Vova, thanks for comments. Anyway, page compression at rebalancing is a good idea even is we have problems with storing on disc.
2018-03-26 19:51 GMT+03:00 Vyacheslav Daradur <daradu...@gmail.com>: > Since PDS is strongly depending on memory page's size I'd like to > compress serialized data inside page exclude page header. > > On Mon, Mar 26, 2018 at 7:49 PM, Vladimir Ozerov <voze...@gridgain.com> > wrote: > > Alex, > > > > In fact there are many approaches to this. Some vendors decided stick to > > page - page is filled with data and then compressed when certain > threshold > > is reached (e.g. page is full or filled up to X%). Another approach is to > > store data in memory in *larger blocks* than on the disk, and when it > comes > > to flush, one may try to compress it. If final size is lower than disk > > block size then compression is considered successfull and data is saved > in > > compressed form. Otherwise data is saved as is. > > > > Both approaches may work, but IMO compression within a single block is > > better and simpler to implement. > > > > On Mon, Mar 26, 2018 at 6:53 PM, Alexey Goncharuk < > > alexey.goncha...@gmail.com> wrote: > > > >> Guys, > >> > >> How does this fit the PageMemory concept? Currently it assumes that the > >> size of the page in memory and the size of the page on disk is the > same, so > >> only per-entry level compression within a page makes sense. > >> > >> If you compress a whole page, how do you calculate the page offset in > the > >> target data file? > >> > >> --AG > >> > >> 2018-03-26 17:39 GMT+03:00 Vladimir Ozerov <voze...@gridgain.com>: > >> > >> > Gents, > >> > > >> > If I understood the idea correctly, the proposal is to compress pages > on > >> > eviction and decompress them on read from disk. Is it correct? > >> > > >> > On Mon, Mar 26, 2018 at 5:13 PM, Anton Vinogradov <a...@apache.org> > wrote: > >> > > >> > > + 1 to Taras's vision. > >> > > > >> > > Compression on eviction is a good case to store more. > >> > > Pages at memory always hot a real system, so complession in memory > will > >> > > definetely slowdown the system, I think. > >> > > > >> > > Anyway, we can split issue to "on eviction compression" and to > >> "in-memory > >> > > compression". > >> > > > >> > > > >> > > 2018-03-06 12:14 GMT+03:00 Taras Ledkov <tled...@gridgain.com>: > >> > > > >> > > > Hi, > >> > > > > >> > > > I guess page level compression make sense on page loading / > eviction. > >> > > > In this case we can decrease I/O operation and performance boost > can > >> be > >> > > > reached. > >> > > > What is goal for in-memory compression? Holds about 2-5x data in > >> memory > >> > > > with performance drop? > >> > > > > >> > > > Also please clarify the case with compression/decompression for > hot > >> and > >> > > > cold pages. > >> > > > Is it right for your approach: > >> > > > 1. Hot pages are always decompressed in memory because many > >> read/write > >> > > > operations touch ones. > >> > > > 2. So we can compress only cold pages. > >> > > > > >> > > > So the way is suitable when the hot data size << available RAM > size. > >> > > > > >> > > > Thoughts? > >> > > > > >> > > > > >> > > > On 05.03.2018 20:18, Vyacheslav Daradur wrote: > >> > > > > >> > > >> Hi Igniters! > >> > > >> > >> > > >> I’d like to do next step in our data compression discussion [1]. > >> > > >> > >> > > >> Most Igniters vote for per-data-page compression. > >> > > >> > >> > > >> I’d like to accumulate main theses to start implementation: > >> > > >> - page will be compressed with the dictionary-based approach > >> (e.g.LZV) > >> > > >> - page will be compressed in batch mode (not on every change) > >> > > >> - page compression should been initiated by an event, for > example, a > >> > > >> page’s free space drops below 20% > >> > > >> - compression process will be under page write lock > >> > > >> > >> > > >> Vladimir Ozerov has written: > >> > > >> > >> > > >>> What we do not understand yet: > >> > > >>>> 1) Granularity of compression algorithm. > >> > > >>>> 1.1) It could be per-entry - i.e. we compress the whole entry > >> > content, > >> > > >>>> but > >> > > >>>> respect boundaries between entries. E.g.: before - > >> > [ENTRY_1][ENTRY_2], > >> > > >>>> after - [COMPRESSED_ENTRY_1][COMPRESSED_ENTRY_2] (as opposed > to > >> > > >>>> [COMPRESSED ENTRY_1 and ENTRY_2]). > >> > > >>>> v1.2) Or it could be per-field - i.e. we compress fields, but > >> > respect > >> > > >>>> binary > >> > > >>>> object layout. First approach is simple, straightforward, and > will > >> > > give > >> > > >>>> acceptable compression rate, but we will have to compress the > >> whole > >> > > >>>> binary > >> > > >>>> object on every field access, what may ruin our SQL > performance. > >> > > Second > >> > > >>>> approach is more complex, we are not sure about it's > compression > >> > rate, > >> > > >>>> but > >> > > >>>> as BinaryObject structure is preserved, we will still have fast > >> > > >>>> constant-time per-field access. > >> > > >>>> > >> > > >>> I think there are advantages in both approaches and we will be > able > >> > to > >> > > >> compare different approaches and algorithms after prototype > >> > > >> implementation. > >> > > >> > >> > > >> Main approach in brief: > >> > > >> 1) When page’s free space drops below 20% will be triggered > >> > compression > >> > > >> event > >> > > >> 2) Page will be locked by write lock > >> > > >> 3) Page will be passed to page’s compressor implementation > >> > > >> 4) Page will be replaced by compressed page > >> > > >> > >> > > >> Whole object or a field reading: > >> > > >> 1) If page marked as compressed then the page will be handled by > >> > > >> page’s compressor implementation, otherwise, it will be handled > as > >> > > >> usual. > >> > > >> > >> > > >> Thoughts? > >> > > >> > >> > > >> Should we create new IEP and register tickets to start > >> implementation? > >> > > >> This will allow us to watch for the feature progress and related > >> > > >> tasks. > >> > > >> > >> > > >> > >> > > >> [1] http://apache-ignite-developers.2346864.n4.nabble.com/Data- > >> > > >> compression-in-Ignite-tc20679.html > >> > > >> > >> > > >> > >> > > >> > >> > > > -- > >> > > > Taras Ledkov > >> > > > Mail-To: tled...@gridgain.com > >> > > > > >> > > > > >> > > > >> > > >> > > > > -- > Best Regards, Vyacheslav D. >
