search for: do_utime

While going through an old todo list I found that these patches had fallen by the way-side. About a year ago I initiated a discussion[1] with the Linux kernel folks regarding the lack of any useable fadvise support on the kernel side. As a result, I was observing extremely poor performance on my server after backup as executable pages were being swapped out in favor of data waiting to be flushed

https://bugzilla.samba.org/show_bug.cgi?id=5506 Summary: support utime differences at runtime, not configure/build time Product: rsync Version: 3.0.3 Platform: All URL: http://thread.gmane.org/gmane.network.rsync.general/1794 8 OS/Version: Linux Status: NEW Severity:

...f810ee1ce>] ? do_sync_write+0xce/0x113 [ 240.602082] [<ffffffff81051e75>] ? current_fs_time+0x1e/0x24 [ 240.602968] [<ffffffff811009b7>] ? notify_change+0x180/0x2c5 [ 240.604245] [<ffffffff8110b7b5>] ? utimes_common+0x12d/0x14d [ 240.605355] [<ffffffff8110b856>] ? do_utimes+0x81/0xca [ 240.606558] [<ffffffff8110b9ab>] ? sys_utimensat+0x5b/0x6a [ 240.607817] [<ffffffff81010b42>] ? system_call_fastpath+0x16/0x1b [ 240.609124] INFO: task find:1866 blocked for more than 120 seconds. [ 240.610409] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs...

...f810ee1ce>] ? do_sync_write+0xce/0x113 [ 240.602082] [<ffffffff81051e75>] ? current_fs_time+0x1e/0x24 [ 240.602968] [<ffffffff811009b7>] ? notify_change+0x180/0x2c5 [ 240.604245] [<ffffffff8110b7b5>] ? utimes_common+0x12d/0x14d [ 240.605355] [<ffffffff8110b856>] ? do_utimes+0x81/0xca [ 240.606558] [<ffffffff8110b9ab>] ? sys_utimensat+0x5b/0x6a [ 240.607817] [<ffffffff81010b42>] ? system_call_fastpath+0x16/0x1b [ 240.609124] INFO: task find:1866 blocked for more than 120 seconds. [ 240.610409] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs...

...c 7 19:18:38 revo [<b0196197>] inode_setattr+0xb7/0x180 Dec 7 19:18:38 revo [<b01cee9e>] btrfs_setattr+0x3e/0x2a0 Dec 7 19:18:38 revo [<b01712e2>] handle_mm_fault+0xf2/0x570 Dec 7 19:18:38 revo [<b019633c>] notify_change+0xdc/0x2c0 Dec 7 19:18:38 revo [<b01a1611>] do_utimes+0x161/0x250 Dec 7 19:18:38 revo [<b01712e2>] handle_mm_fault+0xf2/0x570 Dec 7 19:18:38 revo [<b01a1721>] sys_futimesat+0x21/0xa0 Dec 7 19:18:38 revo [<b01a17bf>] sys_utimes+0x1f/0x30 Dec 7 19:18:38 revo [<b0104256>] sysenter_past_esp+0x5f/0x85 Dec 7 19:18:38 revo =====...