From 119a394ab0eee137a5198ad3fffab45fb11ef108 Mon Sep 17 00:00:00 2001 From: Etienne Dechamps Date: Sun, 10 Nov 2013 15:00:11 +0000 Subject: Only commit the ZIL once in zpl_writepages() (msync() case). Currently, using msync() results in the following code path: sys_msync -> zpl_fsync -> filemap_write_and_wait_range -> zpl_writepages -> write_cache_pages -> zpl_putpage In such a code path, zil_commit() is called as part of zpl_putpage(). This means that for each page, the write is handed to the DMU, the ZIL is committed, and only then do we move on to the next page. As one might imagine, this results in atrocious performance where there is a large number of pages to write: instead of committing a batch of N writes, we do N commits containing one page each. In some extreme cases this can result in msync() being ~700 times slower than it should be, as well as very inefficient use of ZIL resources. This patch fixes this issue by making sure that the requested writes are batched and then committed only once. Unfortunately, the implementation is somewhat non-trivial because there is no way to run write_cache_pages in SYNC mode (so that we get all pages) without making it wait on the writeback tag for each page. The solution implemented here is composed of two parts: - I added a new callback system to the ZIL, which allows the caller to be notified when its ITX gets written to stable storage. One nice thing is that the callback is called not only in zil_commit() but in zil_sync() as well, which means that the caller doesn't have to care whether the write ended up in the ZIL or the DMU: it will get notified as soon as it's safe, period. This is an improvement over dmu_tx_callback_register() that was used previously, which only supports DMU writes. The rationale for this change is to allow zpl_putpage() to be notified when a ZIL commit is completed without having to block on zil_commit() itself. - zpl_writepages() now calls write_cache_pages in non-SYNC mode, which will prevent (1) write_cache_pages from blocking, and (2) zpl_putpage from issuing ZIL commits. zpl_writepages() will issue the commit itself instead of relying on zpl_putpage() to do it, thus nicely batching the writes. Note, however, that we still have to call write_cache_pages() again in SYNC mode because there is an edge case documented in the implementation of write_cache_pages() whereas it will not give us all dirty pages when running in non-SYNC mode. Thus we need to run it at least once in SYNC mode to make sure we honor persistency guarantees. This only happens when the pages are modified at the same time msync() is running, which should be rare. In most cases there won't be any additional pages and this second call will do nothing. Note that this change also fixes a bug related to #907 whereas calling msync() on pages that were already handed over to the DMU in a previous writepages() call would make msync() block until the next TXG sync instead of returning as soon as the ZIL commit is complete. The new callback system fixes that problem. Signed-off-by: Richard Yao Signed-off-by: Brian Behlendorf Closes #1849 Closes #907 --- include/sys/zfs_znode.h | 3 ++- include/sys/zil.h | 4 ++++ 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/sys/zfs_znode.h b/include/sys/zfs_znode.h index b5ab7dbae..620244556 100644 --- a/include/sys/zfs_znode.h +++ b/include/sys/zfs_znode.h @@ -353,7 +353,8 @@ extern void zfs_log_symlink(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype, extern void zfs_log_rename(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype, znode_t *sdzp, char *sname, znode_t *tdzp, char *dname, znode_t *szp); extern void zfs_log_write(zilog_t *zilog, dmu_tx_t *tx, int txtype, - znode_t *zp, offset_t off, ssize_t len, int ioflag); + znode_t *zp, offset_t off, ssize_t len, int ioflag, + zil_callback_t callback, void *callback_data); extern void zfs_log_truncate(zilog_t *zilog, dmu_tx_t *tx, int txtype, znode_t *zp, uint64_t off, uint64_t len); extern void zfs_log_setattr(zilog_t *zilog, dmu_tx_t *tx, int txtype, diff --git a/include/sys/zil.h b/include/sys/zil.h index d3e4b8ec6..b6718b93c 100644 --- a/include/sys/zil.h +++ b/include/sys/zil.h @@ -361,11 +361,15 @@ typedef enum { WR_NUM_STATES /* number of states */ } itx_wr_state_t; +typedef void (*zil_callback_t)(void *data); + typedef struct itx { list_node_t itx_node; /* linkage on zl_itx_list */ void *itx_private; /* type-specific opaque data */ itx_wr_state_t itx_wr_state; /* write state */ uint8_t itx_sync; /* synchronous transaction */ + zil_callback_t itx_callback; /* Called when the itx is persistent */ + void *itx_callback_data; /* User data for the callback */ uint64_t itx_sod; /* record size on disk */ uint64_t itx_oid; /* object id */ lr_t itx_lr; /* common part of log record */ -- cgit v1.2.3