sub_io->ci_lock_no_expand = io->ci_lock_no_expand;
sub_io->ci_ndelay = io->ci_ndelay;
sub_io->ci_layout_version = io->ci_layout_version;
+ sub_io->ci_tried_all_mirrors = io->ci_tried_all_mirrors;
result = cl_io_sub_init(sub->sub_env, sub_io, io->ci_type, sub_obj);
* Lov io operations.
*
*/
-
-int lov_page_index(const struct cl_page *page)
-{
- const struct cl_page_slice *slice;
- ENTRY;
-
- slice = cl_page_at(page, &lov_device_type);
- LASSERT(slice != NULL);
- LASSERT(slice->cpl_obj != NULL);
-
- RETURN(cl2lov_page(slice)->lps_index);
-}
-
static int lov_io_subio_init(const struct lu_env *env, struct lov_io *lio,
struct cl_io *io)
{
if (!lu_extent_is_overlapped(ext, lle->lle_extent))
continue;
- ext->e_start = MIN(ext->e_start, lle->lle_extent->e_start);
- ext->e_end = MAX(ext->e_end, lle->lle_extent->e_end);
+ ext->e_start = min(ext->e_start, lle->lle_extent->e_start);
+ ext->e_end = max(ext->e_end, lle->lle_extent->e_end);
++count;
}
if (count == 0) {
found = true;
break;
}
- }
-
+ } /* each component of the mirror */
if (found) {
index = (index + i) % comp->lo_mirror_count;
break;
}
- }
+ } /* each mirror */
+
if (i == comp->lo_mirror_count) {
CERROR(DFID": failed to find a component covering "
"I/O region at %llu\n",
* of this client has been partitioned. We should relinquish CPU for
* a while before trying again.
*/
- ++io->ci_ndelay_tried;
- if (io->ci_ndelay && io->ci_ndelay_tried >= comp->lo_mirror_count) {
+ if (io->ci_ndelay && io->ci_ndelay_tried > 0 &&
+ (io->ci_ndelay_tried % comp->lo_mirror_count == 0)) {
set_current_state(TASK_INTERRUPTIBLE);
- schedule_timeout(msecs_to_jiffies(MSEC_PER_SEC)); /* 10ms */
+ schedule_timeout(cfs_time_seconds(1) / 100); /* 10ms */
if (signal_pending(current))
RETURN(-EINTR);
- /* reset retry counter */
- io->ci_ndelay_tried = 1;
+ /**
+ * we'd set ci_tried_all_mirrors to turn off fast mirror
+ * switching for read after we've tried all mirrors several
+ * rounds.
+ */
+ io->ci_tried_all_mirrors = io->ci_ndelay_tried %
+ (comp->lo_mirror_count * 4) == 0;
}
+ ++io->ci_ndelay_tried;
CDEBUG(D_VFSTRACE, "use %sdelayed RPC state for this IO\n",
io->ci_ndelay ? "non-" : "");
*/
if (cl_io_is_trunc(io)) {
io->ci_write_intent.e_start = 0;
- io->ci_write_intent.e_end = io->u.ci_setattr.sa_attr.lvb_size;
+ /* for writes, e_end is endpos, the location of the file
+ * pointer after the write is completed, so it is not accessed.
+ * For truncate, 'end' is the size, and *is* acccessed.
+ * In other words, writes are [start, end), but truncate is
+ * [start, size], where both are included. So add 1 to the
+ * size when creating the write intent to account for this.
+ */
+ io->ci_write_intent.e_end =
+ io->u.ci_setattr.sa_attr.lvb_size + 1;
} else {
io->ci_write_intent.e_start = lio->lis_pos;
io->ci_write_intent.e_end = lio->lis_endpos;
case CIT_READ:
case CIT_WRITE: {
io->u.ci_wr.wr_sync = cl_io_is_sync_write(parent);
+ io->ci_tried_all_mirrors = parent->ci_tried_all_mirrors;
if (cl_io_is_append(parent)) {
io->u.ci_wr.wr_append = 1;
} else {
ra);
CDEBUG(D_READA, DFID " cra_end = %lu, stripes = %d, rc = %d\n",
- PFID(lu_object_fid(lov2lu(loo))), ra->cra_end, r0->lo_nr, rc);
+ PFID(lu_object_fid(lov2lu(loo))), ra->cra_end_idx,
+ r0->lo_nr, rc);
if (rc != 0)
RETURN(rc);
*/
/* cra_end is stripe level, convert it into file level */
- ra_end = ra->cra_end;
+ ra_end = ra->cra_end_idx;
if (ra_end != CL_PAGE_EOF)
- ra->cra_end = lov_stripe_pgoff(loo->lo_lsm, index,
- ra_end, stripe);
+ ra->cra_end_idx = lov_stripe_pgoff(loo->lo_lsm, index,
+ ra_end, stripe);
/* boundary of current component */
ra_end = cl_index(obj, (loff_t)lov_io_extent(lio, index)->e_end);
- if (ra_end != CL_PAGE_EOF && ra->cra_end >= ra_end)
- ra->cra_end = ra_end - 1;
+ if (ra_end != CL_PAGE_EOF && ra->cra_end_idx >= ra_end)
+ ra->cra_end_idx = ra_end - 1;
if (r0->lo_nr == 1) /* single stripe file */
RETURN(0);
pps = lov_lse(loo, index)->lsme_stripe_size >> PAGE_SHIFT;
- CDEBUG(D_READA, DFID " max_index = %lu, pps = %u, index = %u, "
+ CDEBUG(D_READA, DFID " max_index = %lu, pps = %u, index = %d, "
"stripe_size = %u, stripe no = %u, start index = %lu\n",
- PFID(lu_object_fid(lov2lu(loo))), ra->cra_end, pps, index,
+ PFID(lu_object_fid(lov2lu(loo))), ra->cra_end_idx, pps, index,
lov_lse(loo, index)->lsme_stripe_size, stripe, start);
/* never exceed the end of the stripe */
- ra->cra_end = min_t(pgoff_t,
- ra->cra_end, start + pps - start % pps - 1);
+ ra->cra_end_idx = min_t(pgoff_t, ra->cra_end_idx,
+ start + pps - start % pps - 1);
RETURN(0);
}
struct lov_io_sub *sub;
struct cl_page_list *plist = &lov_env_info(env)->lti_plist;
struct cl_page *page;
+ struct cl_page *tmp;
int index;
int rc = 0;
ENTRY;
cl_2queue_init(cl2q);
cl_page_list_move(&cl2q->c2_qin, qin, page);
- index = lov_page_index(page);
- while (qin->pl_nr > 0) {
- page = cl_page_list_first(qin);
- if (index != lov_page_index(page))
- break;
+ index = page->cp_lov_index;
+ cl_page_list_for_each_safe(page, tmp, qin) {
+ /* this page is not on this stripe */
+ if (index != page->cp_lov_index)
+ continue;
cl_page_list_move(&cl2q->c2_qin, qin, page);
}
cl_page_list_move(plist, queue, page);
- index = lov_page_index(page);
+ index = page->cp_lov_index;
while (queue->pl_nr > 0) {
page = cl_page_list_first(queue);
- if (index != lov_page_index(page))
+ if (index != page->cp_lov_index)
break;
cl_page_list_move(plist, queue, page);
fio = &ios->cis_io->u.ci_fault;
lio = cl2lov_io(env, ios);
- sub = lov_sub_get(env, lio, lov_page_index(fio->ft_page));
+ sub = lov_sub_get(env, lio, fio->ft_page->cp_lov_index);
sub->sub_io.u.ci_fault.ft_nob = fio->ft_nob;
RETURN(lov_io_start(env, ios));
git://git.whamcloud.com / fs / lustre-release.git / blobdiff