diff options
| author | Stefan Boberg <[email protected]> | 2025-10-10 18:09:53 +0200 |
|---|---|---|
| committer | GitHub Enterprise <[email protected]> | 2025-10-10 18:09:53 +0200 |
| commit | c4801320150ea0c492cf343d490a0a339432f060 (patch) | |
| tree | d3013ef82c1707e38db3abac94d1fec0ca352394 /src/zenstore/compactcas.cpp | |
| parent | shorten thread pool names for Linux which has a limit of 15 characters (#563) (diff) | |
| download | zen-c4801320150ea0c492cf343d490a0a339432f060.tar.xz zen-c4801320150ea0c492cf343d490a0a339432f060.zip | |
add ability to limit concurrency (#565)
effective concurrency in zenserver can be limited via the `--corelimit=<N>` option on the command line. Any value passed in here will be used instead of the return value from `std::thread::hardware_concurrency()` if it is lower.
* added --corelimit option to zenserver
* made sure thread pools are configured lazily and not during global init
* added log output indicating effective and HW concurrency
* added change log entry
* removed debug logging from ZenEntryPoint::Run()
also removed main thread naming on Linux since it makes the output from `top` and similar tools confusing (it shows `main` instead of `zenserver`)
Diffstat (limited to 'src/zenstore/compactcas.cpp')
| -rw-r--r-- | src/zenstore/compactcas.cpp | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/src/zenstore/compactcas.cpp b/src/zenstore/compactcas.cpp index 5cc4dad54..bf843171e 100644 --- a/src/zenstore/compactcas.cpp +++ b/src/zenstore/compactcas.cpp @@ -1722,7 +1722,7 @@ TEST_CASE("compactcas.restart") { uint64_t ExpectedSize = 0; - WorkerThreadPool ThreadPool(Max(std::thread::hardware_concurrency() - 1u, 2u), "put"); + WorkerThreadPool ThreadPool(Max(GetHardwareConcurrency() - 1u, 2u), "put"); auto GenerateChunks = [&](CasContainerStrategy& Cas, size_t ChunkCount, uint64_t ChunkSize, std::vector<IoHash>& Hashes) { Latch WorkLatch(1); @@ -1959,7 +1959,7 @@ TEST_CASE("compactcas.restart") TEST_CASE("compactcas.iteratechunks") { std::atomic<size_t> WorkCompleted = 0; - WorkerThreadPool ThreadPool(Max(std::thread::hardware_concurrency() - 1u, 2u), "put"); + WorkerThreadPool ThreadPool(Max(GetHardwareConcurrency() - 1u, 2u), "put"); const uint64_t kChunkSize = 1048 + 395; const size_t kChunkCount = 63840; @@ -2035,7 +2035,7 @@ TEST_CASE("compactcas.iteratechunks") WorkLatch.Wait(); } - WorkerThreadPool BatchWorkerPool(Max(std::thread::hardware_concurrency() - 1u, 2u), "fetch"); + WorkerThreadPool BatchWorkerPool(Max(GetHardwareConcurrency() - 1u, 2u), "fetch"); { std::vector<std::atomic<bool>> FetchedFlags(Hashes.size()); std::atomic<uint64_t> FetchedSize = 0; |