lidavidm commented on a change in pull request #7022:
URL: https://github.com/apache/arrow/pull/7022#discussion_r413990293
##########
File path: cpp/src/arrow/io/caching.h
##########
@@ -27,6 +27,44 @@
namespace arrow {
namespace io {
+
+struct ARROW_EXPORT CacheOptions {
+ static constexpr double kDefaultIdealBandwidthUtilizationFrac = 0.9;
+ static constexpr int64_t kDefaultMaxIdealRequestSizeMib = 64;
+
+ /// /brief The maximum distance in bytes between two consecutive
+ /// ranges; beyond this value, ranges are not combined
+ int64_t hole_size_limit;
+ /// /brief The maximum size in bytes of a combined range; if
+ /// combining two consecutive ranges would produce a range of a
+ /// size greater than this, they are not combined
+ int64_t range_size_limit;
+
+ bool operator==(const CacheOptions& other) const {
+ return hole_size_limit == other.hole_size_limit &&
+ range_size_limit == other.range_size_limit;
+ }
+
+ /// \brief Construct CacheOptions from S3 storage metrics.
+ ///
+ /// \param[in] time_to_first_byte_millis Seek-time or Time-To-First-Byte
(TTFB) in
+ /// milliseconds, also called call setup latency of a new S3 request.
+ /// The value is a positive integer.
+ /// \param[in] transfer_bandwidth_mib_per_sec Data transfer Bandwidth (BW)
in MiB/sec.
+ /// The value is a positive integer.
+ /// \param[in] ideal_bandwidth_utilization_frac Transfer bandwidth
utilization fraction
+ /// (per connection) to maximize the net data load.
+ /// The value is a positive double precision number less than or equal to
1.
+ /// \param[in] max_ideal_request_size_mib The maximum single data request
size (in MiB)
+ /// to maximize the net data load.
+ /// The value is a positive integer.
+ /// \return A new instance of CacheOptions.
+ static CacheOptions MakeFromS3Metrics(
Review comment:
This might be better named 'NetworkMetrics' or something along those
lines; it's not specific to S3 and would be likely be useful for the
in-progress Google Cloud Storage filesystem, and perhaps others.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
