Previously posted series patches: http://lists.nongnu.org/archive/html/qemu-devel/2017-03/msg02044.html
This series helps to optimize the I/O performance of VMDK driver. Patch 1 helps us to refactor and introduce some new helper functions. Patch 2 performs a simple function re-naming task. Patch 3 introduces two new functions to make loading of metadata tables easier and avoid code duplication. Patch 4 adds two new functions to help us allocate multiple clusters according to the size requested, perform COW if required and return the offset of the first newly allocated cluster. Patch 5 performs a simple function re-naming task and re-factors it to make use of new metadata functions to avoid code duplication. Patch 6 helps to allocate multiple clusters by making use of the new cluster allocation functions and sets bytes requested in one cycle to be not more than the extent size. Patch 7 changes the metadata update code to update the L2 tables for multiple clusters at once. Optimization test results: This patch series improves 128 KB sequential write performance to an empty VMDK file by 29%. Benchmark command: ./qemu-img bench -w -c 1024 -s 128K -d 1 -t none -f vmdk test.vmdk Note: These patches pass all 41/41 tests suitable for the VMDK driver. Changes in v2: - segregate the ugly Patch 1 in v1 into 6 readable and sensible patches - include benchmark test results in v2 Ashijeet Acharya (7): vmdk: Refactor and introduce new helper functions vmdk: Rename get_whole_cluster() to vmdk_perform_cow() vmdk: Factor out metadata loading code out of get_cluster_offset() vmdk: New functions to allocate multiple clusters and cluster offset vmdk: Rename get_cluster_offset() to vmdk_get_cluster_offset() vmdk: Allocate multiple clusters at once vmdk: Update metadata for multiple clusters block/vmdk.c | 595 ++++++++++++++++++++++++++++++++++++++++++++--------------- 1 file changed, 443 insertions(+), 152 deletions(-) -- 2.6.2
