Discussion:
[leveldb] 1024*1024 value size
Benoit Chesneau
2015-12-08 18:01:15 UTC
Permalink
would leveldb perform enough well for a 1024*1024 bytes value size ? Or
should it be better spliited?
--
You received this message because you are subscribed to the Google Groups "leveldb" group.
To unsubscribe from this group and stop receiving emails from it, send an email to leveldb+***@googlegroups.com.
For more options, visit https://groups.google.com/d/optout.
'Sanjay Ghemawat' via leveldb
2015-12-08 19:16:37 UTC
Permalink
Post by Benoit Chesneau
would leveldb perform enough well for a 1024*1024 bytes value size ? Or
should it be better spliited?
It will get copied a couple of times on various paths. The memory usage
might fluctuate by a couple of megabytes. So it should probably be ok. But
that answer might change based on what your performance eneds are. I
suggest that before going to the complexity of splitting you benchmark
parts of your application without splitting to see if non-split performance
is good enough for you.
Post by Benoit Chesneau
--
You received this message because you are subscribed to the Google Groups "leveldb" group.
To unsubscribe from this group and stop receiving emails from it, send an
For more options, visit https://groups.google.com/d/optout.
--
You received this message because you are subscribed to the Google Groups "leveldb" group.
To unsubscribe from this group and stop receiving emails from it, send an email to leveldb+***@googlegroups.com.
For more options, visit https://groups.google.com/d/optout.
Benoit Chesneau
2015-12-21 10:12:07 UTC
Permalink
Post by 'Sanjay Ghemawat' via leveldb
Post by Benoit Chesneau
would leveldb perform enough well for a 1024*1024 bytes value size ? Or
should it be better spliited?
It will get copied a couple of times on various paths. The memory usage
might fluctuate by a couple of megabytes. So it should probably be ok. But
that answer might change based on what your performance eneds are. I
suggest that before going to the complexity of splitting you benchmark
parts of your application without splitting to see if non-split performance
is good enough for you.
Right! Thanks for the answer anyway :)

- benoit
Post by 'Sanjay Ghemawat' via leveldb
Post by Benoit Chesneau
--
You received this message because you are subscribed to the Google Groups
"leveldb" group.
To unsubscribe from this group and stop receiving emails from it, send an
For more options, visit https://groups.google.com/d/optout.
--
You received this message because you are subscribed to the Google Groups "leveldb" group.
To unsubscribe from this group and stop receiving emails from it, send an email to leveldb+***@googlegroups.com.
For more options, visit https://groups.google.com/d/optout.
1971 powerChina
2015-12-22 07:16:30 UTC
Permalink
you can try my pwwMap
it is best
https://sourceforge.net/projects/pwwhashmap/files/stats/timeline
--
You received this message because you are subscribed to the Google Groups "leveldb" group.
To unsubscribe from this group and stop receiving emails from it, send an email to leveldb+***@googlegroups.com.
For more options, visit https://groups.google.com/d/optout.
Loading...