From: Dave Chinner <dchinner@xxxxxxxxxx>
XFS has a per-cpu counter implementation for in-core superblock
counters that pre-dated the generic implementation. It is complex
and baroque as it is tailored directly to the needs of ENOSPC
detection. Implement the complex accurate-compare-and-add
calculation in the generic per-cpu counter code and convert the
XFS counters to use the much simpler generic counter code.
Passes xfsqa on SMP system.
Still to do:
1. UP build and test.
2. split into separate patches
For discussion:
1. kill the no-per-cpu-counter mode?
2. does we need a custom batch size?
3. do we need to factor xfs_mod_sb_incore()?
4. should all the readers just sum the counters themselves
and kill the wrapperÑ?
Signed-off-by: Dave Chinner <dchinner@xxxxxxxxxx>
---
fs/xfs/linux-2.6/xfs_linux.h | 9 -
fs/xfs/linux-2.6/xfs_super.c | 4 +-
fs/xfs/xfs_fsops.c | 4 +-
fs/xfs/xfs_mount.c | 834 +++++++++++-----------------------------
fs/xfs/xfs_mount.h | 80 +---
include/linux/percpu_counter.h | 16 +
lib/percpu_counter.c | 79 ++++
7 files changed, 341 insertions(+), 685 deletions(-)
diff --git a/fs/xfs/linux-2.6/xfs_linux.h b/fs/xfs/linux-2.6/xfs_linux.h
index 214ddd7..9fa4f2a 100644
--- a/fs/xfs/linux-2.6/xfs_linux.h
+++ b/fs/xfs/linux-2.6/xfs_linux.h
@@ -88,15 +88,6 @@
#include <xfs_super.h>
#include <xfs_buf.h>
-/*
- * Feature macros (disable/enable)
- */
-#ifdef CONFIG_SMP
-#define HAVE_PERCPU_SB /* per cpu superblock counters are a 2.6 feature */
-#else
-#undef HAVE_PERCPU_SB /* per cpu superblock counters are a 2.6 feature */
-#endif
-
#define irix_sgid_inherit xfs_params.sgid_inherit.val
#define irix_symlink_mode xfs_params.symlink_mode.val
#define xfs_panic_mask xfs_params.panic_mask.val
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index 53ab47f..fa789b7 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -1230,9 +1230,9 @@ xfs_fs_statfs(
statp->f_fsid.val[0] = (u32)id;
statp->f_fsid.val[1] = (u32)(id >> 32);
- xfs_icsb_sync_counters(mp, XFS_ICSB_LAZY_COUNT);
-
spin_lock(&mp->m_sb_lock);
+ xfs_icsb_sync_counters_locked(mp);
+
statp->f_bsize = sbp->sb_blocksize;
lsize = sbp->sb_logstart ? sbp->sb_logblocks : 0;
statp->f_blocks = sbp->sb_dblocks - lsize;
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index a7c116e..44ecf1b 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -478,7 +478,7 @@ xfs_fs_counts(
xfs_mount_t *mp,
xfs_fsop_counts_t *cnt)
{
- xfs_icsb_sync_counters(mp, XFS_ICSB_LAZY_COUNT);
+ xfs_icsb_sync_counters(mp);
spin_lock(&mp->m_sb_lock);
cnt->freedata = mp->m_sb.sb_fdblocks - XFS_ALLOC_SET_ASIDE(mp);
cnt->freertx = mp->m_sb.sb_frextents;
@@ -540,7 +540,7 @@ xfs_reserve_blocks(
*/
retry:
spin_lock(&mp->m_sb_lock);
- xfs_icsb_sync_counters_locked(mp, 0);
+ xfs_icsb_sync_counters_locked(mp);
/*
* If our previous reservation was larger than the current value,
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 19e9dfa..0d9a030 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -46,19 +46,6 @@
STATIC void xfs_unmountfs_wait(xfs_mount_t *);
-
-#ifdef HAVE_PERCPU_SB
-STATIC void xfs_icsb_balance_counter(xfs_mount_t *, xfs_sb_field_t,
- int);
-STATIC void xfs_icsb_balance_counter_locked(xfs_mount_t *, xfs_sb_field_t,
- int);
-STATIC void xfs_icsb_disable_counter(xfs_mount_t *, xfs_sb_field_t);
-#else
-
-#define xfs_icsb_balance_counter(mp, a, b) do { } while (0)
-#define xfs_icsb_balance_counter_locked(mp, a, b) do { } while (0)
-#endif
-
static const struct {
short offset;
short type; /* 0 = integer
@@ -280,6 +267,111 @@ xfs_free_perag(
}
}
+
+/*
+ * Per-cpu incore superblock counters
+ *
+ * Simple concept, difficult implementation, now somewhat simplified by generic
+ * per-cpu counter support. This provides distributed per cpu counters for
+ * contended fields (e.g. free block count).
+ *
+ * Difficulties arise in that the incore sb is used for ENOSPC checking, and
+ * hence needs to be accurately read when we are running low on space. Hence We
+ * need to check against counter error bounds and determine how accurately to
+ * sum based on that metric. The percpu counters take care of this for us,
+ * so we only need to modify the fast path to handle per-cpu counter error
+ * cases.
+ */
+static inline int
+xfs_icsb_add(
+ struct xfs_mount *mp,
+ int counter,
+ int64_t delta,
+ int64_t threshold)
+{
+ int ret;
+
+ ret = percpu_counter_add_unless_lt(&mp->m_icsb[counter], delta,
+ threshold);
+ if (ret < 0)
+ return -ENOSPC;
+ return 0;
+}
+
+static inline void
+xfs_icsb_set(
+ struct xfs_mount *mp,
+ int counter,
+ int64_t value)
+{
+ percpu_counter_set(&mp->m_icsb[counter], value);
+}
+
+static inline int64_t
+xfs_icsb_sum(
+ struct xfs_mount *mp,
+ int counter)
+{
+ return percpu_counter_sum_positive(&mp->m_icsb[counter]);
+}
+
+static inline int64_t
+xfs_icsb_read(
+ struct xfs_mount *mp,
+ int counter)
+{
+ return percpu_counter_read_positive(&mp->m_icsb[counter]);
+}
+
+void
+xfs_icsb_reinit_counters(
+ struct xfs_mount *mp)
+{
+ xfs_icsb_set(mp, XFS_ICSB_FDBLOCKS, mp->m_sb.sb_fdblocks);
+ xfs_icsb_set(mp, XFS_ICSB_IFREE, mp->m_sb.sb_ifree);
+ xfs_icsb_set(mp, XFS_ICSB_ICOUNT, mp->m_sb.sb_icount);
+}
+
+int
+xfs_icsb_init_counters(
+ struct xfs_mount *mp)
+{
+ int i;
+ int error;
+
+ for (i = 0; i < XFS_ICSB_MAX; i++) {
+ error = percpu_counter_init(&mp->m_icsb[i], 0);
+ if (error)
+ goto out_error;
+ }
+ xfs_icsb_reinit_counters(mp);
+ return 0;
+
+out_error:
+ for (; i >= 0; i--)
+ percpu_counter_destroy(&mp->m_icsb[i]);
+ return error;
+}
+
+void
+xfs_icsb_destroy_counters(
+ xfs_mount_t *mp)
+{
+ int i;
+
+ for (i = 0; i < XFS_ICSB_MAX; i++)
+ percpu_counter_destroy(&mp->m_icsb[i]);
+}
+
+void
+xfs_icsb_sync_counters_locked(
+ xfs_mount_t *mp)
+{
+ mp->m_sb.sb_icount = xfs_icsb_sum(mp, XFS_ICSB_ICOUNT);
+ mp->m_sb.sb_ifree = xfs_icsb_sum(mp, XFS_ICSB_IFREE);
+ mp->m_sb.sb_fdblocks = xfs_icsb_sum(mp, XFS_ICSB_FDBLOCKS);
+}
+
/*
* Check size of device based on the (data/realtime) block count.
* Note: this check is used by the growfs code as well as mount.
@@ -1562,7 +1654,7 @@ xfs_log_sbcount(
if (!xfs_fs_writable(mp))
return 0;
- xfs_icsb_sync_counters(mp, 0);
+ xfs_icsb_sync_counters(mp);
/*
* we don't need to do this if we are updating the superblock
@@ -1674,9 +1766,9 @@ xfs_mod_incore_sb_unlocked(
int64_t delta,
int rsvd)
{
- int scounter; /* short counter for 32 bit fields */
- long long lcounter; /* long counter for 64 bit fields */
- long long res_used, rem;
+ int scounter = 0; /* short counter for 32 bit fields */
+ long long lcounter = 0; /* long counter for 64 bit fields */
+ long long res_used;
/*
* With the in-core superblock spin lock held, switch
@@ -1708,43 +1800,45 @@ xfs_mod_incore_sb_unlocked(
mp->m_sb.sb_fdblocks - XFS_ALLOC_SET_ASIDE(mp);
res_used = (long long)(mp->m_resblks - mp->m_resblks_avail);
- if (delta > 0) { /* Putting blocks back */
+ /*
+ * if we are putting blocks back, put them into the reserve
+ * block pool first.
+ */
+ if (res_used && delta > 0) {
if (res_used > delta) {
mp->m_resblks_avail += delta;
+ delta = 0;
} else {
- rem = delta - res_used;
mp->m_resblks_avail = mp->m_resblks;
- lcounter += rem;
+ delta -= res_used;
}
- } else { /* Taking blocks away */
- lcounter += delta;
- if (lcounter >= 0) {
- mp->m_sb.sb_fdblocks = lcounter +
- XFS_ALLOC_SET_ASIDE(mp);
+ if (!delta)
return 0;
- }
+ }
- /*
- * We are out of blocks, use any available reserved
- * blocks if were allowed to.
- */
- if (!rsvd)
- return XFS_ERROR(ENOSPC);
+ lcounter += delta;
+ if (likely(lcounter >= 0)) {
+ mp->m_sb.sb_fdblocks = lcounter +
+ XFS_ALLOC_SET_ASIDE(mp);
+ return 0;
+ }
- lcounter = (long long)mp->m_resblks_avail + delta;
- if (lcounter >= 0) {
- mp->m_resblks_avail = lcounter;
- return 0;
- }
- printk_once(KERN_WARNING
- "Filesystem \"%s\": reserve blocks depleted! "
- "Consider increasing reserve pool size.",
- mp->m_fsname);
+ /* ENOSPC */
+ ASSERT(delta < 0);
+ if (!rsvd)
return XFS_ERROR(ENOSPC);
+
+ lcounter = (long long)mp->m_resblks_avail + delta;
+ if (lcounter >= 0) {
+ mp->m_resblks_avail = lcounter;
+ return 0;
}
+ printk_once(KERN_WARNING
+ "Filesystem \"%s\": reserve blocks depleted! "
+ "Consider increasing reserve pool size.",
+ mp->m_fsname);
+ return XFS_ERROR(ENOSPC);
- mp->m_sb.sb_fdblocks = lcounter + XFS_ALLOC_SET_ASIDE(mp);
- return 0;
case XFS_SBS_FREXTENTS:
lcounter = (long long)mp->m_sb.sb_frextents;
lcounter += delta;
@@ -1846,9 +1940,7 @@ xfs_mod_incore_sb(
{
int status;
-#ifdef HAVE_PERCPU_SB
ASSERT(field < XFS_SBS_ICOUNT || field > XFS_SBS_FDBLOCKS);
-#endif
spin_lock(&mp->m_sb_lock);
status = xfs_mod_incore_sb_unlocked(mp, field, delta, rsvd);
spin_unlock(&mp->m_sb_lock);
@@ -1907,6 +1999,89 @@ unwind:
return error;
}
+int
+xfs_icsb_modify_counters(
+ xfs_mount_t *mp,
+ xfs_sb_field_t field,
+ int64_t delta,
+ int rsvd)
+{
+ int64_t lcounter;
+ int64_t res_used;
+ int ret = 0;
+
+
+ switch (field) {
+ case XFS_SBS_ICOUNT:
+ ret = xfs_icsb_add(mp, XFS_ICSB_ICOUNT, delta, 0);
+ if (ret < 0) {
+ ASSERT(0);
+ return XFS_ERROR(EINVAL);
+ }
+ return 0;
+
+ case XFS_SBS_IFREE:
+ ret = xfs_icsb_add(mp, XFS_ICSB_IFREE, delta, 0);
+ if (ret < 0) {
+ ASSERT(0);
+ return XFS_ERROR(EINVAL);
+ }
+ return 0;
+
+ case XFS_SBS_FDBLOCKS:
+ /*
+ * if we are putting blocks back, put them into the reserve
+ * block pool first.
+ */
+ if (mp->m_resblks != mp->m_resblks_avail && delta > 0) {
+ spin_lock(&mp->m_sb_lock);
+ res_used = (int64_t)(mp->m_resblks -
+ mp->m_resblks_avail);
+ if (res_used > delta) {
+ mp->m_resblks_avail += delta;
+ delta = 0;
+ } else {
+ delta -= res_used;
+ mp->m_resblks_avail = mp->m_resblks;
+ }
+ spin_unlock(&mp->m_sb_lock);
+ if (!delta)
+ return 0;
+ }
+
+ /* try the change */
+ ret = xfs_icsb_add(mp, XFS_ICSB_FDBLOCKS, delta,
+ XFS_ALLOC_SET_ASIDE(mp));
+ if (likely(ret >= 0))
+ return 0;
+
+ /* ENOSPC */
+ ASSERT(ret == -ENOSPC);
+ ASSERT(delta < 0);
+
+ if (!rsvd)
+ return XFS_ERROR(ENOSPC);
+
+ spin_lock(&mp->m_sb_lock);
+ lcounter = (int64_t)mp->m_resblks_avail + delta;
+ if (lcounter >= 0) {
+ mp->m_resblks_avail = lcounter;
+ spin_unlock(&mp->m_sb_lock);
+ return 0;
+ }
+ spin_unlock(&mp->m_sb_lock);
+ printk_once(KERN_WARNING
+ "Filesystem \"%s\": reserve blocks depleted! "
+ "Consider increasing reserve pool size.",
+ mp->m_fsname);
+ return XFS_ERROR(ENOSPC);
+ default:
+ ASSERT(0);
+ return XFS_ERROR(EINVAL);
+ }
+ return 0;
+}
+
/*
* xfs_getsb() is called to obtain the buffer for the superblock.
* The buffer is returned locked and read in from disk.
@@ -2000,572 +2175,3 @@ xfs_dev_is_read_only(
}
return 0;
}
-
-#ifdef HAVE_PERCPU_SB
-/*
- * Per-cpu incore superblock counters
- *
- * Simple concept, difficult implementation
- *
- * Basically, replace the incore superblock counters with a distributed per cpu
- * counter for contended fields (e.g. free block count).
- *
- * Difficulties arise in that the incore sb is used for ENOSPC checking, and
- * hence needs to be accurately read when we are running low on space. Hence
- * there is a method to enable and disable the per-cpu counters based on how
- * much "stuff" is available in them.
- *
- * Basically, a counter is enabled if there is enough free resource to justify
- * running a per-cpu fast-path. If the per-cpu counter runs out (i.e. a local
- * ENOSPC), then we disable the counters to synchronise all callers and
- * re-distribute the available resources.
- *
- * If, once we redistributed the available resources, we still get a failure,
- * we disable the per-cpu counter and go through the slow path.
- *
- * The slow path is the current xfs_mod_incore_sb() function. This means that
- * when we disable a per-cpu counter, we need to drain its resources back to
- * the global superblock. We do this after disabling the counter to prevent
- * more threads from queueing up on the counter.
- *
- * Essentially, this means that we still need a lock in the fast path to enable
- * synchronisation between the global counters and the per-cpu counters. This
- * is not a problem because the lock will be local to a CPU almost all the time
- * and have little contention except when we get to ENOSPC conditions.
- *
- * Basically, this lock becomes a barrier that enables us to lock out the fast
- * path while we do things like enabling and disabling counters and
- * synchronising the counters.
- *
- * Locking rules:
- *
- * 1. m_sb_lock before picking up per-cpu locks
- * 2. per-cpu locks always picked up via for_each_online_cpu() order
- * 3. accurate counter sync requires m_sb_lock + per cpu locks
- * 4. modifying per-cpu counters requires holding per-cpu lock
- * 5. modifying global counters requires holding m_sb_lock
- * 6. enabling or disabling a counter requires holding the m_sb_lock
- * and _none_ of the per-cpu locks.
- *
- * Disabled counters are only ever re-enabled by a balance operation
- * that results in more free resources per CPU than a given threshold.
- * To ensure counters don't remain disabled, they are rebalanced when
- * the global resource goes above a higher threshold (i.e. some hysteresis
- * is present to prevent thrashing).
- */
-
-#ifdef CONFIG_HOTPLUG_CPU
-/*
- * hot-plug CPU notifier support.
- *
- * We need a notifier per filesystem as we need to be able to identify
- * the filesystem to balance the counters out. This is achieved by
- * having a notifier block embedded in the xfs_mount_t and doing pointer
- * magic to get the mount pointer from the notifier block address.
- */
-STATIC int
-xfs_icsb_cpu_notify(
- struct notifier_block *nfb,
- unsigned long action,
- void *hcpu)
-{
- xfs_icsb_cnts_t *cntp;
- xfs_mount_t *mp;
-
- mp = (xfs_mount_t *)container_of(nfb, xfs_mount_t, m_icsb_notifier);
- cntp = (xfs_icsb_cnts_t *)
- per_cpu_ptr(mp->m_sb_cnts, (unsigned long)hcpu);
- switch (action) {
- case CPU_UP_PREPARE:
- case CPU_UP_PREPARE_FROZEN:
- /* Easy Case - initialize the area and locks, and
- * then rebalance when online does everything else for us. */
- memset(cntp, 0, sizeof(xfs_icsb_cnts_t));
- break;
- case CPU_ONLINE:
- case CPU_ONLINE_FROZEN:
- xfs_icsb_lock(mp);
- xfs_icsb_balance_counter(mp, XFS_SBS_ICOUNT, 0);
- xfs_icsb_balance_counter(mp, XFS_SBS_IFREE, 0);
- xfs_icsb_balance_counter(mp, XFS_SBS_FDBLOCKS, 0);
- xfs_icsb_unlock(mp);
- break;
- case CPU_DEAD:
- case CPU_DEAD_FROZEN:
- /* Disable all the counters, then fold the dead cpu's
- * count into the total on the global superblock and
- * re-enable the counters. */
- xfs_icsb_lock(mp);
- spin_lock(&mp->m_sb_lock);
- xfs_icsb_disable_counter(mp, XFS_SBS_ICOUNT);
- xfs_icsb_disable_counter(mp, XFS_SBS_IFREE);
- xfs_icsb_disable_counter(mp, XFS_SBS_FDBLOCKS);
-
- mp->m_sb.sb_icount += cntp->icsb_icount;
- mp->m_sb.sb_ifree += cntp->icsb_ifree;
- mp->m_sb.sb_fdblocks += cntp->icsb_fdblocks;
-
- memset(cntp, 0, sizeof(xfs_icsb_cnts_t));
-
- xfs_icsb_balance_counter_locked(mp, XFS_SBS_ICOUNT, 0);
- xfs_icsb_balance_counter_locked(mp, XFS_SBS_IFREE, 0);
- xfs_icsb_balance_counter_locked(mp, XFS_SBS_FDBLOCKS, 0);
- spin_unlock(&mp->m_sb_lock);
- xfs_icsb_unlock(mp);
- break;
- }
-
- return NOTIFY_OK;
-}
-#endif /* CONFIG_HOTPLUG_CPU */
-
-int
-xfs_icsb_init_counters(
- xfs_mount_t *mp)
-{
- xfs_icsb_cnts_t *cntp;
- int i;
-
- mp->m_sb_cnts = alloc_percpu(xfs_icsb_cnts_t);
- if (mp->m_sb_cnts == NULL)
- return -ENOMEM;
-
-#ifdef CONFIG_HOTPLUG_CPU
- mp->m_icsb_notifier.notifier_call = xfs_icsb_cpu_notify;
- mp->m_icsb_notifier.priority = 0;
- register_hotcpu_notifier(&mp->m_icsb_notifier);
-#endif /* CONFIG_HOTPLUG_CPU */
-
- for_each_online_cpu(i) {
- cntp = (xfs_icsb_cnts_t *)per_cpu_ptr(mp->m_sb_cnts, i);
- memset(cntp, 0, sizeof(xfs_icsb_cnts_t));
- }
-
- mutex_init(&mp->m_icsb_mutex);
-
- /*
- * start with all counters disabled so that the
- * initial balance kicks us off correctly
- */
- mp->m_icsb_counters = -1;
- return 0;
-}
-
-void
-xfs_icsb_reinit_counters(
- xfs_mount_t *mp)
-{
- xfs_icsb_lock(mp);
- /*
- * start with all counters disabled so that the
- * initial balance kicks us off correctly
- */
- mp->m_icsb_counters = -1;
- xfs_icsb_balance_counter(mp, XFS_SBS_ICOUNT, 0);
- xfs_icsb_balance_counter(mp, XFS_SBS_IFREE, 0);
- xfs_icsb_balance_counter(mp, XFS_SBS_FDBLOCKS, 0);
- xfs_icsb_unlock(mp);
-}
-
-void
-xfs_icsb_destroy_counters(
- xfs_mount_t *mp)
-{
- if (mp->m_sb_cnts) {
- unregister_hotcpu_notifier(&mp->m_icsb_notifier);
- free_percpu(mp->m_sb_cnts);
- }
- mutex_destroy(&mp->m_icsb_mutex);
-}
-
-STATIC void
-xfs_icsb_lock_cntr(
- xfs_icsb_cnts_t *icsbp)
-{
- while (test_and_set_bit(XFS_ICSB_FLAG_LOCK, &icsbp->icsb_flags)) {
- ndelay(1000);
- }
-}
-
-STATIC void
-xfs_icsb_unlock_cntr(
- xfs_icsb_cnts_t *icsbp)
-{
- clear_bit(XFS_ICSB_FLAG_LOCK, &icsbp->icsb_flags);
-}
-
-
-STATIC void
-xfs_icsb_lock_all_counters(
- xfs_mount_t *mp)
-{
- xfs_icsb_cnts_t *cntp;
- int i;
-
- for_each_online_cpu(i) {
- cntp = (xfs_icsb_cnts_t *)per_cpu_ptr(mp->m_sb_cnts, i);
- xfs_icsb_lock_cntr(cntp);
- }
-}
-
-STATIC void
-xfs_icsb_unlock_all_counters(
- xfs_mount_t *mp)
-{
- xfs_icsb_cnts_t *cntp;
- int i;
-
- for_each_online_cpu(i) {
- cntp = (xfs_icsb_cnts_t *)per_cpu_ptr(mp->m_sb_cnts, i);
- xfs_icsb_unlock_cntr(cntp);
- }
-}
-
-STATIC void
-xfs_icsb_count(
- xfs_mount_t *mp,
- xfs_icsb_cnts_t *cnt,
- int flags)
-{
- xfs_icsb_cnts_t *cntp;
- int i;
-
- memset(cnt, 0, sizeof(xfs_icsb_cnts_t));
-
- if (!(flags & XFS_ICSB_LAZY_COUNT))
- xfs_icsb_lock_all_counters(mp);
-
- for_each_online_cpu(i) {
- cntp = (xfs_icsb_cnts_t *)per_cpu_ptr(mp->m_sb_cnts, i);
- cnt->icsb_icount += cntp->icsb_icount;
- cnt->icsb_ifree += cntp->icsb_ifree;
- cnt->icsb_fdblocks += cntp->icsb_fdblocks;
- }
-
- if (!(flags & XFS_ICSB_LAZY_COUNT))
- xfs_icsb_unlock_all_counters(mp);
-}
-
-STATIC int
-xfs_icsb_counter_disabled(
- xfs_mount_t *mp,
- xfs_sb_field_t field)
-{
- ASSERT((field >= XFS_SBS_ICOUNT) && (field <= XFS_SBS_FDBLOCKS));
- return test_bit(field, &mp->m_icsb_counters);
-}
-
-STATIC void
-xfs_icsb_disable_counter(
- xfs_mount_t *mp,
- xfs_sb_field_t field)
-{
- xfs_icsb_cnts_t cnt;
-
- ASSERT((field >= XFS_SBS_ICOUNT) && (field <= XFS_SBS_FDBLOCKS));
-
- /*
- * If we are already disabled, then there is nothing to do
- * here. We check before locking all the counters to avoid
- * the expensive lock operation when being called in the
- * slow path and the counter is already disabled. This is
- * safe because the only time we set or clear this state is under
- * the m_icsb_mutex.
- */
- if (xfs_icsb_counter_disabled(mp, field))
- return;
-
- xfs_icsb_lock_all_counters(mp);
- if (!test_and_set_bit(field, &mp->m_icsb_counters)) {
- /* drain back to superblock */
-
- xfs_icsb_count(mp, &cnt, XFS_ICSB_LAZY_COUNT);
- switch(field) {
- case XFS_SBS_ICOUNT:
- mp->m_sb.sb_icount = cnt.icsb_icount;
- break;
- case XFS_SBS_IFREE:
- mp->m_sb.sb_ifree = cnt.icsb_ifree;
- break;
- case XFS_SBS_FDBLOCKS:
- mp->m_sb.sb_fdblocks = cnt.icsb_fdblocks;
- break;
- default:
- BUG();
- }
- }
-
- xfs_icsb_unlock_all_counters(mp);
-}
-
-STATIC void
-xfs_icsb_enable_counter(
- xfs_mount_t *mp,
- xfs_sb_field_t field,
- uint64_t count,
- uint64_t resid)
-{
- xfs_icsb_cnts_t *cntp;
- int i;
-
- ASSERT((field >= XFS_SBS_ICOUNT) && (field <= XFS_SBS_FDBLOCKS));
-
- xfs_icsb_lock_all_counters(mp);
- for_each_online_cpu(i) {
- cntp = per_cpu_ptr(mp->m_sb_cnts, i);
- switch (field) {
- case XFS_SBS_ICOUNT:
- cntp->icsb_icount = count + resid;
- break;
- case XFS_SBS_IFREE:
- cntp->icsb_ifree = count + resid;
- break;
- case XFS_SBS_FDBLOCKS:
- cntp->icsb_fdblocks = count + resid;
- break;
- default:
- BUG();
- break;
- }
- resid = 0;
- }
- clear_bit(field, &mp->m_icsb_counters);
- xfs_icsb_unlock_all_counters(mp);
-}
-
-void
-xfs_icsb_sync_counters_locked(
- xfs_mount_t *mp,
- int flags)
-{
- xfs_icsb_cnts_t cnt;
-
- xfs_icsb_count(mp, &cnt, flags);
-
- if (!xfs_icsb_counter_disabled(mp, XFS_SBS_ICOUNT))
- mp->m_sb.sb_icount = cnt.icsb_icount;
- if (!xfs_icsb_counter_disabled(mp, XFS_SBS_IFREE))
- mp->m_sb.sb_ifree = cnt.icsb_ifree;
- if (!xfs_icsb_counter_disabled(mp, XFS_SBS_FDBLOCKS))
- mp->m_sb.sb_fdblocks = cnt.icsb_fdblocks;
-}
-
-/*
- * Accurate update of per-cpu counters to incore superblock
- */
-void
-xfs_icsb_sync_counters(
- xfs_mount_t *mp,
- int flags)
-{
- spin_lock(&mp->m_sb_lock);
- xfs_icsb_sync_counters_locked(mp, flags);
- spin_unlock(&mp->m_sb_lock);
-}
-
-/*
- * Balance and enable/disable counters as necessary.
- *
- * Thresholds for re-enabling counters are somewhat magic. inode counts are
- * chosen to be the same number as single on disk allocation chunk per CPU, and
- * free blocks is something far enough zero that we aren't going thrash when we
- * get near ENOSPC. We also need to supply a minimum we require per cpu to
- * prevent looping endlessly when xfs_alloc_space asks for more than will
- * be distributed to a single CPU but each CPU has enough blocks to be
- * reenabled.
- *
- * Note that we can be called when counters are already disabled.
- * xfs_icsb_disable_counter() optimises the counter locking in this case to
- * prevent locking every per-cpu counter needlessly.
- */
-
-#define XFS_ICSB_INO_CNTR_REENABLE (uint64_t)64
-#define XFS_ICSB_FDBLK_CNTR_REENABLE(mp) \
- (uint64_t)(512 + XFS_ALLOC_SET_ASIDE(mp))
-STATIC void
-xfs_icsb_balance_counter_locked(
- xfs_mount_t *mp,
- xfs_sb_field_t field,
- int min_per_cpu)
-{
- uint64_t count, resid;
- int weight = num_online_cpus();
- uint64_t min = (uint64_t)min_per_cpu;
-
- /* disable counter and sync counter */
- xfs_icsb_disable_counter(mp, field);
-
- /* update counters - first CPU gets residual*/
- switch (field) {
- case XFS_SBS_ICOUNT:
- count = mp->m_sb.sb_icount;
- resid = do_div(count, weight);
- if (count < max(min, XFS_ICSB_INO_CNTR_REENABLE))
- return;
- break;
- case XFS_SBS_IFREE:
- count = mp->m_sb.sb_ifree;
- resid = do_div(count, weight);
- if (count < max(min, XFS_ICSB_INO_CNTR_REENABLE))
- return;
- break;
- case XFS_SBS_FDBLOCKS:
- count = mp->m_sb.sb_fdblocks;
- resid = do_div(count, weight);
- if (count < max(min, XFS_ICSB_FDBLK_CNTR_REENABLE(mp)))
- return;
- break;
- default:
- BUG();
- count = resid = 0; /* quiet, gcc */
- break;
- }
-
- xfs_icsb_enable_counter(mp, field, count, resid);
-}
-
-STATIC void
-xfs_icsb_balance_counter(
- xfs_mount_t *mp,
- xfs_sb_field_t fields,
- int min_per_cpu)
-{
- spin_lock(&mp->m_sb_lock);
- xfs_icsb_balance_counter_locked(mp, fields, min_per_cpu);
- spin_unlock(&mp->m_sb_lock);
-}
-
-int
-xfs_icsb_modify_counters(
- xfs_mount_t *mp,
- xfs_sb_field_t field,
- int64_t delta,
- int rsvd)
-{
- xfs_icsb_cnts_t *icsbp;
- long long lcounter; /* long counter for 64 bit fields */
- int ret = 0;
-
- might_sleep();
-again:
- preempt_disable();
- icsbp = this_cpu_ptr(mp->m_sb_cnts);
-
- /*
- * if the counter is disabled, go to slow path
- */
- if (unlikely(xfs_icsb_counter_disabled(mp, field)))
- goto slow_path;
- xfs_icsb_lock_cntr(icsbp);
- if (unlikely(xfs_icsb_counter_disabled(mp, field))) {
- xfs_icsb_unlock_cntr(icsbp);
- goto slow_path;
- }
-
- switch (field) {
- case XFS_SBS_ICOUNT:
- lcounter = icsbp->icsb_icount;
- lcounter += delta;
- if (unlikely(lcounter < 0))
- goto balance_counter;
- icsbp->icsb_icount = lcounter;
- break;
-
- case XFS_SBS_IFREE:
- lcounter = icsbp->icsb_ifree;
- lcounter += delta;
- if (unlikely(lcounter < 0))
- goto balance_counter;
- icsbp->icsb_ifree = lcounter;
- break;
-
- case XFS_SBS_FDBLOCKS:
- BUG_ON((mp->m_resblks - mp->m_resblks_avail) != 0);
-
- lcounter = icsbp->icsb_fdblocks - XFS_ALLOC_SET_ASIDE(mp);
- lcounter += delta;
- if (unlikely(lcounter < 0))
- goto balance_counter;
- icsbp->icsb_fdblocks = lcounter + XFS_ALLOC_SET_ASIDE(mp);
- break;
- default:
- BUG();
- break;
- }
- xfs_icsb_unlock_cntr(icsbp);
- preempt_enable();
- return 0;
-
-slow_path:
- preempt_enable();
-
- /*
- * serialise with a mutex so we don't burn lots of cpu on
- * the superblock lock. We still need to hold the superblock
- * lock, however, when we modify the global structures.
- */
- xfs_icsb_lock(mp);
-
- /*
- * Now running atomically.
- *
- * If the counter is enabled, someone has beaten us to rebalancing.
- * Drop the lock and try again in the fast path....
- */
- if (!(xfs_icsb_counter_disabled(mp, field))) {
- xfs_icsb_unlock(mp);
- goto again;
- }
-
- /*
- * The counter is currently disabled. Because we are
- * running atomically here, we know a rebalance cannot
- * be in progress. Hence we can go straight to operating
- * on the global superblock. We do not call xfs_mod_incore_sb()
- * here even though we need to get the m_sb_lock. Doing so
- * will cause us to re-enter this function and deadlock.
- * Hence we get the m_sb_lock ourselves and then call
- * xfs_mod_incore_sb_unlocked() as the unlocked path operates
- * directly on the global counters.
- */
- spin_lock(&mp->m_sb_lock);
- ret = xfs_mod_incore_sb_unlocked(mp, field, delta, rsvd);
- spin_unlock(&mp->m_sb_lock);
-
- /*
- * Now that we've modified the global superblock, we
- * may be able to re-enable the distributed counters
- * (e.g. lots of space just got freed). After that
- * we are done.
- */
- if (ret != ENOSPC)
- xfs_icsb_balance_counter(mp, field, 0);
- xfs_icsb_unlock(mp);
- return ret;
-
-balance_counter:
- xfs_icsb_unlock_cntr(icsbp);
- preempt_enable();
-
- /*
- * We may have multiple threads here if multiple per-cpu
- * counters run dry at the same time. This will mean we can
- * do more balances than strictly necessary but it is not
- * the common slowpath case.
- */
- xfs_icsb_lock(mp);
-
- /*
- * running atomically.
- *
- * This will leave the counter in the correct state for future
- * accesses. After the rebalance, we simply try again and our retry
- * will either succeed through the fast path or slow path without
- * another balance operation being required.
- */
- xfs_icsb_balance_counter(mp, field, delta);
- xfs_icsb_unlock(mp);
- goto again;
-}
-
-#endif
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 5861b49..7efae1d 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -65,44 +65,19 @@ struct xfs_nameops;
struct xfs_ail;
struct xfs_quotainfo;
-#ifdef HAVE_PERCPU_SB
-
/*
- * Valid per-cpu incore superblock counters. Note that if you add new counters,
- * you may need to define new counter disabled bit field descriptors as there
- * are more possible fields in the superblock that can fit in a bitfield on a
- * 32 bit platform. The XFS_SBS_* values for the current current counters just
- * fit.
+ * Per-cpu incore superblock counters.
*/
-typedef struct xfs_icsb_cnts {
- uint64_t icsb_fdblocks;
- uint64_t icsb_ifree;
- uint64_t icsb_icount;
- unsigned long icsb_flags;
-} xfs_icsb_cnts_t;
-
-#define XFS_ICSB_FLAG_LOCK (1 << 0) /* counter lock bit */
+enum {
+ XFS_ICSB_FDBLOCKS = 0,
+ XFS_ICSB_IFREE,
+ XFS_ICSB_ICOUNT,
+ XFS_ICSB_MAX,
+};
-#define XFS_ICSB_LAZY_COUNT (1 << 1) /* accuracy not needed */
-
-extern int xfs_icsb_init_counters(struct xfs_mount *);
-extern void xfs_icsb_reinit_counters(struct xfs_mount *);
-extern void xfs_icsb_destroy_counters(struct xfs_mount *);
-extern void xfs_icsb_sync_counters(struct xfs_mount *, int);
-extern void xfs_icsb_sync_counters_locked(struct xfs_mount *, int);
extern int xfs_icsb_modify_counters(struct xfs_mount *, xfs_sb_field_t,
int64_t, int);
-#else
-#define xfs_icsb_init_counters(mp) (0)
-#define xfs_icsb_destroy_counters(mp) do { } while (0)
-#define xfs_icsb_reinit_counters(mp) do { } while (0)
-#define xfs_icsb_sync_counters(mp, flags) do { } while (0)
-#define xfs_icsb_sync_counters_locked(mp, flags) do { } while (0)
-#define xfs_icsb_modify_counters(mp, field, delta, rsvd) \
- xfs_mod_incore_sb(mp, field, delta, rsvd)
-#endif
-
typedef struct xfs_mount {
struct super_block *m_super;
xfs_tid_t m_tid; /* next unused tid for fs */
@@ -186,12 +161,6 @@ typedef struct xfs_mount {
struct xfs_chash *m_chash; /* fs private inode per-cluster
* hash table */
atomic_t m_active_trans; /* number trans frozen */
-#ifdef HAVE_PERCPU_SB
- xfs_icsb_cnts_t __percpu *m_sb_cnts; /* per-cpu superblock counters */
- unsigned long m_icsb_counters; /* disabled per-cpu counters */
- struct notifier_block m_icsb_notifier; /* hotplug cpu notifier */
- struct mutex m_icsb_mutex; /* balancer sync lock */
-#endif
struct xfs_mru_cache *m_filestream; /* per-mount filestream data */
struct task_struct *m_sync_task; /* generalised sync thread */
xfs_sync_work_t m_sync_work; /* work item for VFS_SYNC */
@@ -202,6 +171,7 @@ typedef struct xfs_mount {
__int64_t m_update_flags; /* sb flags we need to update
on the next remount,rw */
struct shrinker m_inode_shrink; /* inode reclaim shrinker */
+ struct percpu_counter m_icsb[XFS_ICSB_MAX];
} xfs_mount_t;
/*
@@ -333,26 +303,6 @@ struct xfs_perag *xfs_perag_get_tag(struct xfs_mount *mp, xfs_agnumber_t agno,
void xfs_perag_put(struct xfs_perag *pag);
/*
- * Per-cpu superblock locking functions
- */
-#ifdef HAVE_PERCPU_SB
-static inline void
-xfs_icsb_lock(xfs_mount_t *mp)
-{
- mutex_lock(&mp->m_icsb_mutex);
-}
-
-static inline void
-xfs_icsb_unlock(xfs_mount_t *mp)
-{
- mutex_unlock(&mp->m_icsb_mutex);
-}
-#else
-#define xfs_icsb_lock(mp)
-#define xfs_icsb_unlock(mp)
-#endif
-
-/*
* This structure is for use by the xfs_mod_incore_sb_batch() routine.
* xfs_growfs can specify a few fields which are more than int limit
*/
@@ -379,6 +329,20 @@ extern int xfs_sb_validate_fsb_count(struct xfs_sb *, __uint64_t);
extern int xfs_dev_is_read_only(struct xfs_mount *, char *);
+extern int xfs_icsb_init_counters(struct xfs_mount *);
+extern void xfs_icsb_reinit_counters(struct xfs_mount *);
+extern void xfs_icsb_destroy_counters(struct xfs_mount *);
+extern void xfs_icsb_sync_counters_locked(struct xfs_mount *);
+
+static inline void
+xfs_icsb_sync_counters(
+ struct xfs_mount *mp)
+{
+ spin_lock(&mp->m_sb_lock);
+ xfs_icsb_sync_counters_locked(mp);
+ spin_unlock(&mp->m_sb_lock);
+}
+
#endif /* __KERNEL__ */
extern void xfs_mod_sb(struct xfs_trans *, __int64_t);
diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h
index 46f6ba5..32014a4 100644
--- a/include/linux/percpu_counter.h
+++ b/include/linux/percpu_counter.h
@@ -41,6 +41,8 @@ void percpu_counter_set(struct percpu_counter *fbc, s64 amount);
void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch);
s64 __percpu_counter_sum(struct percpu_counter *fbc);
int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs);
+int percpu_counter_add_unless_lt(struct percpu_counter *fbc, s64 amount,
+ s64 threshold);
static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount)
{
@@ -153,6 +155,20 @@ static inline int percpu_counter_initialized(struct percpu_counter *fbc)
return 1;
}
+static inline int percpu_counter_test_and_add_delta(struct percpu_counter *fbc, s64 delta)
+{
+ s64 count;
+
+ preempt_disable();
+ count = fbc->count + delta;
+ if (count < 0)
+ return -1;
+ fbc->count = count;
+ preempt_enable();
+ return count ? 1 : 0;
+}
+
+
#endif /* CONFIG_SMP */
static inline void percpu_counter_inc(struct percpu_counter *fbc)
diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index 604678d..13c4ff3 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -213,6 +213,85 @@ int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs)
}
EXPORT_SYMBOL(percpu_counter_compare);
+/**
+ *
+ * percpu_counter_add_unless_lt - add to a counter avoiding underruns
+ * @fbc: counter
+ * @amount: amount to add
+ * @threshold: underrun threshold
+ *
+ * Add @amount to @fdc if and only if result of addition is greater than or
+ * equal to @threshold Return 1 if greater and added, 0 if equal and added
+ * and -1 if and underrun would have occured.
+ *
+ * This is useful for operations that must accurately and atomically only add a
+ * delta to a counter if the result is greater than a given (e.g. for freespace
+ * accounting with ENOSPC checking in filesystems).
+ */
+int percpu_counter_add_unless_lt(struct percpu_counter *fbc, s64 amount, s64
+threshold)
+{
+ s64 count;
+ s64 error = 2 * percpu_counter_batch * num_online_cpus();
+ int cpu;
+ int ret = -1;
+
+ preempt_disable();
+
+ /* Check to see if rough count will be sufficient for comparison */
+ count = percpu_counter_read(fbc);
+ if (count + amount < threshold - error)
+ goto out;
+
+ /*
+ * If the counter is over the threshold and the change is less than the
+ * batch size, we might be able to avoid locking.
+ */
+ if (count > threshold + error && abs(amount) < percpu_counter_batch) {
+ __percpu_counter_add(fbc, amount, percpu_counter_batch);
+ ret = 1;
+ goto out;
+ }
+
+ /*
+ * If the result is is over the error threshold, we can just add it
+ * into the global counter ignoring what is in the per-cpu counters
+ * as they will not change the result of the calculation.
+ */
+ spin_lock(&fbc->lock);
+ if (fbc->count + amount > threshold + error) {
+ fbc->count += amount;
+ ret = 1;
+ goto out_unlock;
+ }
+
+ /*
+ * Result is withing the error margin. Run an open-coded sum of the
+ * per-cpu counters to get the exact value at this point in time,
+ * and if the result woul dbe above the threshold, add the amount to
+ * the global counter.
+ */
+ count = fbc->count;
+ for_each_online_cpu(cpu) {
+ s32 *pcount = per_cpu_ptr(fbc->counters, cpu);
+ count += *pcount;
+ }
+ WARN_ON(count < threshold);
+
+ if (count + amount >= threshold) {
+ ret = 0;
+ if (count + amount > threshold)
+ ret = 1;
+ fbc->count += amount;
+ }
+out_unlock:
+ spin_unlock(&fbc->lock);
+out:
+ preempt_enable();
+ return ret;
+}
+EXPORT_SYMBOL(percpu_counter_add_unless_lt);
+
static int __init percpu_counter_startup(void)
{
compute_batch_value();
--
1.7.2.3
_______________________________________________
xfs mailing list
xfs@xxxxxxxxxxx
http://oss.sgi.com/mailman/listinfo/xfs
