*
*/
-#define DEBUG_SUBSYSTEM S_CLASS
+#define DEBUG_SUBSYSTEM S_LOV
#include <linux/module.h>
#include <linux/list.h>
#include <linux/random.h>
#include <libcfs/libcfs.h>
-#include <libcfs/libcfs_hash.h> /* hash_long() */
#include <libcfs/linux/linux-mem.h>
#include <obd_class.h>
#include <obd_support.h>
u64 rand = 0;
if (ep_ro) {
-#if BITS_PER_LONG == 32
+#ifdef HAVE_GET_RANDOM_U32_AND_U64
+ rand = get_random_u64() % ep_ro;
+#elif BITS_PER_LONG == 32
/*
* If ep_ro > 32-bit, first generate the high
* 32 bits of the random number, then add in the low
* 32 bits (truncated to the upper limit, if needed)
*/
if (ep_ro > 0xffffffffULL)
- rand = (u64)prandom_u32_max((u32)(ep_ro >> 32)) << 32;
+ rand = (u64)get_random_u32_below((u32)(ep_ro >> 32)) << 32;
if (rand == (ep_ro & 0xffffffff00000000ULL))
- rand |= prandom_u32_max((u32)ep_ro);
+ rand |= get_random_u32_below((u32)ep_ro);
else
- rand |= prandom_u32();
+ rand |= get_random_u32();
#else
- rand = ((u64)prandom_u32() << 32 | prandom_u32()) % ep_ro;
+ rand = ((u64)get_random_u32() << 32 | get_random_u32()) % ep_ro;
#endif
}
}
EXPORT_SYMBOL(lu_prandom_u64_max);
-void lu_qos_rr_init(struct lu_qos_rr *lqr)
-{
- spin_lock_init(&lqr->lqr_alloc);
- set_bit(LQ_DIRTY, &lqr->lqr_flags);
-}
-EXPORT_SYMBOL(lu_qos_rr_init);
-
/**
* Add a new target to Quality of Service (QoS) target table.
*
list_add_tail(&svr->lsq_svr_list, &tempsvr->lsq_svr_list);
set_bit(LQ_DIRTY, &qos->lq_flags);
+#ifdef HAVE_SERVER_SUPPORT
set_bit(LQ_DIRTY, &qos->lq_rr.lqr_flags);
+#endif
out:
up_write(&qos->lq_rw_sem);
RETURN(rc);
* \retval 0 on success
* \retval -ENOENT if no server was found
*/
-static int lu_qos_del_tgt(struct lu_qos *qos, struct lu_tgt_desc *ltd)
+int lu_qos_del_tgt(struct lu_qos *qos, struct lu_tgt_desc *ltd)
{
struct lu_svr_qos *svr;
int rc = 0;
if (!svr)
GOTO(out, rc = -ENOENT);
+ ltd->ltd_qos.ltq_svr = NULL;
svr->lsq_tgt_count--;
if (svr->lsq_tgt_count == 0) {
CDEBUG(D_OTHER, "removing server %s\n",
obd_uuid2str(&svr->lsq_uuid));
list_del(&svr->lsq_svr_list);
- ltd->ltd_qos.ltq_svr = NULL;
OBD_FREE_PTR(svr);
}
set_bit(LQ_DIRTY, &qos->lq_flags);
+#ifdef HAVE_SERVER_SUPPORT
set_bit(LQ_DIRTY, &qos->lq_rr.lqr_flags);
+#endif
out:
up_write(&qos->lq_rw_sem);
RETURN(rc);
}
-
-static inline __u64 tgt_statfs_bavail(struct lu_tgt_desc *tgt)
-{
- struct obd_statfs *statfs = &tgt->ltd_statfs;
-
- return statfs->os_bavail * statfs->os_bsize;
-}
-
-static inline __u64 tgt_statfs_iavail(struct lu_tgt_desc *tgt)
-{
- return tgt->ltd_statfs.os_ffree;
-}
+EXPORT_SYMBOL(lu_qos_del_tgt);
/**
* Calculate weight for a given tgt.
*
- * The final tgt weight is bavail >> 16 * iavail >> 8 minus the tgt and server
- * penalties. See ltd_qos_penalties_calc() for how penalties are calculated.
+ * The final tgt weight uses only free space for OSTs, but combines
+ * both free space and inodes for MDTs, minus tgt and server penalties.
+ * See ltd_qos_penalties_calc() for how penalties are calculated.
*
* \param[in] tgt target descriptor
+ * \param[in] is_mdt target table is for MDT selection (use inodes)
*/
-void lu_tgt_qos_weight_calc(struct lu_tgt_desc *tgt)
+void lu_tgt_qos_weight_calc(struct lu_tgt_desc *tgt, bool is_mdt)
{
struct lu_tgt_qos *ltq = &tgt->ltd_qos;
- __u64 temp, temp2;
+ __u64 penalty;
- temp = (tgt_statfs_bavail(tgt) >> 16) * (tgt_statfs_iavail(tgt) >> 8);
- temp2 = ltq->ltq_penalty + ltq->ltq_svr->lsq_penalty;
- if (temp < temp2)
+ if (is_mdt)
+ ltq->ltq_avail = (tgt_statfs_bavail(tgt) >> 16) *
+ (tgt_statfs_iavail(tgt) >> 8);
+ else
+ ltq->ltq_avail = tgt_statfs_bavail(tgt) >> 8;
+ penalty = ltq->ltq_penalty + ltq->ltq_svr->lsq_penalty;
+ CDEBUG(D_OTHER, "ltq_penalty: %llu lsq_penalty: %llu tgt_bavail: %llu\n",
+ ltq->ltq_penalty, ltq->ltq_svr->lsq_penalty, ltq->ltq_avail);
+ if (ltq->ltq_avail < penalty)
ltq->ltq_weight = 0;
else
- ltq->ltq_weight = temp - temp2;
+ ltq->ltq_weight = ltq->ltq_avail - penalty;
}
EXPORT_SYMBOL(lu_tgt_qos_weight_calc);
init_rwsem(<d->ltd_qos.lq_rw_sem);
set_bit(LQ_DIRTY, <d->ltd_qos.lq_flags);
set_bit(LQ_RESET, <d->ltd_qos.lq_flags);
- /* Default priority is toward free space balance */
- ltd->ltd_qos.lq_prio_free = 232;
- /* Default threshold for rr (roughly 17%) */
- ltd->ltd_qos.lq_threshold_rr = 43;
ltd->ltd_is_mdt = is_mdt;
- if (is_mdt)
+ /* MDT imbalance threshold is low to balance across MDTs
+ * relatively quickly, because each directory may result
+ * in a large number of files/subdirs created therein.
+ */
+ if (is_mdt) {
ltd->ltd_lmv_desc.ld_pattern = LMV_HASH_TYPE_DEFAULT;
-
- lu_qos_rr_init(<d->ltd_qos.lq_rr);
+ ltd->ltd_qos.lq_prio_free = LMV_QOS_DEF_PRIO_FREE * 256 / 100;
+ ltd->ltd_qos.lq_threshold_rr =
+ LMV_QOS_DEF_THRESHOLD_RR_PCT *
+ QOS_THRESHOLD_MAX / 100;
+ } else {
+ ltd->ltd_qos.lq_prio_free = LOV_QOS_DEF_PRIO_FREE * 256 / 100;
+ ltd->ltd_qos.lq_threshold_rr =
+ LOV_QOS_DEF_THRESHOLD_RR_PCT *
+ QOS_THRESHOLD_MAX / 100;
+ }
return 0;
}
int i;
bitmap_free(ltd->ltd_tgt_bitmap);
- for (i = 0; i < TGT_PTRS; i++) {
+ for (i = 0; i < ARRAY_SIZE(ltd->ltd_tgt_idx); i++) {
if (ltd->ltd_tgt_idx[i])
OBD_FREE_PTR(ltd->ltd_tgt_idx[i]);
}
if (index >= ltd->ltd_tgts_size) {
__u32 newsize = 1;
+ if (index > TGT_PTRS * TGT_PTRS_PER_BLOCK)
+ RETURN(-ENFILE);
+
while (newsize < index + 1)
newsize = newsize << 1;
EXPORT_SYMBOL(ltd_del_tgt);
/**
- * Whether QoS data is up-to-date and QoS can be applied.
- */
-bool ltd_qos_is_usable(struct lu_tgt_descs *ltd)
-{
- if (!test_bit(LQ_DIRTY, <d->ltd_qos.lq_flags) &&
- test_bit(LQ_SAME_SPACE, <d->ltd_qos.lq_flags))
- return false;
-
- if (ltd->ltd_lov_desc.ld_active_tgt_count < 2)
- return false;
-
- return true;
-}
-EXPORT_SYMBOL(ltd_qos_is_usable);
-
-/**
* Calculate penalties per-tgt and per-server
*
* Re-calculate penalties when the configuration changes, active targets
/*
* per-tgt penalty is
- * prio * bavail * iavail / (num_tgt - 1) / 2
+ * prio * bavail * iavail / (num_tgt - 1) / prio_max / 2
*/
- tgt->ltd_qos.ltq_penalty_per_obj = prio_wide * ba * ia >> 8;
+ tgt->ltd_qos.ltq_penalty_per_obj = prio_wide * ba * ia >> 9;
do_div(tgt->ltd_qos.ltq_penalty_per_obj, num_active);
- tgt->ltd_qos.ltq_penalty_per_obj >>= 1;
age = (now - tgt->ltd_qos.ltq_used) >> 3;
- if (test_bit(LQ_RESET, &qos->lq_flags) ||
+ if (test_bit(LQ_RESET, &qos->lq_flags) ||
age > 32 * desc->ld_qos_maxage)
tgt->ltd_qos.ltq_penalty = 0;
else if (age > desc->ld_qos_maxage)
svr->lsq_penalty_per_obj >>= 1;
age = (now - svr->lsq_used) >> 3;
- if (test_bit(LQ_RESET, &qos->lq_flags) ||
+ if (test_bit(LQ_RESET, &qos->lq_flags) ||
age > 32 * desc->ld_qos_maxage)
svr->lsq_penalty = 0;
else if (age > desc->ld_qos_maxage)
svr->lsq_penalty >>= age / desc->ld_qos_maxage;
}
- clear_bit(LQ_DIRTY, &qos->lq_flags);
- clear_bit(LQ_RESET, &qos->lq_flags);
/*
* If each tgt has almost same free space, do rr allocation for better
* creation performance
*/
- clear_bit(LQ_SAME_SPACE, &qos->lq_flags);
- if ((ba_max * (256 - qos->lq_threshold_rr)) >> 8 < ba_min &&
- (ia_max * (256 - qos->lq_threshold_rr)) >> 8 < ia_min) {
+ if (((ba_max * (QOS_THRESHOLD_MAX - qos->lq_threshold_rr)) /
+ QOS_THRESHOLD_MAX) < ba_min &&
+ ((ia_max * (QOS_THRESHOLD_MAX - qos->lq_threshold_rr)) /
+ QOS_THRESHOLD_MAX) < ia_min) {
set_bit(LQ_SAME_SPACE, &qos->lq_flags);
/* Reset weights for the next time we enter qos mode */
set_bit(LQ_RESET, &qos->lq_flags);
+ } else {
+ clear_bit(LQ_SAME_SPACE, &qos->lq_flags);
+ clear_bit(LQ_RESET, &qos->lq_flags);
}
+ clear_bit(LQ_DIRTY, &qos->lq_flags);
rc = 0;
out:
/* Set max penalties for this tgt and server */
ltq->ltq_penalty += ltq->ltq_penalty_per_obj *
ltd->ltd_lov_desc.ld_active_tgt_count;
+ CDEBUG(D_OTHER, "ltq_penalty: %llu per_obj: %llu tgt_count: %d\n",
+ ltq->ltq_penalty, ltq->ltq_penalty_per_obj,
+ ltd->ltd_lov_desc.ld_active_tgt_count);
svr->lsq_penalty += svr->lsq_penalty_per_obj *
- ltd->ltd_lov_desc.ld_active_tgt_count;
+ qos->lq_active_svr_count;
+ CDEBUG(D_OTHER, "lsq_penalty: %llu per_obj: %llu srv_count: %d\n",
+ svr->lsq_penalty, svr->lsq_penalty_per_obj,
+ qos->lq_active_svr_count);
+
/* Decrease all MDS penalties */
list_for_each_entry(svr, &qos->lq_svr_list, lsq_svr_list) {
else
ltq->ltq_penalty -= ltq->ltq_penalty_per_obj;
- lu_tgt_qos_weight_calc(tgt);
+ lu_tgt_qos_weight_calc(tgt, ltd->ltd_is_mdt);
/* Recalc the total weight of usable osts */
if (ltq->ltq_usable)
git://git.whamcloud.com / fs / lustre-release.git / blobdiff