@cloudbitmaps/roaring 0.12.0 → 0.13.0

package/PRIVACY.md

@@ -125,8 +125,8 @@ after it returns, and re-run any erasure a rollback interrupted.
 
 Erasure and crypto-shred are **immediate in storage and immediate in the store whose verb performed them**, for
 every read that starts after the verb returns. A read already in progress in that store can still yield an erased id
-from a chunk it had requested before the verb ran: up to 8 chunks for `iterate` and `count`, and up to `concurrency`
-keys for a combine. They are not immediate in any *other* store, in the same process or another, and this library ships nothing that could
+from a chunk it had requested before the verb ran: up to 32 chunks for `iterate` and `count`, and up to `concurrency`
+keys (32 by default) for a combine. They are not immediate in any *other* store, in the same process or another, and this library ships nothing that could
 make them so — there is no daemon, no bus, and no connection between two stores that happen to point at the same
 bucket.
 

package/README.md

@@ -69,10 +69,10 @@ name.
 
 ## What it costs
 
-Measured against real S3 in `us-east-1`, with the pointer in the same bucket as the data: the median cold `intersect`
-of two 500,000-id segments sharing 100 of their 1,999 chunks made 206 GETs, **$82.40 per million**, requesting only
-the shared chunks. Inside the region it is expected at 204 GETs, $81.60 per million. Writing and publishing a segment
-is **$11.20 per million**, pointer included, from its measured requests at list prices. A cold `count()` is one pointer read: it reads no payload and no object.
+Measured against real S3 in `us-east-1`, from inside the region, with the pointer in the same bucket as the data: the median cold `intersect`
+of two 500,000-id segments sharing 100 of their 1,999 chunks made 204 GETs, **$81.60 per million**, requesting only
+the shared chunks, and took 492.69 ms from inside the region, by an engine whose combine window held 8 chunk keys (this release opens it 8 wide and widens it to 32, so fewer rounds are expected; not yet measured). A segment's first `store.load()`
+is **$11.60 per million**, pointer included, from its measured requests at list prices. A cold `count()` is one pointer read: it reads no payload and no object.
 
 The trade is stated plainly. A membership check that misses the cache costs a ranged GET against object storage,
 where an in-process store costs a memory read. If you need sub-millisecond answers on a working set that fits a

package/dist/bin/export-segments.js

@@ -1981,7 +1981,7 @@ var Segment = class _Segment {
    * Chunk-skipping intersection: stream the ids in **this** segment AND every segment in `others`, ascending.
    * Fetches only the Storage chunks present in *all* operands (a key absent from any operand contributes nothing
    * and is never downloaded), streaming under a bounded in-flight window — so the Storage footprint stays small
-   * (Lambda-friendly) regardless of segment size. Pass `concurrency` to tune that window (a positive integer).
+   * (Lambda-friendly) regardless of segment size. Pass `concurrency` to tune that window (a positive integer, 32 by default).
    * AND is commutative, so `a.intersect([b])` and `b.intersect([a])` yield the same ids. Pass `budget` to
    * override the store's per-op denial-of-wallet budget for this call (or `false` to lift it).
    */