + /*
> > > + * Make sure the tmp bitmap buffer is big enough, e.g., on 32bit
> > > + * machines we may need 4 more bytes for padding (see below
> > > + * comment). So extend it a bit before hand.
> > > + */
> > > + le_bitmap = bitmap_new(nbits + BITS_PER_LONG);
> >
> > I do worry what will happen on really huge RAMBlocks; the worst case is
> > that this temporary bitmap is a few GB.
>
> IIUC the bitmap ratio is 32K, so the ramblock will be 1GB only if the
> guest RAM region size is 1GB * 32K = 32TB.
>
> Then, can I just assume allocating (only) 1GB temporary memory for a
> guest using more than 32TB memory not a problem? :-)
>
> I hope I didn't calculate it wrongly though.
No, I think that's right; I was off a few bits.
If they've got 32TB of RAM, then 1GB is probably no issue.
Dave
> >
> > > + /*
> > > + * Always use little endian when sending the bitmap. This is
> > > + * required that when source and destination VMs are not using the
> > > + * same endianess. (Note: big endian won't work.)
> > > + */
> > > + bitmap_to_le(le_bitmap, block->receivedmap, nbits);
> > > +
> > > + /* Size of the bitmap, in bytes */
> > > + size = nbits / 8;
> > > +
> > > + /*
> > > + * size is always aligned to 8 bytes for 64bit machines, but it
> > > + * may not be true for 32bit machines. We need this padding to
> > > + * make sure the migration can survive even between 32bit and
> > > + * 64bit machines.
> > > + */
> > > + size = ROUND_UP(size, 8);
> > > +
> > > + qemu_put_be64(file, size);
> > > + qemu_put_buffer(file, (const uint8_t *)le_bitmap, size);
> > > + /*
> > > + * Mark as an end, in case the middle part is screwed up due to
> > > + * some "misterious" reason.
> > > + */
> > > + qemu_put_be64(file, RAMBLOCK_RECV_BITMAP_ENDING);
> > > + qemu_fflush(file);
> > > +
> > > + free(le_bitmap);
> > > +
> > > + if (qemu_file_get_error(file)) {
> > > + return qemu_file_get_error(file);
> > > + }
> > > +
> > > + return size + sizeof(size);
> > > +}
> > > +
> > > /*
> > > * An outstanding page request, on the source, having been received
> > > * and queued
> > > @@ -2706,6 +2770,83 @@ static int ram_load(QEMUFile *f, void *opaque, int
> > > version_id)
> > > return ret;
> > > }
> > >
> > > +/*
> > > + * Read the received bitmap, revert it as the initial dirty bitmap.
> > > + * This is only used when the postcopy migration is paused but wants
> > > + * to resume from a middle point.
> > > + */
> > > +int ram_dirty_bitmap_reload(MigrationState *s, RAMBlock *block)
> > > +{
> > > + int ret = -EINVAL;
> > > + QEMUFile *file = s->rp_state.from_dst_file;
> > > + unsigned long *le_bitmap, nbits = block->used_length >>
> > > TARGET_PAGE_BITS;
> > > + uint64_t local_size = nbits / 8;
> > > + uint64_t size, end_mark;
> > > +
> > > + if (s->state != MIGRATION_STATUS_POSTCOPY_RECOVER) {
> > > + error_report("%s: incorrect state %s", __func__,
> > > + MigrationStatus_lookup[s->state]);
> > > + return -EINVAL;
> > > + }
> > > +
> > > + /*
> > > + * Note: see comments in ramblock_recv_bitmap_send() on why we
> > > + * need the endianess convertion, and the paddings.
> > > + */
> > > + local_size = ROUND_UP(local_size, 8);
> > > +
> > > + /* Add addings */
> > > + le_bitmap = bitmap_new(nbits + BITS_PER_LONG);
> > > +
> > > + size = qemu_get_be64(file);
> > > +
> > > + /* The size of the bitmap should match with our ramblock */
> > > + if (size != local_size) {
> > > + error_report("%s: ramblock '%s' bitmap size mismatch "
> > > + "(0x%lx != 0x%lx)", __func__, block->idstr,
> > > + size, local_size);
> >
> > You need to use PRIx64 formatters there - %lx isn't portable.
>
> Yes. Fixing.
>
> >
> > > + ret = -EINVAL;
> > > + goto out;
> > > + }
> > > +
> > > + size = qemu_get_buffer(file, (uint8_t *)le_bitmap, local_size);
> > > + end_mark = qemu_get_be64(file);
> > > +
> > > + ret = qemu_file_get_error(file);
> > > + if (ret || size != local_size) {
> > > + error_report("%s: read bitmap failed for ramblock '%s': %d",
> > > + __func__, block->idstr, ret);
> >
> > You might like to include size/local_size in the error.
>
> Will do. Thanks,
>
> --
> Peter Xu
--
Dr. David Alan Gilbert / dgilb...@redhat.com / Manchester, UK
