[v7,0/6] 9pfs: readdir optimization

Message

Christian Schoenebeck July 19, 2020, 1:43 p.m. UTC

As previously mentioned, I was investigating performance issues with 9pfs.
Raw file read/write of 9pfs is actually quite good, provided that client
picked a reasonable high msize (maximum message size). I would recommend
to log a warning on 9p server side if a client attached with a small msize
that would cause performance issues for that reason.

However there are other aspects where 9pfs currently performs suboptimally,
especially readdir handling of 9pfs is extremely slow, a simple readdir
request of a guest typically blocks for several hundred milliseconds or
even several seconds, no matter how powerful the underlying hardware is.
The reason for this performance issue: latency.
Currently 9pfs is heavily dispatching a T_readdir request numerous times
between main I/O thread and a background I/O thread back and forth; in fact
it is actually hopping between threads even multiple times for every single
directory entry during T_readdir request handling which leads in total to
huge latencies for a single T_readdir request.

This patch series aims to address this severe performance issue of 9pfs
T_readdir request handling. The actual performance optimization is patch 4.

v6->v7:

  * Rebased to master: SHA-1 b442119329

  * Handle directory seeking more consistently by doing it in
    do_readdir_many() instead of in v9fs_readdir() [patch 3], [patch 4].

  * Updated API doc on v9fs_co_readdir_many(): make it clear that
    v9fs_free_dirents() must always be called, including error cases
    [patch 3].

  * New patch: use different lock type for 9p2000.u vs. 9p2000.L
    [patch 5].

Unchanged patches: [patch 1], [patch 2], [patch 6].

Message-ID of previous version (v6):
  [e-mail]

Message-ID of version with performance benchmark (v4):
  [e-mail]

Christian Schoenebeck (6):
  tests/virtio-9p: added split readdir tests
  9pfs: make v9fs_readdir_response_size() public
  9pfs: add new function v9fs_co_readdir_many()
  9pfs: T_readdir latency optimization
  9pfs: differentiate readdir lock between 9P2000.u vs. 9P2000.L
  9pfs: clarify latency of v9fs_co_run_in_worker()

 hw/9pfs/9p.c                 | 144 ++++++++++++-------------
 hw/9pfs/9p.h                 |  50 ++++++++-
 hw/9pfs/codir.c              | 196 +++++++++++++++++++++++++++++++++--
 hw/9pfs/coth.h               |  15 ++-
 tests/qtest/virtio-9p-test.c | 108 +++++++++++++++++++
 5 files changed, 419 insertions(+), 94 deletions(-)