Hello, On (11/28/16 09:41), Minchan Kim wrote: > > I'm going on a long vacation so forgive if I respond slowly. :) no prob. have a good one! > On Sun, Nov 27, 2016 at 10:19:10PM +0900, Sergey Senozhatsky wrote: [..] > > wondering - how many pages can it hold? we are in low memory, that's why we > > failed to zsmalloc in fast path, so how likely this to worsen memory pressure? > > Actually, I don't have real number to say but a thing I can say surely is > it's really hard to meet in normal stress test I have done until now. > That's why it takes a long time to find(i.e., I could encounter the bug > once two days). But once I understood the problem, I can reproduce the > problem in 15 minutes. > > About memory pressure, my testing was already severe memory pressure(i.e., > many memory failure and frequent OOM kill) so it doesn't make any > meaningful difference before and after. > > > just asking. in async zram the window between zram_rw_page() and actual > > write of a page even bigger, isn't it? > > Yes. That's why I found the problem with that feature enabled. Lucky. ;) I see. just curious, the worst case is deflate compression (which can be 8-9 slower than lz4) and sync zram. right? are we speaking of megabytes here? > > we *probably* and *may be* can try handle it in zram: > > > > -- store the previous clen before re-compression > > -- check if new clen > saved_clen and if it is - we can't use previously > > allocate handle and need to allocate a new one again. if it's less or > > equal than the saved one - store the object (wasting some space, > > yes. but we are in low mem). > > It was my first attempt but changed mind. > It can save against crash but broken data could go to the disk > (i.e., zram). If someone want to read block directly(e.g., > open /dev/zram0; read /dev/zram or DIO), it cannot read the data > forever until someone writes some stable data into that sectors. > Instead, he will see many decompression failure message. > It's weired. > > I believe stable page problem should be solved by generic layer, > not driver itself. yeah, I'm fine with this. at the same, there are chances, I suspect, that may be we will see some 'regressions'. well, just may be. -ss -- To unsubscribe from this list: send the line "unsubscribe stable" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html