Reapply "pageserver: revert flush backpressure" (#10270) (#10402)

This reapplies #10135. Just removing this flush backpressure without
further mitigations caused read amp increases during bulk ingestion
(predictably), so it was reverted. We will replace it by
compaction-based backpressure.

## Problem

In #8550, we made the flush loop wait for uploads after every layer.
This was to avoid unbounded buildup of uploads, and to reduce compaction
debt. However, the approach has several problems:

* It prevents upload parallelism.
* It prevents flush and upload pipelining.
* It slows down ingestion even when there is no need to backpressure.
* It does not directly backpressure based on compaction debt and read
amplification.

We will instead implement compaction-based backpressure in a PR
immediately following this removal (#5415).

Touches #5415.
Touches #10095.

## Summary of changes

Remove waiting on the upload queue in the flush loop.
This commit is contained in:
Erik Grinaker
2025-01-24 08:35:35 +00:00
committed by GitHub
parent 8d47a60de2
commit 9e55d79803
5 changed files with 13 additions and 112 deletions
-1
View File
@@ -165,7 +165,6 @@ PAGESERVER_PER_TENANT_METRICS: tuple[str, ...] = (
"pageserver_evictions_with_low_residence_duration_total",
"pageserver_aux_file_estimated_size",
"pageserver_valid_lsn_lease_count",
"pageserver_flush_wait_upload_seconds",
counter("pageserver_tenant_throttling_count_accounted_start"),
counter("pageserver_tenant_throttling_count_accounted_finish"),
counter("pageserver_tenant_throttling_wait_usecs_sum"),