2026-09-14 07:40:42 +00:00
|
|
|
|
# PackFS vs. the host filesystem: benchmark results
|
|
|
|
|
|
|
2026-09-14 08:09:49 +00:00
|
|
|
|
**Status: the O(n²) bulk create/unlink finding this document originally
|
|
|
|
|
|
reported has been fixed.** The index (`UpperSnapshot`) is now a persistent
|
2026-09-14 08:53:04 +00:00
|
|
|
|
treap instead of a flat sorted array (`src/upper.c`; see `CLAUDE.md`'s
|
|
|
|
|
|
"Known performance characteristics"). This document keeps the original
|
|
|
|
|
|
run's numbers as the historical record of the problem — per this project's
|
|
|
|
|
|
own documentation standard, a correction extends the record rather than
|
|
|
|
|
|
erasing it — and adds the post-fix run's numbers alongside them, in full,
|
|
|
|
|
|
not a curated subset of either. **Read "Resolution" below before drawing
|
|
|
|
|
|
conclusions from the "Before" tables**, which describe a version of the
|
|
|
|
|
|
index this codebase no longer has.
|
2026-09-14 08:09:49 +00:00
|
|
|
|
|
|
|
|
|
|
This document reports the results of `bench/bench.c` (`make bench`), each
|
|
|
|
|
|
run once on the environment described below. These are single runs, not a
|
|
|
|
|
|
statistically-averaged series — treat the numbers as illustrative of *shape*
|
|
|
|
|
|
(which operations are faster, by roughly what factor, and why) more than as
|
|
|
|
|
|
precise absolute figures for a different machine. The methodology, including
|
|
|
|
|
|
exactly what each backend label measures, is documented in `bench/bench.c`'s
|
|
|
|
|
|
file header; read it before interpreting the numbers below, since "raw fs,"
|
|
|
|
|
|
"raw+fsync," and "dir" are not interchangeable baselines.
|
2026-09-14 07:40:42 +00:00
|
|
|
|
|
2026-09-14 08:53:04 +00:00
|
|
|
|
Every table below reproduces every one of the 45 measurements each run's
|
|
|
|
|
|
`=== summary (45 measurements) ===` block reported — none omitted, none
|
|
|
|
|
|
combined — and the complete verbatim program output for both runs, exactly
|
|
|
|
|
|
as captured, is preserved in the two appendices at the end as the primary
|
|
|
|
|
|
source record.
|
|
|
|
|
|
|
2026-09-14 07:40:42 +00:00
|
|
|
|
## Environment
|
|
|
|
|
|
|
|
|
|
|
|
- Host: containerized, 12 logical CPUs (AMD Ryzen 5 3600), running under an
|
|
|
|
|
|
`overlay` root filesystem (`overlay` on `overlay`, per `mount`) — there is
|
|
|
|
|
|
no separate tmpfs at `/tmp` in this environment; every "raw fs" and `dir`
|
|
|
|
|
|
number below is against that container overlay filesystem, not a bare
|
|
|
|
|
|
disk or tmpfs. This matters most for the `fsync` numbers (see below).
|
|
|
|
|
|
- `N_SMALL` = 20,000 files × 128 bytes for the metadata-heavy suite;
|
|
|
|
|
|
`N_DIRS` = 4,000; concurrency = 8 threads × 4,000 ops; large files up to
|
|
|
|
|
|
64 MB. Full parameters are in `bench/bench.c`.
|
2026-09-14 08:53:04 +00:00
|
|
|
|
- Wall-clock time: 5m49s (before), 4m4s (after), almost entirely spent in
|
|
|
|
|
|
the single `raw+fsync` 20,000-file create test (~116s in both runs — this
|
|
|
|
|
|
cost is on the host's storage, not PackFS, and is within measurement noise
|
|
|
|
|
|
of identical before and after the fix, as expected, since that test never
|
|
|
|
|
|
touches PackFS's index at all).
|
2026-09-14 07:40:42 +00:00
|
|
|
|
|
2026-09-14 08:09:49 +00:00
|
|
|
|
## Resolution
|
|
|
|
|
|
|
2026-09-14 08:53:04 +00:00
|
|
|
|
The original run found bulk sequential `create`/`unlink`/`mkdir` on
|
2026-09-14 08:09:49 +00:00
|
|
|
|
`mem`/`dir` to be O(n²) in file count, because every structural write copied
|
|
|
|
|
|
the entire sorted entry array before publishing the next snapshot
|
|
|
|
|
|
(Section 5.3). `concept.md` itself names the trigger condition for
|
|
|
|
|
|
reconsidering that design — "a persistent (structurally shared) tree
|
|
|
|
|
|
structure is not required until this assumption is empirically violated" —
|
|
|
|
|
|
and the original run was exactly that violation, measured rather than
|
|
|
|
|
|
hypothesized.
|
|
|
|
|
|
|
|
|
|
|
|
The index was rewritten as a **persistent treap** (`src/upper.c`): a
|
|
|
|
|
|
structural write now builds only the O(log n) nodes on the path to the
|
|
|
|
|
|
change, sharing every other node (refcounted) with the snapshot it was
|
|
|
|
|
|
built from, instead of copying all n entries. The choice of treap over a
|
|
|
|
|
|
persistent AVL/red-black/weight-balanced tree, and the reasoning behind it,
|
|
|
|
|
|
is documented in `src/upper.c`'s comment above `struct TreapNode` and cited
|
|
|
|
|
|
there: Seidel & Aragon, "Randomized Search Trees" (1996), for the O(1)
|
|
|
|
|
|
amortized rotation count on both insert and delete (persistent balanced
|
|
|
|
|
|
trees that need O(log n) rotations pay a real, repeated allocation cost per
|
|
|
|
|
|
rotation, which a treap avoids); Liljenzin, "Confluently Persistent Sets and
|
|
|
|
|
|
Maps" (arXiv:1301.3388), for persistent treaps specifically as an MVCC
|
|
|
|
|
|
snapshot mechanism, which is this exact use case.
|
|
|
|
|
|
|
2026-09-14 08:53:04 +00:00
|
|
|
|
**Headline result, measured, same methodology as the original finding:**
|
2026-09-14 08:09:49 +00:00
|
|
|
|
|
|
|
|
|
|
| Category | Before | After | Speedup |
|
|
|
|
|
|
|---|---|---|---|
|
2026-09-14 08:53:04 +00:00
|
|
|
|
| create 20,000 files (mem) | 9.5565s / 2,093 ops/s | 0.0372s / 537,103 ops/s | **257x** |
|
|
|
|
|
|
| unlink 20,000 files (mem) | 10.5575s / 1,894 ops/s | 0.0320s / 625,437 ops/s | **330x** |
|
|
|
|
|
|
| mkdir 4,000 dirs (mem) | 0.3363s / 11,896 ops/s | 0.0052s / 771,085 ops/s | **65x** |
|
|
|
|
|
|
| rmdir 4,000 dirs (mem) | 0.3395s / 11,782 ops/s | 0.0045s / 898,169 ops/s | **75x** |
|
|
|
|
|
|
| create 20,000 files (dir) | 12.0367s / 1,662 ops/s | 1.1531s / 17,345 ops/s | **10x** |
|
|
|
|
|
|
| unlink 20,000 files (dir) | 10.1851s / 1,964 ops/s | 0.5146s / 38,864 ops/s | **20x** |
|
|
|
|
|
|
| concurrent create+read+unlink (mem) | 36.7261s / 2,614 ops/s | 0.2807s / 341,972 ops/s | **131x** |
|
2026-09-14 08:09:49 +00:00
|
|
|
|
|
|
|
|
|
|
`mem` now *beats* raw fs (not merely "no longer loses to it") at every one
|
|
|
|
|
|
of these: create is 27x faster than raw fs (was 9.5x slower), unlink is 15x
|
|
|
|
|
|
faster (was 22x slower), and the concurrent mixed workload is 22x faster
|
|
|
|
|
|
(was 6x slower) — the single-writer design's "optimizes for read-heavy
|
|
|
|
|
|
concurrent workloads" caveat from the original analysis (below) no longer
|
|
|
|
|
|
needs to exclude bulk-write workloads, because the write side is no longer
|
|
|
|
|
|
the bottleneck it was.
|
|
|
|
|
|
|
|
|
|
|
|
**The complexity-class change is confirmed quantitatively, the same way the
|
|
|
|
|
|
original O(n²) finding was** — not just "it got faster," which an unrelated
|
|
|
|
|
|
constant-factor optimization could also produce: `mkdir` at N=4,000 vs.
|
|
|
|
|
|
`create` at N=20,000 (same structural-write mechanism, 5x the N) now shows a
|
2026-09-14 08:53:04 +00:00
|
|
|
|
**7.15x** slowdown (0.0372s / 0.0052s). O(n) predicts 5.0x; O(n log n)
|
|
|
|
|
|
predicts 5.97x; the old O(n²) regime predicted, and measured, 25–28.4x.
|
|
|
|
|
|
7.15x lands close to the O(n log n) prediction (some excess is expected —
|
|
|
|
|
|
`create` writes bytes into a fresh `MutCell` and `mkdir` does not, a
|
|
|
|
|
|
constant-factor difference the pure index-complexity comparison doesn't
|
|
|
|
|
|
account for) and nowhere near quadratic. The index's asymptotic behavior
|
|
|
|
|
|
changed, not merely its constant factor.
|
2026-09-14 08:09:49 +00:00
|
|
|
|
|
2026-09-14 08:53:04 +00:00
|
|
|
|
Full output of both runs is reproduced verbatim in the appendices below and
|
|
|
|
|
|
is reproducible again with `make bench`; the correctness of the new index
|
|
|
|
|
|
under heavy randomized structural churn (non-sequential creates/deletes/
|
|
|
|
|
|
renames, nested directories, thousands of entries, cross-checked against an
|
|
|
|
|
|
independent reference model — not just "the benchmark ran fast without
|
|
|
|
|
|
crashing") is `tests/test_index_stress.c`, part of `make test`.
|
2026-09-14 08:09:49 +00:00
|
|
|
|
|
2026-09-14 08:53:04 +00:00
|
|
|
|
## Before: complete results (pre-fix; kept as the historical record — see "Resolution" above)
|
|
|
|
|
|
|
|
|
|
|
|
All 45 measurements from that run's summary block, none omitted or combined.
|
2026-09-14 07:40:42 +00:00
|
|
|
|
|
|
|
|
|
|
| Category | Backend | Time | Throughput | MB/s |
|
|
|
|
|
|
|---|---|---|---|---|
|
2026-09-14 08:53:04 +00:00
|
|
|
|
| create 20,000 files | mem | 9.5565s | 2,093 ops/s | 0.3 |
|
|
|
|
|
|
| create 20,000 files | raw fs | 1.0083s | 19,836 ops/s | 2.4 |
|
|
|
|
|
|
| create 20,000 files | raw+fsync | 116.1030s | 172 ops/s | 0.0 |
|
|
|
|
|
|
| read 20,000 files | mem | 0.0071s | 2,798,731 ops/s | 341.6 |
|
|
|
|
|
|
| read 20,000 files | raw fs | 0.1611s | 124,122 ops/s | 15.2 |
|
|
|
|
|
|
| stat 20,000 files | mem | 0.0062s | 3,223,599 ops/s | — |
|
|
|
|
|
|
| stat 20,000 files | raw fs | 0.0703s | 284,465 ops/s | — |
|
2026-09-14 07:40:42 +00:00
|
|
|
|
| readdir (20,000 entries) | mem | 0.0037s | 5,397,828 /s | — |
|
|
|
|
|
|
| readdir (20,000 entries) | raw fs | 0.0071s | 2,831,904 /s | — |
|
2026-09-14 08:53:04 +00:00
|
|
|
|
| create 20,000 files | dir | 12.0367s | 1,662 ops/s | 0.2 |
|
|
|
|
|
|
| read 20,000 files | dir | 0.1674s | 119,468 ops/s | 14.6 |
|
|
|
|
|
|
| stat 20,000 files | dir | 0.1516s | 131,937 ops/s | — |
|
|
|
|
|
|
| readdir (20,000 entries) | dir | 0.0028s | 7,058,003 /s | — |
|
|
|
|
|
|
| unlink 20,000 files | mem | 10.5575s | 1,894 ops/s | — |
|
|
|
|
|
|
| unlink 20,000 files | dir | 10.1851s | 1,964 ops/s | — |
|
|
|
|
|
|
| unlink 20,000 files | raw fs | 0.4782s | 41,823 ops/s | — |
|
|
|
|
|
|
| mkdir 4,000 dirs | mem | 0.3363s | 11,896 ops/s | — |
|
|
|
|
|
|
| rmdir 4,000 dirs | mem | 0.3395s | 11,782 ops/s | — |
|
|
|
|
|
|
| mkdir 4,000 dirs | dir | 0.5109s | 7,829 ops/s | — |
|
|
|
|
|
|
| rmdir 4,000 dirs | dir | 0.4892s | 8,177 ops/s | — |
|
|
|
|
|
|
| mkdir 4,000 dirs | raw fs | 0.1591s | 25,143 ops/s | — |
|
|
|
|
|
|
| rmdir 4,000 dirs | raw fs | 0.2119s | 18,876 ops/s | — |
|
|
|
|
|
|
| write 1MB | mem | 0.0001s | 6,687 ops/s | 6,687.1 |
|
|
|
|
|
|
| read 1MB | mem | 0.0000s | 50,941 ops/s | 50,941.4 |
|
|
|
|
|
|
| write 16MB | mem | 0.0138s | 72 ops/s | 1,157.8 |
|
|
|
|
|
|
| read 16MB | mem | 0.0010s | 1,015 ops/s | 16,240.8 |
|
|
|
|
|
|
| write 64MB | mem | 0.0566s | 18 ops/s | 1,129.8 |
|
|
|
|
|
|
| read 64MB | mem | 0.0034s | 292 ops/s | 18,705.5 |
|
|
|
|
|
|
| write 1MB | raw fs | 0.0004s | 2,685 ops/s | 2,685.4 |
|
|
|
|
|
|
| read 1MB | raw fs | 0.0001s | 16,584 ops/s | 16,583.7 |
|
|
|
|
|
|
| write 16MB | raw fs | 0.0047s | 213 ops/s | 3,412.8 |
|
|
|
|
|
|
| read 16MB | raw fs | 0.0010s | 960 ops/s | 15,363.8 |
|
|
|
|
|
|
| write 64MB | raw fs | 0.0186s | 54 ops/s | 3,435.6 |
|
|
|
|
|
|
| read 64MB | raw fs | 0.0047s | 213 ops/s | 13,635.3 |
|
|
|
|
|
|
| write 1MB | raw+fsync | 0.0087s | 116 ops/s | 115.5 |
|
|
|
|
|
|
| read 1MB | raw+fsync | 0.0001s | 8,857 ops/s | 8,857.4 |
|
|
|
|
|
|
| write 16MB | raw+fsync | 0.0840s | 12 ops/s | 190.5 |
|
|
|
|
|
|
| read 16MB | raw+fsync | 0.0013s | 796 ops/s | 12,737.8 |
|
|
|
|
|
|
| write 64MB | raw+fsync | 0.0891s | 11 ops/s | 718.3 |
|
|
|
|
|
|
| read 64MB | raw+fsync | 0.0045s | 220 ops/s | 14,096.3 |
|
|
|
|
|
|
| compact 20,000 entries to pack | pack | 0.0291s | 687,097 ops/s | 83.9 |
|
2026-09-14 07:40:42 +00:00
|
|
|
|
| random-read 20,000 entries | pack (mmap'd) | 0.0085s | 2,350,224 ops/s | 286.9 |
|
2026-09-14 08:53:04 +00:00
|
|
|
|
| random-read 20,000 entries | raw fs | 0.1767s | 113,198 ops/s | 13.8 |
|
|
|
|
|
|
| concurrent create+read+unlink (8×4,000×3) | mem | 36.7261s | 2,614 ops/s | — |
|
|
|
|
|
|
| concurrent create+read+unlink (8×4,000×3) | raw fs | 6.1202s | 15,686 ops/s | — |
|
2026-09-14 07:40:42 +00:00
|
|
|
|
|
2026-09-14 08:53:04 +00:00
|
|
|
|
## After: complete results (post-fix)
|
|
|
|
|
|
|
|
|
|
|
|
All 45 measurements from that run's summary block, none omitted or combined.
|
2026-09-14 08:09:49 +00:00
|
|
|
|
|
|
|
|
|
|
| Category | Backend | Time | Throughput | MB/s |
|
|
|
|
|
|
|---|---|---|---|---|
|
2026-09-14 08:53:04 +00:00
|
|
|
|
| create 20,000 files | mem | 0.0372s | 537,103 ops/s | 65.6 |
|
|
|
|
|
|
| create 20,000 files | raw fs | 1.0098s | 19,805 ops/s | 2.4 |
|
|
|
|
|
|
| create 20,000 files | raw+fsync | 116.0980s | 172 ops/s | 0.0 |
|
2026-09-14 08:09:49 +00:00
|
|
|
|
| read 20,000 files | mem | 0.0085s | 2,364,410 ops/s | 288.6 |
|
2026-09-14 08:53:04 +00:00
|
|
|
|
| read 20,000 files | raw fs | 0.1594s | 125,459 ops/s | 15.3 |
|
2026-09-14 08:09:49 +00:00
|
|
|
|
| stat 20,000 files | mem | 0.0073s | 2,723,001 ops/s | — |
|
2026-09-14 08:53:04 +00:00
|
|
|
|
| stat 20,000 files | raw fs | 0.0697s | 287,063 ops/s | — |
|
2026-09-14 08:09:49 +00:00
|
|
|
|
| readdir (20,000 entries) | mem | 0.0042s | 4,816,418 /s | — |
|
|
|
|
|
|
| readdir (20,000 entries) | raw fs | 0.0070s | 2,840,890 /s | — |
|
2026-09-14 08:53:04 +00:00
|
|
|
|
| create 20,000 files | dir | 1.1531s | 17,345 ops/s | 2.1 |
|
|
|
|
|
|
| read 20,000 files | dir | 0.1601s | 124,933 ops/s | 15.3 |
|
|
|
|
|
|
| stat 20,000 files | dir | 0.1509s | 132,517 ops/s | — |
|
|
|
|
|
|
| readdir (20,000 entries) | dir | 0.0039s | 5,128,581 /s | — |
|
|
|
|
|
|
| unlink 20,000 files | mem | 0.0320s | 625,437 ops/s | — |
|
|
|
|
|
|
| unlink 20,000 files | dir | 0.5146s | 38,864 ops/s | — |
|
|
|
|
|
|
| unlink 20,000 files | raw fs | 0.4923s | 40,628 ops/s | — |
|
2026-09-14 08:09:49 +00:00
|
|
|
|
| mkdir 4,000 dirs | mem | 0.0052s | 771,085 ops/s | — |
|
2026-09-14 08:53:04 +00:00
|
|
|
|
| rmdir 4,000 dirs | mem | 0.0045s | 898,169 ops/s | — |
|
|
|
|
|
|
| mkdir 4,000 dirs | dir | 0.1774s | 22,551 ops/s | — |
|
|
|
|
|
|
| rmdir 4,000 dirs | dir | 0.1118s | 35,778 ops/s | — |
|
|
|
|
|
|
| mkdir 4,000 dirs | raw fs | 0.1367s | 29,251 ops/s | — |
|
|
|
|
|
|
| rmdir 4,000 dirs | raw fs | 0.0901s | 44,388 ops/s | — |
|
|
|
|
|
|
| write 1MB | mem | 0.0003s | 2,937 ops/s | 2,937.3 |
|
|
|
|
|
|
| read 1MB | mem | 0.0000s | 49,752 ops/s | 49,751.7 |
|
|
|
|
|
|
| write 16MB | mem | 0.0108s | 93 ops/s | 1,483.0 |
|
|
|
|
|
|
| read 16MB | mem | 0.0010s | 1,050 ops/s | 16,796.7 |
|
|
|
|
|
|
| write 64MB | mem | 0.0589s | 17 ops/s | 1,086.8 |
|
|
|
|
|
|
| read 64MB | mem | 0.0033s | 304 ops/s | 19,475.8 |
|
|
|
|
|
|
| write 1MB | raw fs | 0.0004s | 2,463 ops/s | 2,462.6 |
|
|
|
|
|
|
| read 1MB | raw fs | 0.0001s | 15,738 ops/s | 15,738.2 |
|
|
|
|
|
|
| write 16MB | raw fs | 0.0046s | 217 ops/s | 3,477.6 |
|
|
|
|
|
|
| read 16MB | raw fs | 0.0011s | 945 ops/s | 15,121.6 |
|
|
|
|
|
|
| write 64MB | raw fs | 0.0183s | 55 ops/s | 3,495.7 |
|
|
|
|
|
|
| read 64MB | raw fs | 0.0050s | 198 ops/s | 12,702.5 |
|
|
|
|
|
|
| write 1MB | raw+fsync | 0.0235s | 43 ops/s | 42.5 |
|
|
|
|
|
|
| read 1MB | raw+fsync | 0.0001s | 9,816 ops/s | 9,816.4 |
|
|
|
|
|
|
| write 16MB | raw+fsync | 0.0228s | 44 ops/s | 701.5 |
|
|
|
|
|
|
| read 16MB | raw+fsync | 0.0012s | 832 ops/s | 13,316.1 |
|
|
|
|
|
|
| write 64MB | raw+fsync | 0.0825s | 12 ops/s | 775.9 |
|
|
|
|
|
|
| read 64MB | raw+fsync | 0.0057s | 176 ops/s | 11,254.5 |
|
|
|
|
|
|
| compact 20,000 entries to pack | pack | 0.0245s | 814,864 ops/s | 99.5 |
|
2026-09-14 08:09:49 +00:00
|
|
|
|
| random-read 20,000 entries | pack (mmap'd) | 0.0082s | 2,445,144 ops/s | 298.5 |
|
2026-09-14 08:53:04 +00:00
|
|
|
|
| random-read 20,000 entries | raw fs | 0.1657s | 120,709 ops/s | 14.7 |
|
|
|
|
|
|
| concurrent create+read+unlink (8×4,000×3) | mem | 0.2807s | 341,972 ops/s | — |
|
|
|
|
|
|
| concurrent create+read+unlink (8×4,000×3) | raw fs | 6.2980s | 15,243 ops/s | — |
|
2026-09-14 08:09:49 +00:00
|
|
|
|
|
|
|
|
|
|
Everything not involving bulk `mem`/`dir` structural writes (reads, `stat`,
|
|
|
|
|
|
`readdir`, large sequential I/O, pack random-access, compaction) is
|
2026-09-14 08:53:04 +00:00
|
|
|
|
unchanged within normal run-to-run noise, as the row-by-row comparison
|
|
|
|
|
|
above shows — the treap rewrite only touches the structural-write path
|
|
|
|
|
|
(Section 5.3), not content reads, content writes, or the pack format. The
|
|
|
|
|
|
`raw+fsync` create row is identical to three decimal places (116.1030s vs
|
|
|
|
|
|
116.0980s) precisely because it never touches PackFS at all.
|
2026-09-14 07:40:42 +00:00
|
|
|
|
|
|
|
|
|
|
## Analysis
|
|
|
|
|
|
|
2026-09-14 08:09:49 +00:00
|
|
|
|
The bullets below are preserved from the original run for the categories
|
|
|
|
|
|
the fix did not change (the "wins" and the non-structural-write "losses"),
|
2026-09-14 08:53:04 +00:00
|
|
|
|
with the historical O(n²) explanation kept as the record of what was found,
|
|
|
|
|
|
now marked where "Resolution" above supersedes it.
|
2026-09-14 08:09:49 +00:00
|
|
|
|
|
2026-09-14 07:40:42 +00:00
|
|
|
|
### Where PackFS wins clearly
|
|
|
|
|
|
|
|
|
|
|
|
- **Reads of small files: 20–23x faster than both raw fs and the `dir`
|
2026-09-14 08:09:49 +00:00
|
|
|
|
backend** (2.4M ops/s vs ~125K ops/s). No syscall per read — `mem`
|
|
|
|
|
|
reads are an expected-O(log n) treap lookup plus a `memcpy` out of an
|
2026-09-14 07:40:42 +00:00
|
|
|
|
already-resident buffer (Section 5.3, 9.1).
|
2026-09-14 08:09:49 +00:00
|
|
|
|
- **`stat`: ~10x faster than raw fs.** Same reason — no syscall, and the
|
|
|
|
|
|
index is sorted for expected-O(log n) lookup rather than requiring a
|
|
|
|
|
|
directory entry scan.
|
|
|
|
|
|
- **Random-access reads against a compacted pack: ~20x faster than raw fs**
|
|
|
|
|
|
(2.4M ops/s vs 121K ops/s), because the pack is one `mmap`'d file with a
|
2026-09-14 07:40:42 +00:00
|
|
|
|
binary-searchable index (Section 9.1), against 20,000 individual
|
|
|
|
|
|
`open`/`read`/`close` syscall triples on the raw-fs side. This is the
|
|
|
|
|
|
single result that most directly validates the architecture's stated
|
|
|
|
|
|
purpose — Section 3.2's claim that "random access is a flat table
|
|
|
|
|
|
lookup, not a linear scan or a directory-parse-then-seek" — under an
|
|
|
|
|
|
actual measured workload, not just by construction.
|
2026-09-14 08:09:49 +00:00
|
|
|
|
- **Compaction throughput**: ~100 MB/s / ~815K entries/s to serialize the
|
2026-09-14 07:40:42 +00:00
|
|
|
|
live tree into a fresh pack (Section 4.1 step 5) — not directly
|
|
|
|
|
|
comparable to any raw-fs operation, but fast enough that compacting a
|
2026-09-14 08:09:49 +00:00
|
|
|
|
20,000-file, 2.5 MB tree is not a practically-felt pause (25ms).
|
2026-09-14 08:53:04 +00:00
|
|
|
|
- **Bulk create/unlink/mkdir/rmdir: RESOLVED, now 10–330x faster than the
|
|
|
|
|
|
pre-fix `mem`/`dir` numbers, and (for `mem`) 15–27x faster than raw fs** —
|
|
|
|
|
|
see "Resolution" above; this used to be PackFS's clearest loss and is now
|
2026-09-14 08:09:49 +00:00
|
|
|
|
among its clearest wins.
|
2026-09-14 08:53:04 +00:00
|
|
|
|
- **Concurrent mixed create+read+unlink: RESOLVED, now 22x faster than raw
|
|
|
|
|
|
fs** (was 6x *slower* before the fix) — see "Resolution."
|
2026-09-14 07:40:42 +00:00
|
|
|
|
|
2026-09-14 08:09:49 +00:00
|
|
|
|
### Where raw fs still wins, and why that's expected, not a bug
|
2026-09-14 07:40:42 +00:00
|
|
|
|
|
2026-09-14 08:09:49 +00:00
|
|
|
|
- **`dir` backend `stat` is ~2.2x *slower* than raw fs `stat`** (133K ops/s
|
|
|
|
|
|
vs 287K ops/s) — because `pfs_dir_statat` (Section 6.2's containment)
|
2026-09-14 07:40:42 +00:00
|
|
|
|
resolves and opens the path via `openat2`/`O_NOFOLLOW`, then `fstat`s
|
|
|
|
|
|
the resulting fd, where a raw `stat()` call is a single syscall. This is
|
|
|
|
|
|
the direct, measured cost of path containment on the metadata path,
|
|
|
|
|
|
separate from and smaller than the containment cost paid on `open`
|
|
|
|
|
|
itself (which raw fs pays an equivalent single-syscall cost for anyway).
|
2026-09-14 08:09:49 +00:00
|
|
|
|
Unaffected by the index rewrite.
|
2026-09-14 07:40:42 +00:00
|
|
|
|
- **`raw+fsync` create is catastrophically slow on this environment**
|
2026-09-14 08:53:04 +00:00
|
|
|
|
(172 ops/s — 116 seconds for 20,000 files, ~5.8ms per `fsync`, identical
|
|
|
|
|
|
in both runs to three decimal places), because this container's overlay
|
|
|
|
|
|
filesystem has poor per-call `fsync` latency. This is a property of the
|
|
|
|
|
|
container, not of PackFS or of a bare disk — flagged in the environment
|
|
|
|
|
|
section above precisely so it isn't misread as "PackFS's journal must be
|
|
|
|
|
|
this slow too." The journal (Section 4.4) does call `fsync` once per
|
|
|
|
|
|
journaled write for the same durability reason raw `fsync` is slow here,
|
|
|
|
|
|
which is a real, inherited cost on this kind of storage — not a
|
|
|
|
|
|
PackFS-specific one. Unaffected by the index rewrite (the journal's cost
|
|
|
|
|
|
is per-write `fsync` latency, not index maintenance).
|
2026-09-14 08:09:49 +00:00
|
|
|
|
- **Large writes above ~16 MB: raw fs is faster than `mem`** (3,478–
|
|
|
|
|
|
3,496 MB/s vs 1,087–1,483 MB/s). Section 5.7's buffer-growth discipline
|
2026-09-14 07:40:42 +00:00
|
|
|
|
(allocate new, copy old + new, publish, retire old — never realloc in
|
|
|
|
|
|
place) means every capacity doubling re-copies everything written so
|
|
|
|
|
|
far; a plain unsynced `write()` to a real file only ever appends new
|
2026-09-14 08:09:49 +00:00
|
|
|
|
pages to the page cache, never re-copying prior ones. This is entirely
|
|
|
|
|
|
independent of the index structure (Section 5.7's buffer-growth
|
|
|
|
|
|
discipline governs a `MutCell`'s content buffer, not the index the
|
|
|
|
|
|
treap rewrite replaced) and is unaffected by this fix — the safety
|
|
|
|
|
|
property Section 5.7 requires (no reader can ever see a freed buffer)
|
|
|
|
|
|
still has a real, quantifiable cost for very large sequential writes,
|
|
|
|
|
|
traded for correctness under concurrent access that a plain in-place
|
|
|
|
|
|
realloc would not have.
|
2026-09-14 07:40:42 +00:00
|
|
|
|
|
2026-09-14 08:53:04 +00:00
|
|
|
|
## Appendix A: complete verbatim output, before the fix
|
|
|
|
|
|
|
|
|
|
|
|
Captured exactly as produced by `make bench` against the pre-fix (flat
|
|
|
|
|
|
array) index; reformatted into the tables above, but reproduced here
|
|
|
|
|
|
unedited as the primary source record.
|
|
|
|
|
|
|
|
|
|
|
|
```text
|
|
|
|
|
|
=== PackFS vs. host filesystem: benchmark ===
|
|
|
|
|
|
|
|
|
|
|
|
environment:
|
|
|
|
|
|
raw fs test root: /tmp/packfs_bench_raw_unzuwh
|
|
|
|
|
|
dir backend root: /tmp/packfs_bench_dir_MXB4CT
|
|
|
|
|
|
small files (N): 20000, 128 bytes each
|
|
|
|
|
|
directories (N): 4000
|
|
|
|
|
|
concurrency: 8 threads x 4000 ops (create+read+unlink)
|
|
|
|
|
|
large-file sizes: 1MB 16MB 64MB
|
|
|
|
|
|
NOTE: see the file header for what "raw fs" vs "raw+fsync" vs
|
|
|
|
|
|
"dir" actually measure — they are not interchangeable.
|
|
|
|
|
|
|
|
|
|
|
|
== 1. create N small files ==
|
|
|
|
|
|
create N small files mem 9.5565s 2093 ops/s 0.3 MB/s
|
|
|
|
|
|
create N small files raw fs 1.0083s 19836 ops/s 2.4 MB/s
|
|
|
|
|
|
create N small files raw+fsync 116.1030s 172 ops/s 0.0 MB/s
|
|
|
|
|
|
|
|
|
|
|
|
== 2. read N small files ==
|
|
|
|
|
|
read N small files mem 0.0071s 2798731 ops/s 341.6 MB/s
|
|
|
|
|
|
read N small files raw fs 0.1611s 124122 ops/s 15.2 MB/s
|
|
|
|
|
|
|
|
|
|
|
|
== 3. stat N files ==
|
|
|
|
|
|
stat N files mem 0.0062s 3223599 ops/s
|
|
|
|
|
|
stat N files raw fs 0.0703s 284465 ops/s
|
|
|
|
|
|
|
|
|
|
|
|
== 4. readdir ==
|
|
|
|
|
|
readdir (N entries) mem 0.0037s 5397828 ops/s
|
|
|
|
|
|
readdir (N entries) raw fs 0.0071s 2831904 ops/s
|
|
|
|
|
|
|
|
|
|
|
|
== 1b. create N small files (dir backend vs. what it wraps) ==
|
|
|
|
|
|
create N small files dir 12.0367s 1662 ops/s 0.2 MB/s
|
|
|
|
|
|
|
|
|
|
|
|
== 2b. read N small files (dir backend) ==
|
|
|
|
|
|
read N small files dir 0.1674s 119468 ops/s 14.6 MB/s
|
|
|
|
|
|
|
|
|
|
|
|
== 3b. stat N files (dir backend) ==
|
|
|
|
|
|
stat N files dir 0.1516s 131937 ops/s
|
|
|
|
|
|
|
|
|
|
|
|
== 4b. readdir (dir backend) ==
|
|
|
|
|
|
readdir (N entries) dir 0.0028s 7058003 ops/s
|
|
|
|
|
|
|
|
|
|
|
|
== 5. unlink N files ==
|
|
|
|
|
|
unlink N files mem 10.5575s 1894 ops/s
|
|
|
|
|
|
unlink N files dir 10.1851s 1964 ops/s
|
|
|
|
|
|
unlink N files raw fs 0.4782s 41823 ops/s
|
|
|
|
|
|
|
|
|
|
|
|
== 6. mkdir/rmdir N directories ==
|
|
|
|
|
|
mkdir N dirs mem 0.3363s 11896 ops/s
|
|
|
|
|
|
rmdir N dirs mem 0.3395s 11782 ops/s
|
|
|
|
|
|
mkdir N dirs dir 0.5109s 7829 ops/s
|
|
|
|
|
|
rmdir N dirs dir 0.4892s 8177 ops/s
|
|
|
|
|
|
mkdir N dirs raw fs 0.1591s 25143 ops/s
|
|
|
|
|
|
rmdir N dirs raw fs 0.2119s 18876 ops/s
|
|
|
|
|
|
|
|
|
|
|
|
== 7. large sequential write/read ==
|
|
|
|
|
|
write 1MB mem 0.0001s 6687 ops/s 6687.1 MB/s
|
|
|
|
|
|
read 1MB mem 0.0000s 50941 ops/s 50941.4 MB/s
|
|
|
|
|
|
write 16MB mem 0.0138s 72 ops/s 1157.8 MB/s
|
|
|
|
|
|
read 16MB mem 0.0010s 1015 ops/s 16240.8 MB/s
|
|
|
|
|
|
write 64MB mem 0.0566s 18 ops/s 1129.8 MB/s
|
|
|
|
|
|
read 64MB mem 0.0034s 292 ops/s 18705.5 MB/s
|
|
|
|
|
|
write 1MB raw fs 0.0004s 2685 ops/s 2685.4 MB/s
|
|
|
|
|
|
read 1MB raw fs 0.0001s 16584 ops/s 16583.7 MB/s
|
|
|
|
|
|
write 16MB raw fs 0.0047s 213 ops/s 3412.8 MB/s
|
|
|
|
|
|
read 16MB raw fs 0.0010s 960 ops/s 15363.8 MB/s
|
|
|
|
|
|
write 64MB raw fs 0.0186s 54 ops/s 3435.6 MB/s
|
|
|
|
|
|
read 64MB raw fs 0.0047s 213 ops/s 13635.3 MB/s
|
|
|
|
|
|
write 1MB raw+fsync 0.0087s 116 ops/s 115.5 MB/s
|
|
|
|
|
|
read 1MB raw+fsync 0.0001s 8857 ops/s 8857.4 MB/s
|
|
|
|
|
|
write 16MB raw+fsync 0.0840s 12 ops/s 190.5 MB/s
|
|
|
|
|
|
read 16MB raw+fsync 0.0013s 796 ops/s 12737.8 MB/s
|
|
|
|
|
|
write 64MB raw+fsync 0.0891s 11 ops/s 718.3 MB/s
|
|
|
|
|
|
read 64MB raw+fsync 0.0045s 220 ops/s 14096.3 MB/s
|
|
|
|
|
|
|
|
|
|
|
|
== 8. random-access read: mmap'd pack vs. raw fs ==
|
|
|
|
|
|
compact N entries to pack pack 0.0291s 687097 ops/s 83.9 MB/s
|
|
|
|
|
|
random-read N entries pack 0.0085s 2350224 ops/s 286.9 MB/s
|
|
|
|
|
|
random-read N entries raw fs 0.1767s 113198 ops/s 13.8 MB/s
|
|
|
|
|
|
|
|
|
|
|
|
== 9. concurrency (create+read+unlink) ==
|
|
|
|
|
|
concurrent create+read+unlink mem 36.7261s 2614 ops/s
|
|
|
|
|
|
concurrent create+read+unlink raw fs 6.1202s 15686 ops/s
|
|
|
|
|
|
|
|
|
|
|
|
=== summary (45 measurements) ===
|
|
|
|
|
|
category backend seconds throughput MB/s
|
|
|
|
|
|
create N small files mem 9.5565s 2093 ops/s 0.3 MB/s
|
|
|
|
|
|
create N small files raw fs 1.0083s 19836 ops/s 2.4 MB/s
|
|
|
|
|
|
create N small files raw+fsync 116.1030s 172 ops/s 0.0 MB/s
|
|
|
|
|
|
read N small files mem 0.0071s 2798731 ops/s 341.6 MB/s
|
|
|
|
|
|
read N small files raw fs 0.1611s 124122 ops/s 15.2 MB/s
|
|
|
|
|
|
stat N files mem 0.0062s 3223599 ops/s
|
|
|
|
|
|
stat N files raw fs 0.0703s 284465 ops/s
|
|
|
|
|
|
readdir (N entries) mem 0.0037s 5397828 ops/s
|
|
|
|
|
|
readdir (N entries) raw fs 0.0071s 2831904 ops/s
|
|
|
|
|
|
create N small files dir 12.0367s 1662 ops/s 0.2 MB/s
|
|
|
|
|
|
read N small files dir 0.1674s 119468 ops/s 14.6 MB/s
|
|
|
|
|
|
stat N files dir 0.1516s 131937 ops/s
|
|
|
|
|
|
readdir (N entries) dir 0.0028s 7058003 ops/s
|
|
|
|
|
|
unlink N files mem 10.5575s 1894 ops/s
|
|
|
|
|
|
unlink N files dir 10.1851s 1964 ops/s
|
|
|
|
|
|
unlink N files raw fs 0.4782s 41823 ops/s
|
|
|
|
|
|
mkdir N dirs mem 0.3363s 11896 ops/s
|
|
|
|
|
|
rmdir N dirs mem 0.3395s 11782 ops/s
|
|
|
|
|
|
mkdir N dirs dir 0.5109s 7829 ops/s
|
|
|
|
|
|
rmdir N dirs dir 0.4892s 8177 ops/s
|
|
|
|
|
|
mkdir N dirs raw fs 0.1591s 25143 ops/s
|
|
|
|
|
|
rmdir N dirs raw fs 0.2119s 18876 ops/s
|
|
|
|
|
|
write 1MB mem 0.0001s 6687 ops/s 6687.1 MB/s
|
|
|
|
|
|
read 1MB mem 0.0000s 50941 ops/s 50941.4 MB/s
|
|
|
|
|
|
write 16MB mem 0.0138s 72 ops/s 1157.8 MB/s
|
|
|
|
|
|
read 16MB mem 0.0010s 1015 ops/s 16240.8 MB/s
|
|
|
|
|
|
write 64MB mem 0.0566s 18 ops/s 1129.8 MB/s
|
|
|
|
|
|
read 64MB mem 0.0034s 292 ops/s 18705.5 MB/s
|
|
|
|
|
|
write 1MB raw fs 0.0004s 2685 ops/s 2685.4 MB/s
|
|
|
|
|
|
read 1MB raw fs 0.0001s 16584 ops/s 16583.7 MB/s
|
|
|
|
|
|
write 16MB raw fs 0.0047s 213 ops/s 3412.8 MB/s
|
|
|
|
|
|
read 16MB raw fs 0.0010s 960 ops/s 15363.8 MB/s
|
|
|
|
|
|
write 64MB raw fs 0.0186s 54 ops/s 3435.6 MB/s
|
|
|
|
|
|
read 64MB raw fs 0.0047s 213 ops/s 13635.3 MB/s
|
|
|
|
|
|
write 1MB raw+fsync 0.0087s 116 ops/s 115.5 MB/s
|
|
|
|
|
|
read 1MB raw+fsync 0.0001s 8857 ops/s 8857.4 MB/s
|
|
|
|
|
|
write 16MB raw+fsync 0.0840s 12 ops/s 190.5 MB/s
|
|
|
|
|
|
read 16MB raw+fsync 0.0013s 796 ops/s 12737.8 MB/s
|
|
|
|
|
|
write 64MB raw+fsync 0.0891s 11 ops/s 718.3 MB/s
|
|
|
|
|
|
read 64MB raw+fsync 0.0045s 220 ops/s 14096.3 MB/s
|
|
|
|
|
|
compact N entries to pack pack 0.0291s 687097 ops/s 83.9 MB/s
|
|
|
|
|
|
random-read N entries pack 0.0085s 2350224 ops/s 286.9 MB/s
|
|
|
|
|
|
random-read N entries raw fs 0.1767s 113198 ops/s 13.8 MB/s
|
|
|
|
|
|
concurrent create+read+unlink mem 36.7261s 2614 ops/s
|
|
|
|
|
|
concurrent create+read+unlink raw fs 6.1202s 15686 ops/s
|
|
|
|
|
|
|
|
|
|
|
|
real 5m49.507s
|
|
|
|
|
|
user 2m9.600s
|
|
|
|
|
|
sys 0m20.941s
|
|
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
|
|
## Appendix B: complete verbatim output, after the fix
|
|
|
|
|
|
|
|
|
|
|
|
Captured exactly as produced by `make bench` against the post-fix
|
|
|
|
|
|
(persistent treap) index; reformatted into the tables above, but reproduced
|
|
|
|
|
|
here unedited as the primary source record.
|
|
|
|
|
|
|
|
|
|
|
|
```text
|
|
|
|
|
|
=== PackFS vs. host filesystem: benchmark ===
|
|
|
|
|
|
|
|
|
|
|
|
environment:
|
|
|
|
|
|
raw fs test root: /tmp/packfs_bench_raw_fbOZ1b
|
|
|
|
|
|
dir backend root: /tmp/packfs_bench_dir_7tEOsC
|
|
|
|
|
|
small files (N): 20000, 128 bytes each
|
|
|
|
|
|
directories (N): 4000
|
|
|
|
|
|
concurrency: 8 threads x 4000 ops (create+read+unlink)
|
|
|
|
|
|
large-file sizes: 1MB 16MB 64MB
|
|
|
|
|
|
NOTE: see the file header for what "raw fs" vs "raw+fsync" vs
|
|
|
|
|
|
"dir" actually measure — they are not interchangeable.
|
|
|
|
|
|
|
|
|
|
|
|
== 1. create N small files ==
|
|
|
|
|
|
create N small files mem 0.0372s 537103 ops/s 65.6 MB/s
|
|
|
|
|
|
create N small files raw fs 1.0098s 19805 ops/s 2.4 MB/s
|
|
|
|
|
|
create N small files raw+fsync 116.0980s 172 ops/s 0.0 MB/s
|
|
|
|
|
|
|
|
|
|
|
|
== 2. read N small files ==
|
|
|
|
|
|
read N small files mem 0.0085s 2364410 ops/s 288.6 MB/s
|
|
|
|
|
|
read N small files raw fs 0.1594s 125459 ops/s 15.3 MB/s
|
|
|
|
|
|
|
|
|
|
|
|
== 3. stat N files ==
|
|
|
|
|
|
stat N files mem 0.0073s 2723001 ops/s
|
|
|
|
|
|
stat N files raw fs 0.0697s 287063 ops/s
|
|
|
|
|
|
|
|
|
|
|
|
== 4. readdir ==
|
|
|
|
|
|
readdir (N entries) mem 0.0042s 4816418 ops/s
|
|
|
|
|
|
readdir (N entries) raw fs 0.0070s 2840890 ops/s
|
|
|
|
|
|
|
|
|
|
|
|
== 1b. create N small files (dir backend vs. what it wraps) ==
|
|
|
|
|
|
create N small files dir 1.1531s 17345 ops/s 2.1 MB/s
|
|
|
|
|
|
|
|
|
|
|
|
== 2b. read N small files (dir backend) ==
|
|
|
|
|
|
read N small files dir 0.1601s 124933 ops/s 15.3 MB/s
|
|
|
|
|
|
|
|
|
|
|
|
== 3b. stat N files (dir backend) ==
|
|
|
|
|
|
stat N files dir 0.1509s 132517 ops/s
|
|
|
|
|
|
|
|
|
|
|
|
== 4b. readdir (dir backend) ==
|
|
|
|
|
|
readdir (N entries) dir 0.0039s 5128581 ops/s
|
|
|
|
|
|
|
|
|
|
|
|
== 5. unlink N files ==
|
|
|
|
|
|
unlink N files mem 0.0320s 625437 ops/s
|
|
|
|
|
|
unlink N files dir 0.5146s 38864 ops/s
|
|
|
|
|
|
unlink N files raw fs 0.4923s 40628 ops/s
|
|
|
|
|
|
|
|
|
|
|
|
== 6. mkdir/rmdir N directories ==
|
|
|
|
|
|
mkdir N dirs mem 0.0052s 771085 ops/s
|
|
|
|
|
|
rmdir N dirs mem 0.0045s 898169 ops/s
|
|
|
|
|
|
mkdir N dirs dir 0.1774s 22551 ops/s
|
|
|
|
|
|
rmdir N dirs dir 0.1118s 35778 ops/s
|
|
|
|
|
|
mkdir N dirs raw fs 0.1367s 29251 ops/s
|
|
|
|
|
|
rmdir N dirs raw fs 0.0901s 44388 ops/s
|
|
|
|
|
|
|
|
|
|
|
|
== 7. large sequential write/read ==
|
|
|
|
|
|
write 1MB mem 0.0003s 2937 ops/s 2937.3 MB/s
|
|
|
|
|
|
read 1MB mem 0.0000s 49752 ops/s 49751.7 MB/s
|
|
|
|
|
|
write 16MB mem 0.0108s 93 ops/s 1483.0 MB/s
|
|
|
|
|
|
read 16MB mem 0.0010s 1050 ops/s 16796.7 MB/s
|
|
|
|
|
|
write 64MB mem 0.0589s 17 ops/s 1086.8 MB/s
|
|
|
|
|
|
read 64MB mem 0.0033s 304 ops/s 19475.8 MB/s
|
|
|
|
|
|
write 1MB raw fs 0.0004s 2463 ops/s 2462.6 MB/s
|
|
|
|
|
|
read 1MB raw fs 0.0001s 15738 ops/s 15738.2 MB/s
|
|
|
|
|
|
write 16MB raw fs 0.0046s 217 ops/s 3477.6 MB/s
|
|
|
|
|
|
read 16MB raw fs 0.0011s 945 ops/s 15121.6 MB/s
|
|
|
|
|
|
write 64MB raw fs 0.0183s 55 ops/s 3495.7 MB/s
|
|
|
|
|
|
read 64MB raw fs 0.0050s 198 ops/s 12702.5 MB/s
|
|
|
|
|
|
write 1MB raw+fsync 0.0235s 43 ops/s 42.5 MB/s
|
|
|
|
|
|
read 1MB raw+fsync 0.0001s 9816 ops/s 9816.4 MB/s
|
|
|
|
|
|
write 16MB raw+fsync 0.0228s 44 ops/s 701.5 MB/s
|
|
|
|
|
|
read 16MB raw+fsync 0.0012s 832 ops/s 13316.1 MB/s
|
|
|
|
|
|
write 64MB raw+fsync 0.0825s 12 ops/s 775.9 MB/s
|
|
|
|
|
|
read 64MB raw+fsync 0.0057s 176 ops/s 11254.5 MB/s
|
|
|
|
|
|
|
|
|
|
|
|
== 8. random-access read: mmap'd pack vs. raw fs ==
|
|
|
|
|
|
compact N entries to pack pack 0.0245s 814864 ops/s 99.5 MB/s
|
|
|
|
|
|
random-read N entries pack 0.0082s 2445144 ops/s 298.5 MB/s
|
|
|
|
|
|
random-read N entries raw fs 0.1657s 120709 ops/s 14.7 MB/s
|
|
|
|
|
|
|
|
|
|
|
|
== 9. concurrency (create+read+unlink) ==
|
|
|
|
|
|
concurrent create+read+unlink mem 0.2807s 341972 ops/s
|
|
|
|
|
|
concurrent create+read+unlink raw fs 6.2980s 15243 ops/s
|
|
|
|
|
|
|
|
|
|
|
|
=== summary (45 measurements) ===
|
|
|
|
|
|
category backend seconds throughput MB/s
|
|
|
|
|
|
create N small files mem 0.0372s 537103 ops/s 65.6 MB/s
|
|
|
|
|
|
create N small files raw fs 1.0098s 19805 ops/s 2.4 MB/s
|
|
|
|
|
|
create N small files raw+fsync 116.0980s 172 ops/s 0.0 MB/s
|
|
|
|
|
|
read N small files mem 0.0085s 2364410 ops/s 288.6 MB/s
|
|
|
|
|
|
read N small files raw fs 0.1594s 125459 ops/s 15.3 MB/s
|
|
|
|
|
|
stat N files mem 0.0073s 2723001 ops/s
|
|
|
|
|
|
stat N files raw fs 0.0697s 287063 ops/s
|
|
|
|
|
|
readdir (N entries) mem 0.0042s 4816418 ops/s
|
|
|
|
|
|
readdir (N entries) raw fs 0.0070s 2840890 ops/s
|
|
|
|
|
|
create N small files dir 1.1531s 17345 ops/s 2.1 MB/s
|
|
|
|
|
|
read N small files dir 0.1601s 124933 ops/s 15.3 MB/s
|
|
|
|
|
|
stat N files dir 0.1509s 132517 ops/s
|
|
|
|
|
|
readdir (N entries) dir 0.0039s 5128581 ops/s
|
|
|
|
|
|
unlink N files mem 0.0320s 625437 ops/s
|
|
|
|
|
|
unlink N files dir 0.5146s 38864 ops/s
|
|
|
|
|
|
unlink N files raw fs 0.4923s 40628 ops/s
|
|
|
|
|
|
mkdir N dirs mem 0.0052s 771085 ops/s
|
|
|
|
|
|
rmdir N dirs mem 0.0045s 898169 ops/s
|
|
|
|
|
|
mkdir N dirs dir 0.1774s 22551 ops/s
|
|
|
|
|
|
rmdir N dirs dir 0.1118s 35778 ops/s
|
|
|
|
|
|
mkdir N dirs raw fs 0.1367s 29251 ops/s
|
|
|
|
|
|
rmdir N dirs raw fs 0.0901s 44388 ops/s
|
|
|
|
|
|
write 1MB mem 0.0003s 2937 ops/s 2937.3 MB/s
|
|
|
|
|
|
read 1MB mem 0.0000s 49752 ops/s 49751.7 MB/s
|
|
|
|
|
|
write 16MB mem 0.0108s 93 ops/s 1483.0 MB/s
|
|
|
|
|
|
read 16MB mem 0.0010s 1050 ops/s 16796.7 MB/s
|
|
|
|
|
|
write 64MB mem 0.0589s 17 ops/s 1086.8 MB/s
|
|
|
|
|
|
read 64MB mem 0.0033s 304 ops/s 19475.8 MB/s
|
|
|
|
|
|
write 1MB raw fs 0.0004s 2463 ops/s 2462.6 MB/s
|
|
|
|
|
|
read 1MB raw fs 0.0001s 15738 ops/s 15738.2 MB/s
|
|
|
|
|
|
write 16MB raw fs 0.0046s 217 ops/s 3477.6 MB/s
|
|
|
|
|
|
read 16MB raw fs 0.0011s 945 ops/s 15121.6 MB/s
|
|
|
|
|
|
write 64MB raw fs 0.0183s 55 ops/s 3495.7 MB/s
|
|
|
|
|
|
read 64MB raw fs 0.0050s 198 ops/s 12702.5 MB/s
|
|
|
|
|
|
write 1MB raw+fsync 0.0235s 43 ops/s 42.5 MB/s
|
|
|
|
|
|
read 1MB raw+fsync 0.0001s 9816 ops/s 9816.4 MB/s
|
|
|
|
|
|
write 16MB raw+fsync 0.0228s 44 ops/s 701.5 MB/s
|
|
|
|
|
|
read 16MB raw+fsync 0.0012s 832 ops/s 13316.1 MB/s
|
|
|
|
|
|
write 64MB raw+fsync 0.0825s 12 ops/s 775.9 MB/s
|
|
|
|
|
|
read 64MB raw+fsync 0.0057s 176 ops/s 11254.5 MB/s
|
|
|
|
|
|
compact N entries to pack pack 0.0245s 814864 ops/s 99.5 MB/s
|
|
|
|
|
|
random-read N entries pack 0.0082s 2445144 ops/s 298.5 MB/s
|
|
|
|
|
|
random-read N entries raw fs 0.1657s 120709 ops/s 14.7 MB/s
|
|
|
|
|
|
concurrent create+read+unlink mem 0.2807s 341972 ops/s
|
|
|
|
|
|
concurrent create+read+unlink raw fs 6.2980s 15243 ops/s
|
|
|
|
|
|
|
|
|
|
|
|
real 4m3.827s
|
|
|
|
|
|
user 0m1.039s
|
|
|
|
|
|
sys 0m19.841s
|
|
|
|
|
|
```
|
|
|
|
|
|
|
2026-09-14 07:40:42 +00:00
|
|
|
|
## Reproducing
|
|
|
|
|
|
|
|
|
|
|
|
```sh
|
|
|
|
|
|
make bench
|
|
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
|
|
Takes several minutes on a similarly slow-`fsync` environment, dominated
|
|
|
|
|
|
by the `raw+fsync` create test; expect well under a minute on a host with
|
|
|
|
|
|
normal disk or tmpfs `fsync` latency.
|
