Linux's fsync() woes are getting some attention

Re:Linux's fsync() woes are getting some attention by bodyfour on Tuesday March 11, 2014 @03:30AM (#7377903)

True, and it's good of you to clarify. However, what if the "other pending writes" are to the same file descriptor? Just because I'm eager to know when one write happens doesn't mean I care about other writes I made elsewhere.

sync() is basically a relic. Historically it only existed so that a UNIX userland process could roughly control the rate that dirty buffers went to disk. This was the "update" daemon historically, known as "fsflush" on SYSV. At least on linux that's internal to the kernel these days.

[ Parent | on HN ]

Re:Linux's fsync() woes are getting some attention by e12e on Tuesday March 11, 2014 @04:30AM (#7378032)

Isn't sync() still useful for making sure all file-systems are sync'ed (as by the bin/sync utility -- which apparently basically calls sync())? For instance before shutdown?

[ Parent | on HN ]

Re:Linux's fsync() woes are getting some attention by B-Con on Tuesday March 11, 2014 @03:17PM (#7381515)

Occasionally helpful, yes. But in my experience, usually unnecessary. Filesystems will sync themselves prior to being unmounted, which takes care of most of the obvious sync usecases.

[ Parent | on HN ]