| 307bf766 | 23-Apr-2020 |
Matthew Dillon <dillon@apollo.backplane.com> |
tmpfs - Change paging behavior, fix two directory-entry races
* Change the paging behavior for vfs.tmpfs.bufcache_mode.
These changes try to reduce unnecessary tmpfs flushes to swap when
the pa
tmpfs - Change paging behavior, fix two directory-entry races
* Change the paging behavior for vfs.tmpfs.bufcache_mode.
These changes try to reduce unnecessary tmpfs flushes to swap when
the pageout daemon is able to locate sufficient clean VM pages.
The pageout daemon can still page tmpfs data to swap via its normal
operation, but tmpfs itself will not force write()s to pipeline to
swap unless memory pressure is severe.
0 tmpfs write()s are pipelined to swap via the buffer cache only
if the VM system is below the minimum free page count.
(this is the new default)
1 tmpfs write()s are pipelined to swap via the buffer cache when
the VM system is paging.
2 Same as (1) but be more aggressive about releasing buffer cache
buffers.
3 tmpfs_write()s are always pipelined to swap via the buffer cache,
regardless.
* Fix tmpfs file creation, hard-linking, and rename to ensure that the
new file is not created in a deleted directory. We must lock the
directory node around existing tests and add checks that were missing.
Also remove a few unnecessary recursive locks.
show more ...
|
| 4c154053 | 22-Feb-2020 |
Matthew Dillon <dillon@apollo.backplane.com> |
tmpfs - Fix races in tmpfs_nrename() and tmpfs_nrmdir()
* Lock all nrename elements before checks. This is particularly
important when renaming over a file or empty directory, but other
manipul
tmpfs - Fix races in tmpfs_nrename() and tmpfs_nrmdir()
* Lock all nrename elements before checks. This is particularly
important when renaming over a file or empty directory, but other
manipulations done by this code without locks could also cause
races which result in corruption, particularly with the link count.
* Lock all nrmdir elements before checks, for the same reason.
show more ...
|
| 4eb0bb82 | 13-Feb-2020 |
Matthew Dillon <dillon@apollo.backplane.com> |
tmpfs - Improve write clustering
* Setup bmap and max iosize parameters so the kernel's clustering
code can actually cluster 16KB tmpfs blocks together into 64KB
blocks.
* In low-memory situati
tmpfs - Improve write clustering
* Setup bmap and max iosize parameters so the kernel's clustering
code can actually cluster 16KB tmpfs blocks together into 64KB
blocks.
* In low-memory situations the pageout daemon will flush tmpfs
pages via the VM page queues. This ultimately runs through
the tmpfs_vop_write() UIO_NOCOPY path which was previously using
cluster_awrite(). However, because other nearby buffers are
probably not present (buwrite()'s can allow buffers to be
dismissed early), there is nothing for cluster_awrite() to
latch onto to improve write granularity beyond 16KB.
Go back to using cluster_write() when SYNC and DIRECT are not
specified. This allows the clustering code to collect buffers
and flush them in larger chunks.
* Reduces low-memory tmpfs paging I/O overheads by 4x and
generally increases paging throughput to SSD-based swap by
2x-4x. Tmpfs is now able to issue a lot more 64KB I/Os when under
memory pressure.
show more ...
|