Commit Graph

30 Commits

Author SHA1 Message Date
Eugeniy E. Mikhailov
dab0bb8097
Feature limit caching to prescribed number of bytes per file (#6009)
* feature: we can check if a fileId is already in the cache

We using this to protect cache from adding the same needle to
the cache over and over.

* fuse mount: Do not start dowloader if needle is already in the cache

* added maxFilePartSizeInCache property to ChunkCache

If file very large only first maxFilePartSizeInCache bytes
are going to be put to the cache (subject to the needle size
constrains).

* feature: for large files put in cache no more than prescribed number of bytes

Before this patch only the first needle of a large file was intended for
caching. This patch uses maximum prescribed amount of bytes to be put in
cache. This allows to bypass default 2MB maximum for a file part stored
in the cache.

* added dummy mock methods to satisfy interfaces of ChunkCache
2024-09-11 21:09:20 -07:00
Eugeniy E. Mikhailov
c04edeed68
bug fix in the data received from cache processing (#6002)
The patch addresses #3745.

The cache should return the exact amount of data requested by the buffer.
By construction of the cache it is always all requested data range
or we have error happening.

The old use of minsize miscalculate the requested data size,
if non zero offset is requested.
2024-09-10 13:30:18 -07:00
chrislu
18afdb15b6 Revert "weed mount, weed dav add option to force cache"
This reverts commit 7367b976b0.
2024-09-04 01:38:29 -07:00
chrislu
7367b976b0 weed mount, weed dav add option to force cache 2024-09-04 01:19:14 -07:00
chrislu
26dbc6c905 move to https://github.com/seaweedfs/seaweedfs 2022-07-29 00:17:28 -07:00
chrislu
28b395bef4 better control for reader caching 2022-02-26 02:16:47 -08:00
chrislu
3ad5fa6f6f chunk cache adds function ReadChunkAt 2022-02-25 21:55:04 -08:00
Nathan Hawkins
042de9359c make reader_at handle random reads more efficiently for FUSE 2021-04-28 19:13:37 -04:00
Chris Lu
707936f482 re-enable caching larger than 16MB
revert 62ce85610e
2020-10-03 14:12:38 -07:00
Chris Lu
62ce85610e skip caching too large chunks 2020-09-27 11:58:48 -07:00
Chris Lu
9ad2dcca2b more tests 2020-09-27 11:42:51 -07:00
Chris Lu
31fc7bb2e1 refactor
adjust for faster test
2020-09-27 10:41:29 -07:00
Chris Lu
a41588279a change log level 5 to 4 2020-08-30 20:12:04 -07:00
Chris Lu
09e126bae5 refactoring: use interface 2020-08-17 20:20:08 -07:00
Chris Lu
be4d42b8e2 rename 2020-08-17 20:15:53 -07:00
Chris Lu
97e54a80d4 rename variables 2020-08-17 16:05:13 -07:00
Chris Lu
003d48da21 adjust logs 2020-08-15 19:55:28 -07:00
Chris Lu
bef356ce4c since we already know the chunk size, no need to iterate 2020-06-27 12:51:04 -07:00
Chris Lu
a808b3b5df incase the memory data is too small 2020-06-27 11:59:15 -07:00
Chris Lu
3dbd51c3c2 a little bit more efficient 2020-06-26 10:02:37 -07:00
Chris Lu
212b6e7d42 error logging 2020-06-26 10:01:55 -07:00
Chris Lu
3cec4b3c49 FUSE mount: fix file id written twice?
fix https://github.com/chrislusf/seaweedfs/issues/1373
2020-06-25 20:11:49 -07:00
Chris Lu
2b5c4fbbf3 tiered caching
1/4 for small less than 1MB files. 1/4 for 1~4MB files, 1/2 for bigger than 4MB files
2020-04-13 22:19:27 -07:00
Chris Lu
f282ed444b refactoring 2020-04-13 21:58:10 -07:00
Chris Lu
7764e0465c refactoring 2020-04-12 21:00:55 -07:00
Chris Lu
94e35cdb35 mount: fix
fix bug found by git bisect, but I do not understand why it can cause error!
2020-04-12 03:34:36 -07:00
Chris Lu
2a1f396df5 avoid duplicated setting chunks into cache 2020-04-12 01:06:50 -07:00
Chris Lu
b9b7da905e handle nil chunk cache 2020-04-12 01:00:12 -07:00
Chris Lu
df97da25f9 mount: add on disk caching 2020-04-11 21:12:41 -07:00
Chris Lu
d7f3acb2c0 refactor 2020-04-11 12:45:24 -07:00