On 24/08/2024 02:55, Christophe JAILLET wrote: > Le 23/08/2024 à 21:04, Usama Arif a écrit : >> Approximately 10-20% of pages to be swapped out are zero pages [1]. >> Rather than reading/writing these pages to flash resulting >> in increased I/O and flash wear, a bitmap can be used to mark these >> pages as zero at write time, and the pages can be filled at >> read time if the bit corresponding to the page is set. >> With this patch, NVMe writes in Meta server fleet decreased >> by almost 10% with conventional swap setup (zswap disabled). >> >> [1] https://lore.kernel.org/all/20171018104832epcms5p1b2232e2236258de3d03d1344dde9fce0@epcms5p1/ >> > > ... > >> @@ -3428,6 +3444,17 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) >> goto bad_swap_unlock_inode; >> } >> + /* >> + * Use kvmalloc_array instead of bitmap_zalloc as the allocation order might >> + * be above MAX_PAGE_ORDER incase of a large swap file. >> + */ >> + zeromap = kvmalloc_array(BITS_TO_LONGS(maxpages), sizeof(long), >> + GFP_KERNEL | __GFP_ZERO); > > Nitpick: kvcalloc() maybe, to be slightly less verbose? > There was quite a long discussion [1] on this in v5 of the series, and we settled no kvmalloc_array in the end. I think best to leave it as it is at kvmalloc_array. Thanks [1] https://lore.kernel.org/all/159061bc-27b5-4127-a85d-223bed0ddfd5@xxxxxxxxx/
