Increase swift replication factor for accounts
Open, MediumPublic
Actions

Assigned To

None

Authored By

	• ema
	Jan 24 2017, 2:50 PM

Description

The current swift replication factor for accounts is 3. As account was found to be one of the bottlenecks during the recent cache_upload outage, we should increase the replication factor to allow for more fan-out.

Before doing so in eqiad, the change should be tested in codfw, using ssbench to evaluate the impact.

Event Timeline

• ema created this task.Jan 24 2017, 2:50 PM

Restricted Application added a subscriber: Aklapper. · View Herald TranscriptJan 24 2017, 2:50 PM

• ema added a project: SRE.Jan 24 2017, 2:50 PM

• ema triaged this task as Medium priority.Jan 24 2017, 2:53 PM

• ema added a project: Wikimedia-Incident.

• ema moved this task from Active investigation to Follow-up prevention on the Wikimedia-Incident board.

• Phabricator_maintenance moved this task from Backlog to Acknowledged on the SRE board.Jan 26 2019, 9:01 PM

Krinkle edited projects, added Sustainability (Incident Followup); removed Wikimedia-Incident.Apr 28 2020, 9:50 PM

fgiunchedi moved this task from Inbox to Backlog on the SRE-swift-storage board.Aug 25 2021, 4:20 PM

Krinkle updated the task description. (Show Details)Sep 28 2021, 10:49 PM

Removing SRE, adding Data-Persistence

Kappakayala removed a project: SRE.Mar 14 2023, 5:55 PM

Joe added a project: SRE-Sprint-Week-Sustainability-March2023.Mar 20 2023, 11:31 AM

Joe moved this task from Backlog to E_TOO_BIG_MAYBE_OKR? on the SRE-Sprint-Week-Sustainability-March2023 board.

I'm not sure how much this will actually help from the swift side (as opposed to frontend capacity, memcached, etc).
The account dbs are tiny, though, so it seems like a cheap thing to try...

Increase swift replication factor for accountsOpen, MediumPublicActions

Description

Event Timeline

Increase swift replication factor for accounts
Open, MediumPublic
Actions