From a8b3a677e786fa869d220a6a78b5532a36dc2f4d Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Wed, 2 Nov 2022 17:12:00 -0400 Subject: bcachefs: Nocow support This adds support for nocow mode, where we do writes in-place when possible. Patch components: - New boolean filesystem and inode option, nocow: note that when nocow is enabled, data checksumming and compression are implicitly disabled - To prevent in-place writes from racing with data moves (data_update.c) or bucket reuse (i.e. a bucket being reused and re-allocated while a nocow write is in flight, we have a new locking mechanism. Buckets can be locked for either data update or data move, using a fixed size hash table of two_state_shared locks. We don't have any chaining, meaning updates and moves to different buckets that hash to the same lock will wait unnecessarily - we'll want to watch for this becoming an issue. - The allocator path also needs to check for in-place writes in flight to a given bucket before giving it out: thus we add another counter to bucket_alloc_state so we can track this. - Fsync now may need to issue cache flushes to block devices instead of flushing the journal. We add a device bitmask to bch_inode_info, ei_devs_need_flush, which tracks devices that need to have flushes issued - note that this will lead to unnecessary flushes when other codepaths have already issued flushes, we may want to replace this with a sequence number. - New nocow write path: look up extents, and if they're writable write to them - otherwise fall back to the normal COW write path. XXX: switch to sequence numbers instead of bitmask for devs needing journal flush XXX: ei_quota_lock being a mutex means bch2_nocow_write_done() needs to run in process context - see if we can improve this Signed-off-by: Kent Overstreet --- fs/bcachefs/trace.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'fs/bcachefs/trace.h') diff --git a/fs/bcachefs/trace.h b/fs/bcachefs/trace.h index fabee8302afa..24dd2defe7c7 100644 --- a/fs/bcachefs/trace.h +++ b/fs/bcachefs/trace.h @@ -543,6 +543,7 @@ DECLARE_EVENT_CLASS(bucket_alloc, __field(u64, need_journal_commit ) __field(u64, nouse ) __field(bool, nonblocking ) + __field(u64, nocow ) __array(char, err, 32 ) ), @@ -560,10 +561,11 @@ DECLARE_EVENT_CLASS(bucket_alloc, __entry->need_journal_commit = s->skipped_need_journal_commit; __entry->nouse = s->skipped_nouse; __entry->nonblocking = nonblocking; + __entry->nocow = s->skipped_nocow; strscpy(__entry->err, err, sizeof(__entry->err)); ), - TP_printk("%d,%d reserve %s user %u bucket %llu free %llu avail %llu copygc_wait %llu/%lli seen %llu open %llu need_journal_commit %llu nouse %llu nonblocking %u err %s", + TP_printk("%d,%d reserve %s user %u bucket %llu free %llu avail %llu copygc_wait %llu/%lli seen %llu open %llu need_journal_commit %llu nouse %llu nocow %llu nonblocking %u err %s", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->reserve, __entry->user, @@ -576,6 +578,7 @@ DECLARE_EVENT_CLASS(bucket_alloc, __entry->open, __entry->need_journal_commit, __entry->nouse, + __entry->nocow, __entry->nonblocking, __entry->err) ); -- cgit v1.2.3