Hope My email client configured correctly this time. 在 2020/9/23 下午11:26, Coly Li 写道: > On 2020/9/23 23:18, Liu Hua wrote: >> Hi Coly, >> >> Thanks for you reply! >> >> 在 2020/9/22 下午11:51, Coly Li 写道: >>> On 2020/9/22 23:47, Liu Hua wrote: >>>> Btree spliting and garbage collection process will drop >>>> placeholders, which may cause cache miss collision. We can >>>> insert nonoverlapping bkeys with write lock. It is helpful >>>> for performance. >>>> >>> Could you please to explain more detais about, >>> - How does "Btree spliting and garbage collection process will drop >>> placeholders" happen? >>> - And how does the consequence "cache miss collision" happen? >> Cache miss process is as following: >> >> A. Insert placeholder with read lock >> - lookup missed cache >> - insert placeholder bkey >> B. Read data from backing disk and write to cache >> C. Insert real bkey with write lock >> - check and fixup placeholder in bch_extent_insert_fixup. >> - if bkey to be inserted does not match placeholder bkey. Inserting >> will failed. >> Bcache marks this type of failure as cache miss collision. we can >> get this number >> from /sys/block/bcacheX/bcache/cache/stats_total/cache_miss_collision >> So a failed "c" process will lead the cache miss process fail, even if >> we have data >> in place but metadata failed. There are two types of reasons causing >> this failure: >> >> 1. Two cache miss processes collide as following (two processes names >> ABC and A'B'C') LBAs of the two process should overlap, otherwise ABC will not fail. >> A >> A' >> B >> B' >> C(will fail) >> C'(will succeed) >> 2. placeholder bkeys were dropped before "C". btree_mergesort called >> from GC and >> btree_split will drop "bad" bkeys including placeholder bkeys. >> >> For reason 2，since we hold write lock，if there is no overlaps with >> existing bkeys. >> we can insert bkeys safely. this is what this patch does. >>> - Do you observe performance improvement? If yes, which part is improved >>> and what is the performance number? >> Can we treat this patch as a bugfix? We add a prefetch framework in >> bcache and find 3% performace >> improvement and reduction of collision in an order of one, in spark >> word-count test with 1G ram >> disk as cache. And I think it is helpful both for our situation and >> original bcache. I can add a test based on original bcache. > > Copied. Give me some time to understand your change. Maybe more question > will follow up. Thank you for the above detailed information :-) > > Coly Li >
