search for: posix_fadv_willneed

...liasing=2 \ -I/usr/local/include -MT fs-posix.lo -MD -MP -MF .deps/fs-posix.Tpo \ -c fs-posix.c -fPIC -DPIC -o .libs/fs-posix.o | fs-posix.c: In function 'fs_posix_prefetch': | fs-posix.c:298: warning: implicit declaration of function 'posix_fadvise' | fs-posix.c:298: error: 'POSIX_FADV_WILLNEED' undeclared (first use in this function) | fs-posix.c:298: error: (Each undeclared identifier is reported only once | fs-posix.c:298: error: for each function it appears in.) | gmake[3]: *** [fs-posix.lo] Error 1 | gmake[3]: Leaving directory `/usr/local/etc/dovecot/SOURCE/dovecot-2.2/src/lib-f...

The way we used posix_fadvise was wrong, and yet right! Rich.

...OSIX_FADV_DONTNEED)); +#endif +} + +/** + * Hint that we will access the data in the near future. + * + * It's OK to call this on a non-file since we ignore failure as it is + * only a hint. + */ +void +guestfs_int_fadvise_willneed (int fd) +{ +#if defined(HAVE_POSIX_FADVISE) && defined(POSIX_FADV_WILLNEED) + /* It's not clear from the man page, but the 'advice' parameter is + * NOT a bitmask. You can only pass one parameter with each call. + */ + ignore_value (posix_fadvise (fd, 0, 0, POSIX_FADV_WILLNEED)); +#endif +} -- 2.7.4

...doing (FETCH, wait, FETCH, wait, ...) it can do (FETCH, FETCH, .., wait). For the same reason it's also going to be very useful once I add support for key-value databases / other high latency cloud filesystems. It also works with Maildir, single-dbox and cydir backends by calling posix_fadvise(POSIX_FADV_WILLNEED) for the files. This syscall is apparently only implemented by Linux. It should tell the kernel to start reading the files from disk to page cache. By calling this for multiple files, it should help the kernel optimize disk I/O. For example if 10 files are prefetched, the kernel might figure out th...

Hello! I am writing a Linux server, and I want to pre-fetch a number of CIFS files and cache locally. The files are on a CIFS share mounted as read only. I was planning on opening the file, calling posix_fadvise(........,POSIX_FADV_WILLNEED) on the file descriptor, and then closing the file. Will this work? Is there a better way of doing this? Thanks!! Aaron

...inbind.so.2", O_RDONLY) = 5 read(5, "\177ELF\2\1\1\0\0\0\0\0\0\0\0\0\3\0>\0\1\0\0\0\200\33\0"..., 832) = 832 fstat(5, {st_mode=S_IFREG|0755, st_size=35642, ...}) = 0 mmap(NULL, 2145744, PROT_READ|PROT_EXEC, MAP_PRIVATE|MAP_DENYWRITE, 5, 0) = 0x7f748e928000 fadvise64(5, 0, 2145744, POSIX_FADV_WILLNEED) = 0 mprotect(0x7f748e92d000, 2097152, PROT_NONE) = 0 mmap(0x7f748eb2d000, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED| MAP_DENYWRITE, 5, 0x5000) = 0x7f748eb2d000 mmap(0x7f748eb2f000, 19920, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED| MAP_ANONYMOUS, -1, 0) = 0x7f748eb2f000 close(5)...

Franz Fellner <alpine.art.de at gmail.com> writes: > I also suffer from bad performance of notmuch new. I used notmuch > some years ago and notmuch new always felt instantanious. Had to stop > using it because internet was too slow to sync my mails :/ Now (with > better internet and a completely new setup using mbsync) indexing one > mail takes at least 10 seconds,

...* SEEK_HOLE */ + +#if HAVE_POSIX_FADVISE +/* Caching. */ +int +fileops_cache (void *handle, uint32_t count, uint64_t offset, uint32_t flags) +{ + struct fileops *fops = handle; + int r; + + /* Cache is advisory, we don't care if this fails */ + r = posix_fadvise (fops->fd, offset, count, POSIX_FADV_WILLNEED); + if (r) { + errno = r; + nbdkit_error ("posix_fadvise: %m"); + return -1; + } + return 0; +} +#endif /* HAVE_POSIX_FADVISE */ diff --git a/plugins/file/file.c b/plugins/file/file.c index 8c2ea077..3dd6c944 100644 --- a/plugins/file/file.c +++ b/plugins/file/file.c @@ -34,51...

There's a lot of code in nbdkit-file-plugin which it would be nice to reuse elsewhere. One possible approach (as outlined here) is simply to move the file callbacks (like file.pread, file.pwrite, file.zero etc) to a new mini-library. They can then be consumed by other plugins fairly easily by doing: static void * foo_open (int readonly) { struct fileops *fops; int fd, flags; /*

I'm still working my way through the filters before this series will be complete, but this is enough of a start to at least get some feedback on the idea of implementing another NBD protocol extension. Eric Blake (9): server: Internal hooks for implementing NBD_CMD_CACHE plugins: Add .cache callback file, split: Implement .cache with posix_fadvise nbd: Implement NBD_CMD_CACHE

Since v1: - rework .can_cache to be tri-state, with default of no advertisement (ripple effect through other patches) - add a lot more patches in order to round out filter support And in the meantime, Rich pushed NBD_CMD_CACHE support into libnbd, so in theory we now have a way to test cache commands through the entire stack. Eric Blake (24): server: Internal hooks for implementing

Needs some work still, see in particular the commit message for patch 3. Rich.

...t; tags 614543 + jessie Bug #614543 [src:python2.5] python2.5: FTBFS: network errors Added tag(s) jessie. > tags 556331 + jessie Bug #556331 [src:rubrica] FTBFS with binutils-gold Added tag(s) jessie. > tags 697015 + jessie Bug #697015 [src:imagevis3d] imagevis3d: FTBFS[kfreebsd]: error: 'POSIX_FADV_WILLNEED' was not declared in this scope Added tag(s) jessie. > tags 665027 + jessie Bug #665027 {Done: Francesco Paolo Lovergine <frankie at debian.org>} [src:saga] saga: FTBFS: build-dependency not installable: liblas-dev Added tag(s) jessie. > tags 701397 + jessie Bug #701397 [src:guile-2...