Re: vmstat -z: zfs related failures on r255173

From: Dmitriy Makarov <supportme_at_ukr.net>
Date: Tue, 15 Oct 2013 14:53:31 +0300
('binary' encoding is not supported, stored as-is) Please, any idea, thougth, help! Maybe what information can be useful for diggin - anything... System what I'm talkin about has a huge problem: performance degradation in short time period (day-two). Don't know can we somehow relate this vmstat fails with degradation. > Hi all > > On CURRENT r255173 we have some interesting values from vmstat -z : REQ = FAIL > > [server]# vmstat -z > ITEM                   SIZE  LIMIT     USED     FREE      REQ FAIL SLEEP > ....... skipped.... > NCLNODE:                528,      0,       0,       0,       0,   0,   0 > space_seg_cache:         64,      0,  289198,  299554,25932081,25932081,   0 > zio_cache:              944,      0,   37512,   50124,1638254119,1638254119,   0 > zio_link_cache:          48,      0,   50955,   38104,1306418638,1306418638,   0 > sa_cache:                80,      0,   63694,      56,  198643,198643,   0 > dnode_t:                864,      0,  128813,       3,  184863,184863,   0 > dmu_buf_impl_t:         224,      0, 1610024,  314631,157119686,157119686,   0 > arc_buf_hdr_t:          216,      0,82949975,   56107,156352659,156352659,   0 > arc_buf_t:               72,      0, 1586866,  314374,158076670,158076670,   0 > zil_lwb_cache:          192,      0,    6354,    7526, 2486242,2486242,   0 > zfs_znode_cache:        368,      0,   63694,      16,  198643,198643,   0 > ..... skipped ...... > > Can anybody explain this strange failures in zfs related parameters in vmstat, can we do something with this and is this really bad signal? > > Thanks! Received on Tue Oct 15 2013 - 09:53:44 UTC

This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:40:42 UTC