ping 02.04.2019 18:37, Vladimir Sementsov-Ogievskiy wrote: > v5: rebase on master, some conflicts resolved due to data-file feature > > 01: new patch, just move test from cover letter to a file. I really hope that > it > will not hang the whole series, so, if we don't want it as is or with > really > tiny improvements, I'd prefer to skip it and queue 02-10 first. > 09: "true" parameter added to moved qcow2_pre_write_overlap_check() call due > to > rebase on master (both before and after patch). Seems OK, so keep > Alberto's r-b. > > performance: > > after 01: > # ./tests/perf/block/qcow2/convert-to-encrypted /ssd/src.raw > /ssd/dst.enc.qcow2 > 14.18 > # ./tests/perf/block/qcow2/convert-to-encrypted /ssd/src.raw > /ssd/dst.enc.qcow2 -W > 13.77 > > after 10: > # ./tests/perf/block/qcow2/convert-to-encrypted /ssd/src.raw > /ssd/dst.enc.qcow2 > 14.35 > # ./tests/perf/block/qcow2/convert-to-encrypted /ssd/src.raw > /ssd/dst.enc.qcow2 -W > 5.62 > > Vladimir Sementsov-Ogievskiy (10): > tests/perf: Test qemu-img convert from raw to encrypted qcow2 > qcow2.h: add missing include > qcow2: add separate file for threaded data processing functions > qcow2-threads: use thread_pool_submit_co > qcow2-threads: qcow2_co_do_compress: protect queuing by mutex > qcow2-threads: split out generic path > qcow2: qcow2_co_preadv: improve locking > qcow2: qcow2_co_preadv: skip using hd_qiov when possible > qcow2: bdrv_co_pwritev: move encryption code out of the lock > qcow2: do encryption in threads > > block/qcow2.h | 20 +- > block/qcow2-bitmap.c | 1 - > block/qcow2-cache.c | 1 - > block/qcow2-cluster.c | 8 +- > block/qcow2-refcount.c | 1 - > block/qcow2-snapshot.c | 1 - > block/qcow2-threads.c | 268 +++++++++++++++++++ > block/qcow2.c | 275 ++++---------------- > block/Makefile.objs | 2 +- > tests/perf/block/qcow2/convert-to-encrypted | 48 ++++ > 10 files changed, 389 insertions(+), 236 deletions(-) > create mode 100644 block/qcow2-threads.c > create mode 100755 tests/perf/block/qcow2/convert-to-encrypted >
-- Best regards, Vladimir
