Repository navigation
binutils, ghc-9.6.7: amd64 onto gen-16's plain-loader objects (world rebuild; needs gen-16 published) - #1499
bryan-minimal wants to merge 2 commits into
Conversation
binutils' amd64 cycle-breaker moves from gen-13 binutils-2.46-glibc (bedrock loader on all 22 ELFs) to gen-16 binutils-2.46-glibc-seed (plain /usr/lib loader, no RUNPATH; bootstrap#12). ghc-9.6.7 amd64 moves to gen-16, where unlit is on the plain loader too. arm64 is unchanged (gen-16's arm64 ghc is byte-identical to gen-15). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
|
Warning Review limit reached
This review includes 2 billable files and costs up to $0.50.
Reviews can continue after your included limit without a manual trigger. An admin must approve usage-based billing. Or wait 43 minutes for your next included review. View limit details
|
build-bot builds on push, not on ready_for_review. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
norrietaylor
left a comment
There was a problem hiding this comment.
Scope matches the title. The diff repins only the amd64 binutils cycle-breaker object and the amd64 ghc-9.6.7 object. The arm64 pins are not changed, and nothing else moves. Clobber none. git log on both files shows the previous change was the gen-15 move of ghc-9.6.7 in #1462. This PR keeps that move for arm64 and goes past it for amd64. Correctness In each URL, the sha256 path segment matches the sha256 field. The binutils replace_on_cycle outputs (usr/bin, usr/lib, usr/include, usr/share) do not change, which agrees with the PR body. The prebuilt binutils keeps runtime_deps = [zlib], the same shape as the gcc gen-13 plain-loader cycle-breaker in packages/gcc/build.ncl:125-160. The plain loader comes from the glibc cycle-breaker. Not checked I did not fetch the gen-16 objects, so I did not confirm the ELF claims or the hashes against the bucket. I did not run a build. The rebuild scope (all of amd64) is as the PR states. Queue it alone. One formatting nit is below.
| # -> 7.6.3 -> 7.8.4 -> 7.10.3 -> 8.2.2 -> 8.6.5 -> 8.10.7 -> 9.2.8 -> 9.6.7, every rung built on the | ||
| # hex0-rooted toolchain and this one reproduced byte for byte on two independent machines before | ||
| # publishing (generations/gen-15/manifest.json). Installs the whole compiler at /usr/lib/ghc-9.6.7; | ||
| # publishing (amd64: generations/gen-16/manifest.json; arm64: gen-15, which gen-16 left byte-identical). Installs the whole compiler at /usr/lib/ghc-9.6.7; |
There was a problem hiding this comment.
nit · The edit makes this header comment line about 150 characters long. The lines around it wrap at about 100. Rewrap the paragraph so the block keeps one width. Line 8 has the same problem on a smaller scale.
|
Plan: fold this into the gcc 16 rotation rather than merging it on its own. The rotation is pkgs#1340 now, and a PR queued alone later. Each of #1499 and #1535 is a world rebuild. The registry spec's ruling (gominimal/arch#183, decisions §4) is to make gcc, glibc and bootstrap changes in one rotation, so the catalog is rebuilt once. That rotation also takes the OQ-42 breaker output fixes (bash-bootstrap, bzip2, binutils arm64, attr). #1535 specifically: once gcc-runtime lands, This waits for the current canary run (230721a) to finish. 🤖 Generated with Claude Code |
Both rebuild the world, so they ride the same rotation as gcc 16 instead of each costing one of their own. - #1499: amd64 binutils breaker and ghc-9.6.7 onto gen-16's plain-loader objects (binutils-2.46-glibc-seed, ghc-9.6.7). - #1535: arm64 gcc breaker onto gen-17's gcc-15.2.0-glibc-seed. gcc-runtime's breaker moves with it, since gcc_runtime_guard.py requires the two pins to match. All three objects exist in gs://minimal-bootstrap. #1499's build was green. #1535's failed only on tmd's zig fetch from deps.files.ghostty.org (connection reset), which is unrelated. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…308f31) Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
|
Closing: this is folded into #1545 (gcc 16.2.0 with gcc-runtime). Repinning a cycle breaker rebuilds the world, and so does gcc 16, so both ride one rotation instead of paying for two. #1545's first commit (
That tree built and checked green on both arches as canary #1340 ( 🤖 Generated with Claude Code |
Repins the two amd64 bootstrap objects that gen-16 changed. Nothing else moves: gen-16 is add-only, and every other pin stays on its byte-identical gen-13 or gen-15 object (no
pkgs-flip.pyrun).binutils(replace_on_cycle)binutils-2.46-glibc7fe673db…binutils-2.46-glibc-seed741ece75…ghc-9.6.7fd4510bb…fc0d0c2b…arm64 is unchanged. Its binutils was never on the bedrock loader, and gen-16's arm64 ghc-9.6.7 is byte-identical to the gen-15 object pinned now (
1fbf1656…).Why
The gen-13 amd64 binutils object named
/usr/lib/glibc-bedrock-2.42/libas the PT_INTERP and RUNPATH on all 22 of its ELFs. A build without the bedrock tree can't execas. minimermetic's hermetic glibc pass hit exactly that, and it gates 304 of its queue tasks. bootstrap#12 published the same binutils as a new leaf,binutils-2.46-glibc-seed, on the plain/usr/lib/ld-linux-x86-64.so.2loader with no RUNPATH, behind a build-time guard against any glibc-bedrock reference. Its outputs use the same globs (usr/bin, usr/lib, usr/include), so only the url/sha change. It needs the same thing gcc's gen-13 plain-loader cycle-breaker already relies on: the plain loader and libc in /usr/lib.ghc-9.6.7 amd64: Hadrian built
unlit-ghc-9.6.7andlib/bin/unlitwith ghc-9.2.8's ghc-cc, which appended the bedrock loader. gen-16 rewrites them to the plain loader.Evidence (bootstrap side, gen-16 manifest = bootstrap#13)
/usr/lib/ld-linux-x86-64.so.2.Before merge
sh publish-gen16.sh, bootstrap branchgen-16). Until then these URLs 404, which is why this is a draft.ghcand its dependents. Queue this on its own, not alongside another world rebuild.Follows gominimal/bootstrap#12 and #13. Pairs with #1493 (rustc-1.99.1 from the same generation).
🤖 Generated with Claude Code