Viewing profile — zzsheng
zzsheng
HN member- Joined
- Sat, Nov 02, 2024, 10:45 PM UTC
- HN karma
- 33
- Public activity
- 19 items
- HN profile
- View on Hacker News ↗
About zzsheng
No profile information was provided.
Recent public activity
-
comment
Comment #48705164
[dead]
- story
- comment
- story
-
comment
Comment #48655677
[dead]
- story
-
comment
Comment #48121591
we manage memory instead of relying on page cache
-
comment
Comment #48083123
sorry, typo. data will *not* be lost.
-
comment
Comment #48079800
check s3 express one zone
-
comment
Comment #48079794
journal file was pre-alloacated and we use direct-io for journal write so no need to call fsync.
-
comment
Comment #48079477
nop. we will not ack any write which is not in data or journal. please check the put details in the blog.
-
comment
Comment #48079465
actually both crash consistentcy and durability. after we ack, we make sure data will be lost due to crash, restart or power loss.
-
comment
Comment #48079412
we also use direct-io for reads.
-
comment
Comment #48078850
thanks for feedback. actually it was pointed out in blog that we do not use append only log to avoid fsync due to size change. what we use is preallocate fixed size log file and we…
-
comment
Comment #48048041
[dead]
-
comment
Comment #48047281
Author here. This is not a general argument against fsync; the design depends on SSD-only deployment, preallocated files, O_DIRECT, single-key atomicity, and device write guarantee…
- story
- story
- story