Revision 2a42e3eeb5b1a4b157b1ef6df76e69912ffa94e2 authored by Mark Callaghan on 11 October 2022, 20:43:20 UTC, committed by Mark Callaghan on 11 October 2022, 20:43:20 UTC
Summary: This has several small improvements. benchmark.sh * add BYTES_PER_SYNC as an env variable * use --prepopulate_block_cache when O_DIRECT is used * use --undefok to list options that don't work for all 7.x releases * print "failure" in report.tsv when a benchmark fails * parse the slightly different throughput line used by db_bench for multireadrandom * remove the trailing comma for BlobDB size before printing it in report.tsv * use the last line of the output from /bin/time as there can be more than one line when db_bench has a non-zero exit * fix more bash lint warnings * add ",stats" to the --benchmark=... lines to get stats at the end of each benchmark benchmark_compare.sh * run revrange immediately after fillseq to let compaction debt get removed * add --multiread_batched when --benchmarks=multireadrandom is used * use --benchmarks=overwriteandwait when supported to get a more accurate measure of write-amp Test Plan: Run it for leveled, universal and BlobDB Reviewers: Subscribers: Tasks: Tags:
1 parent 5a5f21c
DUMP_FORMAT.md
## RocksDB dump format
The version 1 RocksDB dump format is fairly simple:
1) The dump starts with the magic 8 byte identifier "ROCKDUMP"
2) The magic is followed by an 8 byte big-endian version which is 0x00000001.
3) Next are arbitrarily sized chunks of bytes prepended by 4 byte little endian number indicating how large each chunk is.
4) The first chunk is special and is a json string indicating some things about the creation of this dump. It contains the following keys:
* database-path: The path of the database this dump was created from.
* hostname: The hostname of the machine where the dump was created.
* creation-time: Unix seconds since epoc when this dump was created.
5) Following the info dump the slices paired into are key/value pairs.
Computing file changes ...
