Re: [PATCH v14 0/5] UFFD write-tracking migration/snapshots

["Dr. David Alan Gilbert" <dgilbert@redhat.com>]

* Andrey Gruzdev (andrey.gruzdev@virtuozzo.com) wrote:
> This patch series is a kind of 'rethinking' of Denis Plotnikov's ideas he's
> implemented in his series '[PATCH v0 0/4] migration: add background snapshot'.
> 
> Currently the only way to make (external) live VM snapshot is using existing
> dirty page logging migration mechanism. The main problem is that it tends to
> produce a lot of page duplicates while running VM goes on updating already
> saved pages. That leads to the fact that vmstate image size is commonly several
> times bigger then non-zero part of virtual machine's RSS. Time required to
> converge RAM migration and the size of snapshot image severely depend on the
> guest memory write rate, sometimes resulting in unacceptably long snapshot
> creation time and huge image size.
> 
> This series propose a way to solve the aforementioned problems. This is done
> by using different RAM migration mechanism based on UFFD write protection
> management introduced in v5.7 kernel. The migration strategy is to 'freeze'
> guest RAM content using write-protection and iteratively release protection
> for memory ranges that have already been saved to the migration stream.
> At the same time we read in pending UFFD write fault events and save those
> pages out-of-order with higher priority.
> 
> How to use:
> 1. Enable write-tracking migration capability
>    virsh qemu-monitor-command <domain> --hmp migrate_set_capability
>    background-snapshot on
> 
> 2. Start the external migration to a file
>    virsh qemu-monitor-command <domain> --hmp migrate exec:'cat > ./vm_state'
> 
> 3. Wait for the migration finish and check that the migration has completed.
> state.
> 
> 
> Changes v13->v14:
> 
> * 1. Removed unneeded '#ifdef CONFIG_LINUX' from [PATCH 1/5] where #ifdef'ed
> *    code was originally introduced. In v13 removed #ifdef's appeared to be
> *    a diff in [PATCH 4/5] on top of previous patches.

Thanks!

Dave

> Changes v12->v13:
> 
> * 1. Fixed codestyle problem for checkpatch.
> 
> Changes v11->v12:
> 
> * 1. Consolidated UFFD-related code under single #if defined(__linux__).
> * 2. Abandoned use of pre/post hooks in ram_find_and_save_block() in favour
> *    of more compact code fragment in ram_save_host_page().
> * 3. Refactored/simplified eBPF code in userfaultfd-wrlat.py script.
> 
> Changes v10->v11:
> 
> * 1. Updated commit messages.
> 
> Changes v9->v10:
> 
> * 1. Fixed commit message for [PATCH v9 1/5].
> 
> Changes v8->v9:
> 
> * 1. Fixed wrong cover letter subject.
> 
> Changes v7->v8:
> 
> * 1. Fixed coding style problems to pass checkpatch.
> 
> Changes v6->v7:
> 
> * 1. Fixed background snapshot on suspended guest: call qemu_system_wakeup_request()
> *    before stopping VM to make runstate transition valid.
> * 2. Disabled dirty page logging and log syn when 'background-snapshot' is enabled.
> * 3. Introduced 'userfaultfd-wrlat.py' script to analyze UFFD write fault latencies.
> 
> Changes v5->v6:
> 
> * 1. Consider possible hot pluggin/unpluggin of memory device - don't use static
> *    for write-tracking support level in migrate_query_write_tracking(), check
> *    each time when one tries to enable 'background-snapshot' capability.
> 
> Changes v4->v5:
> 
> * 1. Refactored util/userfaultfd.c code to support features required by postcopy.
> * 2. Introduced checks for host kernel and guest memory backend compatibility
> *    to 'background-snapshot' branch in migrate_caps_check().
> * 3. Switched to using trace_xxx instead of info_report()/error_report() for
> *    cases when error message must be hidden (probing UFFD-IO) or info may be
> *    really littering output if goes to stderr.
> * 4  Added RCU_READ_LOCK_GUARDs to the code dealing with RAM block list.
> * 5. Added memory_region_ref() for each RAM block being wr-protected.
> * 6. Reused qemu_ram_block_from_host() instead of custom RAM block lookup routine.
> * 7. Refused from using specific hwaddr/ram_addr_t in favour of void */uint64_t.
> * 8. Currently dropped 'linear-scan-rate-limiting' patch. The reason is that
> *    that choosen criteria for high-latency fault detection (i.e. timestamp of
> *    UFFD event fetch) is not representative enough for this task.
> *    At the moment it looks somehow like premature optimization effort.
> * 8. Dropped some unnecessary/unused code.
> 
> Andrey Gruzdev (5):
>   migration: introduce 'background-snapshot' migration capability
>   migration: introduce UFFD-WP low-level interface helpers
>   migration: support UFFD write fault processing in ram_save_iterate()
>   migration: implementation of background snapshot thread
>   migration: introduce 'userfaultfd-wrlat.py' script
> 
>  include/exec/memory.h        |   8 +
>  include/qemu/userfaultfd.h   |  35 ++++
>  migration/migration.c        | 357 ++++++++++++++++++++++++++++++++++-
>  migration/migration.h        |   4 +
>  migration/ram.c              | 303 ++++++++++++++++++++++++++++-
>  migration/ram.h              |   6 +
>  migration/savevm.c           |   1 -
>  migration/savevm.h           |   2 +
>  migration/trace-events       |   2 +
>  qapi/migration.json          |   7 +-
>  scripts/userfaultfd-wrlat.py | 122 ++++++++++++
>  util/meson.build             |   1 +
>  util/trace-events            |   9 +
>  util/userfaultfd.c           | 345 +++++++++++++++++++++++++++++++++
>  14 files changed, 1190 insertions(+), 12 deletions(-)
>  create mode 100644 include/qemu/userfaultfd.h
>  create mode 100755 scripts/userfaultfd-wrlat.py
>  create mode 100644 util/userfaultfd.c
> 
> -- 
> 2.25.1
> 
-- 
Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK