| Commit message (Collapse) | Author | Age | Files | Lines |
|---|
| |
|
|
|
|
|
|
|
|
|
|
| |
091 measures four queries on pgbench's tables of 100,000 accounts, the
same rows and answers on Pure (registered queries, HTTP and JSON
included) and SQLite 3.46.1, through each step: items field by field in
leaves, folds and filters a leaf at a time, and one pass answering a fold
in a column for every row. Per-branch totals went from 398 ms to 4.9 ms
(SQLite 45, 14.3 with a DBA's indexes), a three-table join from 3.3 to
0.48 ms (1.47), and each rich account's rank from 9.2 s to 6.8 ms
(2.84 s, 7.6 ms with an index); counting accounts in credit takes 1.05 ms
where an index lets SQLite count 0.16 ms. Pure declares no index.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
benchmarks/bank/bank.aup keeps accounts, tellers and branches as keyed
lists and a history list; a transfer changes a row of each and appends a
history row in one event, as pgbench's TPC-B-like transaction does in
SQL. run.py makes a scale's rows and drives transfers through the load
generator's new transfer kind; sqlite-bank.c runs the same tables and
SQL on SQLite 3.46.1, a connection a thread, WAL.
With lists as trees, transfers run at 30.5k a second on 1,000 accounts
and 24.5k on 100,000 (RAM store, one connection thread, HTTP and JSON
included), where they ran at 3.2k on 30,000 before. Durable on the SD
card, Pure makes 1,339 a second and SQLite with synchronous=FULL 84 to
153. SQLite in process with no HTTP makes about 40k in RAM: recorded as
it is, with the write amplification of 100,000-row tables on the card
and ad hoc queries as what comes next.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
The roadmap's E2EE messenger made of the runtime's general parts, with
no messenger code in it: sealed, authenticated sessions between nodes
(086, 088), Vega on each node's display as a surface (design 010), the
app in Vega's examples. Vega's check runs two nodes through a recording
relay: a line typed on one display is drawn on the other, frames match
the vega command's, and the relay sees no text.
A line takes 0.79 ms at p50 and 1.1 ms at p99 from one node's program
to the other node's views with stores in RAM, both commits, the HTTP
delivery and the seal included (sealing adds nothing measurable); on the
Pi's SD card 3.5 ms at p50, the long tail being the card's syncs.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
A sealed request cost three X25519 operations (about 0.5 ms), so sealed
sends drained at half the plain rate. A wire now keeps one HPKE context,
encapsulated at its first seal, and seals each request as the context's
next number (a failed seal or a restart starts a new session); the
header carries the session's encapsulated key and the number, so a
receiver opens a session once per connection thread (16 remembered, the
least used replaced) and each seal by its number, also after it restarts,
unasked. A sender with a key of its own seals in HPKE auth mode and names
that key in the header; a receiver started with --sender NAME=KEY takes
deliveries only from the senders it names, each sealed with its key
(403 sender otherwise). The body is now the ciphertext and its tag.
Sealed sends, sender authenticated, drain at 461-464k a second against
462-470k plain and 207-234k sealed a request at a time (Raspberry Pi 5).
The check adds: a wire's requests share one session numbered from 0; a
changed number or sender key does not open; a receiver restarted naming
its sender opens the same session again; another node claiming that
sender's name with its own key is refused and applies nothing.
|
| |
|
|
|
|
|
|
|
|
|
|
| |
What the app model, snapshot reads and delivery had cost small reads
(126.7k -> 116.1k GETs a second) and idle memory (2.0 -> 4.5 MiB), how
the sampler found it, and the four steps and the crypto split that took
it back: 139.9k and 2.3 MiB. Measured again today beside axum 0.8.9 and
drogon 1.9.0 on the same Pi: a one-thread pure-serve answers small GETs
at 139k/s (2.2x axum and drogon a CPU second), 1 MiB GETs at 2,362/s
(axum 1,304, drogon 754), durable app writes at 21.3k/s (both about
200), with the least idle memory of the three.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
--seal OUTPUT=KEY seals each request's body whole to the receiving node's
public key with HPKE (RFC 9180, base mode: X25519, HKDF-SHA256, AES-128-GCM
where the CPU has AES, else ChaCha20-Poly1305), bound to the request's
source, first number and count; X-Pure-Seal names the suite. A receiver's
--key is a raw 32-byte file, made 0600 when missing, held in OpenSSL's
secure heap; it opens the body where it lies (400 seal when it does not
open) and zeroes the plain text when the request's ticket goes.
--sealed-only refuses unsealed deliveries (403 unsealed).
The check puts a recording relay between two apps: every order applies
once, no body shows an item or a field name, a flipped bit is refused, a
replayed request applies nothing twice, and a seal to another key does not
open. Its hosts choose their own ports (--port 0). Sealed sends drain at
233-235k a second against 469-470k plain (Raspberry Pi 5): three X25519
operations a request, 164 us each. The plain request path measured the
same as before.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Commits grew the tree store's tail 256 KiB at a time, each growth a sync
that also committed the ext4 journal for the new size and blocks. A file
installed by compaction now carries written zeros up to where the next
compaction will come (4 x live + slack, plus a commit's margin), capped at
the size of the file it replaces, so a store never takes more space than
before and shrinks when its live data does. The cycle's commits then only
overwrite blocks the file has.
Store commits: 317.5 -> 385.5 a second, ext4 journal commits 109 -> 45 for
4,000 commits; durable app posts +5.3%, their p99 the same within this SD
card's noise. The new cycles test keeps sizes still between compactions
once the live data is whole, and shows the file shrinking with it.
|
| |
|
|
|
|
|
|
|
|
|
|
| |
Nothing a thread can give: with writes saturated the device's one line of
syncs is the bottleneck, so zeroing the tail or compacting on another
thread only queues that device work behind the commits, and the owner's
idle gap is shorter than one journal commit. Built without compaction the
store is no faster; without compaction and without tail growth durable
posts gain 1.4% and the p99 drops 24% (17.4 to 13.3 ms). New blocks are the
tail latency, so the way to it is a store that rewrites its space in place,
a ring cleaned forward instead of compacted into new files.
|
| |
|
|
|
|
|
|
|
|
|
| |
It would not, on this device. One file's syncs or four at once, the SD card
completes the same 510-690 commits per second, the latency growing with the
number of files. The scoreboard app with two owners, each with a store of
its own, took 23% fewer durable posts than one owner (median 16,230 against
20,974 a second) with 2-3x the p99: syncs queue, and each carries half the
events. One owner's group commit stays; cores serve reads, and writes grow
by making the sync itself cheaper.
|
| |
|
|
|
|
|
|
|
|
| |
The HTTP host's end-to-end checks (documents against the earlier server,
lending, kill -9 durability, JSON, timers, links, webhooks and answers) sat
in aup's tests, so a change to the host was verified from the toolchain.
They now live in tests/check.py; make check builds their apps with the
sibling aup and runs them after the unit tests, which stay beside their
parts. Design 009 states the rule for all three repositories.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The app model, the tree store and the HTTP host lived in
prototypes/connections among the earlier document runtime, the store was
known only by its format's name, and Vega compiled six Pure sources by path.
Now, as the README's principle has it:
core/ runtime, flow and the app model (module*.c), with what the core
asks of storage (state.h, store.h)
store/ the tree store (PURETRE3, PUREREC1)
serve/ pure-serve: HTTP host, outbound delivery, JSON in place
cli/ pure-run, pure-edit-module
A top-level make builds libpure.a (app model and store, for hosts to link)
and the hosts; make check runs the store's and the app model's tests. The
earlier runtime still builds from prototypes/connections against core/ and
store/ (check, check-tree and check-core pass). Design 009 records the rule:
parts by role behind libraries; git repositories split by coupling, so the
store stays here while its contract moves with the core, and Vega stays apart.
|
| |
|
|
|
|
|
|
|
| |
After each save the owner walked the whole outbox to find the sends
not yet queued, so a receiver long down made every save walk the
backlog. pure_app_outbox_newest visits saved sends newest first, and
the owner stops once every wired output reaches the number it queued
last, then queues what it found in order.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The final answer to each send of a wired output (a 2xx, or a 4xx but
408 and 429) becomes a message event of the given input: fields from
the answer's JSON object by name, other members skipped; a field the
answer lacks from the send's field of that name and type, so the
request's own id is there; a u32 http_status field is the status. It is
applied with the send's number from the wire's source, before the send
is trimmed and in the same save, so an answer that comes again after a
restart (the API repeating itself for the Idempotency-Key) applies once.
Sends that wait for answers go one per request; answers are saved with
the next round, or at once when none waits.
A server that writes an answer in pieces holds the second until the
first is acknowledged, and a delayed acknowledgement stalled every
answer 40 ms: the client now acknowledges at once (TCP_QUICKACK) after
each read. Against a payments API that answers 200 or 402, with the
sender killed (-9) midway, paid and declined orders matched the API's
answers one to one.
|
| |
|
|
|
|
|
|
|
|
| |
A wire to an https:// URL speaks TLS 1.2 or later through OpenSSL: the
receiver's certificate must chain to the system's CAs (or to the file
--send-ca names) and name its host (SNI and SSL_set1_host, or the IP
address). An untrusted receiver gets nothing: the send stays in the
outbox, the wire logs it and tries again every 10 s. pure-serve now
links libssl and libcrypto.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
pure-serve --send OUTPUT=http://host:port/path wires an output: after
every save the owner queues the new sends as JSON (fields and groups)
and a thread per output posts them in order with X-Pure-Source,
X-Pure-Sequence and Idempotency-Key. A 2xx, or a Pure receiver's
refusal, delivers; the owner then trims. 408, 429, 5xx and no answer
are sent again after a pause growing to 10 s, other answers every 10 s:
nothing is dropped. A Pure receiver applies a delivered message with
pure_app_deliver (now taking placed fields) and advertises
X-Pure-Batch: 256; the sender then posts up to that many numbers in a
row as one JSON array (X-Pure-Count), applied in order in one burst
with one save.
Delivery kept up with orders once batched (391 deliveries/s one at a
time; a backlog of 20,000 went at 60k/s). With four clients ordering,
killing the receiver and then the sender (-9) left the receiver's count
and total equal to what the sender saved, five times and under ASan.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
An output (input kind 5) is a message the app sends; SEND (72) takes
an output's field values in order in a handler, lays them out as a
message's payload and keeps it, numbered per output from 1, with the
event's changes: a failed event sent nothing, and a failed save takes
back every send since the last save with its numbers. A host sees only
saved sends (pure_app_outbox) and trims what its receiver has saved
(pure_app_trim, gone with the next save). pure_app_deliver applies a
message from a named source once: a number heard before succeeds
without applying, a refused message counts as heard, a failed save
forgets what it heard.
Sends, numbers and heard numbers are the app's links state, stored
whole in one runtime document (PLK1) with the states, in the same
commit. Outputs follow their names across module changes; a module
that drops or retypes an output with sends left is refused, and a
dropped output's number is kept for when it returns. Killing the
process at every commit stage leaves an event and its send, or a
delivery and its effect, together or neither. pure-serve answers a
post to an output or a timer with 404 no_input.
|
| |
|
|
|
|
|
| |
Measured with a build that grows its tail by 64 MiB once and never
compacts: durable posts +5-8% (64 connections), p99 about halved; the
slow syncs that remain come from the device.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
pure-serve no longer copies a JSON body's strings into the message's
payload. The ingress is the prefix, a table of each field's start and
size, and the body as it came; the connection thread scans the body
once, puts numbers into the prefix and records where each string is.
Only a string with escapes is unescaped, over itself (it never grows).
A group of fields comes as an object inside the body and, for a fixed
field, as its path in the query (?to.zip=7). A group where a field
belongs, a value where a group does, an array or true/false/null is
json_type; an unknown member, inside a group too, json_field.
The string scan and UTF-8 checks now pass over eight bytes at a time
while none needs a look (pure_utf8_step, so every text check gains).
On the Pi, posting {"name":"k","text":"x..."} to a stateless app went
from 652-655 to 3,737-3,953 requests/s with 256 KiB of text (server
CPU 1.52 to 0.25 ms a request, peak RSS 5.2 to 3.2-3.4 MiB) and from
29.1k to 76.3-76.7k/s with 4 KiB; the load generator gains a json
method and benchmarks/http/echo.aup is the app.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
A tree store commit wrote its bytes over the written zeros of the tail
and its head into a slot at the start of the file: two ranges, and on
the Pi's SD card a sync of two ranges costs about twice one (2.4 ms
against 1.2 ms). A commit now writes a 128-byte record (its head) at
the published end and its bytes right after it, then syncs once. Every
16 commits the head also goes into the older slot. The newest commit
is found from the newer slot's head, or from the newest head this
process has seen in the file while its record is still there, along
the records whose bytes are whole; a torn record or bytes end the walk
at the commit before, which the next writer overwrites. Slots of this
format are PURETRE3; files of the earlier one are read and continued.
Store commits went from 220-233/s to 371-396/s (p50 2.5 to 1.3 ms),
and the scoreboard's durable posts from 13-16k/s to 21-26k/s with 64
connections and from 2.2-2.4k/s to 2.9-3.9k/s with 8, measured
alternately with the previous build. The torn head check now tears a
slot (the walk goes on from the other) and the newest record (a new
process sees the commit before); a new check walks 42 commits from the
slots, in a fresh process too, and stops at a damaged record.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The owner publishes a snapshot of the saved states after every save,
before it hands back the answers; connection threads take the newest
one each round and show views from it with a reader app of their own.
A read made after a write's answer sees the write, nothing unsaved or
undone is ever shown, and reads no longer wait while the owner applies
events or syncs. Apps with states always get an owner thread, even
with one connection thread. A round's inputs go to the owner first;
its views are shown and then answered together (answering each one as
it was shown made one thread's 20-row page 8% slower).
On the Pi 5, with 8 connections posting durable scores and 56 reading
the total, reads went from 10-16k/s at p99 13-29 ms to 107-149k/s at
p99 0.6-0.7 ms, and posts stayed in range; axum and drogon, which sync
under their lock, read 1.1-1.3k/s at p99 111-156 ms. A snapshot of a
changed 1,024-item list costs 1.2 us (65,536 items: 87 us) against a
3-4 ms save.
|
| |
|
|
|
|
|
|
|
|
|
|
| |
A view that shows a text state as it is (pure_module_text_state) now goes
out as the state's stored extents, as a document read does: the answer
holds the store mapping, charged to the budget, until it is sent and its
ticket released; a state with edits not yet stored is copied as before.
Documents and views share one loan path, and the extent array grows as
needed. A 1 MiB note read by 8 connections: 776-817 answers a second
copied, 1,875-1,901 lent, p50 9.2 to 3.5 ms, peak RSS 10.3 to 5.7 MiB.
The load generator learns GET /views/page.
|
| |
|
|
|
|
|
|
|
|
| |
A sent message belongs to its event's transaction in a runtime-owned
outbox; hosts deliver committed messages in order, and a receiver keeps
the last sequence per source in the same commit, so the effect is exactly
once. The note records the design and its order of work; it waits behind
the roadmap's short-term items and goes with outbound calls, which stand
on the same outbox.
|
| |
|
|
|
|
|
|
|
|
|
|
| |
The scoreboard, 22 lines of aup served by its views and inputs, against
the same service written by hand in axum and drogon on the Pi: durable
posts about 76 times as many, reads level with drogon and ahead of axum
with the least CPU and memory. The note keeps what the profile showed on
the way (the kernel's share of a single thread, integers through printf,
an owner that saved too early) and what comes next. run.py gains
pure-serve-2 and waits for a server that prints its port before it
listens.
|
| |
|
|
|
|
|
|
|
|
|
| |
The zero tail wrote as many bytes as the commits under 64 writers, yet
turning it off changed nothing beyond the SD card's own noise and made
8 writers wait longer, so it stays until faster storage is measured.
Overlapping a sync with the next burst would win a few percent at most.
The second sync of a new process's first commit is rare with one owning
server. The larger lever is write amplification: a 16-byte edit rewrites
its whole leaf and catalog path.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
A drogon 1.9 service with the axum baseline's contract joins the benchmark
(memory, fdatasync and crash-safe modes, three IO threads), built from
Debian's packages unpacked under .deps without installing them. drogon
listens once per event loop, so the service picks a free port itself:
with port 0 every loop got a port of its own and the load reached one.
The load generator has one core and saturates near 150k answers a second,
so the harness now also reports answers per second of server CPU time
(all threads). Over three rotated rounds: small GETs 151.6k/s on three
shards (drogon 145.3k, axum 120.9k) and 128k per CPU-second on one thread
(drogon 65k, axum 62k); 1 MiB GETs 2,794/s (axum 1,372, drogon 708);
crash-safe PUTs 5.1-5.8 times axum and 13-30 times drogon; peak RSS
5.0 MiB against 14.4 and 76.5 MiB. --workloads is now a regular expression.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
A commit used to sync its nodes, then write the head and sync again: the
order of writes was forced by syncs. Now the head carries where the
commit's bytes start and their digest, and one fdatasync makes the bytes
and the head durable together. A crash during it can leave a head whose
bytes did not all reach the device; its digest then fails and the older
slot stands, which is safe because a writer only builds on a durable head.
Commits overwrite written zeros kept after the published end, so the sync
changes neither the size nor the block map and needs no journal commit.
On the SD card this is 2.4 ms per commit against 9.1 ms for two syncs;
the store commits 289-304 times a second instead of 94-109, and pure-serve
answers 2,012-2,611 durable PUTs a second against 583 for crash-safe axum.
A process remembers the heads it published or checked, so it reads a
commit's bytes at most once and never its own. Its readers pass over the
head it is still making durable and so never answer with a commit a crash
could take back. Head slots get a block each and the format becomes
PURETRE2; a handle's refresh reads the slots through its mapping.
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
A read of a stored document now answers with the store mapping's extents
through writev, without copying the document. pure_draft_mapping takes a
reference to the mapping a draft opened through a handle reads from; the
answer keeps it until the last byte is sent, so the version read goes out
intact even if the document changes or a compaction replaces the file
meanwhile. Replies the mapping does not hold are copied as before.
pure-serve's output is now a list of extents (the head first). One thread
serves 2,761 1 MiB reads per second (axum: 1,380) and 128k small ones.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
A burst now looks at the store once (pure_store_pin) instead of once per
request; another shard's commit ends before its answer is sent, so a
request made after that answer still reads it. With this alone one thread
serves 125k small keep-alive reads per second, as many as axum on three
cores, with a shorter p99.
--threads N runs a shard per thread: its own SO_REUSEPORT listener, epoll
set, runtime domain, app and store handle. Writer sessions of the tree
store now take turns inside a process with a mutex (the file lock belongs
to the process and does not keep threads apart), and revisions settle
concurrent edits of a key. A module with states runs on one thread. Three
shards serve 151k reads per second; they still commit one by one, so
durable writes and 1 MiB reads are better on one thread for now, which
stays the default. Note 075 records the numbers.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
pure-serve replaces the module mode of server.c, which goes back to what
it was. It keeps the document contract, the runtime core (a work slot per
connection, the payload budget, core-owned ingress, borrowed PUT replies)
and the group commits, and adds what server.c lacked: HTTP/1.1 persistent
connections with in-order pipelining, an edge-triggered epoll owner
thread, up to 1,024 connections allocated as they arrive and reused, one
writev per answer, and documents opened through a store handle.
On the Pi 5 with one thread it serves 106k small keep-alive reads per
second (axum on three cores: 126k) at the same p99, 1,741 1 MiB reads
(axum: 1,370), and 1,126 durable writes from 64 connections (crash-safe
axum: 372), in 7.3 MiB against axum's 17-20 MiB. Note 075 has the table.
|
| |
|
|
|
|
|
|
|
|
|
|
| |
A C load generator, an axum service with the same document contract (in
memory, fdatasync, and crash-safe replacement), and a runner that pins the
servers and the load to separate CPUs. On the Pi 5, Pure uses about 40%
less memory, wins with a new connection per request and with eight durable
writers (3.2x the crash-safe axum), but loses 5x on keep-alive reads and
1.5x on 64 durable writers: no persistent connections, one thread, eight
connection slots and two fsyncs per commit. Note 075 records the numbers
and the targets.
|
| |
|
|
|
|
|
| |
The recorded Raspberry Pi 5 (Linux AArch64, 16 KiB pages, ext4) replaces
Apple Silicon macOS as the device whose results decide completion. The macOS
CI job stays as an optional portability check; no macOS support is claimed.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
state.h gives any app a runtime-owned working version of a stored value on
the tree store. A draft shares unchanged extents with the stored version,
edits in memory by path copying, lends ordered extents without copying, and
commits only its new nodes when the key is still at its base revision. A
failed commit changes neither the draft nor the store; a draft whose file was
replaced by compaction copies its stored extents on commit. Unreachable
arena nodes are reclaimed once they outweigh max(reachable, 32 KiB).
Typing into the middle of a 1 MiB document and saving each character peaked
at about 1,660 KiB RSS with a draft against about 4,480 KiB for an app copy
compared with storage on save; saves were only 1-2 ms faster. This corrects
073, which had attributed the TUI's remaining 8 ms to that comparison.
Drafts are not yet charged to the runtime budget or visible to .pure
definitions.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
store-tree.c keeps every document in one append-only file as a persistent
B-tree of byte extents, with the key catalog in the same structure. A splice
writes only the changed leaf and path; unchanged extents are shared between
versions, readers take no lock, and two alternating head slots publish a
commit after its nodes are durable. Compaction rewrites reachable nodes.
On the recorded ext4 host a durable 1-byte middle insert into a 1 MiB
document took 8.58 ms against 78.51 ms for the default store, and the real
TUI's Ctrl+S after typing took 16.60 ms against 84.59 ms. check-tree runs the
store's crash/oracle tests and the unchanged runtime, splice, async and
real-PTY editor checks on it. It stays opt-in: linked code is 12.7 KB larger
and contiguous multi-leaf reads copy.
|
| | |
|
| | |
|
| |
|
