mirror of
https://github.com/neondatabase/neon.git
synced 2026-01-13 08:22:55 +00:00
2b11466b59
## Problem The vectored read path proposed in https://github.com/neondatabase/neon/pull/6576 seems to be functionally correct, but in my testing (see below) it is about 10-20% slower than the naive sequential vectored implementation. ## Summary of changes There's three parts to this PR: 1. Supporting vectored blob reads. This is actually trickier than it sounds because on disk blobs are prefixed with a variable length size header. Since the blobs are not necessarily fixed size, we need to juggle the offsets such that the callers can retrieve the blobs from the resulting buffer. 2. Merge disk read requests issued by the vectored read path up to a maximum size. Again, the merging is complicated by the fact that blobs are not fixed size. We keep track of the begin and end offset of each blob and pass them into the vectored blob reader. In turn, the reader will return a buffer and the offsets at which the blobs begin and end. 3. A benchmark for basebackup requests against tenant with large SLRU block counts is added. This required a small change to pagebench and a new config variable for the pageserver which toggles the vectored get validation. We can probably optimise things further by adding a little bit of concurrency for our IO. In principle, it's as simple as spawning a task which deals with issuing IO and doing the serialisation and handling on the parent task which receives input via a channel.
56 lines
1.7 KiB
Python
56 lines
1.7 KiB
Python
"""
|
|
Utilities used by all code in this sub-directory
|
|
"""
|
|
|
|
from typing import Any, Callable, Dict, Tuple
|
|
|
|
import fixtures.pageserver.many_tenants as many_tenants
|
|
from fixtures.log_helper import log
|
|
from fixtures.neon_fixtures import (
|
|
NeonEnv,
|
|
NeonEnvBuilder,
|
|
)
|
|
from fixtures.pageserver.utils import wait_until_all_tenants_state
|
|
from fixtures.types import TenantId, TimelineId
|
|
|
|
|
|
def ensure_pageserver_ready_for_benchmarking(env: NeonEnv, n_tenants: int):
|
|
"""
|
|
Helper function.
|
|
"""
|
|
ps_http = env.pageserver.http_client()
|
|
|
|
log.info("wait for all tenants to become active")
|
|
wait_until_all_tenants_state(
|
|
ps_http, "Active", iterations=n_tenants, period=1, http_error_ok=False
|
|
)
|
|
|
|
# ensure all layers are resident for predictiable performance
|
|
tenants = [info["id"] for info in ps_http.tenant_list()]
|
|
for tenant in tenants:
|
|
for timeline in ps_http.tenant_status(tenant)["timelines"]:
|
|
info = ps_http.layer_map_info(tenant, timeline)
|
|
for layer in info.historic_layers:
|
|
assert not layer.remote
|
|
|
|
log.info("ready")
|
|
|
|
|
|
def setup_pageserver_with_tenants(
|
|
neon_env_builder: NeonEnvBuilder,
|
|
name: str,
|
|
n_tenants: int,
|
|
setup: Callable[[NeonEnv], Tuple[TenantId, TimelineId, Dict[str, Any]]],
|
|
) -> NeonEnv:
|
|
"""
|
|
Utility function to set up a pageserver with a given number of identical tenants.
|
|
"""
|
|
|
|
def doit(neon_env_builder: NeonEnvBuilder) -> NeonEnv:
|
|
return many_tenants.single_timeline(neon_env_builder, setup, n_tenants)
|
|
|
|
env = neon_env_builder.build_and_use_snapshot(name, doit)
|
|
env.start()
|
|
ensure_pageserver_ready_for_benchmarking(env, n_tenants)
|
|
return env
|