From: Andiry Xu <jix024@eng.ucsd.edu>
To: linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-nvdimm@lists.01.org
Cc: dan.j.williams@intel.com, andy.rudoff@intel.com,
coughlan@redhat.com, swanson@cs.ucsd.edu, david@fromorbit.com,
jack@suse.com, swhiteho@redhat.com, miklos@szeredi.hu,
andiry.xu@gmail.com, Andiry Xu <jix024@cs.ucsd.edu>
Subject: [RFC v2 78/83] GC: Thorough garbage collection.
Date: Sat, 10 Mar 2018 10:18:59 -0800 [thread overview]
Message-ID: <1520705944-6723-79-git-send-email-jix024@eng.ucsd.edu> (raw)
In-Reply-To: <1520705944-6723-1-git-send-email-jix024@eng.ucsd.edu>
From: Andiry Xu <jix024@cs.ucsd.edu>
After fast gc, if the valid log entries still account for less
than the half of the log size, NOVA starts thorough garbage collection,
allocates a new log, copies the live log entries to it, and switches
to the new log atomically. The radix tree needs to be updated to point
to the new log.
Example:
I = Invalid, V = Valid
VIIV -> IIII -> VVII
||
|| fast gc
\/
VIIV -> VVII
||
|| thorough gc
\/
VVVV
Signed-off-by: Andiry Xu <jix024@cs.ucsd.edu>
---
fs/nova/gc.c | 273 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 273 insertions(+)
diff --git a/fs/nova/gc.c b/fs/nova/gc.c
index 1634c04..d74286e 100644
--- a/fs/nova/gc.c
+++ b/fs/nova/gc.c
@@ -18,6 +18,62 @@
#include "nova.h"
#include "inode.h"
+static bool curr_log_entry_invalid(struct super_block *sb,
+ struct nova_inode *pi, struct nova_inode_info_header *sih,
+ u64 curr_p, size_t *length)
+{
+ struct nova_file_write_entry *entry;
+ struct nova_dentry *dentry;
+ struct nova_setattr_logentry *setattr_entry;
+ struct nova_link_change_entry *linkc_entry;
+ void *entryc;
+ u8 type;
+ bool ret = true;
+
+ entryc = (void *)nova_get_block(sb, curr_p);
+ type = nova_get_entry_type(entryc);
+
+ switch (type) {
+ case SET_ATTR:
+ setattr_entry = (struct nova_setattr_logentry *) entryc;
+ if (setattr_entry->invalid == 0)
+ ret = false;
+ *length = sizeof(struct nova_setattr_logentry);
+ break;
+ case LINK_CHANGE:
+ linkc_entry = (struct nova_link_change_entry *) entryc;
+ if (linkc_entry->invalid == 0)
+ ret = false;
+ *length = sizeof(struct nova_link_change_entry);
+ break;
+ case FILE_WRITE:
+ entry = (struct nova_file_write_entry *) entryc;
+ if (entry->num_pages != entry->invalid_pages)
+ ret = false;
+ *length = sizeof(struct nova_file_write_entry);
+ break;
+ case DIR_LOG:
+ dentry = (struct nova_dentry *) entryc;
+ if (dentry->invalid == 0)
+ ret = false;
+ if (sih->last_dentry == curr_p)
+ ret = false;
+ *length = le16_to_cpu(dentry->de_len);
+ break;
+ case NEXT_PAGE:
+ /* No more entries in this page */
+ *length = PAGE_SIZE - ENTRY_LOC(curr_p);
+ break;
+ default:
+ nova_dbg("%s: unknown type %d, 0x%llx\n",
+ __func__, type, curr_p);
+ NOVA_ASSERT(0);
+ *length = PAGE_SIZE - ENTRY_LOC(curr_p);
+ break;
+ }
+
+ return ret;
+}
static bool curr_page_invalid(struct super_block *sb,
struct nova_inode *pi, struct nova_inode_info_header *sih,
@@ -68,6 +124,210 @@ static void free_curr_page(struct super_block *sb,
nova_get_blocknr(sb, curr_head, btype), 1);
}
+static int nova_gc_assign_file_entry(struct super_block *sb,
+ struct nova_inode_info_header *sih,
+ struct nova_file_write_entry *old_entry,
+ struct nova_file_write_entry *new_entry)
+{
+ struct nova_file_write_entry *temp;
+ void **pentry;
+ unsigned long start_pgoff = old_entry->pgoff;
+ unsigned int num = old_entry->num_pages;
+ unsigned long curr_pgoff;
+ int i;
+ int ret = 0;
+
+ for (i = 0; i < num; i++) {
+ curr_pgoff = start_pgoff + i;
+
+ pentry = radix_tree_lookup_slot(&sih->tree, curr_pgoff);
+ if (pentry) {
+ temp = radix_tree_deref_slot(pentry);
+ if (temp == old_entry)
+ radix_tree_replace_slot(&sih->tree, pentry,
+ new_entry);
+ }
+ }
+
+ return ret;
+}
+
+static int nova_gc_assign_dentry(struct super_block *sb,
+ struct nova_inode_info_header *sih, struct nova_dentry *old_dentry,
+ struct nova_dentry *new_dentry)
+{
+ struct nova_dentry *temp;
+ void **pentry;
+ unsigned long hash;
+ int ret = 0;
+
+ hash = BKDRHash(old_dentry->name, old_dentry->name_len);
+ nova_dbgv("%s: assign %s hash %lu\n", __func__,
+ old_dentry->name, hash);
+
+ /* FIXME: hash collision ignored here */
+ pentry = radix_tree_lookup_slot(&sih->tree, hash);
+ if (pentry) {
+ temp = radix_tree_deref_slot(pentry);
+ if (temp == old_dentry)
+ radix_tree_replace_slot(&sih->tree, pentry, new_dentry);
+ }
+
+ return ret;
+}
+
+static int nova_gc_assign_new_entry(struct super_block *sb,
+ struct nova_inode *pi, struct nova_inode_info_header *sih,
+ u64 curr_p, u64 new_curr)
+{
+ struct nova_file_write_entry *old_entry, *new_entry;
+ struct nova_dentry *old_dentry, *new_dentry;
+ void *addr, *new_addr;
+ u8 type;
+ int ret = 0;
+
+ addr = (void *)nova_get_block(sb, curr_p);
+ type = nova_get_entry_type(addr);
+ switch (type) {
+ case SET_ATTR:
+ sih->last_setattr = new_curr;
+ break;
+ case LINK_CHANGE:
+ sih->last_link_change = new_curr;
+ break;
+ case FILE_WRITE:
+ new_addr = (void *)nova_get_block(sb, new_curr);
+ old_entry = (struct nova_file_write_entry *)addr;
+ new_entry = (struct nova_file_write_entry *)new_addr;
+ ret = nova_gc_assign_file_entry(sb, sih, old_entry, new_entry);
+ break;
+ case DIR_LOG:
+ new_addr = (void *)nova_get_block(sb, new_curr);
+ old_dentry = (struct nova_dentry *)addr;
+ new_dentry = (struct nova_dentry *)new_addr;
+ if (sih->last_dentry == curr_p)
+ sih->last_dentry = new_curr;
+ ret = nova_gc_assign_dentry(sb, sih, old_dentry, new_dentry);
+ break;
+ default:
+ nova_dbg("%s: unknown type %d, 0x%llx\n",
+ __func__, type, curr_p);
+ NOVA_ASSERT(0);
+ break;
+ }
+
+ return ret;
+}
+
+/* Copy live log entries to the new log and atomically replace the old log */
+static unsigned long nova_inode_log_thorough_gc(struct super_block *sb,
+ struct nova_inode *pi, struct nova_inode_info_header *sih,
+ unsigned long blocks, unsigned long checked_pages)
+{
+ struct nova_inode_log_page *curr_page = NULL;
+ size_t length;
+ u64 curr_p, new_curr;
+ u64 old_curr_p;
+ u64 tail_block;
+ u64 old_head;
+ u64 new_head = 0;
+ u64 next;
+ int allocated;
+ int extended = 0;
+ int ret;
+ timing_t gc_time;
+
+ NOVA_START_TIMING(thorough_gc_t, gc_time);
+
+ curr_p = sih->log_head;
+ old_curr_p = curr_p;
+ old_head = sih->log_head;
+ nova_dbg_verbose("Log head 0x%llx, tail 0x%llx\n",
+ curr_p, sih->log_tail);
+ if (curr_p == 0 && sih->log_tail == 0)
+ goto out;
+
+ if (curr_p >> PAGE_SHIFT == sih->log_tail >> PAGE_SHIFT)
+ goto out;
+
+ allocated = nova_allocate_inode_log_pages(sb, sih, blocks,
+ &new_head, ANY_CPU, 0);
+ if (allocated != blocks) {
+ nova_err(sb, "%s: ERROR: no inode log page available\n",
+ __func__);
+ goto out;
+ }
+
+ new_curr = new_head;
+ while (curr_p != sih->log_tail) {
+ old_curr_p = curr_p;
+ if (goto_next_page(sb, curr_p))
+ curr_p = next_log_page(sb, curr_p);
+
+ if (curr_p >> PAGE_SHIFT == sih->log_tail >> PAGE_SHIFT) {
+ /* Don't recycle tail page */
+ break;
+ }
+
+ length = 0;
+ ret = curr_log_entry_invalid(sb, pi, sih, curr_p, &length);
+ if (!ret) {
+ extended = 0;
+ new_curr = nova_get_append_head(sb, pi, sih,
+ new_curr, length, MAIN_LOG,
+ 1, &extended);
+ if (extended)
+ blocks++;
+ /* Copy entry to the new log */
+ memcpy_to_pmem_nocache(nova_get_block(sb, new_curr),
+ nova_get_block(sb, curr_p), length);
+ nova_inc_page_num_entries(sb, new_curr);
+ nova_gc_assign_new_entry(sb, pi, sih, curr_p, new_curr);
+ new_curr += length;
+ }
+
+ curr_p += length;
+ }
+
+ /* Step 1: Link new log to the tail block */
+ tail_block = BLOCK_OFF(sih->log_tail);
+ curr_page = (struct nova_inode_log_page *)nova_get_block(sb,
+ BLOCK_OFF(new_curr));
+ next = next_log_page(sb, new_curr);
+ if (next > 0)
+ nova_free_contiguous_log_blocks(sb, sih, next);
+
+ nova_set_next_page_flag(sb, new_curr);
+ nova_set_next_page_address(sb, curr_page, tail_block, 0);
+
+ /* Step 2: Atomically switch to the new log */
+ pi->log_head = new_head;
+ nova_persist_inode(pi);
+ nova_flush_buffer(pi, sizeof(struct nova_inode), 1);
+ sih->log_head = new_head;
+
+ /* Step 3: Unlink the old log */
+ curr_page = (struct nova_inode_log_page *)nova_get_block(sb,
+ BLOCK_OFF(old_curr_p));
+ next = next_log_page(sb, old_curr_p);
+ if (next != tail_block)
+ nova_err(sb, "Old log error: old curr_p 0x%lx, next 0x%lx ",
+ "curr_p 0x%lx, tail block 0x%lx\n", old_curr_p,
+ next, curr_p, tail_block);
+
+ nova_set_next_page_address(sb, curr_page, 0, 1);
+
+ /* Step 4: Free the old log */
+ nova_free_contiguous_log_blocks(sb, sih, old_head);
+
+ sih->log_pages = sih->log_pages + blocks - checked_pages;
+ NOVA_STATS_ADD(thorough_gc_pages, checked_pages - blocks);
+ NOVA_STATS_ADD(thorough_checked_pages, checked_pages);
+out:
+ NOVA_END_TIMING(thorough_gc_t, gc_time);
+ return blocks;
+}
+
/*
* Scan pages in the log and remove those with no valid log entries.
@@ -178,9 +438,22 @@ int nova_inode_log_fast_gc(struct super_block *sb,
if (sih->num_entries == 0)
return 0;
+ /* Estimate how many pages worth of valid entries the log contains.
+ *
+ * If it is less than half the number pages that remain in the log,
+ * compress them with thorough gc.
+ */
blocks = (sih->valid_entries * checked_pages) / sih->num_entries;
if ((sih->valid_entries * checked_pages) % sih->num_entries)
blocks++;
+ if (force_thorough || (blocks && blocks * 2 < checked_pages)) {
+ nova_dbgv("Thorough GC for inode %lu: checked pages %lu, valid pages %lu\n",
+ sih->ino,
+ checked_pages, blocks);
+ blocks = nova_inode_log_thorough_gc(sb, pi, sih,
+ blocks, checked_pages);
+ }
+
return 0;
}
--
2.7.4
next prev parent reply other threads:[~2018-03-10 18:18 UTC|newest]
Thread overview: 119+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-03-10 18:17 [RFC v2 00/83] NOVA: a new file system for persistent memory Andiry Xu
2018-03-10 18:17 ` [RFC v2 01/83] Introduction and documentation of NOVA filesystem Andiry Xu
2018-03-19 20:43 ` Randy Dunlap
2018-03-19 23:00 ` Andiry Xu
2018-04-22 8:05 ` Pavel Machek
2018-03-10 18:17 ` [RFC v2 02/83] Add nova_def.h Andiry Xu
2018-03-10 18:17 ` [RFC v2 03/83] Add super.h Andiry Xu
2018-03-15 4:54 ` Darrick J. Wong
2018-03-15 6:11 ` Andiry Xu
2018-03-15 9:05 ` Arnd Bergmann
2018-03-15 17:51 ` Andiry Xu
2018-03-15 20:04 ` Andreas Dilger
2018-03-15 20:38 ` Arnd Bergmann
2018-03-16 2:59 ` Theodore Y. Ts'o
2018-03-16 6:17 ` Andiry Xu
2018-03-16 6:30 ` Darrick J. Wong
2018-03-16 9:19 ` Arnd Bergmann
2018-03-10 18:17 ` [RFC v2 04/83] NOVA inode definition Andiry Xu
2018-03-15 5:06 ` Darrick J. Wong
2018-03-15 6:16 ` Andiry Xu
2018-03-10 18:17 ` [RFC v2 05/83] Add NOVA filesystem definitions and useful helper routines Andiry Xu
2018-03-11 12:00 ` Nikolay Borisov
2018-03-11 19:22 ` Eric Biggers
2018-03-11 21:45 ` Andiry Xu
2018-03-19 19:39 ` Andiry Xu
2018-03-19 20:30 ` Eric Biggers
2018-03-19 21:59 ` Andiry Xu
2018-03-10 18:17 ` [RFC v2 06/83] Add inode get/read methods Andiry Xu
2018-04-23 6:12 ` Darrick J. Wong
2018-04-23 15:55 ` Andiry Xu
2018-03-10 18:17 ` [RFC v2 07/83] Initialize inode_info and rebuild inode information in nova_iget() Andiry Xu
2018-03-10 18:17 ` [RFC v2 08/83] NOVA superblock operations Andiry Xu
2018-03-10 18:17 ` [RFC v2 09/83] Add Kconfig and Makefile Andiry Xu
2018-03-11 12:15 ` Nikolay Borisov
2018-03-11 21:32 ` Andiry Xu
2018-03-10 18:17 ` [RFC v2 10/83] Add superblock integrity check Andiry Xu
2018-03-10 18:17 ` [RFC v2 11/83] Add timing and I/O statistics for performance analysis and profiling Andiry Xu
2018-03-10 18:17 ` [RFC v2 12/83] Add timing for mount and init Andiry Xu
2018-03-10 18:17 ` [RFC v2 13/83] Add remount_fs and show_options methods Andiry Xu
2018-03-10 18:17 ` [RFC v2 14/83] Add range node kmem cache Andiry Xu
2018-03-11 11:55 ` Nikolay Borisov
2018-03-11 21:31 ` Andiry Xu
2018-03-10 18:17 ` [RFC v2 15/83] Add free list data structure Andiry Xu
2018-03-10 18:17 ` [RFC v2 16/83] Initialize block map and free lists in nova_init() Andiry Xu
2018-03-11 12:12 ` Nikolay Borisov
2018-03-11 21:30 ` Andiry Xu
2018-03-10 18:17 ` [RFC v2 17/83] Add statfs support Andiry Xu
2018-03-10 18:17 ` [RFC v2 18/83] Add freelist statistics printing Andiry Xu
2018-03-10 18:18 ` [RFC v2 19/83] Add pmem block free routines Andiry Xu
2018-03-10 18:18 ` [RFC v2 20/83] Pmem block allocation routines Andiry Xu
2018-03-10 18:18 ` [RFC v2 21/83] Add log structure Andiry Xu
2018-03-10 18:18 ` [RFC v2 22/83] Inode log pages allocation and reclaimation Andiry Xu
2018-03-10 18:18 ` [RFC v2 23/83] Save allocator to pmem in put_super Andiry Xu
2018-03-10 18:18 ` [RFC v2 24/83] Initialize and allocate inode table Andiry Xu
2018-03-10 18:18 ` [RFC v2 25/83] Support get normal inode address and inode table extentsion Andiry Xu
2018-03-10 18:18 ` [RFC v2 26/83] Add inode_map to track inuse inodes Andiry Xu
2018-03-10 18:18 ` [RFC v2 27/83] Save the inode inuse list to pmem upon umount Andiry Xu
2018-03-10 18:18 ` [RFC v2 28/83] Add NOVA address space operations Andiry Xu
2018-03-10 18:18 ` [RFC v2 29/83] Add write_inode and dirty_inode routines Andiry Xu
2018-03-10 18:18 ` [RFC v2 30/83] New NOVA inode allocation Andiry Xu
2018-03-10 18:18 ` [RFC v2 31/83] Add new vfs " Andiry Xu
2018-03-10 18:18 ` [RFC v2 32/83] Add log entry definitions Andiry Xu
2018-03-10 18:18 ` [RFC v2 33/83] Inode log and entry printing for debug purpose Andiry Xu
2018-03-10 18:18 ` [RFC v2 34/83] Journal: NOVA light weight journal definitions Andiry Xu
2018-03-10 18:18 ` [RFC v2 35/83] Journal: Lite journal helper routines Andiry Xu
2018-03-10 18:18 ` [RFC v2 36/83] Journal: Lite journal recovery Andiry Xu
2018-03-10 18:18 ` [RFC v2 37/83] Journal: Lite journal create and commit Andiry Xu
2018-03-10 18:18 ` [RFC v2 38/83] Journal: NOVA lite journal initialization Andiry Xu
2018-03-10 18:18 ` [RFC v2 39/83] Log operation: dentry append Andiry Xu
2018-03-10 18:18 ` [RFC v2 40/83] Log operation: file write entry append Andiry Xu
2018-03-10 18:18 ` [RFC v2 41/83] Log operation: setattr " Andiry Xu
2018-03-10 18:18 ` [RFC v2 42/83] Log operation: link change append Andiry Xu
2018-03-10 18:18 ` [RFC v2 43/83] Log operation: in-place update log entry Andiry Xu
2018-03-10 18:18 ` [RFC v2 44/83] Log operation: invalidate log entries Andiry Xu
2018-03-10 18:18 ` [RFC v2 45/83] Log operation: file inode log lookup and assign Andiry Xu
2018-03-10 18:18 ` [RFC v2 46/83] Dir: Add Directory radix tree insert/remove methods Andiry Xu
2018-03-10 18:18 ` [RFC v2 47/83] Dir: Add initial dentries when initializing a directory inode log Andiry Xu
2018-03-10 18:18 ` [RFC v2 48/83] Dir: Readdir operation Andiry Xu
2018-03-10 18:18 ` [RFC v2 49/83] Dir: Append create/remove dentry Andiry Xu
2018-03-10 18:18 ` [RFC v2 50/83] Inode: Add nova_evict_inode Andiry Xu
2018-03-10 18:18 ` [RFC v2 51/83] Rebuild: directory inode Andiry Xu
2018-03-10 18:18 ` [RFC v2 52/83] Rebuild: file inode Andiry Xu
2018-03-10 18:18 ` [RFC v2 53/83] Namei: lookup Andiry Xu
2018-03-10 18:18 ` [RFC v2 54/83] Namei: create and mknod Andiry Xu
2018-03-10 18:18 ` [RFC v2 55/83] Namei: mkdir Andiry Xu
2018-03-10 18:18 ` [RFC v2 56/83] Namei: link and unlink Andiry Xu
2018-03-10 18:18 ` [RFC v2 57/83] Namei: rmdir Andiry Xu
2018-03-10 18:18 ` [RFC v2 58/83] Namei: rename Andiry Xu
2018-03-10 18:18 ` [RFC v2 59/83] Namei: setattr Andiry Xu
2018-03-10 18:18 ` [RFC v2 60/83] Add special inode operations Andiry Xu
2018-03-10 18:18 ` [RFC v2 61/83] Super: Add nova_export_ops Andiry Xu
2018-03-10 18:18 ` [RFC v2 62/83] File: getattr and file inode operations Andiry Xu
2018-03-10 18:18 ` [RFC v2 63/83] File operation: llseek Andiry Xu
2018-03-10 18:18 ` [RFC v2 64/83] File operation: open, fsync, flush Andiry Xu
2018-03-10 18:18 ` [RFC v2 65/83] File operation: read Andiry Xu
2018-03-10 18:18 ` [RFC v2 66/83] Super: Add file write item cache Andiry Xu
2018-03-10 18:18 ` [RFC v2 67/83] Dax: commit list of file write items to log Andiry Xu
2018-03-10 18:18 ` [RFC v2 68/83] File operation: copy-on-write write Andiry Xu
2018-03-10 18:18 ` [RFC v2 69/83] Super: Add module param inplace_data_updates Andiry Xu
2018-03-10 18:18 ` [RFC v2 70/83] File operation: Inplace write Andiry Xu
2018-03-10 18:18 ` [RFC v2 71/83] Symlink support Andiry Xu
2018-03-10 18:18 ` [RFC v2 72/83] File operation: fallocate Andiry Xu
2018-03-10 18:18 ` [RFC v2 73/83] Dax: Add iomap operations Andiry Xu
2018-03-10 18:18 ` [RFC v2 74/83] File operation: Mmap Andiry Xu
2018-03-10 18:18 ` [RFC v2 75/83] File operation: read/write iter Andiry Xu
2018-03-10 18:18 ` [RFC v2 76/83] Ioctl support Andiry Xu
2018-03-10 18:18 ` [RFC v2 77/83] GC: Fast garbage collection Andiry Xu
2018-03-10 18:18 ` Andiry Xu [this message]
2018-03-10 18:19 ` [RFC v2 79/83] Normal recovery Andiry Xu
2018-03-10 18:19 ` [RFC v2 80/83] Failure recovery: bitmap operations Andiry Xu
2018-03-10 18:19 ` [RFC v2 81/83] Failure recovery: Inode pages recovery routines Andiry Xu
2018-03-10 18:19 ` [RFC v2 82/83] Failure recovery: Per-CPU recovery Andiry Xu
2018-03-10 18:19 ` [RFC v2 83/83] Sysfs support Andiry Xu
2018-03-15 0:33 ` Randy Dunlap
2018-03-15 6:07 ` Andiry Xu
2018-03-22 15:00 ` David Sterba
2018-03-23 0:31 ` Andiry Xu
2018-03-11 2:14 ` [RFC v2 00/83] NOVA: a new file system for persistent memory Theodore Y. Ts'o
2018-03-11 4:58 ` Andiry Xu
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1520705944-6723-79-git-send-email-jix024@eng.ucsd.edu \
--to=jix024@eng.ucsd.edu \
--cc=andiry.xu@gmail.com \
--cc=andy.rudoff@intel.com \
--cc=coughlan@redhat.com \
--cc=dan.j.williams@intel.com \
--cc=david@fromorbit.com \
--cc=jack@suse.com \
--cc=jix024@cs.ucsd.edu \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nvdimm@lists.01.org \
--cc=miklos@szeredi.hu \
--cc=swanson@cs.ucsd.edu \
--cc=swhiteho@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).