Re: filedesc_sx patch (20070401a)

On Wednesday 04 April 2007 00:01, Robert Watson wrote:
On Sun, 1 Apr 2007, Robert Watson wrote:
The attached patch moves file descriptor locks from being a custom
mutex/sleep lock implemented using msleep() to an sx lock. With the new
sx lock optimizations in place, this is now sensible, avoiding both a
custom lock type and significantly improving performance. Kris has
reported 2x-4x improvement in transactions/sec with MySQL using this
patch, as it greatly reduces the cost of lock contention during file
descriptor lookup for threaded applications, and also moves to shared
locking to avoid exclusive acquisition for read-only operations (the vast
majority in most workloads). Patch is below, but you can also download
from:

http://www.watson.org/~robert/freebsd/netperf/20070401a-filedesc-sx.diff

I'm currently waiting for the sx lock changes to settle for a few days
before committing, so will plan to commit this around Wednesday/Thursday
of this week (unless serious problems arise).

Andrzej has pointed out that shortly after I posted the patch, it came into
conflict with changes in VFS. I've updated the patch and posted it at:

http://www.watson.org/~robert/freebsd/netperf/20070403-filedesc-sx.diff

Just a small comment:

@@ -60,10 +60,7 @@
u_short fd_cmask; /* mask for file creation */
u_short fd_refcnt; /* thread reference count */
u_short fd_holdcnt; /* hold count on structure + mutex */
-
- struct mtx fd_mtx; /* protects members of this struct */
- int fd_locked; /* long lock flag */
- int fd_wanted; /* "" */
+ struct sx fd_sx; /* protects members of this struct */
struct kqlist fd_kqlist; /* list of kqueues on this filedesc */
int fd_holdleaderscount; /* block fdfree() for shared close() */
int fd_holdleaderswakeup; /* fdfree() needs wakeup */

Maybe it is better if you order the elements by size. Then you don't waste so
many extra bytes on platforms where the fields must be aligned.

struct {
struct sx fd_sx;
struct kqlist fd_kqlist;

int ...;

u_short ....;
};

--HPS
_______________________________________________
freebsd-performance@xxxxxxxxxxx mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-performance
To unsubscribe, send any mail to "freebsd-performance-unsubscribe@xxxxxxxxxxx"

Relevant Pages

  • [PATCH] 4/4 i_mmap_lock spinlock2rwsem (#v9 was 1/4)
    ... This is a rediff of Christoph's plain i_mmap_lock2rwsem patch on top ... A rw style lock allows concurrent ... struct page *page; ... struct file *file, struct address_space *mapping) ...
    (Linux-Kernel)
  • Re: [PATCH] lockfs patch for 2.6
    ... Christoph's vfs patch looks good, I've stripped out the XFS bits (FS ... I had to add a struct super_block pointer to ... * block device, we hould a read lock on the s->s_umount sem to make sure ... Lock the filesystem while a device is suspended. ...
    (Linux-Kernel)
  • Re: panic: System call lstat returning with 1 locks held
    ... I'm committing my WITNESS patch now to perforce so that other people ... Add WITNESS support to lockmgr. ... In the case of lockmgr_disown() the lock is simply dropped. ...
    (freebsd-current)
  • Re: panic: System call lstat returning with 1 locks held
    ... I'm committing my WITNESS patch now to perforce so that other people ... Add WITNESS support to lockmgr. ... In the case of lockmgr_disown() the lock is simply dropped. ...
    (freebsd-current)
  • Re: [PATCH -mm v4 6/9] atmel_serial: Split the interrupt handler
    ... existed of a set of patches suitable ... plus an additional patch for Preempt-RT only. ... the splitup of the interrupt handler was also needed for ... * uart_start, which takes the lock. ...
    (Linux-Kernel)