aboutsummaryrefslogtreecommitdiffstats
path: root/fs/xfs/xfs_ag.h
diff options
context:
space:
mode:
authorDavid Chinner <dgc@sgi.com>2007-05-24 01:26:31 -0400
committerTim Shimmin <tes@chook.melbourne.sgi.com>2007-07-14 01:28:50 -0400
commit92821e2ba4ae26887223326fb0b95cdab963b768 (patch)
treea40a2ef10e5b0791df3e522f3139193d39bf2454 /fs/xfs/xfs_ag.h
parent3260f78ad6d5b788e78ea709d377f58e569bee41 (diff)
[XFS] Lazy Superblock Counters
When we have a couple of hundred transactions on the fly at once, they all typically modify the on disk superblock in some way. create/unclink/mkdir/rmdir modify inode counts, allocation/freeing modify free block counts. When these counts are modified in a transaction, they must eventually lock the superblock buffer and apply the mods. The buffer then remains locked until the transaction is committed into the incore log buffer. The result of this is that with enough transactions on the fly the incore superblock buffer becomes a bottleneck. The result of contention on the incore superblock buffer is that transaction rates fall - the more pressure that is put on the superblock buffer, the slower things go. The key to removing the contention is to not require the superblock fields in question to be locked. We do that by not marking the superblock dirty in the transaction. IOWs, we modify the incore superblock but do not modify the cached superblock buffer. In short, we do not log superblock modifications to critical fields in the superblock on every transaction. In fact we only do it just before we write the superblock to disk every sync period or just before unmount. This creates an interesting problem - if we don't log or write out the fields in every transaction, then how do the values get recovered after a crash? the answer is simple - we keep enough duplicate, logged information in other structures that we can reconstruct the correct count after log recovery has been performed. It is the AGF and AGI structures that contain the duplicate information; after recovery, we walk every AGI and AGF and sum their individual counters to get the correct value, and we do a transaction into the log to correct them. An optimisation of this is that if we have a clean unmount record, we know the value in the superblock is correct, so we can avoid the summation walk under normal conditions and so mount/recovery times do not change under normal operation. One wrinkle that was discovered during development was that the blocks used in the freespace btrees are never accounted for in the AGF counters. This was once a valid optimisation to make; when the filesystem is full, the free space btrees are empty and consume no space. Hence when it matters, the "accounting" is correct. But that means the when we do the AGF summations, we would not have a correct count and xfs_check would complain. Hence a new counter was added to track the number of blocks used by the free space btrees. This is an *on-disk format change*. As a result of this, lazy superblock counters are a mkfs option and at the moment on linux there is no way to convert an old filesystem. This is possible - xfs_db can be used to twiddle the right bits and then xfs_repair will do the format conversion for you. Similarly, you can convert backwards as well. At some point we'll add functionality to xfs_admin to do the bit twiddling easily.... SGI-PV: 964999 SGI-Modid: xfs-linux-melb:xfs-kern:28652a Signed-off-by: David Chinner <dgc@sgi.com> Signed-off-by: Christoph Hellwig <hch@infradead.org> Signed-off-by: Tim Shimmin <tes@sgi.com>
Diffstat (limited to 'fs/xfs/xfs_ag.h')
-rw-r--r--fs/xfs/xfs_ag.h8
1 files changed, 6 insertions, 2 deletions
diff --git a/fs/xfs/xfs_ag.h b/fs/xfs/xfs_ag.h
index 9ece7f87ec5b..b1dd0029c60e 100644
--- a/fs/xfs/xfs_ag.h
+++ b/fs/xfs/xfs_ag.h
@@ -68,6 +68,7 @@ typedef struct xfs_agf {
68 __be32 agf_flcount; /* count of blocks in freelist */ 68 __be32 agf_flcount; /* count of blocks in freelist */
69 __be32 agf_freeblks; /* total free blocks */ 69 __be32 agf_freeblks; /* total free blocks */
70 __be32 agf_longest; /* longest free space */ 70 __be32 agf_longest; /* longest free space */
71 __be32 agf_btreeblks; /* # of blocks held in AGF btrees */
71} xfs_agf_t; 72} xfs_agf_t;
72 73
73#define XFS_AGF_MAGICNUM 0x00000001 74#define XFS_AGF_MAGICNUM 0x00000001
@@ -81,7 +82,8 @@ typedef struct xfs_agf {
81#define XFS_AGF_FLCOUNT 0x00000100 82#define XFS_AGF_FLCOUNT 0x00000100
82#define XFS_AGF_FREEBLKS 0x00000200 83#define XFS_AGF_FREEBLKS 0x00000200
83#define XFS_AGF_LONGEST 0x00000400 84#define XFS_AGF_LONGEST 0x00000400
84#define XFS_AGF_NUM_BITS 11 85#define XFS_AGF_BTREEBLKS 0x00000800
86#define XFS_AGF_NUM_BITS 12
85#define XFS_AGF_ALL_BITS ((1 << XFS_AGF_NUM_BITS) - 1) 87#define XFS_AGF_ALL_BITS ((1 << XFS_AGF_NUM_BITS) - 1)
86 88
87/* disk block (xfs_daddr_t) in the AG */ 89/* disk block (xfs_daddr_t) in the AG */
@@ -186,11 +188,13 @@ typedef struct xfs_perag
186 __uint32_t pagf_flcount; /* count of blocks in freelist */ 188 __uint32_t pagf_flcount; /* count of blocks in freelist */
187 xfs_extlen_t pagf_freeblks; /* total free blocks */ 189 xfs_extlen_t pagf_freeblks; /* total free blocks */
188 xfs_extlen_t pagf_longest; /* longest free space */ 190 xfs_extlen_t pagf_longest; /* longest free space */
191 __uint32_t pagf_btreeblks; /* # of blocks held in AGF btrees */
189 xfs_agino_t pagi_freecount; /* number of free inodes */ 192 xfs_agino_t pagi_freecount; /* number of free inodes */
193 xfs_agino_t pagi_count; /* number of allocated inodes */
194 int pagb_count; /* pagb slots in use */
190#ifdef __KERNEL__ 195#ifdef __KERNEL__
191 lock_t pagb_lock; /* lock for pagb_list */ 196 lock_t pagb_lock; /* lock for pagb_list */
192#endif 197#endif
193 int pagb_count; /* pagb slots in use */
194 xfs_perag_busy_t *pagb_list; /* unstable blocks */ 198 xfs_perag_busy_t *pagb_list; /* unstable blocks */
195} xfs_perag_t; 199} xfs_perag_t;
196 200