public inbox for [email protected]help / color / mirror / Atom feed
Re: [EXTERNAL] RDS IO Read time 4+ messages / 2 participants [nested] [flat]
* Re: [EXTERNAL] RDS IO Read time @ 2025-03-31 18:30 Eden Aharoni <[email protected]> 0 siblings, 1 reply; 4+ messages in thread From: Eden Aharoni @ 2025-03-31 18:30 UTC (permalink / raw) To: Christophe Pettus <[email protected]>; +Cc: [email protected] <[email protected]> Can you please tell me what other data might help? Would you like an EXPLAIN output? Get Outlook for Android<https://aka.ms/AAb9ysg; ________________________________ From: Christophe Pettus <[email protected]> Sent: Monday, March 31, 2025 9:23:45 PM To: Eden Aharoni <[email protected]> Cc: [email protected] <[email protected]> Subject: Re: [EXTERNAL] RDS IO Read time > On Mar 31, 2025, at 10:54, Eden Aharoni <[email protected]> wrote: > > So you believe it's strictly an EBS issue? Well, PostgreSQL certainly can read faster than 34MB/s off of disk. With the data you've given, I can't really say if it's purely an EBS issue. ^ permalink raw reply [nested|flat] 4+ messages in thread
* Re: [EXTERNAL] RDS IO Read time @ 2025-03-31 18:43 Christophe Pettus <[email protected]> parent: Eden Aharoni <[email protected]> 0 siblings, 1 reply; 4+ messages in thread From: Christophe Pettus @ 2025-03-31 18:43 UTC (permalink / raw) To: Eden Aharoni <[email protected]>; +Cc: [email protected] <[email protected]> > On Mar 31, 2025, at 11:30, Eden Aharoni <[email protected]> wrote: > > Can you please tell me what other data might help? You can show your work on how you got the megabytes/second number. (Be aware that on a general open-source mailing list, there's only so much debugging that we can do of a specific problem that is not a PostgreSQL bug.) ^ permalink raw reply [nested|flat] 4+ messages in thread
* Re: [EXTERNAL] RDS IO Read time @ 2025-03-31 19:36 Eden Aharoni <[email protected]> parent: Christophe Pettus <[email protected]> 0 siblings, 1 reply; 4+ messages in thread From: Eden Aharoni @ 2025-03-31 19:36 UTC (permalink / raw) To: Christophe Pettus <[email protected]>; +Cc: [email protected] <[email protected]> Aggregate (cost=8581.22..8581.23 rows=1 width=4) (actual time=1209.498..1210.530 rows=1 loops=1) Buffers: shared hit=3108 read=4314 dirtied=1 I/O Timings: shared read=1169.977 -> Gather (cost=8580.80..8581.21 rows=4 width=8) (actual time=1209.371..1210.526 rows=5 loops=1) Workers Planned: 4 Workers Launched: 4 Buffers: shared hit=3108 read=4314 dirtied=1 I/O Timings: shared read=1169.977 -> Aggregate (cost=7580.80..7580.81 rows=1 width=8) (actual time=1206.518..1206.520 rows=1 loops=5) Buffers: shared hit=3105 read=4314 dirtied=1 I/O Timings: shared read=1169.977 -> Hash Join (cost=2620.70..7578.45 rows=937 width=0) (actual time=148.965..1206.330 rows=1897 loops=5) Buffers: shared hit=3105 read=4314 dirtied=1 I/O Timings: shared read=1169.977 -> Index Only Scan using IX_Collaborators_TenantId_IsDeleted_RunningIndex on Collaborators c (cost=0.55..4619.26 rows=11407 width=80) (actual time=2.815..1058.793 rows=7474 loops=5) Index Cond: ((c."TenantId" = '0f8026c775a5499fdd3ccd193a15f94c3b4ae58a'::text) AND (c."IsDeleted" = false)) Heap Fetches: 3711 Buffers: shared hit=2332 read=3563 I/O Timings: shared read=1028.548 -> Hash (cost=2479.01..2479.01 rows=11292 width=79) (actual time=144.988..144.989 rows=1983 loops=5) Buffers: shared hit=637 read=751 dirtied=1 I/O Timings: shared read=141.429 -> Index Only Scan using IX_IntegrationCollaboration_TenantId_IsIntegrationDeleted_IsDe~ on IntegrationCollaboration i (cost=0.55..2479.01 rows=11292 width=79) (actual time=1.804..144.122 rows=1983 loops=5) Index Cond: (i."TenantId" = '0f8026c775a5499fdd3ccd193a15f94c3b4ae58a'::text) Heap Fetches: 112 Buffers: shared hit=637 read=751 dirtied=1 I/O Timings: shared read=141.429 Planning: Buffers: shared hit=440 Execution time: 1210.592 ms So we can see here that the query read 4314 blocks in 1.2 sec.. (ive done 4314 * 8kb / 1.2sec which is about 28 MB/s)… Hope you’ll have any clue 😊 From: Christophe Pettus <[email protected]> Date: Monday, 31 March 2025 at 21:44 To: Eden Aharoni <[email protected]> Cc: [email protected] <[email protected]> Subject: Re: [EXTERNAL] RDS IO Read time > On Mar 31, 2025, at 11:30, Eden Aharoni <[email protected]> wrote: > > Can you please tell me what other data might help? You can show your work on how you got the megabytes/second number. (Be aware that on a general open-source mailing list, there's only so much debugging that we can do of a specific problem that is not a PostgreSQL bug.) ^ permalink raw reply [nested|flat] 4+ messages in thread
* Re: [EXTERNAL] RDS IO Read time @ 2025-03-31 20:22 Christophe Pettus <[email protected]> parent: Eden Aharoni <[email protected]> 0 siblings, 0 replies; 4+ messages in thread From: Christophe Pettus @ 2025-03-31 20:22 UTC (permalink / raw) To: Eden Aharoni <[email protected]>; +Cc: [email protected] <[email protected]> > On Mar 31, 2025, at 12:36, Eden Aharoni <[email protected]> wrote: > Hope you’ll have any clue 😊 Based on that, I'd take it up with AWS. It does seem that the EBS mount is under-performing. ^ permalink raw reply [nested|flat] 4+ messages in thread
end of thread, other threads:[~2025-03-31 20:22 UTC | newest] Thread overview: 4+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2025-03-31 18:30 Re: [EXTERNAL] RDS IO Read time Eden Aharoni <[email protected]> 2025-03-31 18:43 ` Christophe Pettus <[email protected]> 2025-03-31 19:36 ` Eden Aharoni <[email protected]> 2025-03-31 20:22 ` Christophe Pettus <[email protected]>
This inbox is served by agora; see mirroring instructions for how to clone and mirror all data and code used for this inbox